3 from __future__ import unicode_literals
14 from .common import InfoExtractor, SearchInfoExtractor
15 from ..jsinterp import JSInterpreter
16 from ..swfinterp import SWFInterpreter
17 from ..compat import (
22 compat_urllib_parse_unquote,
23 compat_urllib_parse_unquote_plus,
24 compat_urllib_parse_urlencode,
25 compat_urllib_parse_urlparse,
35 get_element_by_attribute,
58 class YoutubeBaseInfoExtractor(InfoExtractor):
59 """Provide base functions for Youtube extractors"""
60 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
61 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
63 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
64 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
65 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
67 _NETRC_MACHINE = 'youtube'
68 # If True it will raise an error if no login info is provided
69 _LOGIN_REQUIRED = False
71 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
73 def _set_language(self):
75 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
76 # YouTube sets the expire time to about two months
77 expire_time=time.time() + 2 * 30 * 24 * 3600)
79 def _ids_to_results(self, ids):
81 self.url_result(vid_id, 'Youtube', video_id=vid_id)
86 Attempt to log in to YouTube.
87 True is returned if successful or skipped.
88 False is returned if login failed.
90 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
92 username, password = self._get_login_info()
93 # No authentication to be performed
95 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
96 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
99 login_page = self._download_webpage(
100 self._LOGIN_URL, None,
101 note='Downloading login page',
102 errnote='unable to fetch login page', fatal=False)
103 if login_page is False:
106 login_form = self._hidden_inputs(login_page)
108 def req(url, f_req, note, errnote):
109 data = login_form.copy()
112 'checkConnection': 'youtube',
113 'checkedDomains': 'youtube',
115 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
116 'f.req': json.dumps(f_req),
117 'flowName': 'GlifWebSignIn',
118 'flowEntry': 'ServiceLogin',
120 return self._download_json(
121 url, None, note=note, errnote=errnote,
122 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
124 data=urlencode_postdata(data), headers={
125 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
126 'Google-Accounts-XSRF': 1,
130 self._downloader.report_warning(message)
134 None, [], None, 'US', None, None, 2, False, True,
138 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
140 1, [None, None, []], None, None, None, True
145 lookup_results = req(
146 self._LOOKUP_URL, lookup_req,
147 'Looking up account info', 'Unable to look up account info')
149 if lookup_results is False:
152 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
154 warn('Unable to extract user hash')
159 None, 1, None, [1, None, None, None, [password, None, True]],
161 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
162 1, [None, None, []], None, None, None, True
165 challenge_results = req(
166 self._CHALLENGE_URL, challenge_req,
167 'Logging in', 'Unable to log in')
169 if challenge_results is False:
172 login_res = try_get(challenge_results, lambda x: x[0][5], list)
174 login_msg = try_get(login_res, lambda x: x[5], compat_str)
176 'Unable to login: %s' % 'Invalid password'
177 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
180 res = try_get(challenge_results, lambda x: x[0][-1], list)
182 warn('Unable to extract result entry')
185 login_challenge = try_get(res, lambda x: x[0][0], list)
187 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
188 if challenge_str == 'TWO_STEP_VERIFICATION':
189 # SEND_SUCCESS - TFA code has been successfully sent to phone
190 # QUOTA_EXCEEDED - reached the limit of TFA codes
191 status = try_get(login_challenge, lambda x: x[5], compat_str)
192 if status == 'QUOTA_EXCEEDED':
193 warn('Exceeded the limit of TFA codes, try later')
196 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
198 warn('Unable to extract TL')
201 tfa_code = self._get_tfa_info('2-step verification code')
205 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
206 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
209 tfa_code = remove_start(tfa_code, 'G-')
212 user_hash, None, 2, None,
214 9, None, None, None, None, None, None, None,
215 [None, tfa_code, True, 2]
219 self._TFA_URL.format(tl), tfa_req,
220 'Submitting TFA code', 'Unable to submit TFA code')
222 if tfa_results is False:
225 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
227 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
229 'Unable to finish TFA: %s' % 'Invalid TFA code'
230 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
233 check_cookie_url = try_get(
234 tfa_results, lambda x: x[0][-1][2], compat_str)
237 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
238 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
239 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
241 challenge = CHALLENGES.get(
243 '%s returned error %s.' % (self.IE_NAME, challenge_str))
244 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
247 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
249 if not check_cookie_url:
250 warn('Unable to extract CheckCookie URL')
253 check_cookie_results = self._download_webpage(
254 check_cookie_url, None, 'Checking cookie', fatal=False)
256 if check_cookie_results is False:
259 if 'https://myaccount.google.com/' not in check_cookie_results:
260 warn('Unable to log in')
265 def _download_webpage_handle(self, *args, **kwargs):
266 query = kwargs.get('query', {}).copy()
267 query['disable_polymer'] = 'true'
268 kwargs['query'] = query
269 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
270 *args, **compat_kwargs(kwargs))
272 def _real_initialize(self):
273 if self._downloader is None:
276 if not self._login():
280 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
281 # Extract entries from page with "Load more" button
282 def _entries(self, page, playlist_id):
283 more_widget_html = content_html = page
284 for page_num in itertools.count(1):
285 for entry in self._process_page(content_html):
288 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
294 while count <= retries:
296 # Downloading page may result in intermittent 5xx HTTP error
297 # that is usually worked around with a retry
298 more = self._download_json(
299 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
300 'Downloading page #%s%s'
301 % (page_num, ' (retry #%d)' % count if count else ''),
302 transform_source=uppercase_escape)
304 except ExtractorError as e:
305 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
311 content_html = more['content_html']
312 if not content_html.strip():
313 # Some webpages show a "Load more" button but they don't
316 more_widget_html = more['load_more_widget_html']
319 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
320 def _process_page(self, content):
321 for video_id, video_title in self.extract_videos_from_page(content):
322 yield self.url_result(video_id, 'Youtube', video_id, video_title)
324 def extract_videos_from_page(self, page):
327 for mobj in re.finditer(self._VIDEO_RE, page):
328 # The link with index 0 is not the first video of the playlist (not sure if still actual)
329 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
331 video_id = mobj.group('id')
332 video_title = unescapeHTML(mobj.group('title'))
334 video_title = video_title.strip()
336 idx = ids_in_page.index(video_id)
337 if video_title and not titles_in_page[idx]:
338 titles_in_page[idx] = video_title
340 ids_in_page.append(video_id)
341 titles_in_page.append(video_title)
342 return zip(ids_in_page, titles_in_page)
345 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
346 def _process_page(self, content):
347 for playlist_id in orderedSet(re.findall(
348 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
350 yield self.url_result(
351 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
353 def _real_extract(self, url):
354 playlist_id = self._match_id(url)
355 webpage = self._download_webpage(url, playlist_id)
356 title = self._og_search_title(webpage, fatal=False)
357 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
360 class YoutubeIE(YoutubeBaseInfoExtractor):
361 IE_DESC = 'YouTube.com'
362 _VALID_URL = r"""(?x)^
364 (?:https?://|//) # http(s):// or protocol-independent URL
365 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
366 (?:www\.)?deturl\.com/www\.youtube\.com/|
367 (?:www\.)?pwnyoutube\.com/|
368 (?:www\.)?hooktube\.com/|
369 (?:www\.)?yourepeat\.com/|
370 tube\.majestyc\.net/|
371 (?:(?:www|dev)\.)?invidio\.us/|
372 (?:www\.)?invidiou\.sh/|
373 (?:www\.)?invidious\.snopyta\.org/|
374 (?:www\.)?invidious\.kabi\.tk/|
375 (?:www\.)?vid\.wxzm\.sx/|
376 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
377 (?:.*?\#/)? # handle anchor (#/) redirect urls
378 (?: # the various things that can precede the ID:
379 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
380 |(?: # or the v= param in all its forms
381 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
382 (?:\?|\#!?) # the params delimiter ? or # or #!
