3 from __future__ import unicode_literals
14 from .common import InfoExtractor, SearchInfoExtractor
15 from ..jsinterp import JSInterpreter
16 from ..swfinterp import SWFInterpreter
17 from ..compat import (
21 compat_urllib_parse_unquote,
22 compat_urllib_parse_unquote_plus,
23 compat_urllib_parse_urlencode,
24 compat_urllib_parse_urlparse,
33 get_element_by_attribute,
56 class YoutubeBaseInfoExtractor(InfoExtractor):
57 """Provide base functions for Youtube extractors"""
58 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
59 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
61 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
62 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
63 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
65 _NETRC_MACHINE = 'youtube'
66 # If True it will raise an error if no login info is provided
67 _LOGIN_REQUIRED = False
69 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
71 def _set_language(self):
73 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
74 # YouTube sets the expire time to about two months
75 expire_time=time.time() + 2 * 30 * 24 * 3600)
77 def _ids_to_results(self, ids):
79 self.url_result(vid_id, 'Youtube', video_id=vid_id)
84 Attempt to log in to YouTube.
85 True is returned if successful or skipped.
86 False is returned if login failed.
88 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
90 username, password = self._get_login_info()
91 # No authentication to be performed
93 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
94 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
97 login_page = self._download_webpage(
98 self._LOGIN_URL, None,
99 note='Downloading login page',
100 errnote='unable to fetch login page', fatal=False)
101 if login_page is False:
104 login_form = self._hidden_inputs(login_page)
106 def req(url, f_req, note, errnote):
107 data = login_form.copy()
110 'checkConnection': 'youtube',
111 'checkedDomains': 'youtube',
113 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
114 'f.req': json.dumps(f_req),
115 'flowName': 'GlifWebSignIn',
116 'flowEntry': 'ServiceLogin',
118 return self._download_json(
119 url, None, note=note, errnote=errnote,
120 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
122 data=urlencode_postdata(data), headers={
123 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
124 'Google-Accounts-XSRF': 1,
128 self._downloader.report_warning(message)
132 None, [], None, 'US', None, None, 2, False, True,
136 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
138 1, [None, None, []], None, None, None, True
143 lookup_results = req(
144 self._LOOKUP_URL, lookup_req,
145 'Looking up account info', 'Unable to look up account info')
147 if lookup_results is False:
150 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
152 warn('Unable to extract user hash')
157 None, 1, None, [1, None, None, None, [password, None, True]],
159 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
160 1, [None, None, []], None, None, None, True
163 challenge_results = req(
164 self._CHALLENGE_URL, challenge_req,
165 'Logging in', 'Unable to log in')
167 if challenge_results is False:
170 login_res = try_get(challenge_results, lambda x: x[0][5], list)
172 login_msg = try_get(login_res, lambda x: x[5], compat_str)
174 'Unable to login: %s' % 'Invalid password'
175 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
178 res = try_get(challenge_results, lambda x: x[0][-1], list)
180 warn('Unable to extract result entry')
183 login_challenge = try_get(res, lambda x: x[0][0], list)
185 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
186 if challenge_str == 'TWO_STEP_VERIFICATION':
187 # SEND_SUCCESS - TFA code has been successfully sent to phone
188 # QUOTA_EXCEEDED - reached the limit of TFA codes
189 status = try_get(login_challenge, lambda x: x[5], compat_str)
190 if status == 'QUOTA_EXCEEDED':
191 warn('Exceeded the limit of TFA codes, try later')
194 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
196 warn('Unable to extract TL')
199 tfa_code = self._get_tfa_info('2-step verification code')
203 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
204 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
207 tfa_code = remove_start(tfa_code, 'G-')
210 user_hash, None, 2, None,
212 9, None, None, None, None, None, None, None,
213 [None, tfa_code, True, 2]
217 self._TFA_URL.format(tl), tfa_req,
218 'Submitting TFA code', 'Unable to submit TFA code')
220 if tfa_results is False:
223 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
225 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
227 'Unable to finish TFA: %s' % 'Invalid TFA code'
228 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
231 check_cookie_url = try_get(
232 tfa_results, lambda x: x[0][-1][2], compat_str)
235 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
236 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
237 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
239 challenge = CHALLENGES.get(
241 '%s returned error %s.' % (self.IE_NAME, challenge_str))
242 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
245 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
247 if not check_cookie_url:
248 warn('Unable to extract CheckCookie URL')
251 check_cookie_results = self._download_webpage(
252 check_cookie_url, None, 'Checking cookie', fatal=False)
254 if check_cookie_results is False:
257 if 'https://myaccount.google.com/' not in check_cookie_results:
258 warn('Unable to log in')
263 def _download_webpage_handle(self, *args, **kwargs):
264 query = kwargs.get('query', {}).copy()
265 query['disable_polymer'] = 'true'
266 kwargs['query'] = query
267 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
268 *args, **compat_kwargs(kwargs))
270 def _real_initialize(self):
271 if self._downloader is None:
274 if not self._login():
278 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
279 # Extract entries from page with "Load more" button
280 def _entries(self, page, playlist_id):
281 more_widget_html = content_html = page
282 for page_num in itertools.count(1):
283 for entry in self._process_page(content_html):
286 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
290 more = self._download_json(
291 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
292 'Downloading page #%s' % page_num,
293 transform_source=uppercase_escape)
294 content_html = more['content_html']
295 if not content_html.strip():
296 # Some webpages show a "Load more" button but they don't
299 more_widget_html = more['load_more_widget_html']
302 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
303 def _process_page(self, content):
304 for video_id, video_title in self.extract_videos_from_page(content):
305 yield self.url_result(video_id, 'Youtube', video_id, video_title)
307 def extract_videos_from_page(self, page):
310 for mobj in re.finditer(self._VIDEO_RE, page):
311 # The link with index 0 is not the first video of the playlist (not sure if still actual)
312 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
314 video_id = mobj.group('id')
315 video_title = unescapeHTML(mobj.group('title'))
317 video_title = video_title.strip()
319 idx = ids_in_page.index(video_id)
320 if video_title and not titles_in_page[idx]:
321 titles_in_page[idx] = video_title
323 ids_in_page.append(video_id)
324 titles_in_page.append(video_title)
325 return zip(ids_in_page, titles_in_page)
328 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
329 def _process_page(self, content):
330 for playlist_id in orderedSet(re.findall(
331 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
333 yield self.url_result(
334 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
336 def _real_extract(self, url):
337 playlist_id = self._match_id(url)
338 webpage = self._download_webpage(url, playlist_id)
339 title = self._og_search_title(webpage, fatal=False)
