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 (
21 compat_urllib_parse_unquote,
22 compat_urllib_parse_unquote_plus,
23 compat_urllib_parse_urlencode,
24 compat_urllib_parse_urlparse,
33 get_element_by_attribute,
56 class YoutubeBaseInfoExtractor(InfoExtractor):
57 """Provide base functions for Youtube extractors"""
58 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
59 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
61 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
62 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
63 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
65 _NETRC_MACHINE = 'youtube'
66 # If True it will raise an error if no login info is provided
67 _LOGIN_REQUIRED = False
69 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
71 def _set_language(self):
73 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
74 # YouTube sets the expire time to about two months
75 expire_time=time.time() + 2 * 30 * 24 * 3600)
77 def _ids_to_results(self, ids):
79 self.url_result(vid_id, 'Youtube', video_id=vid_id)
84 Attempt to log in to YouTube.
85 True is returned if successful or skipped.
86 False is returned if login failed.
88 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
90 username, password = self._get_login_info()
91 # No authentication to be performed
93 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
94 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
97 login_page = self._download_webpage(
98 self._LOGIN_URL, None,
99 note='Downloading login page',
100 errnote='unable to fetch login page', fatal=False)
101 if login_page is False:
104 login_form = self._hidden_inputs(login_page)
106 def req(url, f_req, note, errnote):
107 data = login_form.copy()
110 'checkConnection': 'youtube',
111 'checkedDomains': 'youtube',
113 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
114 'f.req': json.dumps(f_req),
115 'flowName': 'GlifWebSignIn',
116 'flowEntry': 'ServiceLogin',
118 return self._download_json(
119 url, None, note=note, errnote=errnote,
120 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
122 data=urlencode_postdata(data), headers={
123 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
124 'Google-Accounts-XSRF': 1,
128 self._downloader.report_warning(message)
132 None, [], None, 'US', None, None, 2, False, True,
136 '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',
138 1, [None, None, []], None, None, None, True
143 lookup_results = req(
144 self._LOOKUP_URL, lookup_req,
145 'Looking up account info', 'Unable to look up account info')
147 if lookup_results is False:
150 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
152 warn('Unable to extract user hash')
157 None, 1, None, [1, None, None, None, [password, None, True]],
159 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],
160 1, [None, None, []], None, None, None, True
163 challenge_results = req(
164 self._CHALLENGE_URL, challenge_req,
165 'Logging in', 'Unable to log in')
167 if challenge_results is False:
170 login_res = try_get(challenge_results, lambda x: x[0][5], list)
172 login_msg = try_get(login_res, lambda x: x[5], compat_str)
174 'Unable to login: %s' % 'Invalid password'
175 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
178 res = try_get(challenge_results, lambda x: x[0][-1], list)
180 warn('Unable to extract result entry')
183 login_challenge = try_get(res, lambda x: x[0][0], list)
185 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
186 if challenge_str == 'TWO_STEP_VERIFICATION':
187 # SEND_SUCCESS - TFA code has been successfully sent to phone
188 # QUOTA_EXCEEDED - reached the limit of TFA codes
189 status = try_get(login_challenge, lambda x: x[5], compat_str)
190 if status == 'QUOTA_EXCEEDED':
191 warn('Exceeded the limit of TFA codes, try later')
194 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
196 warn('Unable to extract TL')
199 tfa_code = self._get_tfa_info('2-step verification code')
203 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
204 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
207 tfa_code = remove_start(tfa_code, 'G-')
210 user_hash, None, 2, None,
212 9, None, None, None, None, None, None, None,
213 [None, tfa_code, True, 2]
217 self._TFA_URL.format(tl), tfa_req,
218 'Submitting TFA code', 'Unable to submit TFA code')
220 if tfa_results is False:
223 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
225 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
227 'Unable to finish TFA: %s' % 'Invalid TFA code'
228 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
231 check_cookie_url = try_get(
232 tfa_results, lambda x: x[0][-1][2], compat_str)
235 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
236 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
237 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
239 challenge = CHALLENGES.get(
241 '%s returned error %s.' % (self.IE_NAME, challenge_str))
242 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
245 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
247 if not check_cookie_url:
248 warn('Unable to extract CheckCookie URL')
251 check_cookie_results = self._download_webpage(
252 check_cookie_url, None, 'Checking cookie', fatal=False)
254 if check_cookie_results is False:
257 if 'https://myaccount.google.com/' not in check_cookie_results:
258 warn('Unable to log in')
263 def _download_webpage_handle(self, *args, **kwargs):
264 query = kwargs.get('query', {}).copy()
265 query['disable_polymer'] = 'true'
266 kwargs['query'] = query
267 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
268 *args, **compat_kwargs(kwargs))
270 def _real_initialize(self):
271 if self._downloader is None:
274 if not self._login():
278 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
279 # Extract entries from page with "Load more" button
280 def _entries(self, page, playlist_id):
281 more_widget_html = content_html = page
282 for page_num in itertools.count(1):
283 for entry in self._process_page(content_html):
286 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
290 more = self._download_json(
291 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
292 'Downloading page #%s' % page_num,
293 transform_source=uppercase_escape)
294 content_html = more['content_html']
295 if not content_html.strip():
296 # Some webpages show a "Load more" button but they don't
299 more_widget_html = more['load_more_widget_html']
302 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
303 def _process_page(self, content):
304 for video_id, video_title in self.extract_videos_from_page(content):
305 yield self.url_result(video_id, 'Youtube', video_id, video_title)
307 def extract_videos_from_page(self, page):
310 for mobj in re.finditer(self._VIDEO_RE, page):
311 # The link with index 0 is not the first video of the playlist (not sure if still actual)
312 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
314 video_id = mobj.group('id')
315 video_title = unescapeHTML(mobj.group('title'))
317 video_title = video_title.strip()
319 idx = ids_in_page.index(video_id)
320 if video_title and not titles_in_page[idx]:
321 titles_in_page[idx] = video_title
323 ids_in_page.append(video_id)
324 titles_in_page.append(video_title)
325 return zip(ids_in_page, titles_in_page)
328 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
329 def _process_page(self, content):
330 for playlist_id in orderedSet(re.findall(
331 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
333 yield self.url_result(
334 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
336 def _real_extract(self, url):
337 playlist_id = self._match_id(url)
338 webpage = self._download_webpage(url, playlist_id)
339 title = self._og_search_title(webpage, fatal=False)
340 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
343 class YoutubeIE(YoutubeBaseInfoExtractor):
344 IE_DESC = 'YouTube.com'
345 _VALID_URL = r"""(?x)^
347 (?:https?://|//) # http(s):// or protocol-independent URL
348 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
349 (?:www\.)?deturl\.com/www\.youtube\.com/|
350 (?:www\.)?pwnyoutube\.com/|
351 (?:www\.)?hooktube\.com/|
352 (?:www\.)?yourepeat\.com/|
353 tube\.majestyc\.net/|
354 (?:(?:www|dev)\.)?invidio\.us/|
355 (?:www\.)?invidiou\.sh/|
356 (?:www\.)?invidious\.snopyta\.org/|
357 (?:www\.)?invidious\.kabi\.tk/|
358 (?:www\.)?vid\.wxzm\.sx/|
359 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
360 (?:.*?\#/)? # handle anchor (#/) redirect urls
361 (?: # the various things that can precede the ID:
362 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
363 |(?: # or the v= param in all its forms
364 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
365 (?:\?|\#!?) # the params delimiter ? or # or #!