383 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
388 youtu\.be| # just youtu.be/xxxx
389 vid\.plus| # or vid.plus/xxxx
390 zwearz\.com/watch| # or zwearz.com/watch/xxxx
392 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
394 )? # all until now is optional -> you can pass the naked ID
395 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
398 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
399 WL # WL are handled by the watch later IE
402 (?(1).+)? # if we found the ID, everything can follow
403 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
404 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
406 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
407 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
408 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
409 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
410 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
411 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
412 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
413 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
414 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
415 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
416 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
417 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
418 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
419 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
420 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
421 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
422 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
423 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
427 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
428 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
429 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
430 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
431 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
432 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
433 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
435 # Apple HTTP Live Streaming
436 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
437 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
438 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
439 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
440 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
441 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
442 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
443 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
446 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
447 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
448 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
449 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
450 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
451 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
452 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
453 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
454 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
455 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
456 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
457 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
460 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
461 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
462 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
463 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
464 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
465 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
466 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
469 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
470 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
471 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
472 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
473 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
474 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
475 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
476 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
477 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
478 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
479 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
480 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
481 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
482 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
483 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
484 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
485 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
486 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
487 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
488 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
489 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
490 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
493 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
494 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
496 # Dash webm audio with opus inside
497 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
498 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
499 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
502 '_rtmp': {'protocol': 'rtmp'},
504 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
511 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
515 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
516 'uploader': 'Philipp Hagemeister',
517 'uploader_id': 'phihag',
518 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
519 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
520 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
521 'upload_date': '20121002',
522 '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 .',
523 'categories': ['Science & Technology'],
524 'tags': ['youtube-dl'],
528 'dislike_count': int,
534 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
535 'note': 'Test generic use_cipher_signature video (#897)',
539 'upload_date': '20120506',
540 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
541 'alt_title': 'I Love It (feat. Charli XCX)',
542 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
543 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
544 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
545 'iconic ep', 'iconic', 'love', 'it'],
547 'uploader': 'Icona Pop',
548 'uploader_id': 'IconaPop',
549 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
550 'creator': 'Icona Pop',
551 'track': 'I Love It (feat. Charli XCX)',
552 'artist': 'Icona Pop',
556 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
557 'note': 'Test VEVO video with age protection (#956)',
561 'upload_date': '20130703',
562 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
563 'alt_title': 'Tunnel Vision',
564 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
566 'uploader': 'justintimberlakeVEVO',
567 'uploader_id': 'justintimberlakeVEVO',
568 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
569 'creator': 'Justin Timberlake',
570 'track': 'Tunnel Vision',
571 'artist': 'Justin Timberlake',
576 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
577 'note': 'Embed-only video (#1746)',
581 'upload_date': '20120608',
582 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
583 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
584 'uploader': 'SET India',
585 'uploader_id': 'setindia',
586 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
591 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
592 'note': 'Use the first video ID in the URL',
596 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
597 'uploader': 'Philipp Hagemeister',
598 'uploader_id': 'phihag',
599 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
600 'upload_date': '20121002',
601 '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 .',
602 'categories': ['Science & Technology'],
603 'tags': ['youtube-dl'],
607 'dislike_count': int,
610 'skip_download': True,
614 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
615 'note': '256k DASH audio (format 141) via DASH manifest',
619 'upload_date': '20121002',
620 'uploader_id': '8KVIDEO',
621 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
623 'uploader': '8KVIDEO',
624 'title': 'UHDTV TEST 8K VIDEO.mp4'
627 'youtube_include_dash_manifest': True,
630 'skip': 'format 141 not served anymore',
632 # DASH manifest with encrypted signature
634 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
638 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
639 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
641 'uploader': 'AfrojackVEVO',
642 'uploader_id': 'AfrojackVEVO',
643 'upload_date': '20131011',
646 'youtube_include_dash_manifest': True,
647 'format': '141/bestaudio[ext=m4a]',
650 # JS player signature function name containing $
652 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
656 'title': 'Taylor Swift - Shake It Off',
657 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
659 'uploader': 'TaylorSwiftVEVO',
660 'uploader_id': 'TaylorSwiftVEVO',
661 'upload_date': '20140818',
662 'creator': 'Taylor Swift',
665 'youtube_include_dash_manifest': True,
666 'format': '141/bestaudio[ext=m4a]',
671 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
676 'upload_date': '20100909',
677 'uploader': 'Amazing Atheist',
678 'uploader_id': 'TheAmazingAtheist',
679 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
680 'title': 'Burning Everyone\'s Koran',
681 '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',
684 # Normal age-gate video (No vevo, embed allowed)
686 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
690 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
691 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
693 'uploader': 'The Witcher',
694 'uploader_id': 'WitcherGame',
695 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
696 'upload_date': '20140605',
700 # Age-gate video with encrypted signature
702 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
706 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
707 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
709 'uploader': 'LloydVEVO',
710 'uploader_id': 'LloydVEVO',
711 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
712 'upload_date': '20110629',
716 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
717 # YouTube Red ad is not captured for creator
719 'url': '__2ABJjxzNo',
724 'upload_date': '20100430',
725 'uploader_id': 'deadmau5',
726 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
727 'creator': 'deadmau5',
728 'description': 'md5:12c56784b8032162bb936a5f76d55360',
729 'uploader': 'deadmau5',
730 'title': 'Deadmau5 - Some Chords (HD)',
731 'alt_title': 'Some Chords',
733 'expected_warnings': [
734 'DASH manifest missing',
737 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
739 'url': 'lqQg6PlCWgI',
744 'upload_date': '20150827',
745 'uploader_id': 'olympic',
746 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
747 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
748 'uploader': 'Olympic',
749 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
752 'skip_download': 'requires avconv',
757 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
761 'stretched_ratio': 16 / 9.,
763 'upload_date': '20110310',
764 'uploader_id': 'AllenMeow',
765 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
766 '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',
768 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
771 # url_encoded_fmt_stream_map is empty string
773 'url': 'qEJwOuvDf7I',
777 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
779 'upload_date': '20150404',
780 'uploader_id': 'spbelect',
781 'uploader': 'Наблюдатели Петербурга',
784 'skip_download': 'requires avconv',
786 'skip': 'This live event has ended.',
788 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
790 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
794 'title': 'md5:7b81415841e02ecd4313668cde88737a',
795 'description': 'md5:116377fd2963b81ec4ce64b542173306',
797 'upload_date': '20150625',
798 'uploader_id': 'dorappi2000',
799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
800 'uploader': 'dorappi2000',
801 'formats': 'mincount:31',
803 'skip': 'not actual anymore',
805 # DASH manifest with segment_list
807 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
808 'md5': '8ce563a1d667b599d21064e982ab9e31',
812 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
813 'uploader': 'Airtek',
814 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
815 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
816 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
819 'youtube_include_dash_manifest': True,
820 'format': '135', # bestvideo
822 'skip': 'This live event has ended.',
825 # Multifeed videos (multiple cameras), URL is for Main Camera
826 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
829 'title': 'teamPGP: Rocket League Noob Stream',
830 'description': 'md5:dc7872fb300e143831327f1bae3af010',
836 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
837 'description': 'md5:dc7872fb300e143831327f1bae3af010',
839 'upload_date': '20150721',
840 'uploader': 'Beer Games Beer',
841 'uploader_id': 'beergamesbeer',
842 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
843 'license': 'Standard YouTube License',
849 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
850 'description': 'md5:dc7872fb300e143831327f1bae3af010',
852 'upload_date': '20150721',
853 'uploader': 'Beer Games Beer',
854 'uploader_id': 'beergamesbeer',
855 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
856 'license': 'Standard YouTube License',
862 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
863 'description': 'md5:dc7872fb300e143831327f1bae3af010',
865 'upload_date': '20150721',
866 'uploader': 'Beer Games Beer',
867 'uploader_id': 'beergamesbeer',
868 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
869 'license': 'Standard YouTube License',
875 'title': 'teamPGP: Rocket League Noob Stream (zim)',
876 'description': 'md5:dc7872fb300e143831327f1bae3af010',
878 'upload_date': '20150721',
879 'uploader': 'Beer Games Beer',
880 'uploader_id': 'beergamesbeer',
881 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
882 'license': 'Standard YouTube License',
886 'skip_download': True,
888 'skip': 'This video is not available.',
891 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
892 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
895 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
898 'skip': 'Not multifeed anymore',
901 'url': 'https://vid.plus/FlRa-iH7PGw',
902 'only_matching': True,
905 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
906 'only_matching': True,
909 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
910 # Also tests cut-off URL expansion in video description (see
911 # https://github.com/ytdl-org/youtube-dl/issues/1892,
912 # https://github.com/ytdl-org/youtube-dl/issues/8164)
913 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
917 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
918 'alt_title': 'Dark Walk - Position Music',
919 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
921 'upload_date': '20151119',
922 'uploader_id': 'IronSoulElf',
923 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
924 'uploader': 'IronSoulElf',
925 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
926 'track': 'Dark Walk - Position Music',
927 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
928 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
931 'skip_download': True,
935 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
936 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
937 'only_matching': True,
940 # Video with yt:stretch=17:0
941 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
945 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
946 'description': 'md5:ee18a25c350637c8faff806845bddee9',
947 'upload_date': '20151107',
948 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
949 'uploader': 'CH GAMER DROID',
952 'skip_download': True,
954 'skip': 'This video does not exist.',
957 # Video licensed under Creative Commons
958 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
962 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
963 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
965 'upload_date': '20150127',
966 'uploader_id': 'BerkmanCenter',
967 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
968 'uploader': 'The Berkman Klein Center for Internet & Society',
969 'license': 'Creative Commons Attribution license (reuse allowed)',
972 'skip_download': True,
976 # Channel-like uploader_url
977 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
981 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
982 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
984 'upload_date': '20151119',
985 'uploader': 'Bernie Sanders',
986 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
987 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
988 'license': 'Creative Commons Attribution license (reuse allowed)',
991 'skip_download': True,
995 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
996 'only_matching': True,
999 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1000 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1001 'only_matching': True,
1004 # Rental video preview
1005 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1007 'id': 'uGpuVWrhIzE',
1009 'title': 'Piku - Trailer',
1010 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1011 'upload_date': '20150811',
1012 'uploader': 'FlixMatrix',
1013 'uploader_id': 'FlixMatrixKaravan',
1014 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1015 'license': 'Standard YouTube License',
1018 'skip_download': True,
1020 'skip': 'This video is not available.',
1023 # YouTube Red video with episode data
1024 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1026 'id': 'iqKdEhx-dD4',
1028 'title': 'Isolation - Mind Field (Ep 1)',
1029 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1031 'upload_date': '20170118',
1032 'uploader': 'Vsauce',
1033 'uploader_id': 'Vsauce',
1034 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1035 'series': 'Mind Field',
1037 'episode_number': 1,
1040 'skip_download': True,
1042 'expected_warnings': [
1043 'Skipping DASH manifest',
1047 # The following content has been identified by the YouTube community
1048 # as inappropriate or offensive to some audiences.