340 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
343 class YoutubeIE(YoutubeBaseInfoExtractor):
344 IE_DESC = 'YouTube.com'
345 _VALID_URL = r"""(?x)^
347 (?:https?://|//) # http(s):// or protocol-independent URL
348 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
349 (?:www\.)?deturl\.com/www\.youtube\.com/|
350 (?:www\.)?pwnyoutube\.com/|
351 (?:www\.)?hooktube\.com/|
352 (?:www\.)?yourepeat\.com/|
353 tube\.majestyc\.net/|
354 (?:www\.)?invidio\.us/|
355 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
356 (?:.*?\#/)? # handle anchor (#/) redirect urls
357 (?: # the various things that can precede the ID:
358 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
359 |(?: # or the v= param in all its forms
360 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
361 (?:\?|\#!?) # the params delimiter ? or # or #!
362 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
367 youtu\.be| # just youtu.be/xxxx
368 vid\.plus| # or vid.plus/xxxx
369 zwearz\.com/watch| # or zwearz.com/watch/xxxx
371 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
373 )? # all until now is optional -> you can pass the naked ID
374 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
377 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
378 WL # WL are handled by the watch later IE
381 (?(1).+)? # if we found the ID, everything can follow
382 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
383 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
385 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
386 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
387 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
388 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
389 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
390 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
391 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
392 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
393 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
394 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
395 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
396 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
397 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
398 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
399 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
400 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
401 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
402 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
406 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
407 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
408 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
409 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
410 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
411 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
412 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
414 # Apple HTTP Live Streaming
415 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
416 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
417 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
418 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
419 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
420 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
421 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
422 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
425 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
426 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
427 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
428 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
429 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
430 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
431 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
432 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
433 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
434 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
435 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
436 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
439 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
440 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
441 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
442 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
443 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
444 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
445 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
448 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
449 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
450 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
451 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
452 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
453 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
454 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
455 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
456 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
457 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
458 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
459 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
460 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
461 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
462 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
463 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
464 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
465 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
466 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
467 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
468 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
469 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
472 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
473 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
475 # Dash webm audio with opus inside
476 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
477 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
478 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
481 '_rtmp': {'protocol': 'rtmp'},
483 _SUBTITLE_FORMATS = ('ttml', 'vtt')
490 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
494 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
495 'uploader': 'Philipp Hagemeister',
496 'uploader_id': 'phihag',
497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
498 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
499 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
500 'upload_date': '20121002',
501 'license': 'Standard YouTube License',
502 '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 .',
503 'categories': ['Science & Technology'],
504 'tags': ['youtube-dl'],
508 'dislike_count': int,
514 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
515 'note': 'Test generic use_cipher_signature video (#897)',
519 'upload_date': '20120506',
520 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
521 'alt_title': 'I Love It (feat. Charli XCX)',
522 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
523 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
524 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
525 'iconic ep', 'iconic', 'love', 'it'],
527 'uploader': 'Icona Pop',
528 'uploader_id': 'IconaPop',
529 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
530 'license': 'Standard YouTube License',
531 'creator': 'Icona Pop',
532 'track': 'I Love It (feat. Charli XCX)',
533 'artist': 'Icona Pop',
537 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
538 'note': 'Test VEVO video with age protection (#956)',
542 'upload_date': '20130703',
543 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
544 'alt_title': 'Tunnel Vision',
545 'description': 'md5:64249768eec3bc4276236606ea996373',