366 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
371 youtu\.be| # just youtu.be/xxxx
372 vid\.plus| # or vid.plus/xxxx
373 zwearz\.com/watch| # or zwearz.com/watch/xxxx
375 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
377 )? # all until now is optional -> you can pass the naked ID
378 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
381 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
382 WL # WL are handled by the watch later IE
385 (?(1).+)? # if we found the ID, everything can follow
386 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
387 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
389 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
390 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
391 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
392 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
393 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
394 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
395 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
396 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
397 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
398 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
399 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
400 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
401 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
402 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
403 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
404 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
405 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
406 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
410 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
411 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
412 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
413 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
414 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
415 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
416 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
418 # Apple HTTP Live Streaming
419 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
420 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
421 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
422 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
423 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
424 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
425 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
426 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
429 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
430 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
431 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
432 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
433 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
434 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
435 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
436 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
437 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
438 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
439 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
440 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
443 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
444 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
445 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
446 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
447 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
448 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
449 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
452 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
453 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
454 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
455 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
456 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
457 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
458 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
459 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
460 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
461 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
462 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
463 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
464 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
465 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
466 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
467 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
468 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
469 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
470 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
471 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
472 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
473 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
476 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
477 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
479 # Dash webm audio with opus inside
480 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
481 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
482 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
485 '_rtmp': {'protocol': 'rtmp'},
487 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
494 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
498 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
499 'uploader': 'Philipp Hagemeister',
500 'uploader_id': 'phihag',
501 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
502 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
503 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
504 'upload_date': '20121002',
505 '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 .',
506 'categories': ['Science & Technology'],
507 'tags': ['youtube-dl'],
511 'dislike_count': int,
517 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
518 'note': 'Test generic use_cipher_signature video (#897)',
522 'upload_date': '20120506',
523 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
524 'alt_title': 'I Love It (feat. Charli XCX)',
525 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
526 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
527 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
528 'iconic ep', 'iconic', 'love', 'it'],
530 'uploader': 'Icona Pop',
531 'uploader_id': 'IconaPop',
532 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
533 'creator': 'Icona Pop',
534 'track': 'I Love It (feat. Charli XCX)',
535 'artist': 'Icona Pop',
539 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
540 'note': 'Test VEVO video with age protection (#956)',
544 'upload_date': '20130703',
545 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
546 'alt_title': 'Tunnel Vision',
547 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
549 'uploader': 'justintimberlakeVEVO',
550 'uploader_id': 'justintimberlakeVEVO',
551 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
552 'creator': 'Justin Timberlake',
553 'track': 'Tunnel Vision',
554 'artist': 'Justin Timberlake',
559 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
560 'note': 'Embed-only video (#1746)',
564 'upload_date': '20120608',
565 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
566 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
567 'uploader': 'SET India',
568 'uploader_id': 'setindia',
569 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
574 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
575 'note': 'Use the first video ID in the URL',
579 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
580 'uploader': 'Philipp Hagemeister',
581 'uploader_id': 'phihag',
582 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
583 'upload_date': '20121002',
584 '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 .',
585 'categories': ['Science & Technology'],
586 'tags': ['youtube-dl'],
590 'dislike_count': int,
593 'skip_download': True,
597 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
598 'note': '256k DASH audio (format 141) via DASH manifest',
602 'upload_date': '20121002',
603 'uploader_id': '8KVIDEO',
604 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
606 'uploader': '8KVIDEO',
607 'title': 'UHDTV TEST 8K VIDEO.mp4'
610 'youtube_include_dash_manifest': True,
613 'skip': 'format 141 not served anymore',
615 # DASH manifest with encrypted signature
617 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
621 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
622 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
624 'uploader': 'AfrojackVEVO',
625 'uploader_id': 'AfrojackVEVO',
626 'upload_date': '20131011',
629 'youtube_include_dash_manifest': True,
630 'format': '141/bestaudio[ext=m4a]',
633 # JS player signature function name containing $
635 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
639 'title': 'Taylor Swift - Shake It Off',
640 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
642 'uploader': 'TaylorSwiftVEVO',
643 'uploader_id': 'TaylorSwiftVEVO',
644 'upload_date': '20140818',
645 'creator': 'Taylor Swift',
648 'youtube_include_dash_manifest': True,
649 'format': '141/bestaudio[ext=m4a]',
654 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
659 'upload_date': '20100909',
660 'uploader': 'Amazing Atheist',
661 'uploader_id': 'TheAmazingAtheist',
662 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
663 'title': 'Burning Everyone\'s Koran',
664 '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',
667 # Normal age-gate video (No vevo, embed allowed)
669 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
673 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
674 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
676 'uploader': 'The Witcher',
677 'uploader_id': 'WitcherGame',
678 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
679 'upload_date': '20140605',
683 # Age-gate video with encrypted signature
685 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
689 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
690 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
692 'uploader': 'LloydVEVO',
693 'uploader_id': 'LloydVEVO',
694 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
695 'upload_date': '20110629',
699 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
700 # YouTube Red ad is not captured for creator
702 'url': '__2ABJjxzNo',
707 'upload_date': '20100430',
708 'uploader_id': 'deadmau5',
709 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
710 'creator': 'deadmau5',
711 'description': 'md5:12c56784b8032162bb936a5f76d55360',
712 'uploader': 'deadmau5',
713 'title': 'Deadmau5 - Some Chords (HD)',
714 'alt_title': 'Some Chords',
716 'expected_warnings': [
717 'DASH manifest missing',
720 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
722 'url': 'lqQg6PlCWgI',
727 'upload_date': '20150827',
728 'uploader_id': 'olympic',
729 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
730 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
731 'uploader': 'Olympic',
732 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
735 'skip_download': 'requires avconv',
740 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
744 'stretched_ratio': 16 / 9.,
746 'upload_date': '20110310',
747 'uploader_id': 'AllenMeow',
748 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
749 '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',
751 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
754 # url_encoded_fmt_stream_map is empty string
756 'url': 'qEJwOuvDf7I',
760 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
762 'upload_date': '20150404',
763 'uploader_id': 'spbelect',
764 'uploader': 'Наблюдатели Петербурга',
767 'skip_download': 'requires avconv',
769 'skip': 'This live event has ended.',
771 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
773 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
777 'title': 'md5:7b81415841e02ecd4313668cde88737a',
778 'description': 'md5:116377fd2963b81ec4ce64b542173306',
780 'upload_date': '20150625',
781 'uploader_id': 'dorappi2000',
782 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
783 'uploader': 'dorappi2000',
784 'formats': 'mincount:31',
786 'skip': 'not actual anymore',
788 # DASH manifest with segment_list
790 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
791 'md5': '8ce563a1d667b599d21064e982ab9e31',
795 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
796 'uploader': 'Airtek',
797 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
798 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
799 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
802 'youtube_include_dash_manifest': True,
803 'format': '135', # bestvideo
805 'skip': 'This live event has ended.',
808 # Multifeed videos (multiple cameras), URL is for Main Camera
809 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
812 'title': 'teamPGP: Rocket League Noob Stream',
813 'description': 'md5:dc7872fb300e143831327f1bae3af010',
819 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
820 'description': 'md5:dc7872fb300e143831327f1bae3af010',
822 'upload_date': '20150721',
823 'uploader': 'Beer Games Beer',
824 'uploader_id': 'beergamesbeer',
825 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
826 'license': 'Standard YouTube License',
832 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
833 'description': 'md5:dc7872fb300e143831327f1bae3af010',
835 'upload_date': '20150721',
836 'uploader': 'Beer Games Beer',
837 'uploader_id': 'beergamesbeer',
838 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
839 'license': 'Standard YouTube License',
845 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
846 'description': 'md5:dc7872fb300e143831327f1bae3af010',
848 'upload_date': '20150721',
849 'uploader': 'Beer Games Beer',
850 'uploader_id': 'beergamesbeer',
851 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
852 'license': 'Standard YouTube License',
858 'title': 'teamPGP: Rocket League Noob Stream (zim)',
859 'description': 'md5:dc7872fb300e143831327f1bae3af010',
861 'upload_date': '20150721',
862 'uploader': 'Beer Games Beer',
863 'uploader_id': 'beergamesbeer',
864 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
865 'license': 'Standard YouTube License',
869 'skip_download': True,
871 'skip': 'This video is not available.',
874 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
875 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
878 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
881 'skip': 'Not multifeed anymore',
884 'url': 'https://vid.plus/FlRa-iH7PGw',
885 'only_matching': True,
888 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
889 'only_matching': True,
892 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
893 # Also tests cut-off URL expansion in video description (see
894 # https://github.com/ytdl-org/youtube-dl/issues/1892,
895 # https://github.com/ytdl-org/youtube-dl/issues/8164)
896 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
900 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
901 'alt_title': 'Dark Walk - Position Music',
902 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
904 'upload_date': '20151119',
905 'uploader_id': 'IronSoulElf',
906 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
907 'uploader': 'IronSoulElf',
908 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
909 'track': 'Dark Walk - Position Music',
910 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
913 'skip_download': True,
917 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
918 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
919 'only_matching': True,
922 # Video with yt:stretch=17:0
923 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
927 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
928 'description': 'md5:ee18a25c350637c8faff806845bddee9',
929 'upload_date': '20151107',
930 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
931 'uploader': 'CH GAMER DROID',
934 'skip_download': True,
936 'skip': 'This video does not exist.',
939 # Video licensed under Creative Commons
940 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
944 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
945 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
947 'upload_date': '20150127',
948 'uploader_id': 'BerkmanCenter',
949 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
950 'uploader': 'The Berkman Klein Center for Internet & Society',
951 'license': 'Creative Commons Attribution license (reuse allowed)',
954 'skip_download': True,
958 # Channel-like uploader_url
959 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
963 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
964 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
966 'upload_date': '20151119',
967 'uploader': 'Bernie Sanders',
968 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
969 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
970 'license': 'Creative Commons Attribution license (reuse allowed)',
973 'skip_download': True,
977 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
978 'only_matching': True,
981 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
982 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
983 'only_matching': True,
986 # Rental video preview
987 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
991 'title': 'Piku - Trailer',
992 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
993 'upload_date': '20150811',
994 'uploader': 'FlixMatrix',
995 'uploader_id': 'FlixMatrixKaravan',
996 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
997 'license': 'Standard YouTube License',
1000 'skip_download': True,
1002 'skip': 'This video is not available.',
1005 # YouTube Red video with episode data
1006 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1008 'id': 'iqKdEhx-dD4',
1010 'title': 'Isolation - Mind Field (Ep 1)',
1011 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1013 'upload_date': '20170118',
1014 'uploader': 'Vsauce',
1015 'uploader_id': 'Vsauce',
1016 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1017 'series': 'Mind Field',
1019 'episode_number': 1,
1022 'skip_download': True,
1024 'expected_warnings': [
1025 'Skipping DASH manifest',
1029 # The following content has been identified by the YouTube community
1030 # as inappropriate or offensive to some audiences.