1049 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1051 'id': '6SJNVb0GnPI',
1053 'title': 'Race Differences in Intelligence',
1054 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1056 'upload_date': '20140124',
1057 'uploader': 'New Century Foundation',
1058 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1059 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1062 'skip_download': True,
1067 'url': '1t24XAntNCY',
1068 'only_matching': True,
1071 # geo restricted to JP
1072 'url': 'sJL6WA-aGkQ',
1073 'only_matching': True,
1076 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1077 'only_matching': True,
1080 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1081 'only_matching': True,
1085 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1086 'only_matching': True,
1089 # Video with unsupported adaptive stream type formats
1090 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1092 'id': 'Z4Vy8R84T1U',
1094 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1095 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1097 'upload_date': '20130923',
1098 'uploader': 'Amelia Putri Harwita',
1099 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1100 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1101 'formats': 'maxcount:10',
1104 'skip_download': True,
1105 'youtube_include_dash_manifest': False,
1109 # Youtube Music Auto-generated description
1110 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1112 'id': 'MgNrAu2pzNs',
1114 'title': 'Voyeur Girl',
1115 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1116 'upload_date': '20190312',
1117 'uploader': 'Various Artists - Topic',
1118 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
1119 'artist': 'Stephen',
1120 'track': 'Voyeur Girl',
1121 'album': 'it\'s too much love to know my dear',
1122 'release_date': '20190313',
1123 'release_year': 2019,
1126 'skip_download': True,
1130 # Youtube Music Auto-generated description
1131 # Retrieve 'artist' field from 'Artist:' in video description
1132 # when it is present on youtube music video
1133 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1135 'id': 'k0jLE7tTwjY',
1137 'title': 'Latch Feat. Sam Smith',
1138 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1139 'upload_date': '20150110',
1140 'uploader': 'Various Artists - Topic',
1141 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1142 'artist': 'Disclosure',
1143 'track': 'Latch Feat. Sam Smith',
1144 'album': 'Latch Featuring Sam Smith',
1145 'release_date': '20121008',
1146 'release_year': 2012,
1149 'skip_download': True,
1153 # Youtube Music Auto-generated description
1154 # handle multiple artists on youtube music video
1155 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1157 'id': '74qn0eJSjpA',
1159 'title': 'Eastside',
1160 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1161 'upload_date': '20180710',
1162 'uploader': 'Benny Blanco - Topic',
1163 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1164 'artist': 'benny blanco, Halsey, Khalid',
1165 'track': 'Eastside',
1166 'album': 'Eastside',
1167 'release_date': '20180713',
1168 'release_year': 2018,
1171 'skip_download': True,
1175 # Youtube Music Auto-generated description
1176 # handle youtube music video with release_year and no release_date
1177 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1179 'id': '-hcAI0g-f5M',
1181 'title': 'Put It On Me',
1182 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
1183 'upload_date': '20180426',
1184 'uploader': 'Matt Maeson - Topic',
1185 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1186 'artist': 'Matt Maeson',
1187 'track': 'Put It On Me',
1188 'album': 'The Hearse',
1189 'release_date': None,
1190 'release_year': 2018,
1193 'skip_download': True,
1198 def __init__(self, *args, **kwargs):
1199 super(YoutubeIE, self).__init__(*args, **kwargs)
1200 self._player_cache = {}
1202 def report_video_info_webpage_download(self, video_id):
1203 """Report attempt to download video info webpage."""
1204 self.to_screen('%s: Downloading video info webpage' % video_id)
1206 def report_information_extraction(self, video_id):
1207 """Report attempt to extract video information."""
1208 self.to_screen('%s: Extracting video information' % video_id)
1210 def report_unavailable_format(self, video_id, format):
1211 """Report extracted video URL."""
1212 self.to_screen('%s: Format %s not available' % (video_id, format))
1214 def report_rtmp_download(self):
1215 """Indicate the download will use the RTMP protocol."""
1216 self.to_screen('RTMP download detected')
1218 def _signature_cache_id(self, example_sig):
1219 """ Return a string representation of a signature """
1220 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1222 def _extract_signature_function(self, video_id, player_url, example_sig):
1224 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1227 raise ExtractorError('Cannot identify player %r' % player_url)
1228 player_type = id_m.group('ext')
1229 player_id = id_m.group('id')
1231 # Read from filesystem cache
1232 func_id = '%s_%s_%s' % (
1233 player_type, player_id, self._signature_cache_id(example_sig))
1234 assert os.path.basename(func_id) == func_id
1236 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1237 if cache_spec is not None:
1238 return lambda s: ''.join(s[i] for i in cache_spec)
1241 'Downloading player %s' % player_url
1242 if self._downloader.params.get('verbose') else
1243 'Downloading %s player %s' % (player_type, player_id)
1245 if player_type == 'js':
1246 code = self._download_webpage(
1247 player_url, video_id,
1249 errnote='Download of %s failed' % player_url)
1250 res = self._parse_sig_js(code)
1251 elif player_type == 'swf':
1252 urlh = self._request_webpage(
1253 player_url, video_id,
1255 errnote='Download of %s failed' % player_url)
1257 res = self._parse_sig_swf(code)
1259 assert False, 'Invalid player type %r' % player_type
1261 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1262 cache_res = res(test_string)
1263 cache_spec = [ord(c) for c in cache_res]
1265 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1268 def _print_sig_code(self, func, example_sig):
1269 def gen_sig_code(idxs):
1270 def _genslice(start, end, step):
1271 starts = '' if start == 0 else str(start)
1272 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1273 steps = '' if step == 1 else (':%d' % step)
1274 return 's[%s%s%s]' % (starts, ends, steps)
1277 # Quelch pyflakes warnings - start will be set when step is set
1278 start = '(Never used)'
1279 for i, prev in zip(idxs[1:], idxs[:-1]):
1280 if step is not None:
1281 if i - prev == step:
1283 yield _genslice(start, prev, step)
1286 if i - prev in [-1, 1]:
1291 yield 's[%d]' % prev
1295 yield _genslice(start, i, step)
1297 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1298 cache_res = func(test_string)
1299 cache_spec = [ord(c) for c in cache_res]
1300 expr_code = ' + '.join(gen_sig_code(cache_spec))
1301 signature_id_tuple = '(%s)' % (
1302 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1303 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1304 ' return %s\n') % (signature_id_tuple, expr_code)
1305 self.to_screen('Extracted signature function:\n' + code)
1307 def _parse_sig_js(self, jscode):
1308 funcname = self._search_regex(
1309 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1310 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1311 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
1312 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1313 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1314 jscode, 'Initial JS player signature function name', group='sig')
1316 jsi = JSInterpreter(jscode)
1317 initial_function = jsi.extract_function(funcname)
1318 return lambda s: initial_function([s])
1320 def _parse_sig_swf(self, file_contents):
1321 swfi = SWFInterpreter(file_contents)
1322 TARGET_CLASSNAME = 'SignatureDecipher'
1323 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1324 initial_function = swfi.extract_function(searched_class, 'decipher')
1325 return lambda s: initial_function([s])
1327 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1328 """Turn the encrypted s field into a working signature"""
1330 if player_url is None:
1331 raise ExtractorError('Cannot decrypt signature without player_url')
1333 if player_url.startswith('//'):
1334 player_url = 'https:' + player_url
1335 elif not re.match(r'https?://', player_url):
1336 player_url = compat_urlparse.urljoin(
1337 'https://www.youtube.com', player_url)
1339 player_id = (player_url, self._signature_cache_id(s))
1340 if player_id not in self._player_cache:
1341 func = self._extract_signature_function(
1342 video_id, player_url, s
1344 self._player_cache[player_id] = func
1345 func = self._player_cache[player_id]
1346 if self._downloader.params.get('youtube_print_sig_code'):
1347 self._print_sig_code(func, s)
1349 except Exception as e:
1350 tb = traceback.format_exc()
1351 raise ExtractorError(
1352 'Signature extraction failed: ' + tb, cause=e)
1354 def _get_subtitles(self, video_id, webpage):
1356 subs_doc = self._download_xml(
1357 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1358 video_id, note=False)
1359 except ExtractorError as err:
1360 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1364 for track in subs_doc.findall('track'):
1365 lang = track.attrib['lang_code']
1366 if lang in sub_lang_list:
1369 for ext in self._SUBTITLE_FORMATS:
1370 params = compat_urllib_parse_urlencode({
1374 'name': track.attrib['name'].encode('utf-8'),
1376 sub_formats.append({
1377 'url': 'https://www.youtube.com/api/timedtext?' + params,
1380 sub_lang_list[lang] = sub_formats
1381 if not sub_lang_list:
1382 self._downloader.report_warning('video doesn\'t have subtitles')
1384 return sub_lang_list
1386 def _get_ytplayer_config(self, video_id, webpage):
1388 # User data may contain arbitrary character sequences that may affect
1389 # JSON extraction with regex, e.g. when '};' is contained the second
1390 # regex won't capture the whole JSON. Yet working around by trying more
1391 # concrete regex first keeping in mind proper quoted string handling
1392 # to be implemented in future that will replace this workaround (see
1393 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1394 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1395 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1396 r';ytplayer\.config\s*=\s*({.+?});',
1398 config = self._search_regex(
1399 patterns, webpage, 'ytplayer.config', default=None)
1401 return self._parse_json(
1402 uppercase_escape(config), video_id, fatal=False)
1404 def _get_automatic_captions(self, video_id, webpage):
1405 """We need the webpage for getting the captions url, pass it as an
1406 argument to speed up the process."""