547 'uploader': 'justintimberlakeVEVO',
548 'uploader_id': 'justintimberlakeVEVO',
549 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
550 'license': 'Standard YouTube License',
551 'creator': 'Justin Timberlake',
552 'track': 'Tunnel Vision',
553 'artist': 'Justin Timberlake',
558 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
559 'note': 'Embed-only video (#1746)',
563 'upload_date': '20120608',
564 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
565 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
566 'uploader': 'SET India',
567 'uploader_id': 'setindia',
568 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
569 'license': 'Standard YouTube License',
574 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
575 'note': 'Use the first video ID in the URL',
579 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
580 'uploader': 'Philipp Hagemeister',
581 'uploader_id': 'phihag',
582 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
583 'upload_date': '20121002',
584 'license': 'Standard YouTube License',
585 '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 .',
586 'categories': ['Science & Technology'],
587 'tags': ['youtube-dl'],
591 'dislike_count': int,
594 'skip_download': True,
598 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
599 'note': '256k DASH audio (format 141) via DASH manifest',
603 'upload_date': '20121002',
604 'uploader_id': '8KVIDEO',
605 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
607 'uploader': '8KVIDEO',
608 'license': 'Standard YouTube License',
609 'title': 'UHDTV TEST 8K VIDEO.mp4'
612 'youtube_include_dash_manifest': True,
615 'skip': 'format 141 not served anymore',
617 # DASH manifest with encrypted signature
619 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
623 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
624 'description': 'md5:1900ed86ee514927b9e00fbead6969a5',
626 'uploader': 'AfrojackVEVO',
627 'uploader_id': 'AfrojackVEVO',
628 'upload_date': '20131011',
629 'license': 'Standard YouTube License',
632 'youtube_include_dash_manifest': True,
633 'format': '141/bestaudio[ext=m4a]',
636 # JS player signature function name containing $
638 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
642 'title': 'Taylor Swift - Shake It Off',
643 'alt_title': 'Shake It Off',
644 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
646 'uploader': 'TaylorSwiftVEVO',
647 'uploader_id': 'TaylorSwiftVEVO',
648 'upload_date': '20140818',
649 'license': 'Standard YouTube License',
650 'creator': 'Taylor Swift',
653 'youtube_include_dash_manifest': True,
654 'format': '141/bestaudio[ext=m4a]',
659 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
664 'upload_date': '20100909',
665 'uploader': 'TJ Kirk',
666 'uploader_id': 'TheAmazingAtheist',
667 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
668 'license': 'Standard YouTube License',
669 'title': 'Burning Everyone\'s Koran',
670 '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',
673 # Normal age-gate video (No vevo, embed allowed)
675 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
679 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
680 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
682 'uploader': 'The Witcher',
683 'uploader_id': 'WitcherGame',
684 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
685 'upload_date': '20140605',
686 'license': 'Standard YouTube License',
690 # Age-gate video with encrypted signature
692 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
696 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
697 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
699 'uploader': 'LloydVEVO',
700 'uploader_id': 'LloydVEVO',
701 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
702 'upload_date': '20110629',
703 'license': 'Standard YouTube License',
707 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
708 # YouTube Red ad is not captured for creator
710 'url': '__2ABJjxzNo',
715 'upload_date': '20100430',
716 'uploader_id': 'deadmau5',
717 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
718 'creator': 'deadmau5',
719 'description': 'md5:12c56784b8032162bb936a5f76d55360',
720 'uploader': 'deadmau5',
721 'license': 'Standard YouTube License',
722 'title': 'Deadmau5 - Some Chords (HD)',
723 'alt_title': 'Some Chords',
725 'expected_warnings': [
726 'DASH manifest missing',
729 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
731 'url': 'lqQg6PlCWgI',
736 'upload_date': '20150827',
737 'uploader_id': 'olympic',
738 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
739 'license': 'Standard YouTube License',
740 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
741 'uploader': 'Olympic',
742 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
745 'skip_download': 'requires avconv',
750 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
754 'stretched_ratio': 16 / 9.,
756 'upload_date': '20110310',
757 'uploader_id': 'AllenMeow',
758 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
759 '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',
761 'license': 'Standard YouTube License',
762 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
765 # url_encoded_fmt_stream_map is empty string
767 'url': 'qEJwOuvDf7I',
771 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
773 'upload_date': '20150404',
774 'uploader_id': 'spbelect',
775 'uploader': 'Наблюдатели Петербурга',
778 'skip_download': 'requires avconv',
780 'skip': 'This live event has ended.',
782 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
784 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
788 'title': 'md5:7b81415841e02ecd4313668cde88737a',
789 'description': 'md5:116377fd2963b81ec4ce64b542173306',
791 'upload_date': '20150625',
792 'uploader_id': 'dorappi2000',
793 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
794 'uploader': 'dorappi2000',
795 'license': 'Standard YouTube License',
796 'formats': 'mincount:31',
798 'skip': 'not actual anymore',
800 # DASH manifest with segment_list
802 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
803 'md5': '8ce563a1d667b599d21064e982ab9e31',
807 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
808 'uploader': 'Airtek',
809 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
810 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
811 'license': 'Standard YouTube License',
812 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
815 'youtube_include_dash_manifest': True,
816 'format': '135', # bestvideo
818 'skip': 'This live event has ended.',
821 # Multifeed videos (multiple cameras), URL is for Main Camera
822 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
825 'title': 'teamPGP: Rocket League Noob Stream',
826 'description': 'md5:dc7872fb300e143831327f1bae3af010',
832 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
833 'description': 'md5:dc7872fb300e143831327f1bae3af010',
835 'upload_date': '20150721',
836 'uploader': 'Beer Games Beer',
837 'uploader_id': 'beergamesbeer',
838 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
839 'license': 'Standard YouTube License',
845 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
846 'description': 'md5:dc7872fb300e143831327f1bae3af010',
848 'upload_date': '20150721',
849 'uploader': 'Beer Games Beer',
850 'uploader_id': 'beergamesbeer',
851 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
852 'license': 'Standard YouTube License',
858 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
859 'description': 'md5:dc7872fb300e143831327f1bae3af010',
861 'upload_date': '20150721',
862 'uploader': 'Beer Games Beer',
863 'uploader_id': 'beergamesbeer',
864 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
865 'license': 'Standard YouTube License',
871 'title': 'teamPGP: Rocket League Noob Stream (zim)',
872 'description': 'md5:dc7872fb300e143831327f1bae3af010',