1031 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1033 'id': '6SJNVb0GnPI',
1035 'title': 'Race Differences in Intelligence',
1036 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1038 'upload_date': '20140124',
1039 'uploader': 'New Century Foundation',
1040 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1041 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1044 'skip_download': True,
1049 'url': '1t24XAntNCY',
1050 'only_matching': True,
1053 # geo restricted to JP
1054 'url': 'sJL6WA-aGkQ',
1055 'only_matching': True,
1058 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1059 'only_matching': True,
1062 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1063 'only_matching': True,
1067 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1068 'only_matching': True,
1071 # Video with unsupported adaptive stream type formats
1072 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1074 'id': 'Z4Vy8R84T1U',
1076 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1077 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1079 'upload_date': '20130923',
1080 'uploader': 'Amelia Putri Harwita',
1081 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1082 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1083 'formats': 'maxcount:10',
1086 'skip_download': True,
1087 'youtube_include_dash_manifest': False,
1091 # Youtube Music Auto-generated description
1092 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1094 'id': 'MgNrAu2pzNs',
1096 'title': 'Voyeur Girl',
1097 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1098 'upload_date': '20190312',
1099 'uploader': 'Various Artists - Topic',
1100 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
1101 'artist': 'Stephen',
1102 'track': 'Voyeur Girl',
1103 'album': 'it\'s too much love to know my dear',
1104 'release_date': '20190313',
1105 'release_year': 2019,
1108 'skip_download': True,
1112 # Youtube Music Auto-generated description
1113 # Retrieve 'artist' field from 'Artist:' in video description
1114 # when it is present on youtube music video
1115 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1117 'id': 'k0jLE7tTwjY',
1119 'title': 'Latch Feat. Sam Smith',
1120 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1121 'upload_date': '20150110',
1122 'uploader': 'Various Artists - Topic',
1123 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1124 'artist': 'Disclosure',
1125 'track': 'Latch Feat. Sam Smith',
1126 'album': 'Latch Featuring Sam Smith',
1127 'release_date': '20121008',
1128 'release_year': 2012,
1131 'skip_download': True,
1135 # Youtube Music Auto-generated description
1136 # handle multiple artists on youtube music video
1137 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1139 'id': '74qn0eJSjpA',
1141 'title': 'Eastside',
1142 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1143 'upload_date': '20180710',
1144 'uploader': 'Benny Blanco - Topic',
1145 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1146 'artist': 'benny blanco, Halsey, Khalid',
1147 'track': 'Eastside',
1148 'album': 'Eastside',
1149 'release_date': '20180713',
1150 'release_year': 2018,
1153 'skip_download': True,
1157 # Youtube Music Auto-generated description
1158 # handle youtube music video with release_year and no release_date
1159 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1161 'id': '-hcAI0g-f5M',
1163 'title': 'Put It On Me',
1164 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
1165 'upload_date': '20180426',
1166 'uploader': 'Matt Maeson - Topic',
1167 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1168 'artist': 'Matt Maeson',
1169 'track': 'Put It On Me',
1170 'album': 'The Hearse',
1171 'release_date': None,
1172 'release_year': 2018,
1175 'skip_download': True,
1180 def __init__(self, *args, **kwargs):
1181 super(YoutubeIE, self).__init__(*args, **kwargs)
1182 self._player_cache = {}
1184 def report_video_info_webpage_download(self, video_id):
1185 """Report attempt to download video info webpage."""
1186 self.to_screen('%s: Downloading video info webpage' % video_id)
1188 def report_information_extraction(self, video_id):
1189 """Report attempt to extract video information."""
1190 self.to_screen('%s: Extracting video information' % video_id)
1192 def report_unavailable_format(self, video_id, format):
1193 """Report extracted video URL."""
1194 self.to_screen('%s: Format %s not available' % (video_id, format))
1196 def report_rtmp_download(self):
1197 """Indicate the download will use the RTMP protocol."""
1198 self.to_screen('RTMP download detected')
1200 def _signature_cache_id(self, example_sig):
1201 """ Return a string representation of a signature """
1202 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1204 def _extract_signature_function(self, video_id, player_url, example_sig):
1206 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1209 raise ExtractorError('Cannot identify player %r' % player_url)
1210 player_type = id_m.group('ext')
1211 player_id = id_m.group('id')
1213 # Read from filesystem cache
1214 func_id = '%s_%s_%s' % (
1215 player_type, player_id, self._signature_cache_id(example_sig))
1216 assert os.path.basename(func_id) == func_id
1218 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1219 if cache_spec is not None:
1220 return lambda s: ''.join(s[i] for i in cache_spec)
1223 'Downloading player %s' % player_url
1224 if self._downloader.params.get('verbose') else
1225 'Downloading %s player %s' % (player_type, player_id)
1227 if player_type == 'js':
1228 code = self._download_webpage(
1229 player_url, video_id,
1231 errnote='Download of %s failed' % player_url)
1232 res = self._parse_sig_js(code)
1233 elif player_type == 'swf':
1234 urlh = self._request_webpage(
1235 player_url, video_id,
1237 errnote='Download of %s failed' % player_url)
1239 res = self._parse_sig_swf(code)
1241 assert False, 'Invalid player type %r' % player_type
1243 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1244 cache_res = res(test_string)
1245 cache_spec = [ord(c) for c in cache_res]
1247 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1250 def _print_sig_code(self, func, example_sig):
1251 def gen_sig_code(idxs):
1252 def _genslice(start, end, step):
1253 starts = '' if start == 0 else str(start)
1254 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1255 steps = '' if step == 1 else (':%d' % step)
1256 return 's[%s%s%s]' % (starts, ends, steps)
1259 # Quelch pyflakes warnings - start will be set when step is set
1260 start = '(Never used)'
1261 for i, prev in zip(idxs[1:], idxs[:-1]):
1262 if step is not None:
1263 if i - prev == step:
1265 yield _genslice(start, prev, step)
1268 if i - prev in [-1, 1]:
1273 yield 's[%d]' % prev
1277 yield _genslice(start, i, step)
1279 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1280 cache_res = func(test_string)
1281 cache_spec = [ord(c) for c in cache_res]
1282 expr_code = ' + '.join(gen_sig_code(cache_spec))
1283 signature_id_tuple = '(%s)' % (
1284 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1285 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1286 ' return %s\n') % (signature_id_tuple, expr_code)
1287 self.to_screen('Extracted signature function:\n' + code)
1289 def _parse_sig_js(self, jscode):
1290 funcname = self._search_regex(
1291 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1292 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1293 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
1294 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1295 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1296 jscode, 'Initial JS player signature function name', group='sig')
1298 jsi = JSInterpreter(jscode)
1299 initial_function = jsi.extract_function(funcname)
1300 return lambda s: initial_function([s])
1302 def _parse_sig_swf(self, file_contents):
1303 swfi = SWFInterpreter(file_contents)
1304 TARGET_CLASSNAME = 'SignatureDecipher'
1305 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1306 initial_function = swfi.extract_function(searched_class, 'decipher')
1307 return lambda s: initial_function([s])
1309 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1310 """Turn the encrypted s field into a working signature"""
1312 if player_url is None:
1313 raise ExtractorError('Cannot decrypt signature without player_url')
1315 if player_url.startswith('//'):
1316 player_url = 'https:' + player_url
1317 elif not re.match(r'https?://', player_url):
1318 player_url = compat_urlparse.urljoin(
1319 'https://www.youtube.com', player_url)
1321 player_id = (player_url, self._signature_cache_id(s))
1322 if player_id not in self._player_cache:
1323 func = self._extract_signature_function(
1324 video_id, player_url, s
1326 self._player_cache[player_id] = func
1327 func = self._player_cache[player_id]
1328 if self._downloader.params.get('youtube_print_sig_code'):
1329 self._print_sig_code(func, s)
1331 except Exception as e:
1332 tb = traceback.format_exc()
1333 raise ExtractorError(
1334 'Signature extraction failed: ' + tb, cause=e)
1336 def _get_subtitles(self, video_id, webpage):
1338 subs_doc = self._download_xml(
1339 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1340 video_id, note=False)
1341 except ExtractorError as err:
1342 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1346 for track in subs_doc.findall('track'):
1347 lang = track.attrib['lang_code']
1348 if lang in sub_lang_list:
1351 for ext in self._SUBTITLE_FORMATS:
1352 params = compat_urllib_parse_urlencode({
1356 'name': track.attrib['name'].encode('utf-8'),
1358 sub_formats.append({
1359 'url': 'https://www.youtube.com/api/timedtext?' + params,
1362 sub_lang_list[lang] = sub_formats
1363 if not sub_lang_list:
1364 self._downloader.report_warning('video doesn\'t have subtitles')
1366 return sub_lang_list
1368 def _get_ytplayer_config(self, video_id, webpage):
1370 # User data may contain arbitrary character sequences that may affect
1371 # JSON extraction with regex, e.g. when '};' is contained the second
1372 # regex won't capture the whole JSON. Yet working around by trying more
1373 # concrete regex first keeping in mind proper quoted string handling
1374 # to be implemented in future that will replace this workaround (see
1375 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1376 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1377 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1378 r';ytplayer\.config\s*=\s*({.+?});',
1380 config = self._search_regex(
1381 patterns, webpage, 'ytplayer.config', default=None)
1383 return self._parse_json(
1384 uppercase_escape(config), video_id, fatal=False)
1386 def _get_automatic_captions(self, video_id, webpage):
1387 """We need the webpage for getting the captions url, pass it as an
1388 argument to speed up the process."""