1407 self.to_screen('%s: Looking for automatic captions' % video_id)
1408 player_config = self._get_ytplayer_config(video_id, webpage)
1409 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1410 if not player_config:
1411 self._downloader.report_warning(err_msg)
1414 args = player_config['args']
1415 caption_url = args.get('ttsurl')
1417 timestamp = args['timestamp']
1418 # We get the available subtitles
1419 list_params = compat_urllib_parse_urlencode({
1424 list_url = caption_url + '&' + list_params
1425 caption_list = self._download_xml(list_url, video_id)
1426 original_lang_node = caption_list.find('track')
1427 if original_lang_node is None:
1428 self._downloader.report_warning('Video doesn\'t have automatic captions')
1430 original_lang = original_lang_node.attrib['lang_code']
1431 caption_kind = original_lang_node.attrib.get('kind', '')
1434 for lang_node in caption_list.findall('target'):
1435 sub_lang = lang_node.attrib['lang_code']
1437 for ext in self._SUBTITLE_FORMATS:
1438 params = compat_urllib_parse_urlencode({
1439 'lang': original_lang,
1443 'kind': caption_kind,
1445 sub_formats.append({
1446 'url': caption_url + '&' + params,
1449 sub_lang_list[sub_lang] = sub_formats
1450 return sub_lang_list
1452 def make_captions(sub_url, sub_langs):
1453 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1454 caption_qs = compat_parse_qs(parsed_sub_url.query)
1456 for sub_lang in sub_langs:
1458 for ext in self._SUBTITLE_FORMATS:
1460 'tlang': [sub_lang],
1463 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1464 query=compat_urllib_parse_urlencode(caption_qs, True)))
1465 sub_formats.append({
1469 captions[sub_lang] = sub_formats
1472 # New captions format as of 22.06.2017
1473 player_response = args.get('player_response')
1474 if player_response and isinstance(player_response, compat_str):
1475 player_response = self._parse_json(
1476 player_response, video_id, fatal=False)
1478 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1479 base_url = renderer['captionTracks'][0]['baseUrl']
1481 for lang in renderer['translationLanguages']:
1482 lang_code = lang.get('languageCode')
1484 sub_lang_list.append(lang_code)
1485 return make_captions(base_url, sub_lang_list)
1487 # Some videos don't provide ttsurl but rather caption_tracks and
1488 # caption_translation_languages (e.g. 20LmZk1hakA)
1489 # Does not used anymore as of 22.06.2017
1490 caption_tracks = args['caption_tracks']
1491 caption_translation_languages = args['caption_translation_languages']
1492 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1494 for lang in caption_translation_languages.split(','):
1495 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1496 sub_lang = lang_qs.get('lc', [None])[0]
1498 sub_lang_list.append(sub_lang)
1499 return make_captions(caption_url, sub_lang_list)
1500 # An extractor error can be raise by the download process if there are
1501 # no automatic captions but there are subtitles
1502 except (KeyError, IndexError, ExtractorError):
1503 self._downloader.report_warning(err_msg)
1506 def _mark_watched(self, video_id, video_info, player_response):
1507 playback_url = url_or_none(try_get(
1509 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1510 video_info, lambda x: x['videostats_playback_base_url'][0]))
1511 if not playback_url:
1513 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1514 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1516 # cpn generation algorithm is reverse engineered from base.js.
1517 # In fact it works even with dummy cpn.
1518 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1519 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1525 playback_url = compat_urlparse.urlunparse(
1526 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1528 self._download_webpage(
1529 playback_url, video_id, 'Marking watched',
1530 'Unable to mark watched', fatal=False)
1533 def _extract_urls(webpage):
1534 # Embedded YouTube player
1536 unescapeHTML(mobj.group('url'))
1537 for mobj in re.finditer(r'''(?x)
1547 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1548 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1551 # lazyYT YouTube embed
1552 entries.extend(list(map(
1554 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1556 # Wordpress "YouTube Video Importer" plugin
1557 matches = re.findall(r'''(?x)<div[^>]+
1558 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1559 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1560 entries.extend(m[-1] for m in matches)
1565 def _extract_url(webpage):
1566 urls = YoutubeIE._extract_urls(webpage)
1567 return urls[0] if urls else None
1570 def extract_id(cls, url):
1571 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1573 raise ExtractorError('Invalid URL: %s' % url)
1574 video_id = mobj.group(2)
1577 def _extract_annotations(self, video_id):
1578 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1579 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1582 def _extract_chapters(description, duration):
1585 chapter_lines = re.findall(
1586 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1588 if not chapter_lines:
1591 for next_num, (chapter_line, time_point) in enumerate(
1592 chapter_lines, start=1):
1593 start_time = parse_duration(time_point)
1594 if start_time is None:
1596 if start_time > duration:
1598 end_time = (duration if next_num == len(chapter_lines)
1599 else parse_duration(chapter_lines[next_num][1]))
1600 if end_time is None:
1602 if end_time > duration:
1604 if start_time > end_time:
1606 chapter_title = re.sub(
1607 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1608 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1610 'start_time': start_time,
1611 'end_time': end_time,
1612 'title': chapter_title,
1616 def _real_extract(self, url):
1617 url, smuggled_data = unsmuggle_url(url, {})
1620 'http' if self._downloader.params.get('prefer_insecure', False)
1625 parsed_url = compat_urllib_parse_urlparse(url)
1626 for component in [parsed_url.fragment, parsed_url.query]:
1627 query = compat_parse_qs(component)
1628 if start_time is None and 't' in query:
1629 start_time = parse_duration(query['t'][0])
1630 if start_time is None and 'start' in query:
1631 start_time = parse_duration(query['start'][0])
1632 if end_time is None and 'end' in query:
1633 end_time = parse_duration(query['end'][0])
1635 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1636 mobj = re.search(self._NEXT_URL_RE, url)
1638 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1639 video_id = self.extract_id(url)
1642 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1643 video_webpage = self._download_webpage(url, video_id)
1645 # Attempt to extract SWF player URL
1646 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1647 if mobj is not None:
1648 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1654 def add_dash_mpd(video_info):
1655 dash_mpd = video_info.get('dashmpd')
1656 if dash_mpd and dash_mpd[0] not in dash_mpds:
1657 dash_mpds.append(dash_mpd[0])
1659 def add_dash_mpd_pr(pl_response):
1660 dash_mpd = url_or_none(try_get(
1661 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1663 if dash_mpd and dash_mpd not in dash_mpds:
1664 dash_mpds.append(dash_mpd)
1669 def extract_view_count(v_info):
1670 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1672 def extract_token(v_info):
1673 return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
1675 player_response = {}
1678 embed_webpage = None
1679 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1681 # We simulate the access to the video from www.youtube.com/v/{video_id}
1682 # this can be viewed without login into Youtube
1683 url = proto + '://www.youtube.com/embed/%s' % video_id
1684 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1685 data = compat_urllib_parse_urlencode({
1686 'video_id': video_id,
1687 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1688 'sts': self._search_regex(
1689 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1691 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1692 video_info_webpage = self._download_webpage(
1693 video_info_url, video_id,
1694 note='Refetching age-gated info webpage',
1695 errnote='unable to download video info webpage')
1696 video_info = compat_parse_qs(video_info_webpage)
1697 add_dash_mpd(video_info)
1702 # Try looking directly into the video webpage
1703 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1705 args = ytplayer_config['args']
1706 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1707 # Convert to the same format returned by compat_parse_qs
1708 video_info = dict((k, [v]) for k, v in args.items())
1709 add_dash_mpd(video_info)
1710 # Rental video is not rented but preview is available (e.g.