874 'upload_date': '20150721',
875 'uploader': 'Beer Games Beer',
876 'uploader_id': 'beergamesbeer',
877 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
878 'license': 'Standard YouTube License',
882 'skip_download': True,
886 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
887 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
890 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
893 'skip': 'Not multifeed anymore',
896 'url': 'https://vid.plus/FlRa-iH7PGw',
897 'only_matching': True,
900 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
901 'only_matching': True,
904 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
905 # Also tests cut-off URL expansion in video description (see
906 # https://github.com/rg3/youtube-dl/issues/1892,
907 # https://github.com/rg3/youtube-dl/issues/8164)
908 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
912 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
913 'alt_title': 'Dark Walk - Position Music',
914 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
916 'upload_date': '20151119',
917 'uploader_id': 'IronSoulElf',
918 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
919 'uploader': 'IronSoulElf',
920 'license': 'Standard YouTube License',
921 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
922 'track': 'Dark Walk - Position Music',
923 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
926 'skip_download': True,
930 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
931 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
932 'only_matching': True,
935 # Video with yt:stretch=17:0
936 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
940 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
941 'description': 'md5:ee18a25c350637c8faff806845bddee9',
942 'upload_date': '20151107',
943 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
944 'uploader': 'CH GAMER DROID',
947 'skip_download': True,
949 'skip': 'This video does not exist.',
952 # Video licensed under Creative Commons
953 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
957 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
958 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
960 'upload_date': '20150127',
961 'uploader_id': 'BerkmanCenter',
962 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
963 'uploader': 'The Berkman Klein Center for Internet & Society',
964 'license': 'Creative Commons Attribution license (reuse allowed)',
967 'skip_download': True,
971 # Channel-like uploader_url
972 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
976 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
977 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
979 'upload_date': '20151119',
980 'uploader': 'Bernie Sanders',
981 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
982 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
983 'license': 'Creative Commons Attribution license (reuse allowed)',
986 'skip_download': True,
990 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
991 'only_matching': True,
994 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
995 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
996 'only_matching': True,
999 # Rental video preview
1000 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1002 'id': 'uGpuVWrhIzE',
1004 'title': 'Piku - Trailer',
1005 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1006 'upload_date': '20150811',
1007 'uploader': 'FlixMatrix',
1008 'uploader_id': 'FlixMatrixKaravan',
1009 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1010 'license': 'Standard YouTube License',
1013 'skip_download': True,
1015 'skip': 'This video is not available.',
1018 # YouTube Red video with episode data
1019 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1021 'id': 'iqKdEhx-dD4',
1023 'title': 'Isolation - Mind Field (Ep 1)',
1024 'description': 'md5:25b78d2f64ae81719f5c96319889b736',
1026 'upload_date': '20170118',
1027 'uploader': 'Vsauce',
1028 'uploader_id': 'Vsauce',
1029 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1030 'license': 'Standard YouTube License',
1031 'series': 'Mind Field',
1033 'episode_number': 1,
1036 'skip_download': True,
1038 'expected_warnings': [
1039 'Skipping DASH manifest',
1043 # The following content has been identified by the YouTube community
1044 # as inappropriate or offensive to some audiences.
1045 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1047 'id': '6SJNVb0GnPI',
1049 'title': 'Race Differences in Intelligence',
1050 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1052 'upload_date': '20140124',
1053 'uploader': 'New Century Foundation',
1054 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1055 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1056 'license': 'Standard YouTube License',
1059 'skip_download': True,
1064 'url': '1t24XAntNCY',
1065 'only_matching': True,
1068 # geo restricted to JP
1069 'url': 'sJL6WA-aGkQ',
1070 'only_matching': True,
1073 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1074 'only_matching': True,
1077 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1078 'only_matching': True,
1082 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1083 'only_matching': True,
1087 def __init__(self, *args, **kwargs):
1088 super(YoutubeIE, self).__init__(*args, **kwargs)
1089 self._player_cache = {}
1091 def report_video_info_webpage_download(self, video_id):
1092 """Report attempt to download video info webpage."""
1093 self.to_screen('%s: Downloading video info webpage' % video_id)
1095 def report_information_extraction(self, video_id):
1096 """Report attempt to extract video information."""
1097 self.to_screen('%s: Extracting video information' % video_id)
1099 def report_unavailable_format(self, video_id, format):
1100 """Report extracted video URL."""
1101 self.to_screen('%s: Format %s not available' % (video_id, format))
1103 def report_rtmp_download(self):
1104 """Indicate the download will use the RTMP protocol."""
1105 self.to_screen('RTMP download detected')
1107 def _signature_cache_id(self, example_sig):
1108 """ Return a string representation of a signature """
1109 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1111 def _extract_signature_function(self, video_id, player_url, example_sig):
1113 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1116 raise ExtractorError('Cannot identify player %r' % player_url)
1117 player_type = id_m.group('ext')
1118 player_id = id_m.group('id')
1120 # Read from filesystem cache
1121 func_id = '%s_%s_%s' % (
1122 player_type, player_id, self._signature_cache_id(example_sig))
1123 assert os.path.basename(func_id) == func_id
1125 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1126 if cache_spec is not None:
1127 return lambda s: ''.join(s[i] for i in cache_spec)
1130 'Downloading player %s' % player_url
1131 if self._downloader.params.get('verbose') else
1132 'Downloading %s player %s' % (player_type, player_id)
1134 if player_type == 'js':
1135 code = self._download_webpage(
1136 player_url, video_id,
1138 errnote='Download of %s failed' % player_url)
1139 res = self._parse_sig_js(code)
1140 elif player_type == 'swf':
1141 urlh = self._request_webpage(
1142 player_url, video_id,
1144 errnote='Download of %s failed' % player_url)
1146 res = self._parse_sig_swf(code)
1148 assert False, 'Invalid player type %r' % player_type
1150 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1151 cache_res = res(test_string)
1152 cache_spec = [ord(c) for c in cache_res]
1154 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1157 def _print_sig_code(self, func, example_sig):
1158 def gen_sig_code(idxs):
1159 def _genslice(start, end, step):
1160 starts = '' if start == 0 else str(start)
1161 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1162 steps = '' if step == 1 else (':%d' % step)
1163 return 's[%s%s%s]' % (starts, ends, steps)