1389 self.to_screen('%s: Looking for automatic captions' % video_id)
1390 player_config = self._get_ytplayer_config(video_id, webpage)
1391 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1392 if not player_config:
1393 self._downloader.report_warning(err_msg)
1396 args = player_config['args']
1397 caption_url = args.get('ttsurl')
1399 timestamp = args['timestamp']
1400 # We get the available subtitles
1401 list_params = compat_urllib_parse_urlencode({
1406 list_url = caption_url + '&' + list_params
1407 caption_list = self._download_xml(list_url, video_id)
1408 original_lang_node = caption_list.find('track')
1409 if original_lang_node is None:
1410 self._downloader.report_warning('Video doesn\'t have automatic captions')
1412 original_lang = original_lang_node.attrib['lang_code']
1413 caption_kind = original_lang_node.attrib.get('kind', '')
1416 for lang_node in caption_list.findall('target'):
1417 sub_lang = lang_node.attrib['lang_code']
1419 for ext in self._SUBTITLE_FORMATS:
1420 params = compat_urllib_parse_urlencode({
1421 'lang': original_lang,
1425 'kind': caption_kind,
1427 sub_formats.append({
1428 'url': caption_url + '&' + params,
1431 sub_lang_list[sub_lang] = sub_formats
1432 return sub_lang_list
1434 def make_captions(sub_url, sub_langs):
1435 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1436 caption_qs = compat_parse_qs(parsed_sub_url.query)
1438 for sub_lang in sub_langs:
1440 for ext in self._SUBTITLE_FORMATS:
1442 'tlang': [sub_lang],
1445 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1446 query=compat_urllib_parse_urlencode(caption_qs, True)))
1447 sub_formats.append({
1451 captions[sub_lang] = sub_formats
1454 # New captions format as of 22.06.2017
1455 player_response = args.get('player_response')
1456 if player_response and isinstance(player_response, compat_str):
1457 player_response = self._parse_json(
1458 player_response, video_id, fatal=False)
1460 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1461 base_url = renderer['captionTracks'][0]['baseUrl']
1463 for lang in renderer['translationLanguages']:
1464 lang_code = lang.get('languageCode')
1466 sub_lang_list.append(lang_code)
1467 return make_captions(base_url, sub_lang_list)
1469 # Some videos don't provide ttsurl but rather caption_tracks and
1470 # caption_translation_languages (e.g. 20LmZk1hakA)
1471 # Does not used anymore as of 22.06.2017
1472 caption_tracks = args['caption_tracks']
1473 caption_translation_languages = args['caption_translation_languages']
1474 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1476 for lang in caption_translation_languages.split(','):
1477 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1478 sub_lang = lang_qs.get('lc', [None])[0]
1480 sub_lang_list.append(sub_lang)
1481 return make_captions(caption_url, sub_lang_list)
1482 # An extractor error can be raise by the download process if there are
1483 # no automatic captions but there are subtitles
1484 except (KeyError, IndexError, ExtractorError):
1485 self._downloader.report_warning(err_msg)
1488 def _mark_watched(self, video_id, video_info, player_response):
1489 playback_url = url_or_none(try_get(
1491 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1492 video_info, lambda x: x['videostats_playback_base_url'][0]))
1493 if not playback_url:
1495 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1496 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1498 # cpn generation algorithm is reverse engineered from base.js.
1499 # In fact it works even with dummy cpn.
1500 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1501 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1507 playback_url = compat_urlparse.urlunparse(
1508 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1510 self._download_webpage(
1511 playback_url, video_id, 'Marking watched',
1512 'Unable to mark watched', fatal=False)
1515 def _extract_urls(webpage):
1516 # Embedded YouTube player
1518 unescapeHTML(mobj.group('url'))
1519 for mobj in re.finditer(r'''(?x)
1529 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1530 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1533 # lazyYT YouTube embed
1534 entries.extend(list(map(
1536 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1538 # Wordpress "YouTube Video Importer" plugin
1539 matches = re.findall(r'''(?x)<div[^>]+
1540 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1541 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1542 entries.extend(m[-1] for m in matches)
1547 def _extract_url(webpage):
1548 urls = YoutubeIE._extract_urls(webpage)
1549 return urls[0] if urls else None
1552 def extract_id(cls, url):
1553 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1555 raise ExtractorError('Invalid URL: %s' % url)
1556 video_id = mobj.group(2)
1559 def _extract_annotations(self, video_id):
1560 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1561 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1564 def _extract_chapters(description, duration):
1567 chapter_lines = re.findall(
1568 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1570 if not chapter_lines:
1573 for next_num, (chapter_line, time_point) in enumerate(
1574 chapter_lines, start=1):
1575 start_time = parse_duration(time_point)
1576 if start_time is None:
1578 if start_time > duration:
1580 end_time = (duration if next_num == len(chapter_lines)
1581 else parse_duration(chapter_lines[next_num][1]))
1582 if end_time is None:
1584 if end_time > duration:
1586 if start_time > end_time:
1588 chapter_title = re.sub(
1589 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1590 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1592 'start_time': start_time,
1593 'end_time': end_time,
1594 'title': chapter_title,
1598 def _real_extract(self, url):
1599 url, smuggled_data = unsmuggle_url(url, {})
1602 'http' if self._downloader.params.get('prefer_insecure', False)
1607 parsed_url = compat_urllib_parse_urlparse(url)
1608 for component in [parsed_url.fragment, parsed_url.query]:
1609 query = compat_parse_qs(component)
1610 if start_time is None and 't' in query:
1611 start_time = parse_duration(query['t'][0])
1612 if start_time is None and 'start' in query:
1613 start_time = parse_duration(query['start'][0])
1614 if end_time is None and 'end' in query:
1615 end_time = parse_duration(query['end'][0])
1617 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1618 mobj = re.search(self._NEXT_URL_RE, url)
1620 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1621 video_id = self.extract_id(url)
1624 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1625 video_webpage = self._download_webpage(url, video_id)
1627 # Attempt to extract SWF player URL
1628 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1629 if mobj is not None:
1630 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1636 def add_dash_mpd(video_info):
1637 dash_mpd = video_info.get('dashmpd')
1638 if dash_mpd and dash_mpd[0] not in dash_mpds:
1639 dash_mpds.append(dash_mpd[0])
1641 def add_dash_mpd_pr(pl_response):
1642 dash_mpd = url_or_none(try_get(
1643 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1645 if dash_mpd and dash_mpd not in dash_mpds:
1646 dash_mpds.append(dash_mpd)
1651 def extract_view_count(v_info):
1652 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1654 player_response = {}
1657 embed_webpage = None
1658 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1660 # We simulate the access to the video from www.youtube.com/v/{video_id}
1661 # this can be viewed without login into Youtube
1662 url = proto + '://www.youtube.com/embed/%s' % video_id
1663 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1664 data = compat_urllib_parse_urlencode({
1665 'video_id': video_id,
1666 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1667 'sts': self._search_regex(
1668 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1670 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1671 video_info_webpage = self._download_webpage(
1672 video_info_url, video_id,
1673 note='Refetching age-gated info webpage',
1674 errnote='unable to download video info webpage')
1675 video_info = compat_parse_qs(video_info_webpage)
1676 add_dash_mpd(video_info)
1681 # Try looking directly into the video webpage
1682 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1684 args = ytplayer_config['args']
1685 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1686 # Convert to the same format returned by compat_parse_qs
1687 video_info = dict((k, [v]) for k, v in args.items())
1688 add_dash_mpd(video_info)
1689 # Rental video is not rented but preview is available (e.g.