1711 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1712 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1713 if not video_info and args.get('ypc_vid'):
1714 return self.url_result(
1715 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1716 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1718 sts = ytplayer_config.get('sts')
1719 if not player_response:
1720 pl_response = str_or_none(args.get('player_response'))
1722 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1723 if isinstance(pl_response, dict):
1724 player_response = pl_response
1725 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1726 add_dash_mpd_pr(player_response)
1727 # We also try looking in get_video_info since it may contain different dashmpd
1728 # URL that points to a DASH manifest with possibly different itag set (some itags
1729 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1730 # manifest pointed by get_video_info's dashmpd).
1731 # The general idea is to take a union of itags of both DASH manifests (for example
1732 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1733 self.report_video_info_webpage_download(video_id)
1734 for el in ('embedded', 'detailpage', 'vevo', ''):
1736 'video_id': video_id,
1746 video_info_webpage = self._download_webpage(
1747 '%s://www.youtube.com/get_video_info' % proto,
1748 video_id, note=False,
1749 errnote='unable to download video info webpage',
1750 fatal=False, query=query)
1751 if not video_info_webpage:
1753 get_video_info = compat_parse_qs(video_info_webpage)
1754 if not player_response:
1755 pl_response = get_video_info.get('player_response', [None])[0]
1756 if isinstance(pl_response, dict):
1757 player_response = pl_response
1758 add_dash_mpd_pr(player_response)
1759 add_dash_mpd(get_video_info)
1760 if view_count is None:
1761 view_count = extract_view_count(get_video_info)
1763 video_info = get_video_info
1764 get_token = extract_token(get_video_info)
1766 # Different get_video_info requests may report different results, e.g.
1767 # some may report video unavailability, but some may serve it without
1768 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1769 # the original webpage as well as el=info and el=embedded get_video_info
1770 # requests report video unavailability due to geo restriction while
1771 # el=detailpage succeeds and returns valid data). This is probably
1772 # due to YouTube measures against IP ranges of hosting providers.
1773 # Working around by preferring the first succeeded video_info containing
1774 # the token if no such video_info yet was found.
1775 token = extract_token(video_info)
1777 video_info = get_video_info
1780 def extract_unavailable_message():
1781 return self._html_search_regex(
1782 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1783 video_webpage, 'unavailable message', default=None)
1786 unavailable_message = extract_unavailable_message()
1787 if not unavailable_message:
1788 unavailable_message = 'Unable to extract video data'
1789 raise ExtractorError(
1790 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1792 if video_info.get('license_info'):
1793 raise ExtractorError('This video is DRM protected.', expected=True)
1795 video_details = try_get(
1796 player_response, lambda x: x['videoDetails'], dict) or {}
1799 if 'title' in video_info:
1800 video_title = video_info['title'][0]
1801 elif 'title' in player_response:
1802 video_title = video_details['title']
1804 self._downloader.report_warning('Unable to extract video title')
1808 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1809 if video_description:
1812 redir_url = compat_urlparse.urljoin(url, m.group(1))
1813 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1814 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1815 qs = compat_parse_qs(parsed_redir_url.query)
1821 description_original = video_description = re.sub(r'''(?x)
1823 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1824 (?:title|href)="([^"]+)"\s+
1825 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1829 ''', replace_url, video_description)
1830 video_description = clean_html(video_description)
1832 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1834 video_description = unescapeHTML(fd_mobj.group(1))
1836 video_description = ''
1838 if not smuggled_data.get('force_singlefeed', False):
1839 if not self._downloader.params.get('noplaylist'):
1840 multifeed_metadata_list = try_get(
1842 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1843 compat_str) or try_get(
1844 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1845 if multifeed_metadata_list:
1848 for feed in multifeed_metadata_list.split(','):
1849 # Unquote should take place before split on comma (,) since textual
1850 # fields may contain comma as well (see
1851 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1852 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1854 '_type': 'url_transparent',
1855 'ie_key': 'Youtube',
1857 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1858 {'force_singlefeed': True}),
1859 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1861 feed_ids.append(feed_data['id'][0])
1863 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1864 % (', '.join(feed_ids), video_id))
1865 return self.playlist_result(entries, video_id, video_title, video_description)
1867 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1869 if view_count is None:
1870 view_count = extract_view_count(video_info)
1871 if view_count is None and video_details:
1872 view_count = int_or_none(video_details.get('viewCount'))
1874 # Check for "rental" videos
1875 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1876 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1878 def _extract_filesize(media_url):
1879 return int_or_none(self._search_regex(
1880 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1882 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1883 self.report_rtmp_download()
1885 'format_id': '_rtmp',
1887 'url': video_info['conn'][0],
1888 'player_url': player_url,
1890 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):
1891 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1892 if 'rtmpe%3Dyes' in encoded_url_map:
1893 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1895 fmt_list = video_info.get('fmt_list', [''])[0]
1897 for fmt in fmt_list.split(','):
1898 spec = fmt.split('/')
1900 width_height = spec[1].split('x')
1901 if len(width_height) == 2:
1902 formats_spec[spec[0]] = {
1903 'resolution': spec[1],
1904 'width': int_or_none(width_height[0]),
1905 'height': int_or_none(width_height[1]),
1907 q = qualities(['small', 'medium', 'hd720'])
1908 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1909 if streaming_formats:
1910 for fmt in streaming_formats:
1911 itag = str_or_none(fmt.get('itag'))
1914 quality = fmt.get('quality')
1915 quality_label = fmt.get('qualityLabel') or quality
1916 formats_spec[itag] = {
1917 'asr': int_or_none(fmt.get('audioSampleRate')),
1918 'filesize': int_or_none(fmt.get('contentLength')),
1919 'format_note': quality_label,
1920 'fps': int_or_none(fmt.get('fps')),
1921 'height': int_or_none(fmt.get('height')),
1922 'quality': q(quality),
1923 # bitrate for itag 43 is always 2147483647
1924 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1925 'width': int_or_none(fmt.get('width')),
1928 for url_data_str in encoded_url_map.split(','):
1929 url_data = compat_parse_qs(url_data_str)
1930 if 'itag' not in url_data or 'url' not in url_data:
1932 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1933 # Unsupported FORMAT_STREAM_TYPE_OTF
1934 if stream_type == 3:
1936 format_id = url_data['itag'][0]
1937 url = url_data['url'][0]
1939 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1940 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1941 jsplayer_url_json = self._search_regex(
1943 embed_webpage if age_gate else video_webpage,
1944 'JS player URL (1)', default=None)
1945 if not jsplayer_url_json and not age_gate:
1946 # We need the embed website after all
1947 if embed_webpage is None:
1948 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1949 embed_webpage = self._download_webpage(
1950 embed_url, video_id, 'Downloading embed webpage')
1951 jsplayer_url_json = self._search_regex(
1952 ASSETS_RE, embed_webpage, 'JS player URL')
1954 player_url = json.loads(jsplayer_url_json)
1955 if player_url is None:
1956 player_url_json = self._search_regex(
1957 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1958 video_webpage, 'age gate player URL')
1959 player_url = json.loads(player_url_json)
1961 if 'sig' in url_data:
1962 url += '&signature=' + url_data['sig'][0]
1963 elif 's' in url_data:
1964 encrypted_sig = url_data['s'][0]
1966 if self._downloader.params.get('verbose'):
1967 if player_url is None:
1968 player_version = 'unknown'
1969 player_desc = 'unknown'
1971 if player_url.endswith('swf'):
1972 player_version = self._search_regex(
1973 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1974 'flash player', fatal=False)
1975 player_desc = 'flash player %s' % player_version
1977 player_version = self._search_regex(
1978 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1979 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
1981 'html5 player', fatal=False)
1982 player_desc = 'html5 player %s' % player_version