1166 # Quelch pyflakes warnings - start will be set when step is set
1167 start = '(Never used)'
1168 for i, prev in zip(idxs[1:], idxs[:-1]):
1169 if step is not None:
1170 if i - prev == step:
1172 yield _genslice(start, prev, step)
1175 if i - prev in [-1, 1]:
1180 yield 's[%d]' % prev
1184 yield _genslice(start, i, step)
1186 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1187 cache_res = func(test_string)
1188 cache_spec = [ord(c) for c in cache_res]
1189 expr_code = ' + '.join(gen_sig_code(cache_spec))
1190 signature_id_tuple = '(%s)' % (
1191 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1192 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1193 ' return %s\n') % (signature_id_tuple, expr_code)
1194 self.to_screen('Extracted signature function:\n' + code)
1196 def _parse_sig_js(self, jscode):
1197 funcname = self._search_regex(
1198 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1199 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1200 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1201 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1202 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1203 jscode, 'Initial JS player signature function name', group='sig')
1205 jsi = JSInterpreter(jscode)
1206 initial_function = jsi.extract_function(funcname)
1207 return lambda s: initial_function([s])
1209 def _parse_sig_swf(self, file_contents):
1210 swfi = SWFInterpreter(file_contents)
1211 TARGET_CLASSNAME = 'SignatureDecipher'
1212 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1213 initial_function = swfi.extract_function(searched_class, 'decipher')
1214 return lambda s: initial_function([s])
1216 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1217 """Turn the encrypted s field into a working signature"""
1219 if player_url is None:
1220 raise ExtractorError('Cannot decrypt signature without player_url')
1222 if player_url.startswith('//'):
1223 player_url = 'https:' + player_url
1224 elif not re.match(r'https?://', player_url):
1225 player_url = compat_urlparse.urljoin(
1226 'https://www.youtube.com', player_url)
1228 player_id = (player_url, self._signature_cache_id(s))
1229 if player_id not in self._player_cache:
1230 func = self._extract_signature_function(
1231 video_id, player_url, s
1233 self._player_cache[player_id] = func
1234 func = self._player_cache[player_id]
1235 if self._downloader.params.get('youtube_print_sig_code'):
1236 self._print_sig_code(func, s)
1238 except Exception as e:
1239 tb = traceback.format_exc()
1240 raise ExtractorError(
1241 'Signature extraction failed: ' + tb, cause=e)
1243 def _get_subtitles(self, video_id, webpage):
1245 subs_doc = self._download_xml(
1246 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1247 video_id, note=False)
1248 except ExtractorError as err:
1249 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1253 for track in subs_doc.findall('track'):
1254 lang = track.attrib['lang_code']
1255 if lang in sub_lang_list:
1258 for ext in self._SUBTITLE_FORMATS:
1259 params = compat_urllib_parse_urlencode({
1263 'name': track.attrib['name'].encode('utf-8'),
1265 sub_formats.append({
1266 'url': 'https://www.youtube.com/api/timedtext?' + params,
1269 sub_lang_list[lang] = sub_formats
1270 if not sub_lang_list:
1271 self._downloader.report_warning('video doesn\'t have subtitles')
1273 return sub_lang_list
1275 def _get_ytplayer_config(self, video_id, webpage):
1277 # User data may contain arbitrary character sequences that may affect
1278 # JSON extraction with regex, e.g. when '};' is contained the second
1279 # regex won't capture the whole JSON. Yet working around by trying more
1280 # concrete regex first keeping in mind proper quoted string handling
1281 # to be implemented in future that will replace this workaround (see
1282 # https://github.com/rg3/youtube-dl/issues/7468,
1283 # https://github.com/rg3/youtube-dl/pull/7599)
1284 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1285 r';ytplayer\.config\s*=\s*({.+?});',
1287 config = self._search_regex(
1288 patterns, webpage, 'ytplayer.config', default=None)
1290 return self._parse_json(
1291 uppercase_escape(config), video_id, fatal=False)
1293 def _get_automatic_captions(self, video_id, webpage):
1294 """We need the webpage for getting the captions url, pass it as an
1295 argument to speed up the process."""
1296 self.to_screen('%s: Looking for automatic captions' % video_id)
1297 player_config = self._get_ytplayer_config(video_id, webpage)
1298 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1299 if not player_config:
1300 self._downloader.report_warning(err_msg)
1303 args = player_config['args']
1304 caption_url = args.get('ttsurl')
1306 timestamp = args['timestamp']
1307 # We get the available subtitles
1308 list_params = compat_urllib_parse_urlencode({
1313 list_url = caption_url + '&' + list_params
1314 caption_list = self._download_xml(list_url, video_id)
1315 original_lang_node = caption_list.find('track')
1316 if original_lang_node is None:
1317 self._downloader.report_warning('Video doesn\'t have automatic captions')
1319 original_lang = original_lang_node.attrib['lang_code']
1320 caption_kind = original_lang_node.attrib.get('kind', '')
1323 for lang_node in caption_list.findall('target'):
1324 sub_lang = lang_node.attrib['lang_code']
1326 for ext in self._SUBTITLE_FORMATS:
1327 params = compat_urllib_parse_urlencode({
1328 'lang': original_lang,
1332 'kind': caption_kind,
1334 sub_formats.append({
1335 'url': caption_url + '&' + params,
1338 sub_lang_list[sub_lang] = sub_formats
1339 return sub_lang_list
1341 def make_captions(sub_url, sub_langs):
1342 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1343 caption_qs = compat_parse_qs(parsed_sub_url.query)
1345 for sub_lang in sub_langs:
1347 for ext in self._SUBTITLE_FORMATS:
1349 'tlang': [sub_lang],
1352 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1353 query=compat_urllib_parse_urlencode(caption_qs, True)))
1354 sub_formats.append({
1358 captions[sub_lang] = sub_formats
1361 # New captions format as of 22.06.2017
1362 player_response = args.get('player_response')
1363 if player_response and isinstance(player_response, compat_str):
1364 player_response = self._parse_json(
1365 player_response, video_id, fatal=False)
1367 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1368 base_url = renderer['captionTracks'][0]['baseUrl']
1370 for lang in renderer['translationLanguages']:
1371 lang_code = lang.get('languageCode')
1373 sub_lang_list.append(lang_code)
1374 return make_captions(base_url, sub_lang_list)
1376 # Some videos don't provide ttsurl but rather caption_tracks and
1377 # caption_translation_languages (e.g. 20LmZk1hakA)
1378 # Does not used anymore as of 22.06.2017
1379 caption_tracks = args['caption_tracks']
1380 caption_translation_languages = args['caption_translation_languages']
1381 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1383 for lang in caption_translation_languages.split(','):
1384 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1385 sub_lang = lang_qs.get('lc', [None])[0]
1387 sub_lang_list.append(sub_lang)
1388 return make_captions(caption_url, sub_lang_list)
1389 # An extractor error can be raise by the download process if there are
1390 # no automatic captions but there are subtitles
1391 except (KeyError, IndexError, ExtractorError):
1392 self._downloader.report_warning(err_msg)
1395 def _mark_watched(self, video_id, video_info, player_response):
1396 playback_url = url_or_none(try_get(
1398 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1399 video_info, lambda x: x['videostats_playback_base_url'][0]))
1400 if not playback_url:
1402 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1403 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1405 # cpn generation algorithm is reverse engineered from base.js.