1690 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1691 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1692 if not video_info and args.get('ypc_vid'):
1693 return self.url_result(
1694 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1695 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1697 sts = ytplayer_config.get('sts')
1698 if not player_response:
1699 pl_response = str_or_none(args.get('player_response'))
1701 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1702 if isinstance(pl_response, dict):
1703 player_response = pl_response
1704 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1705 add_dash_mpd_pr(player_response)
1706 # We also try looking in get_video_info since it may contain different dashmpd
1707 # URL that points to a DASH manifest with possibly different itag set (some itags
1708 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1709 # manifest pointed by get_video_info's dashmpd).
1710 # The general idea is to take a union of itags of both DASH manifests (for example
1711 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1712 self.report_video_info_webpage_download(video_id)
1713 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1715 'video_id': video_id,
1725 video_info_webpage = self._download_webpage(
1726 '%s://www.youtube.com/get_video_info' % proto,
1727 video_id, note=False,
1728 errnote='unable to download video info webpage',
1729 fatal=False, query=query)
1730 if not video_info_webpage:
1732 get_video_info = compat_parse_qs(video_info_webpage)
1733 if not player_response:
1734 pl_response = get_video_info.get('player_response', [None])[0]
1735 if isinstance(pl_response, dict):
1736 player_response = pl_response
1737 add_dash_mpd_pr(player_response)
1738 add_dash_mpd(get_video_info)
1739 if view_count is None:
1740 view_count = extract_view_count(get_video_info)
1742 video_info = get_video_info
1743 get_token = get_video_info.get('token') or get_video_info.get('account_playback_token')
1745 # Different get_video_info requests may report different results, e.g.
1746 # some may report video unavailability, but some may serve it without
1747 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1748 # the original webpage as well as el=info and el=embedded get_video_info
1749 # requests report video unavailability due to geo restriction while
1750 # el=detailpage succeeds and returns valid data). This is probably
1751 # due to YouTube measures against IP ranges of hosting providers.
1752 # Working around by preferring the first succeeded video_info containing
1753 # the token if no such video_info yet was found.
1754 token = video_info.get('token') or video_info.get('account_playback_token')
1756 video_info = get_video_info
1759 def extract_unavailable_message():
1760 return self._html_search_regex(
1761 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1762 video_webpage, 'unavailable message', default=None)
1765 unavailable_message = extract_unavailable_message()
1766 if not unavailable_message:
1767 unavailable_message = 'Unable to extract video data'
1768 raise ExtractorError(
1769 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1771 token = video_info.get('token') or video_info.get('account_playback_token')
1773 if 'reason' in video_info:
1774 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1775 regions_allowed = self._html_search_meta(
1776 'regionsAllowed', video_webpage, default=None)
1777 countries = regions_allowed.split(',') if regions_allowed else None
1778 self.raise_geo_restricted(
1779 msg=video_info['reason'][0], countries=countries)
1780 reason = video_info['reason'][0]
1781 if 'Invalid parameters' in reason:
1782 unavailable_message = extract_unavailable_message()
1783 if unavailable_message:
1784 reason = unavailable_message
1785 raise ExtractorError(
1786 'YouTube said: %s' % reason,
1787 expected=True, video_id=video_id)
1789 raise ExtractorError(
1790 '"token" parameter not in video info for unknown reason',
1793 if video_info.get('license_info'):
1794 raise ExtractorError('This video is DRM protected.', expected=True)
1796 video_details = try_get(
1797 player_response, lambda x: x['videoDetails'], dict) or {}
1800 if 'title' in video_info:
1801 video_title = video_info['title'][0]
1802 elif 'title' in player_response:
1803 video_title = video_details['title']
1805 self._downloader.report_warning('Unable to extract video title')
1809 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1810 if video_description:
1813 redir_url = compat_urlparse.urljoin(url, m.group(1))
1814 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1815 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1816 qs = compat_parse_qs(parsed_redir_url.query)
1822 description_original = video_description = re.sub(r'''(?x)
1824 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1825 (?:title|href)="([^"]+)"\s+
1826 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1830 ''', replace_url, video_description)
1831 video_description = clean_html(video_description)
1833 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1835 video_description = unescapeHTML(fd_mobj.group(1))
1837 video_description = ''
1839 if not smuggled_data.get('force_singlefeed', False):
1840 if not self._downloader.params.get('noplaylist'):
1841 multifeed_metadata_list = try_get(
1843 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1844 compat_str) or try_get(
1845 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1846 if multifeed_metadata_list:
1849 for feed in multifeed_metadata_list.split(','):
1850 # Unquote should take place before split on comma (,) since textual
1851 # fields may contain comma as well (see
1852 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1853 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1855 '_type': 'url_transparent',
1856 'ie_key': 'Youtube',
1858 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1859 {'force_singlefeed': True}),
1860 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1862 feed_ids.append(feed_data['id'][0])
1864 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1865 % (', '.join(feed_ids), video_id))
1866 return self.playlist_result(entries, video_id, video_title, video_description)
1868 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1870 if view_count is None:
1871 view_count = extract_view_count(video_info)
1872 if view_count is None and video_details:
1873 view_count = int_or_none(video_details.get('viewCount'))
1875 # Check for "rental" videos
1876 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1877 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1879 def _extract_filesize(media_url):
1880 return int_or_none(self._search_regex(
1881 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1883 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1884 self.report_rtmp_download()
1886 'format_id': '_rtmp',
1888 'url': video_info['conn'][0],
1889 'player_url': player_url,
1891 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):
1892 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1893 if 'rtmpe%3Dyes' in encoded_url_map:
1894 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1896 fmt_list = video_info.get('fmt_list', [''])[0]
1898 for fmt in fmt_list.split(','):
1899 spec = fmt.split('/')
1901 width_height = spec[1].split('x')
1902 if len(width_height) == 2:
1903 formats_spec[spec[0]] = {
1904 'resolution': spec[1],
1905 'width': int_or_none(width_height[0]),
1906 'height': int_or_none(width_height[1]),
1908 q = qualities(['small', 'medium', 'hd720'])
1909 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1910 if streaming_formats:
1911 for fmt in streaming_formats:
1912 itag = str_or_none(fmt.get('itag'))
1915 quality = fmt.get('quality')
1916 quality_label = fmt.get('qualityLabel') or quality
1917 formats_spec[itag] = {
1918 'asr': int_or_none(fmt.get('audioSampleRate')),
1919 'filesize': int_or_none(fmt.get('contentLength')),
1920 'format_note': quality_label,
1921 'fps': int_or_none(fmt.get('fps')),
1922 'height': int_or_none(fmt.get('height')),
1923 'quality': q(quality),
1924 # bitrate for itag 43 is always 2147483647
1925 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1926 'width': int_or_none(fmt.get('width')),
1929 for url_data_str in encoded_url_map.split(','):
1930 url_data = compat_parse_qs(url_data_str)
1931 if 'itag' not in url_data or 'url' not in url_data:
1933 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1934 # Unsupported FORMAT_STREAM_TYPE_OTF
1935 if stream_type == 3:
1937 format_id = url_data['itag'][0]
1938 url = url_data['url'][0]
1940 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1941 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1942 jsplayer_url_json = self._search_regex(
1944 embed_webpage if age_gate else video_webpage,
1945 'JS player URL (1)', default=None)
1946 if not jsplayer_url_json and not age_gate:
1947 # We need the embed website after all
1948 if embed_webpage is None:
1949 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1950 embed_webpage = self._download_webpage(
1951 embed_url, video_id, 'Downloading embed webpage')
1952 jsplayer_url_json = self._search_regex(
1953 ASSETS_RE, embed_webpage, 'JS player URL')
1955 player_url = json.loads(jsplayer_url_json)
1956 if player_url is None:
1957 player_url_json = self._search_regex(
1958 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1959 video_webpage, 'age gate player URL')
1960 player_url = json.loads(player_url_json)
1962 if 'sig' in url_data:
1963 url += '&signature=' + url_data['sig'][0]
1964 elif 's' in url_data:
1965 encrypted_sig = url_data['s'][0]
1967 if self._downloader.params.get('verbose'):
1968 if player_url is None:
1969 player_version = 'unknown'
1970 player_desc = 'unknown'
1972 if player_url.endswith('swf'):
1973 player_version = self._search_regex(