1984 parts_sizes = self._signature_cache_id(encrypted_sig)
1985 self.to_screen('{%s} signature length %s, %s' %
1986 (format_id, parts_sizes, player_desc))
1988 signature = self._decrypt_signature(
1989 encrypted_sig, video_id, player_url, age_gate)
1990 url += '&signature=' + signature
1991 if 'ratebypass' not in url:
1992 url += '&ratebypass=yes'
1995 'format_id': format_id,
1997 'player_url': player_url,
1999 if format_id in self._formats:
2000 dct.update(self._formats[format_id])
2001 if format_id in formats_spec:
2002 dct.update(formats_spec[format_id])
2004 # Some itags are not included in DASH manifest thus corresponding formats will
2005 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2006 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2007 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2008 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2010 filesize = int_or_none(url_data.get(
2011 'clen', [None])[0]) or _extract_filesize(url)
2013 quality = url_data.get('quality', [None])[0]
2016 'filesize': filesize,
2017 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
2020 'fps': int_or_none(url_data.get('fps', [None])[0]),
2021 'format_note': url_data.get('quality_label', [None])[0] or quality,
2022 'quality': q(quality),
2024 for key, value in more_fields.items():
2027 type_ = url_data.get('type', [None])[0]
2029 type_split = type_.split(';')
2030 kind_ext = type_split[0].split('/')
2031 if len(kind_ext) == 2:
2033 dct['ext'] = mimetype2ext(type_split[0])
2034 if kind in ('audio', 'video'):
2036 for mobj in re.finditer(
2037 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2038 if mobj.group('key') == 'codecs':
2039 codecs = mobj.group('val')
2042 dct.update(parse_codecs(codecs))
2043 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2044 dct['downloader_options'] = {
2045 # Youtube throttles chunks >~10M
2046 'http_chunk_size': 10485760,
2051 url_or_none(try_get(
2053 lambda x: x['streamingData']['hlsManifestUrl'],
2055 url_or_none(try_get(
2056 video_info, lambda x: x['hlsvp'][0], compat_str)))
2059 m3u8_formats = self._extract_m3u8_formats(
2060 manifest_url, video_id, 'mp4', fatal=False)
2061 for a_format in m3u8_formats:
2062 itag = self._search_regex(
2063 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2065 a_format['format_id'] = itag
2066 if itag in self._formats:
2067 dct = self._formats[itag].copy()
2068 dct.update(a_format)
2070 a_format['player_url'] = player_url
2071 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2072 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2073 formats.append(a_format)
2075 error_message = clean_html(video_info.get('reason', [None])[0])
2076 if not error_message:
2077 error_message = extract_unavailable_message()
2079 raise ExtractorError(error_message, expected=True)
2080 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2083 video_uploader = try_get(
2084 video_info, lambda x: x['author'][0],
2085 compat_str) or str_or_none(video_details.get('author'))
2087 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2089 self._downloader.report_warning('unable to extract uploader name')
2092 video_uploader_id = None
2093 video_uploader_url = None
2095 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2097 if mobj is not None:
2098 video_uploader_id = mobj.group('uploader_id')
2099 video_uploader_url = mobj.group('uploader_url')
2101 self._downloader.report_warning('unable to extract uploader nickname')
2103 channel_id = self._html_search_meta(
2104 'channelId', video_webpage, 'channel id')
2105 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2108 # We try first to get a high quality image:
2109 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2110 video_webpage, re.DOTALL)
2111 if m_thumb is not None:
2112 video_thumbnail = m_thumb.group(1)
2113 elif 'thumbnail_url' not in video_info:
2114 self._downloader.report_warning('unable to extract video thumbnail')
2115 video_thumbnail = None
2116 else: # don't panic if we can't find it
2117 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2120 upload_date = self._html_search_meta(
2121 'datePublished', video_webpage, 'upload date', default=None)
2123 upload_date = self._search_regex(
2124 [r'(?s)id="eow-date.*?>(.*?)</span>',
2125 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2126 video_webpage, 'upload date', default=None)
2127 upload_date = unified_strdate(upload_date)
2129 video_license = self._html_search_regex(
2130 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2131 video_webpage, 'license', default=None)
2133 m_music = re.search(
2135 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2143 \bhref=["\']/red[^>]*>| # drop possible
2144 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2151 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2152 video_creator = clean_html(m_music.group('creator'))
2154 video_alt_title = video_creator = None
2156 def extract_meta(field):
2157 return self._html_search_regex(
2158 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2159 video_webpage, field, default=None)
2161 track = extract_meta('Song')
2162 artist = extract_meta('Artist')
2163 album = extract_meta('Album')
2165 # Youtube Music Auto-generated description
2166 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('·'))
2175 album = mobj.group('album'.strip())
2176 release_year = mobj.group('release_year')
2177 release_date = mobj.group('release_date')
2179 release_date = release_date.replace('-', '')
2180 if not release_year:
2181 release_year = int(release_date[:4])
2183 release_year = int(release_year)
2185 m_episode = re.search(
2186 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2189 series = unescapeHTML(m_episode.group('series'))
2190 season_number = int(m_episode.group('season'))
2191 episode_number = int(m_episode.group('episode'))
2193 series = season_number = episode_number = None
2195 m_cat_container = self._search_regex(
2196 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2197 video_webpage, 'categories', default=None)
2199 category = self._html_search_regex(
2200 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2202 video_categories = None if category is None else [category]
2204 video_categories = None
2207 unescapeHTML(m.group('content'))
2208 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2210 def _extract_count(count_name):
2211 return str_to_int(self._search_regex(
2212 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2213 % re.escape(count_name),
2214 video_webpage, count_name, default=None))
2216 like_count = _extract_count('like')
2217 dislike_count = _extract_count('dislike')
2219 if view_count is None:
2220 view_count = str_to_int(self._search_regex(
2221 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2222 'view count', default=None))
2225 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2226 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2228 video_duration = try_get(
2229 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2230 if not video_duration:
2231 video_duration = int_or_none(video_details.get('lengthSeconds'))
2232 if not video_duration:
2233 video_duration = parse_duration(self._html_search_meta(
2234 'duration', video_webpage, 'video duration'))
2237 video_annotations = None
2238 if self._downloader.params.get('writeannotations', False):
2239 video_annotations = self._extract_annotations(video_id)
2241 chapters = self._extract_chapters(description_original, video_duration)
2243 # Look for the DASH manifest
2244 if self._downloader.params.get('youtube_include_dash_manifest', True):
2245 dash_mpd_fatal = True
2246 for mpd_url in dash_mpds:
2249 def decrypt_sig(mobj):
2251 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2252 return '/signature/%s' % dec_s
2254 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2256 for df in self._extract_mpd_formats(
2257 mpd_url, video_id, fatal=dash_mpd_fatal,
2258 formats_dict=self._formats):
2259 if not df.get('filesize'):
2260 df['filesize'] = _extract_filesize(df['url'])
2261 # Do not overwrite DASH format found in some previous DASH manifest
2262 if df['format_id'] not in dash_formats:
2263 dash_formats[df['format_id']] = df
2264 # Additional DASH manifests may end up in HTTP Error 403 therefore
2265 # allow them to fail without bug report message if we already have
2266 # some DASH manifest succeeded. This is temporary workaround to reduce
2267 # burst of bug reports until we figure out the reason and whether it
2268 # can be fixed at all.
2269 dash_mpd_fatal = False
2270 except (ExtractorError, KeyError) as e:
2271 self.report_warning(
2272 'Skipping DASH manifest: %r' % e, video_id)
2274 # Remove the formats we found through non-DASH, they
2275 # contain less info and it can be wrong, because we use
2276 # fixed values (for example the resolution). See
2277 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2279 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2280 formats.extend(dash_formats.values())
2282 # Check for malformed aspect ratio
2283 stretched_m = re.search(
2284 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2287 w = float(stretched_m.group('w'))
2288 h = float(stretched_m.group('h'))
2289 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2290 # We will only process correct ratios.