1406 # In fact it works even with dummy cpn.
1407 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1408 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1414 playback_url = compat_urlparse.urlunparse(
1415 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1417 self._download_webpage(
1418 playback_url, video_id, 'Marking watched',
1419 'Unable to mark watched', fatal=False)
1422 def _extract_urls(webpage):
1423 # Embedded YouTube player
1425 unescapeHTML(mobj.group('url'))
1426 for mobj in re.finditer(r'''(?x)
1436 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1437 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1440 # lazyYT YouTube embed
1441 entries.extend(list(map(
1443 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1445 # Wordpress "YouTube Video Importer" plugin
1446 matches = re.findall(r'''(?x)<div[^>]+
1447 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1448 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1449 entries.extend(m[-1] for m in matches)
1454 def _extract_url(webpage):
1455 urls = YoutubeIE._extract_urls(webpage)
1456 return urls[0] if urls else None
1459 def extract_id(cls, url):
1460 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1462 raise ExtractorError('Invalid URL: %s' % url)
1463 video_id = mobj.group(2)
1466 def _extract_annotations(self, video_id):
1467 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1468 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1471 def _extract_chapters(description, duration):
1474 chapter_lines = re.findall(
1475 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1477 if not chapter_lines:
1480 for next_num, (chapter_line, time_point) in enumerate(
1481 chapter_lines, start=1):
1482 start_time = parse_duration(time_point)
1483 if start_time is None:
1485 if start_time > duration:
1487 end_time = (duration if next_num == len(chapter_lines)
1488 else parse_duration(chapter_lines[next_num][1]))
1489 if end_time is None:
1491 if end_time > duration:
1493 if start_time > end_time:
1495 chapter_title = re.sub(
1496 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1497 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1499 'start_time': start_time,
1500 'end_time': end_time,
1501 'title': chapter_title,
1505 def _real_extract(self, url):
1506 url, smuggled_data = unsmuggle_url(url, {})
1509 'http' if self._downloader.params.get('prefer_insecure', False)
1514 parsed_url = compat_urllib_parse_urlparse(url)
1515 for component in [parsed_url.fragment, parsed_url.query]:
1516 query = compat_parse_qs(component)
1517 if start_time is None and 't' in query:
1518 start_time = parse_duration(query['t'][0])
1519 if start_time is None and 'start' in query:
1520 start_time = parse_duration(query['start'][0])
1521 if end_time is None and 'end' in query:
1522 end_time = parse_duration(query['end'][0])
1524 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1525 mobj = re.search(self._NEXT_URL_RE, url)
1527 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1528 video_id = self.extract_id(url)
1531 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1532 video_webpage = self._download_webpage(url, video_id)
1534 # Attempt to extract SWF player URL
1535 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1536 if mobj is not None:
1537 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1543 def add_dash_mpd(video_info):
1544 dash_mpd = video_info.get('dashmpd')
1545 if dash_mpd and dash_mpd[0] not in dash_mpds:
1546 dash_mpds.append(dash_mpd[0])
1551 def extract_view_count(v_info):
1552 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1554 player_response = {}
1557 embed_webpage = None
1558 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1560 # We simulate the access to the video from www.youtube.com/v/{video_id}
1561 # this can be viewed without login into Youtube
1562 url = proto + '://www.youtube.com/embed/%s' % video_id
1563 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1564 data = compat_urllib_parse_urlencode({
1565 'video_id': video_id,
1566 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1567 'sts': self._search_regex(
1568 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1570 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1571 video_info_webpage = self._download_webpage(
1572 video_info_url, video_id,
1573 note='Refetching age-gated info webpage',
1574 errnote='unable to download video info webpage')
1575 video_info = compat_parse_qs(video_info_webpage)
1576 add_dash_mpd(video_info)
1581 # Try looking directly into the video webpage
1582 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1584 args = ytplayer_config['args']
1585 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1586 # Convert to the same format returned by compat_parse_qs
1587 video_info = dict((k, [v]) for k, v in args.items())
1588 add_dash_mpd(video_info)
1589 # Rental video is not rented but preview is available (e.g.