1974 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1975 'flash player', fatal=False)
1976 player_desc = 'flash player %s' % player_version
1978 player_version = self._search_regex(
1979 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1980 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
1982 'html5 player', fatal=False)
1983 player_desc = 'html5 player %s' % player_version
1985 parts_sizes = self._signature_cache_id(encrypted_sig)
1986 self.to_screen('{%s} signature length %s, %s' %
1987 (format_id, parts_sizes, player_desc))
1989 signature = self._decrypt_signature(
1990 encrypted_sig, video_id, player_url, age_gate)
1991 url += '&signature=' + signature
1992 if 'ratebypass' not in url:
1993 url += '&ratebypass=yes'
1996 'format_id': format_id,
1998 'player_url': player_url,
2000 if format_id in self._formats:
2001 dct.update(self._formats[format_id])
2002 if format_id in formats_spec:
2003 dct.update(formats_spec[format_id])
2005 # Some itags are not included in DASH manifest thus corresponding formats will
2006 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2007 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2008 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2009 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2011 filesize = int_or_none(url_data.get(
2012 'clen', [None])[0]) or _extract_filesize(url)
2014 quality = url_data.get('quality', [None])[0]
2017 'filesize': filesize,
2018 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
2021 'fps': int_or_none(url_data.get('fps', [None])[0]),
2022 'format_note': url_data.get('quality_label', [None])[0] or quality,
2023 'quality': q(quality),
2025 for key, value in more_fields.items():
2028 type_ = url_data.get('type', [None])[0]
2030 type_split = type_.split(';')
2031 kind_ext = type_split[0].split('/')
2032 if len(kind_ext) == 2:
2034 dct['ext'] = mimetype2ext(type_split[0])
2035 if kind in ('audio', 'video'):
2037 for mobj in re.finditer(
2038 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2039 if mobj.group('key') == 'codecs':
2040 codecs = mobj.group('val')
2043 dct.update(parse_codecs(codecs))
2044 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2045 dct['downloader_options'] = {
2046 # Youtube throttles chunks >~10M
2047 'http_chunk_size': 10485760,
2052 url_or_none(try_get(
2054 lambda x: x['streamingData']['hlsManifestUrl'],
2056 url_or_none(try_get(
2057 video_info, lambda x: x['hlsvp'][0], compat_str)))
2060 m3u8_formats = self._extract_m3u8_formats(
2061 manifest_url, video_id, 'mp4', fatal=False)
2062 for a_format in m3u8_formats:
2063 itag = self._search_regex(
2064 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2066 a_format['format_id'] = itag
2067 if itag in self._formats:
2068 dct = self._formats[itag].copy()
2069 dct.update(a_format)
2071 a_format['player_url'] = player_url
2072 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2073 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2074 formats.append(a_format)
2076 error_message = clean_html(video_info.get('reason', [None])[0])
2077 if not error_message:
2078 error_message = extract_unavailable_message()
2080 raise ExtractorError(error_message, expected=True)
2081 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2084 video_uploader = try_get(
2085 video_info, lambda x: x['author'][0],
2086 compat_str) or str_or_none(video_details.get('author'))
2088 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2090 self._downloader.report_warning('unable to extract uploader name')
2093 video_uploader_id = None
2094 video_uploader_url = None
2096 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2098 if mobj is not None:
2099 video_uploader_id = mobj.group('uploader_id')
2100 video_uploader_url = mobj.group('uploader_url')
2102 self._downloader.report_warning('unable to extract uploader nickname')
2104 channel_id = self._html_search_meta(
2105 'channelId', video_webpage, 'channel id')
2106 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2109 # We try first to get a high quality image:
2110 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2111 video_webpage, re.DOTALL)
2112 if m_thumb is not None:
2113 video_thumbnail = m_thumb.group(1)
2114 elif 'thumbnail_url' not in video_info:
2115 self._downloader.report_warning('unable to extract video thumbnail')
2116 video_thumbnail = None
2117 else: # don't panic if we can't find it
2118 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2121 upload_date = self._html_search_meta(
2122 'datePublished', video_webpage, 'upload date', default=None)
2124 upload_date = self._search_regex(
2125 [r'(?s)id="eow-date.*?>(.*?)</span>',
2126 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2127 video_webpage, 'upload date', default=None)
2128 upload_date = unified_strdate(upload_date)
2130 video_license = self._html_search_regex(
2131 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2132 video_webpage, 'license', default=None)
2134 m_music = re.search(
2136 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2144 \bhref=["\']/red[^>]*>| # drop possible
2145 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2152 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2153 video_creator = clean_html(m_music.group('creator'))
2155 video_alt_title = video_creator = None
2157 def extract_meta(field):
2158 return self._html_search_regex(
2159 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2160 video_webpage, field, default=None)
2162 track = extract_meta('Song')
2163 artist = extract_meta('Artist')
2165 # Youtube Music Auto-generated description
2166 album = release_date = release_year = None
2167 if video_description:
2168 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)
2171 track = mobj.group('track').strip()
2173 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2174 album = mobj.group('album'.strip())
2175 release_year = mobj.group('release_year')
2176 release_date = mobj.group('release_date')
2178 release_date = release_date.replace('-', '')
2179 if not release_year:
2180 release_year = int(release_date[:4])
2182 release_year = int(release_year)
2184 m_episode = re.search(
2185 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2188 series = unescapeHTML(m_episode.group('series'))
2189 season_number = int(m_episode.group('season'))
2190 episode_number = int(m_episode.group('episode'))
2192 series = season_number = episode_number = None
2194 m_cat_container = self._search_regex(
2195 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2196 video_webpage, 'categories', default=None)
2198 category = self._html_search_regex(
2199 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2201 video_categories = None if category is None else [category]
2203 video_categories = None
2206 unescapeHTML(m.group('content'))
2207 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2209 def _extract_count(count_name):
2210 return str_to_int(self._search_regex(
2211 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2212 % re.escape(count_name),
2213 video_webpage, count_name, default=None))
2215 like_count = _extract_count('like')
2216 dislike_count = _extract_count('dislike')
2218 if view_count is None:
2219 view_count = str_to_int(self._search_regex(
2220 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2221 'view count', default=None))
2224 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2225 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2227 video_duration = try_get(
2228 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2229 if not video_duration:
2230 video_duration = int_or_none(video_details.get('lengthSeconds'))
2231 if not video_duration:
2232 video_duration = parse_duration(self._html_search_meta(
2233 'duration', video_webpage, 'video duration'))
2236 video_annotations = None
2237 if self._downloader.params.get('writeannotations', False):
2238 video_annotations = self._extract_annotations(video_id)
2240 chapters = self._extract_chapters(description_original, video_duration)
2242 # Look for the DASH manifest
2243 if self._downloader.params.get('youtube_include_dash_manifest', True):
2244 dash_mpd_fatal = True
2245 for mpd_url in dash_mpds:
2248 def decrypt_sig(mobj):
2250 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2251 return '/signature/%s' % dec_s
2253 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2255 for df in self._extract_mpd_formats(
2256 mpd_url, video_id, fatal=dash_mpd_fatal,
2257 formats_dict=self._formats):
2258 if not df.get('filesize'):
2259 df['filesize'] = _extract_filesize(df['url'])
2260 # Do not overwrite DASH format found in some previous DASH manifest
2261 if df['format_id'] not in dash_formats:
2262 dash_formats[df['format_id']] = df
2263 # Additional DASH manifests may end up in HTTP Error 403 therefore
2264 # allow them to fail without bug report message if we already have
2265 # some DASH manifest succeeded. This is temporary workaround to reduce
2266 # burst of bug reports until we figure out the reason and whether it
2267 # can be fixed at all.
2268 dash_mpd_fatal = False
2269 except (ExtractorError, KeyError) as e:
2270 self.report_warning(
2271 'Skipping DASH manifest: %r' % e, video_id)
2273 # Remove the formats we found through non-DASH, they
2274 # contain less info and it can be wrong, because we use
2275 # fixed values (for example the resolution). See
2276 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2278 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2279 formats.extend(dash_formats.values())
2281 # Check for malformed aspect ratio
2282 stretched_m = re.search(
2283 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2286 w = float(stretched_m.group('w'))
2287 h = float(stretched_m.group('h'))
2288 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2289 # We will only process correct ratios.