2294 if f.get('vcodec') != 'none':
2295 f['stretched_ratio'] = ratio
2298 token = extract_token(video_info)
2300 if 'reason' in video_info:
2301 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2302 regions_allowed = self._html_search_meta(
2303 'regionsAllowed', video_webpage, default=None)
2304 countries = regions_allowed.split(',') if regions_allowed else None
2305 self.raise_geo_restricted(
2306 msg=video_info['reason'][0], countries=countries)
2307 reason = video_info['reason'][0]
2308 if 'Invalid parameters' in reason:
2309 unavailable_message = extract_unavailable_message()
2310 if unavailable_message:
2311 reason = unavailable_message
2312 raise ExtractorError(
2313 'YouTube said: %s' % reason,
2314 expected=True, video_id=video_id)
2316 raise ExtractorError(
2317 '"token" parameter not in video info for unknown reason',
2320 self._sort_formats(formats)
2322 self.mark_watched(video_id, video_info, player_response)
2326 'uploader': video_uploader,
2327 'uploader_id': video_uploader_id,
2328 'uploader_url': video_uploader_url,
2329 'channel_id': channel_id,
2330 'channel_url': channel_url,
2331 'upload_date': upload_date,
2332 'license': video_license,
2333 'creator': video_creator or artist,
2334 'title': video_title,
2335 'alt_title': video_alt_title or track,
2336 'thumbnail': video_thumbnail,
2337 'description': video_description,
2338 'categories': video_categories,
2340 'subtitles': video_subtitles,
2341 'automatic_captions': automatic_captions,
2342 'duration': video_duration,
2343 'age_limit': 18 if age_gate else 0,
2344 'annotations': video_annotations,
2345 'chapters': chapters,
2346 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2347 'view_count': view_count,
2348 'like_count': like_count,
2349 'dislike_count': dislike_count,
2350 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
2353 'start_time': start_time,
2354 'end_time': end_time,
2356 'season_number': season_number,
2357 'episode_number': episode_number,
2361 'release_date': release_date,
2362 'release_year': release_year,
2366 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2367 IE_DESC = 'YouTube.com playlists'
2368 _VALID_URL = r"""(?x)(?:
2378 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2379 \? (?:.*?[&;])*? (?:p|a|list)=
2382 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2385 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2386 # Top tracks, they can also include dots
2392 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2393 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2394 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2395 IE_NAME = 'youtube:playlist'
2397 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2399 'title': 'ytdl test PL',
2400 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2402 'playlist_count': 3,
2404 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2406 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2407 'title': 'YDL_Empty_List',
2409 'playlist_count': 0,
2410 'skip': 'This playlist is private',
2412 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2413 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2415 'title': '29C3: Not my department',
2416 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2418 'playlist_count': 95,
2420 'note': 'issue #673',
2421 'url': 'PLBB231211A4F62143',
2423 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2424 'id': 'PLBB231211A4F62143',
2426 'playlist_mincount': 26,
2428 'note': 'Large playlist',
2429 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2431 'title': 'Uploads from Cauchemar',
2432 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2434 'playlist_mincount': 799,
2436 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2438 'title': 'YDL_safe_search',
2439 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2441 'playlist_count': 2,
2442 'skip': 'This playlist is private',
2445 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2446 'playlist_count': 4,
2449 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2452 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2453 'playlist_mincount': 485,
2455 'title': '2017 華語最新單曲 (2/24更新)',
2456 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2459 'note': 'Embedded SWF player',
2460 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2461 'playlist_count': 4,
2464 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2467 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2468 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2470 'title': 'Uploads from Interstellar Movie',
2471 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2473 'playlist_mincount': 21,
2475 # Playlist URL that does not actually serve a playlist
2476 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2478 'id': 'FqZTN594JQw',
2480 'title': "Smiley's People 01 detective, Adventure Series, Action",
2481 'uploader': 'STREEM',
2482 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2483 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2484 'upload_date': '20150526',
2485 'license': 'Standard YouTube License',
2486 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2487 'categories': ['People & Blogs'],
2491 'dislike_count': int,
2494 'skip_download': True,
2496 'add_ie': [YoutubeIE.ie_key()],
2498 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2500 'id': 'yeWKywCrFtk',
2502 'title': 'Small Scale Baler and Braiding Rugs',
2503 'uploader': 'Backus-Page House Museum',
2504 'uploader_id': 'backuspagemuseum',
2505 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2506 'upload_date': '20161008',
2507 'license': 'Standard YouTube License',
2508 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2509 'categories': ['Nonprofits & Activism'],
2512 'dislike_count': int,
2516 'skip_download': True,
2519 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2520 'only_matching': True,
2522 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2523 'only_matching': True,
2525 # music album playlist
2526 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2527 'only_matching': True,
2529 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2530 'only_matching': True,
2533 def _real_initialize(self):
2536 def _extract_mix(self, playlist_id):
2537 # The mixes are generated from a single video
2538 # the id of the playlist is just 'RD' + video_id
2540 last_id = playlist_id[-11:]
2541 for n in itertools.count(1):
2542 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2543 webpage = self._download_webpage(
2544 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2545 new_ids = orderedSet(re.findall(
2546 r'''(?xs)data-video-username=".*?".*?
2547 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2549 # Fetch new pages until all the videos are repeated, it seems that
2550 # there are always 51 unique videos.
2551 new_ids = [_id for _id in new_ids if _id not in ids]
2557 url_results = self._ids_to_results(ids)
2559 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2561 search_title('playlist-title') or
2562 search_title('title long-title') or
2563 search_title('title'))
2564 title = clean_html(title_span)
2566 return self.playlist_result(url_results, playlist_id, title)
2568 def _extract_playlist(self, playlist_id):
2569 url = self._TEMPLATE_URL % playlist_id
2570 page = self._download_webpage(url, playlist_id)
2572 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2573 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2574 match = match.strip()
2575 # Check if the playlist exists or is private
2576 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2578 reason = mobj.group('reason')
2579 message = 'This playlist %s' % reason
2580 if 'private' in reason:
2581 message += ', use --username or --netrc to access it'
2583 raise ExtractorError(message, expected=True)
2584 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2585 raise ExtractorError(
2586 'Invalid parameters. Maybe URL is incorrect.',
2588 elif re.match(r'[^<]*Choose your language[^<]*', match):
2591 self.report_warning('Youtube gives an alert message: ' + match)
2593 playlist_title = self._html_search_regex(
2594 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2595 page, 'title', default=None)
2597 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2598 uploader = self._search_regex(
2599 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2600 page, 'uploader', default=None)
2602 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2605 uploader_id = mobj.group('uploader_id')
2606 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2608 uploader_id = uploader_url = None
2612 if not playlist_title:
2614 # Some playlist URLs don't actually serve a playlist (e.g.
2615 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2616 next(self._entries(page, playlist_id))
2617 except StopIteration:
2620 playlist = self.playlist_result(
2621 self._entries(page, playlist_id), playlist_id, playlist_title)
2623 'uploader': uploader,
2624 'uploader_id': uploader_id,
2625 'uploader_url': uploader_url,
2628 return has_videos, playlist
2630 def _check_download_just_video(self, url, playlist_id):
2631 # Check if it's a video-specific URL
2632 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2633 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2634 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2635 'video id', default=None)
2637 if self._downloader.params.get('noplaylist'):
2638 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2639 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2641 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2642 return video_id, None
2645 def _real_extract(self, url):
2646 # Extract playlist id
2647 mobj = re.match(self._VALID_URL, url)
2649 raise ExtractorError('Invalid URL: %s' % url)
2650 playlist_id = mobj.group(1) or mobj.group(2)
2652 video_id, video = self._check_download_just_video(url, playlist_id)
2656 if playlist_id.startswith(('RD', 'UL', 'PU')):
2657 # Mixes require a custom extraction process
2658 return self._extract_mix(playlist_id)
2660 has_videos, playlist = self._extract_playlist(playlist_id)
2661 if has_videos or not video_id:
2664 # Some playlist URLs don't actually serve a playlist (see
2665 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2666 # Fallback to plain video extraction if there is a video id
2667 # along with playlist id.
2668 return self.url_result(video_id, 'Youtube', video_id=video_id)
2671 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2672 IE_DESC = 'YouTube.com channels'
2673 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2674 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2675 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2676 IE_NAME = 'youtube:channel'
2678 'note': 'paginated channel',
2679 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2680 'playlist_mincount': 91,
2682 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2683 'title': 'Uploads from lex will',
2686 'note': 'Age restricted channel',
2687 # from https://www.youtube.com/user/DeusExOfficial
2688 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2689 'playlist_mincount': 64,
2691 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2692 'title': 'Uploads from Deus Ex',
2695 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2696 'only_matching': True,
2700 def suitable(cls, url):
2701 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2702 else super(YoutubeChannelIE, cls).suitable(url))
2704 def _build_template_url(self, url, channel_id):
2705 return self._TEMPLATE_URL % channel_id
2707 def _real_extract(self, url):
2708 channel_id = self._match_id(url)
2710 url = self._build_template_url(url, channel_id)
2712 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2713 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2714 # otherwise fallback on channel by page extraction
2715 channel_page = self._download_webpage(
2716 url + '?view=57', channel_id,
2717 'Downloading channel page', fatal=False)
2718 if channel_page is False:
2719 channel_playlist_id = False
2721 channel_playlist_id = self._html_search_meta(
2722 'channelId', channel_page, 'channel id', default=None)
2723 if not channel_playlist_id:
2724 channel_url = self._html_search_meta(
2725 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2726 channel_page, 'channel url', default=None)
2728 channel_playlist_id = self._search_regex(
2729 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2730 channel_url, 'channel id', default=None)
2731 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2732 playlist_id = 'UU' + channel_playlist_id[2:]
2733 return self.url_result(
2734 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2736 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2737 autogenerated = re.search(r'''(?x)
2739 channel-header-autogenerated-label|
2740 yt-channel-title-autogenerated
2741 )[^"]*"''', channel_page) is not None
2744 # The videos are contained in a single page
2745 # the ajax pages can't be used, they are empty
2748 video_id, 'Youtube', video_id=video_id,
2749 video_title=video_title)
2750 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2751 return self.playlist_result(entries, channel_id)
2754 next(self._entries(channel_page, channel_id))
2755 except StopIteration:
2756 alert_message = self._html_search_regex(
2757 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2758 channel_page, 'alert', default=None, group='alert')
2760 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2762 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2765 class YoutubeUserIE(YoutubeChannelIE):
2766 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2767 _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_-]+)'
2768 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2769 IE_NAME = 'youtube:user'
2772 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2773 'playlist_mincount': 320,
2775 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2776 'title': 'Uploads from The Linux Foundation',
2779 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2780 # but not https://www.youtube.com/user/12minuteathlete/videos
2781 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2782 'playlist_mincount': 249,
2784 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2785 'title': 'Uploads from 12 Minute Athlete',
2788 'url': 'ytuser:phihag',
2789 'only_matching': True,
2791 'url': 'https://www.youtube.com/c/gametrailers',
2792 'only_matching': True,
2794 'url': 'https://www.youtube.com/gametrailers',
2795 'only_matching': True,
2797 # This channel is not available, geo restricted to JP
2798 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2799 'only_matching': True,
2803 def suitable(cls, url):
2804 # Don't return True if the url can be extracted with other youtube
2805 # extractor, the regex would is too permissive and it would match.
2806 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2807 if any(ie.suitable(url) for ie in other_yt_ies):
2810 return super(YoutubeUserIE, cls).suitable(url)
2812 def _build_template_url(self, url, channel_id):
2813 mobj = re.match(self._VALID_URL, url)
2814 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2817 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2818 IE_DESC = 'YouTube.com live streams'
2819 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2820 IE_NAME = 'youtube:live'
2823 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2825 'id': 'a48o2S1cPoo',
2827 'title': 'The Young Turks - Live Main Show',
2828 'uploader': 'The Young Turks',
2829 'uploader_id': 'TheYoungTurks',
2830 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2831 'upload_date': '20150715',
2832 'license': 'Standard YouTube License',
2833 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2834 'categories': ['News & Politics'],
2835 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2837 'dislike_count': int,
2840 'skip_download': True,
2843 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2844 'only_matching': True,
2846 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2847 'only_matching': True,
2849 'url': 'https://www.youtube.com/TheYoungTurks/live',
2850 'only_matching': True,
2853 def _real_extract(self, url):
2854 mobj = re.match(self._VALID_URL, url)
2855 channel_id = mobj.group('id')
2856 base_url = mobj.group('base_url')
2857 webpage = self._download_webpage(url, channel_id, fatal=False)
2859 page_type = self._og_search_property(
2860 'type', webpage, 'page type', default='')
2861 video_id = self._html_search_meta(
2862 'videoId', webpage, 'video id', default=None)
2863 if page_type.startswith('video') and video_id and re.match(
2864 r'^[0-9A-Za-z_-]{11}$', video_id):
2865 return self.url_result(video_id, YoutubeIE.ie_key())
2866 return self.url_result(base_url)
2869 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2870 IE_DESC = 'YouTube.com user/channel playlists'
2871 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2872 IE_NAME = 'youtube:playlists'
2875 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2876 'playlist_mincount': 4,
2878 'id': 'ThirstForScience',
2879 'title': 'Thirst for Science',
2882 # with "Load more" button
2883 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2884 'playlist_mincount': 70,
2887 'title': 'Игорь Клейнер',
2890 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2891 'playlist_mincount': 17,
2893 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2894 'title': 'Chem Player',
2899 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2900 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2903 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2904 IE_DESC = 'YouTube.com searches'
2905 # there doesn't appear to be a real limit, for example if you search for
2906 # 'python' you get more than 8.000.000 results
2907 _MAX_RESULTS = float('inf')
2908 IE_NAME = 'youtube:search'
2909 _SEARCH_KEY = 'ytsearch'
2910 _EXTRA_QUERY_ARGS = {}
2913 def _get_n_results(self, query, n):
2914 """Get a specified number of results for a query"""
2920 'search_query': query.encode('utf-8'),
2922 url_query.update(self._EXTRA_QUERY_ARGS)
2923 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2925 for pagenum in itertools.count(1):
2926 data = self._download_json(
2927 result_url, video_id='query "%s"' % query,
2928 note='Downloading page %s' % pagenum,
2929 errnote='Unable to download API page',
2930 query={'spf': 'navigate'})
2931 html_content = data[1]['body']['content']
2933 if 'class="search-message' in html_content:
2934 raise ExtractorError(
2935 '[youtube] No video results', expected=True)
2937 new_videos = list(self._process_page(html_content))
2938 videos += new_videos
2939 if not new_videos or len(videos) > limit:
2941 next_link = self._html_search_regex(
2942 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2943 html_content, 'next link', default=None)
2944 if next_link is None:
2946 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2950 return self.playlist_result(videos, query)
2953 class YoutubeSearchDateIE(YoutubeSearchIE):
2954 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2955 _SEARCH_KEY = 'ytsearchdate'
2956 IE_DESC = 'YouTube.com searches, newest videos first'
2957 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2960 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
2961 IE_DESC = 'YouTube.com search URLs'
2962 IE_NAME = 'youtube:search_url'
2963 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2965 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2966 'playlist_mincount': 5,
2968 'title': 'youtube-dl test video',
2971 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2972 'only_matching': True,
2975 def _real_extract(self, url):
2976 mobj = re.match(self._VALID_URL, url)
2977 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2978 webpage = self._download_webpage(url, query)
2979 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2982 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2983 IE_DESC = 'YouTube.com (multi-season) shows'
2984 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2985 IE_NAME = 'youtube:show'
2987 'url': 'https://www.youtube.com/show/airdisasters',
2988 'playlist_mincount': 5,
2990 'id': 'airdisasters',
2991 'title': 'Air Disasters',
2995 def _real_extract(self, url):
2996 playlist_id = self._match_id(url)
2997 return super(YoutubeShowIE, self)._real_extract(
2998 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3001 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3003 Base class for feed extractors
3004 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3006 _LOGIN_REQUIRED = True
3010 return 'youtube:%s' % self._FEED_NAME
3012 def _real_initialize(self):
3015 def _entries(self, page):
3016 # The extraction process is the same as for playlists, but the regex
3017 # for the video ids doesn't contain an index
3019 more_widget_html = content_html = page
3020 for page_num in itertools.count(1):
3021 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3023 # 'recommended' feed has infinite 'load more' and each new portion spins
3024 # the same videos in (sometimes) slightly different order, so we'll check
3025 # for unicity and break when portion has no new videos
3026 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3032 for entry in self._ids_to_results(new_ids):
3035 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3039 more = self._download_json(
3040 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3041 'Downloading page #%s' % page_num,
3042 transform_source=uppercase_escape)
3043 content_html = more['content_html']
3044 more_widget_html = more['load_more_widget_html']
3046 def _real_extract(self, url):
3047 page = self._download_webpage(
3048 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3049 self._PLAYLIST_TITLE)
3050 return self.playlist_result(
3051 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3054 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3055 IE_NAME = 'youtube:watchlater'
3056 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3057 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3060 'url': 'https://www.youtube.com/playlist?list=WL',
3061 'only_matching': True,
3063 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3064 'only_matching': True,
3067 def _real_extract(self, url):
3068 _, video = self._check_download_just_video(url, 'WL')
3071 _, playlist = self._extract_playlist('WL')
3075 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3076 IE_NAME = 'youtube:favorites'
3077 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3078 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3079 _LOGIN_REQUIRED = True
3081 def _real_extract(self, url):
3082 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3083 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3084 return self.url_result(playlist_id, 'YoutubePlaylist')
3087 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3088 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3089 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3090 _FEED_NAME = 'recommended'
3091 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3094 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3095 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3096 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3097 _FEED_NAME = 'subscriptions'
3098 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3101 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3102 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3103 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3104 _FEED_NAME = 'history'
3105 _PLAYLIST_TITLE = 'Youtube History'
3108 class YoutubeTruncatedURLIE(InfoExtractor):
3109 IE_NAME = 'youtube:truncated_url'
3110 IE_DESC = False # Do not list
3111 _VALID_URL = r'''(?x)
3113 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3116 annotation_id=annotation_[^&]+|
3122 attribution_link\?a=[^&]+
3128 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3129 'only_matching': True,
3131 'url': 'https://www.youtube.com/watch?',
3132 'only_matching': True,
3134 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3135 'only_matching': True,
3137 'url': 'https://www.youtube.com/watch?feature=foo',
3138 'only_matching': True,
3140 'url': 'https://www.youtube.com/watch?hl=en-GB',
3141 'only_matching': True,
3143 'url': 'https://www.youtube.com/watch?t=2372',
3144 'only_matching': True,
3147 def _real_extract(self, url):
3148 raise ExtractorError(
3149 'Did you forget to quote the URL? Remember that & is a meta '
3150 'character in most shells, so you want to put the URL in quotes, '
3152 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3153 ' or simply youtube-dl BaW_jenozKc .',
3157 class YoutubeTruncatedIDIE(InfoExtractor):
3158 IE_NAME = 'youtube:truncated_id'
3159 IE_DESC = False # Do not list
3160 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3163 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3164 'only_matching': True,
3167 def _real_extract(self, url):
3168 video_id = self._match_id(url)
3169 raise ExtractorError(
3170 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),