2293 if f.get('vcodec') != 'none':
2294 f['stretched_ratio'] = ratio
2296 self._sort_formats(formats)
2298 self.mark_watched(video_id, video_info, player_response)
2302 'uploader': video_uploader,
2303 'uploader_id': video_uploader_id,
2304 'uploader_url': video_uploader_url,
2305 'channel_id': channel_id,
2306 'channel_url': channel_url,
2307 'upload_date': upload_date,
2308 'license': video_license,
2309 'creator': video_creator or artist,
2310 'title': video_title,
2311 'alt_title': video_alt_title or track,
2312 'thumbnail': video_thumbnail,
2313 'description': video_description,
2314 'categories': video_categories,
2316 'subtitles': video_subtitles,
2317 'automatic_captions': automatic_captions,
2318 'duration': video_duration,
2319 'age_limit': 18 if age_gate else 0,
2320 'annotations': video_annotations,
2321 'chapters': chapters,
2322 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2323 'view_count': view_count,
2324 'like_count': like_count,
2325 'dislike_count': dislike_count,
2326 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
2329 'start_time': start_time,
2330 'end_time': end_time,
2332 'season_number': season_number,
2333 'episode_number': episode_number,
2337 'release_date': release_date,
2338 'release_year': release_year,
2342 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2343 IE_DESC = 'YouTube.com playlists'
2344 _VALID_URL = r"""(?x)(?:
2354 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2355 \? (?:.*?[&;])*? (?:p|a|list)=
2358 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2361 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2362 # Top tracks, they can also include dots
2368 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2369 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2370 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2371 IE_NAME = 'youtube:playlist'
2373 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2375 'title': 'ytdl test PL',
2376 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2378 'playlist_count': 3,
2380 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2382 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2383 'title': 'YDL_Empty_List',
2385 'playlist_count': 0,
2386 'skip': 'This playlist is private',
2388 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2389 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2391 'title': '29C3: Not my department',
2392 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2394 'playlist_count': 95,
2396 'note': 'issue #673',
2397 'url': 'PLBB231211A4F62143',
2399 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2400 'id': 'PLBB231211A4F62143',
2402 'playlist_mincount': 26,
2404 'note': 'Large playlist',
2405 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2407 'title': 'Uploads from Cauchemar',
2408 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2410 'playlist_mincount': 799,
2412 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2414 'title': 'YDL_safe_search',
2415 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2417 'playlist_count': 2,
2418 'skip': 'This playlist is private',
2421 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2422 'playlist_count': 4,
2425 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2428 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2429 'playlist_mincount': 485,
2431 'title': '2017 華語最新單曲 (2/24更新)',
2432 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2435 'note': 'Embedded SWF player',
2436 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2437 'playlist_count': 4,
2440 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2443 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2444 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2446 'title': 'Uploads from Interstellar Movie',
2447 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2449 'playlist_mincount': 21,
2451 # Playlist URL that does not actually serve a playlist
2452 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2454 'id': 'FqZTN594JQw',
2456 'title': "Smiley's People 01 detective, Adventure Series, Action",
2457 'uploader': 'STREEM',
2458 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2460 'upload_date': '20150526',
2461 'license': 'Standard YouTube License',
2462 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2463 'categories': ['People & Blogs'],
2467 'dislike_count': int,
2470 'skip_download': True,
2472 'add_ie': [YoutubeIE.ie_key()],
2474 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2476 'id': 'yeWKywCrFtk',
2478 'title': 'Small Scale Baler and Braiding Rugs',
2479 'uploader': 'Backus-Page House Museum',
2480 'uploader_id': 'backuspagemuseum',
2481 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2482 'upload_date': '20161008',
2483 'license': 'Standard YouTube License',
2484 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2485 'categories': ['Nonprofits & Activism'],
2488 'dislike_count': int,
2492 'skip_download': True,
2495 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2496 'only_matching': True,
2498 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2499 'only_matching': True,
2501 # music album playlist
2502 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2503 'only_matching': True,
2505 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2506 'only_matching': True,
2509 def _real_initialize(self):
2512 def _extract_mix(self, playlist_id):
2513 # The mixes are generated from a single video
2514 # the id of the playlist is just 'RD' + video_id
2516 last_id = playlist_id[-11:]
2517 for n in itertools.count(1):
2518 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2519 webpage = self._download_webpage(
2520 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2521 new_ids = orderedSet(re.findall(
2522 r'''(?xs)data-video-username=".*?".*?
2523 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2525 # Fetch new pages until all the videos are repeated, it seems that
2526 # there are always 51 unique videos.
2527 new_ids = [_id for _id in new_ids if _id not in ids]
2533 url_results = self._ids_to_results(ids)
2535 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2537 search_title('playlist-title') or
2538 search_title('title long-title') or
2539 search_title('title'))
2540 title = clean_html(title_span)
2542 return self.playlist_result(url_results, playlist_id, title)
2544 def _extract_playlist(self, playlist_id):
2545 url = self._TEMPLATE_URL % playlist_id
2546 page = self._download_webpage(url, playlist_id)
2548 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2549 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2550 match = match.strip()
2551 # Check if the playlist exists or is private
2552 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2554 reason = mobj.group('reason')
2555 message = 'This playlist %s' % reason
2556 if 'private' in reason:
2557 message += ', use --username or --netrc to access it'
2559 raise ExtractorError(message, expected=True)
2560 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2561 raise ExtractorError(
2562 'Invalid parameters. Maybe URL is incorrect.',
2564 elif re.match(r'[^<]*Choose your language[^<]*', match):
2567 self.report_warning('Youtube gives an alert message: ' + match)
2569 playlist_title = self._html_search_regex(
2570 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2571 page, 'title', default=None)
2573 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2574 uploader = self._search_regex(
2575 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2576 page, 'uploader', default=None)
2578 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2581 uploader_id = mobj.group('uploader_id')
2582 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2584 uploader_id = uploader_url = None
2588 if not playlist_title:
2590 # Some playlist URLs don't actually serve a playlist (e.g.
2591 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2592 next(self._entries(page, playlist_id))
2593 except StopIteration:
2596 playlist = self.playlist_result(
2597 self._entries(page, playlist_id), playlist_id, playlist_title)
2599 'uploader': uploader,
2600 'uploader_id': uploader_id,
2601 'uploader_url': uploader_url,
2604 return has_videos, playlist
2606 def _check_download_just_video(self, url, playlist_id):
2607 # Check if it's a video-specific URL
2608 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2609 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2610 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2611 'video id', default=None)
2613 if self._downloader.params.get('noplaylist'):
2614 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2615 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2617 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2618 return video_id, None
2621 def _real_extract(self, url):
2622 # Extract playlist id
2623 mobj = re.match(self._VALID_URL, url)
2625 raise ExtractorError('Invalid URL: %s' % url)
2626 playlist_id = mobj.group(1) or mobj.group(2)
2628 video_id, video = self._check_download_just_video(url, playlist_id)
2632 if playlist_id.startswith(('RD', 'UL', 'PU')):
2633 # Mixes require a custom extraction process
2634 return self._extract_mix(playlist_id)
2636 has_videos, playlist = self._extract_playlist(playlist_id)
2637 if has_videos or not video_id:
2640 # Some playlist URLs don't actually serve a playlist (see
2641 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2642 # Fallback to plain video extraction if there is a video id
2643 # along with playlist id.
2644 return self.url_result(video_id, 'Youtube', video_id=video_id)
2647 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2648 IE_DESC = 'YouTube.com channels'
2649 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2650 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2651 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2652 IE_NAME = 'youtube:channel'
2654 'note': 'paginated channel',
2655 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2656 'playlist_mincount': 91,
2658 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2659 'title': 'Uploads from lex will',
2662 'note': 'Age restricted channel',
2663 # from https://www.youtube.com/user/DeusExOfficial
2664 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2665 'playlist_mincount': 64,
2667 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2668 'title': 'Uploads from Deus Ex',
2671 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2672 'only_matching': True,
2676 def suitable(cls, url):
2677 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2678 else super(YoutubeChannelIE, cls).suitable(url))
2680 def _build_template_url(self, url, channel_id):
2681 return self._TEMPLATE_URL % channel_id
2683 def _real_extract(self, url):
2684 channel_id = self._match_id(url)
2686 url = self._build_template_url(url, channel_id)
2688 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2689 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2690 # otherwise fallback on channel by page extraction
2691 channel_page = self._download_webpage(
2692 url + '?view=57', channel_id,
2693 'Downloading channel page', fatal=False)
2694 if channel_page is False:
2695 channel_playlist_id = False
2697 channel_playlist_id = self._html_search_meta(
2698 'channelId', channel_page, 'channel id', default=None)
2699 if not channel_playlist_id:
2700 channel_url = self._html_search_meta(
2701 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2702 channel_page, 'channel url', default=None)
2704 channel_playlist_id = self._search_regex(
2705 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2706 channel_url, 'channel id', default=None)
2707 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2708 playlist_id = 'UU' + channel_playlist_id[2:]
2709 return self.url_result(
2710 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2712 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2713 autogenerated = re.search(r'''(?x)
2715 channel-header-autogenerated-label|
2716 yt-channel-title-autogenerated
2717 )[^"]*"''', channel_page) is not None
2720 # The videos are contained in a single page
2721 # the ajax pages can't be used, they are empty
2724 video_id, 'Youtube', video_id=video_id,
2725 video_title=video_title)
2726 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2727 return self.playlist_result(entries, channel_id)
2730 next(self._entries(channel_page, channel_id))
2731 except StopIteration:
2732 alert_message = self._html_search_regex(
2733 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2734 channel_page, 'alert', default=None, group='alert')
2736 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2738 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2741 class YoutubeUserIE(YoutubeChannelIE):
2742 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2743 _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_-]+)'
2744 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2745 IE_NAME = 'youtube:user'
2748 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2749 'playlist_mincount': 320,
2751 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2752 'title': 'Uploads from The Linux Foundation',
2755 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2756 # but not https://www.youtube.com/user/12minuteathlete/videos
2757 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2758 'playlist_mincount': 249,
2760 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2761 'title': 'Uploads from 12 Minute Athlete',
2764 'url': 'ytuser:phihag',
2765 'only_matching': True,
2767 'url': 'https://www.youtube.com/c/gametrailers',
2768 'only_matching': True,
2770 'url': 'https://www.youtube.com/gametrailers',
2771 'only_matching': True,
2773 # This channel is not available, geo restricted to JP
2774 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2775 'only_matching': True,
2779 def suitable(cls, url):
2780 # Don't return True if the url can be extracted with other youtube
2781 # extractor, the regex would is too permissive and it would match.
2782 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2783 if any(ie.suitable(url) for ie in other_yt_ies):
2786 return super(YoutubeUserIE, cls).suitable(url)
2788 def _build_template_url(self, url, channel_id):
2789 mobj = re.match(self._VALID_URL, url)
2790 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2793 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2794 IE_DESC = 'YouTube.com live streams'
2795 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2796 IE_NAME = 'youtube:live'
2799 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2801 'id': 'a48o2S1cPoo',
2803 'title': 'The Young Turks - Live Main Show',
2804 'uploader': 'The Young Turks',
2805 'uploader_id': 'TheYoungTurks',
2806 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2807 'upload_date': '20150715',
2808 'license': 'Standard YouTube License',
2809 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2810 'categories': ['News & Politics'],
2811 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2813 'dislike_count': int,
2816 'skip_download': True,
2819 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2820 'only_matching': True,
2822 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2823 'only_matching': True,
2825 'url': 'https://www.youtube.com/TheYoungTurks/live',
2826 'only_matching': True,
2829 def _real_extract(self, url):
2830 mobj = re.match(self._VALID_URL, url)
2831 channel_id = mobj.group('id')
2832 base_url = mobj.group('base_url')
2833 webpage = self._download_webpage(url, channel_id, fatal=False)
2835 page_type = self._og_search_property(
2836 'type', webpage, 'page type', default='')
2837 video_id = self._html_search_meta(
2838 'videoId', webpage, 'video id', default=None)
2839 if page_type.startswith('video') and video_id and re.match(
2840 r'^[0-9A-Za-z_-]{11}$', video_id):
2841 return self.url_result(video_id, YoutubeIE.ie_key())
2842 return self.url_result(base_url)
2845 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2846 IE_DESC = 'YouTube.com user/channel playlists'
2847 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2848 IE_NAME = 'youtube:playlists'
2851 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2852 'playlist_mincount': 4,
2854 'id': 'ThirstForScience',
2855 'title': 'Thirst for Science',
2858 # with "Load more" button
2859 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2860 'playlist_mincount': 70,
2863 'title': 'Игорь Клейнер',
2866 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2867 'playlist_mincount': 17,
2869 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2870 'title': 'Chem Player',
2875 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2876 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2879 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2880 IE_DESC = 'YouTube.com searches'
2881 # there doesn't appear to be a real limit, for example if you search for
2882 # 'python' you get more than 8.000.000 results
2883 _MAX_RESULTS = float('inf')
2884 IE_NAME = 'youtube:search'
2885 _SEARCH_KEY = 'ytsearch'
2886 _EXTRA_QUERY_ARGS = {}
2889 def _get_n_results(self, query, n):
2890 """Get a specified number of results for a query"""
2896 'search_query': query.encode('utf-8'),
2898 url_query.update(self._EXTRA_QUERY_ARGS)
2899 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2901 for pagenum in itertools.count(1):
2902 data = self._download_json(
2903 result_url, video_id='query "%s"' % query,
2904 note='Downloading page %s' % pagenum,
2905 errnote='Unable to download API page',
2906 query={'spf': 'navigate'})
2907 html_content = data[1]['body']['content']
2909 if 'class="search-message' in html_content:
2910 raise ExtractorError(
2911 '[youtube] No video results', expected=True)
2913 new_videos = list(self._process_page(html_content))
2914 videos += new_videos
2915 if not new_videos or len(videos) > limit:
2917 next_link = self._html_search_regex(
2918 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2919 html_content, 'next link', default=None)
2920 if next_link is None:
2922 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2926 return self.playlist_result(videos, query)
2929 class YoutubeSearchDateIE(YoutubeSearchIE):
2930 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2931 _SEARCH_KEY = 'ytsearchdate'
2932 IE_DESC = 'YouTube.com searches, newest videos first'
2933 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2936 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
2937 IE_DESC = 'YouTube.com search URLs'
2938 IE_NAME = 'youtube:search_url'
2939 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2941 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2942 'playlist_mincount': 5,
2944 'title': 'youtube-dl test video',
2947 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2948 'only_matching': True,
2951 def _real_extract(self, url):
2952 mobj = re.match(self._VALID_URL, url)
2953 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2954 webpage = self._download_webpage(url, query)
2955 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2958 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2959 IE_DESC = 'YouTube.com (multi-season) shows'
2960 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2961 IE_NAME = 'youtube:show'
2963 'url': 'https://www.youtube.com/show/airdisasters',
2964 'playlist_mincount': 5,
2966 'id': 'airdisasters',
2967 'title': 'Air Disasters',
2971 def _real_extract(self, url):
2972 playlist_id = self._match_id(url)
2973 return super(YoutubeShowIE, self)._real_extract(
2974 'https://www.youtube.com/show/%s/playlists' % playlist_id)
2977 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
2979 Base class for feed extractors
2980 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2982 _LOGIN_REQUIRED = True
2986 return 'youtube:%s' % self._FEED_NAME
2988 def _real_initialize(self):
2991 def _entries(self, page):
2992 # The extraction process is the same as for playlists, but the regex
2993 # for the video ids doesn't contain an index
2995 more_widget_html = content_html = page
2996 for page_num in itertools.count(1):
2997 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
2999 # 'recommended' feed has infinite 'load more' and each new portion spins
3000 # the same videos in (sometimes) slightly different order, so we'll check
3001 # for unicity and break when portion has no new videos
3002 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3008 for entry in self._ids_to_results(new_ids):
3011 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3015 more = self._download_json(
3016 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3017 'Downloading page #%s' % page_num,
3018 transform_source=uppercase_escape)
3019 content_html = more['content_html']
3020 more_widget_html = more['load_more_widget_html']
3022 def _real_extract(self, url):
3023 page = self._download_webpage(
3024 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3025 self._PLAYLIST_TITLE)
3026 return self.playlist_result(
3027 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3030 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3031 IE_NAME = 'youtube:watchlater'
3032 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3033 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3036 'url': 'https://www.youtube.com/playlist?list=WL',
3037 'only_matching': True,
3039 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3040 'only_matching': True,
3043 def _real_extract(self, url):
3044 _, video = self._check_download_just_video(url, 'WL')
3047 _, playlist = self._extract_playlist('WL')
3051 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3052 IE_NAME = 'youtube:favorites'
3053 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3054 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3055 _LOGIN_REQUIRED = True
3057 def _real_extract(self, url):
3058 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3059 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3060 return self.url_result(playlist_id, 'YoutubePlaylist')
3063 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3064 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3065 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3066 _FEED_NAME = 'recommended'
3067 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3070 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3071 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3072 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3073 _FEED_NAME = 'subscriptions'
3074 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3077 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3078 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3079 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3080 _FEED_NAME = 'history'
3081 _PLAYLIST_TITLE = 'Youtube History'
3084 class YoutubeTruncatedURLIE(InfoExtractor):
3085 IE_NAME = 'youtube:truncated_url'
3086 IE_DESC = False # Do not list
3087 _VALID_URL = r'''(?x)
3089 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3092 annotation_id=annotation_[^&]+|
3098 attribution_link\?a=[^&]+
3104 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3105 'only_matching': True,
3107 'url': 'https://www.youtube.com/watch?',
3108 'only_matching': True,
3110 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3111 'only_matching': True,
3113 'url': 'https://www.youtube.com/watch?feature=foo',
3114 'only_matching': True,
3116 'url': 'https://www.youtube.com/watch?hl=en-GB',
3117 'only_matching': True,
3119 'url': 'https://www.youtube.com/watch?t=2372',
3120 'only_matching': True,
3123 def _real_extract(self, url):
3124 raise ExtractorError(
3125 'Did you forget to quote the URL? Remember that & is a meta '
3126 'character in most shells, so you want to put the URL in quotes, '
3128 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3129 ' or simply youtube-dl BaW_jenozKc .',
3133 class YoutubeTruncatedIDIE(InfoExtractor):
3134 IE_NAME = 'youtube:truncated_id'
3135 IE_DESC = False # Do not list
3136 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3139 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3140 'only_matching': True,
3143 def _real_extract(self, url):
3144 video_id = self._match_id(url)
3145 raise ExtractorError(
3146 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),