1590 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1591 # https://github.com/rg3/youtube-dl/issues/10532)
1592 if not video_info and args.get('ypc_vid'):
1593 return self.url_result(
1594 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1595 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1597 sts = ytplayer_config.get('sts')
1598 if not player_response:
1599 pl_response = str_or_none(args.get('player_response'))
1601 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1602 if isinstance(pl_response, dict):
1603 player_response = pl_response
1604 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1605 # We also try looking in get_video_info since it may contain different dashmpd
1606 # URL that points to a DASH manifest with possibly different itag set (some itags
1607 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1608 # manifest pointed by get_video_info's dashmpd).
1609 # The general idea is to take a union of itags of both DASH manifests (for example
1610 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1611 self.report_video_info_webpage_download(video_id)
1612 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1614 'video_id': video_id,
1624 video_info_webpage = self._download_webpage(
1625 '%s://www.youtube.com/get_video_info' % proto,
1626 video_id, note=False,
1627 errnote='unable to download video info webpage',
1628 fatal=False, query=query)
1629 if not video_info_webpage:
1631 get_video_info = compat_parse_qs(video_info_webpage)
1632 if not player_response:
1633 pl_response = get_video_info.get('player_response', [None])[0]
1634 if isinstance(pl_response, dict):
1635 player_response = pl_response
1636 add_dash_mpd(get_video_info)
1637 if view_count is None:
1638 view_count = extract_view_count(get_video_info)
1640 video_info = get_video_info
1641 if 'token' in get_video_info:
1642 # Different get_video_info requests may report different results, e.g.
1643 # some may report video unavailability, but some may serve it without
1644 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1645 # the original webpage as well as el=info and el=embedded get_video_info
1646 # requests report video unavailability due to geo restriction while
1647 # el=detailpage succeeds and returns valid data). This is probably
1648 # due to YouTube measures against IP ranges of hosting providers.
1649 # Working around by preferring the first succeeded video_info containing
1650 # the token if no such video_info yet was found.
1651 if 'token' not in video_info:
1652 video_info = get_video_info
1655 def extract_unavailable_message():
1656 return self._html_search_regex(
1657 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1658 video_webpage, 'unavailable message', default=None)
1660 if 'token' not in video_info:
1661 if 'reason' in video_info:
1662 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1663 regions_allowed = self._html_search_meta(
1664 'regionsAllowed', video_webpage, default=None)
1665 countries = regions_allowed.split(',') if regions_allowed else None
1666 self.raise_geo_restricted(
1667 msg=video_info['reason'][0], countries=countries)
1668 reason = video_info['reason'][0]
1669 if 'Invalid parameters' in reason:
1670 unavailable_message = extract_unavailable_message()
1671 if unavailable_message:
1672 reason = unavailable_message
1673 raise ExtractorError(
1674 'YouTube said: %s' % reason,
1675 expected=True, video_id=video_id)
1677 raise ExtractorError(
1678 '"token" parameter not in video info for unknown reason',
1681 if video_info.get('license_info'):
1682 raise ExtractorError('This video is DRM protected.', expected=True)
1684 video_details = try_get(
1685 player_response, lambda x: x['videoDetails'], dict) or {}
1688 if 'title' in video_info:
1689 video_title = video_info['title'][0]
1690 elif 'title' in player_response:
1691 video_title = video_details['title']
1693 self._downloader.report_warning('Unable to extract video title')
1697 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1698 if video_description:
1701 redir_url = compat_urlparse.urljoin(url, m.group(1))
1702 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1703 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1704 qs = compat_parse_qs(parsed_redir_url.query)
1710 description_original = video_description = re.sub(r'''(?x)
1712 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1713 (?:title|href)="([^"]+)"\s+
1714 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1718 ''', replace_url, video_description)
1719 video_description = clean_html(video_description)
1721 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1723 video_description = unescapeHTML(fd_mobj.group(1))
1725 video_description = ''
1727 if not smuggled_data.get('force_singlefeed', False):
1728 if not self._downloader.params.get('noplaylist'):
1729 multifeed_metadata_list = try_get(
1731 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1732 compat_str) or try_get(
1733 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1734 if multifeed_metadata_list:
1737 for feed in multifeed_metadata_list.split(','):
1738 # Unquote should take place before split on comma (,) since textual
1739 # fields may contain comma as well (see
1740 # https://github.com/rg3/youtube-dl/issues/8536)
1741 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1743 '_type': 'url_transparent',
1744 'ie_key': 'Youtube',
1746 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1747 {'force_singlefeed': True}),
1748 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1750 feed_ids.append(feed_data['id'][0])
1752 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1753 % (', '.join(feed_ids), video_id))
1754 return self.playlist_result(entries, video_id, video_title, video_description)
1756 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1758 if view_count is None:
1759 view_count = extract_view_count(video_info)
1760 if view_count is None and video_details:
1761 view_count = int_or_none(video_details.get('viewCount'))
1763 # Check for "rental" videos
1764 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1765 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
1767 def _extract_filesize(media_url):
1768 return int_or_none(self._search_regex(
1769 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1771 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1772 self.report_rtmp_download()
1774 'format_id': '_rtmp',
1776 'url': video_info['conn'][0],
1777 'player_url': player_url,
1779 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):
1780 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1781 if 'rtmpe%3Dyes' in encoded_url_map:
1782 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
1784 fmt_list = video_info.get('fmt_list', [''])[0]
1786 for fmt in fmt_list.split(','):
1787 spec = fmt.split('/')
1789 width_height = spec[1].split('x')
1790 if len(width_height) == 2:
1791 formats_spec[spec[0]] = {
1792 'resolution': spec[1],
1793 'width': int_or_none(width_height[0]),
1794 'height': int_or_none(width_height[1]),
1796 q = qualities(['small', 'medium', 'hd720'])
1797 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1798 if streaming_formats:
1799 for fmt in streaming_formats:
1800 itag = str_or_none(fmt.get('itag'))
1803 quality = fmt.get('quality')
1804 quality_label = fmt.get('qualityLabel') or quality
1805 formats_spec[itag] = {
1806 'asr': int_or_none(fmt.get('audioSampleRate')),
1807 'filesize': int_or_none(fmt.get('contentLength')),
1808 'format_note': quality_label,
1809 'fps': int_or_none(fmt.get('fps')),
1810 'height': int_or_none(fmt.get('height')),
1811 'quality': q(quality),
1812 # bitrate for itag 43 is always 2147483647
1813 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1814 'width': int_or_none(fmt.get('width')),
1817 for url_data_str in encoded_url_map.split(','):
1818 url_data = compat_parse_qs(url_data_str)
1819 if 'itag' not in url_data or 'url' not in url_data:
1821 format_id = url_data['itag'][0]
1822 url = url_data['url'][0]
1824 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1825 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1826 jsplayer_url_json = self._search_regex(
1828 embed_webpage if age_gate else video_webpage,
1829 'JS player URL (1)', default=None)
1830 if not jsplayer_url_json and not age_gate:
1831 # We need the embed website after all
1832 if embed_webpage is None:
1833 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1834 embed_webpage = self._download_webpage(
1835 embed_url, video_id, 'Downloading embed webpage')
1836 jsplayer_url_json = self._search_regex(
1837 ASSETS_RE, embed_webpage, 'JS player URL')
1839 player_url = json.loads(jsplayer_url_json)
1840 if player_url is None:
1841 player_url_json = self._search_regex(
1842 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1843 video_webpage, 'age gate player URL')
1844 player_url = json.loads(player_url_json)
1846 if 'sig' in url_data:
1847 url += '&signature=' + url_data['sig'][0]
1848 elif 's' in url_data:
1849 encrypted_sig = url_data['s'][0]
1851 if self._downloader.params.get('verbose'):
1852 if player_url is None:
1853 player_version = 'unknown'
1854 player_desc = 'unknown'
1856 if player_url.endswith('swf'):
1857 player_version = self._search_regex(
1858 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1859 'flash player', fatal=False)
1860 player_desc = 'flash player %s' % player_version
1862 player_version = self._search_regex(
1863 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1864 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
1866 'html5 player', fatal=False)
1867 player_desc = 'html5 player %s' % player_version
1869 parts_sizes = self._signature_cache_id(encrypted_sig)
1870 self.to_screen('{%s} signature length %s, %s' %
1871 (format_id, parts_sizes, player_desc))
1873 signature = self._decrypt_signature(
1874 encrypted_sig, video_id, player_url, age_gate)
1875 url += '&signature=' + signature
1876 if 'ratebypass' not in url:
1877 url += '&ratebypass=yes'
1880 'format_id': format_id,
1882 'player_url': player_url,
1884 if format_id in self._formats:
1885 dct.update(self._formats[format_id])
1886 if format_id in formats_spec:
1887 dct.update(formats_spec[format_id])
1889 # Some itags are not included in DASH manifest thus corresponding formats will
1890 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1891 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1892 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1893 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
1895 filesize = int_or_none(url_data.get(
1896 'clen', [None])[0]) or _extract_filesize(url)
1898 quality = url_data.get('quality', [None])[0]
1901 'filesize': filesize,
1902 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
1905 'fps': int_or_none(url_data.get('fps', [None])[0]),
1906 'format_note': url_data.get('quality_label', [None])[0] or quality,
1907 'quality': q(quality),
1909 for key, value in more_fields.items():
1912 type_ = url_data.get('type', [None])[0]
1914 type_split = type_.split(';')
1915 kind_ext = type_split[0].split('/')
1916 if len(kind_ext) == 2:
1918 dct['ext'] = mimetype2ext(type_split[0])
1919 if kind in ('audio', 'video'):
1921 for mobj in re.finditer(
1922 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1923 if mobj.group('key') == 'codecs':
1924 codecs = mobj.group('val')
1927 dct.update(parse_codecs(codecs))
1928 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
1929 dct['downloader_options'] = {
1930 # Youtube throttles chunks >~10M
1931 'http_chunk_size': 10485760,
1934 elif video_info.get('hlsvp'):
1935 manifest_url = video_info['hlsvp'][0]
1937 m3u8_formats = self._extract_m3u8_formats(
1938 manifest_url, video_id, 'mp4', fatal=False)
1939 for a_format in m3u8_formats:
1940 itag = self._search_regex(
1941 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1943 a_format['format_id'] = itag
1944 if itag in self._formats:
1945 dct = self._formats[itag].copy()
1946 dct.update(a_format)
1948 a_format['player_url'] = player_url
1949 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1950 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1951 formats.append(a_format)
1953 error_message = clean_html(video_info.get('reason', [None])[0])
1954 if not error_message:
1955 error_message = extract_unavailable_message()
1957 raise ExtractorError(error_message, expected=True)
1958 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
1961 video_uploader = try_get(
1962 video_info, lambda x: x['author'][0],
1963 compat_str) or str_or_none(video_details.get('author'))
1965 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
1967 self._downloader.report_warning('unable to extract uploader name')
1970 video_uploader_id = None
1971 video_uploader_url = None
1973 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1975 if mobj is not None:
1976 video_uploader_id = mobj.group('uploader_id')
1977 video_uploader_url = mobj.group('uploader_url')
1979 self._downloader.report_warning('unable to extract uploader nickname')
1981 channel_id = self._html_search_meta(
1982 'channelId', video_webpage, 'channel id')
1983 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
1986 # We try first to get a high quality image:
1987 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1988 video_webpage, re.DOTALL)
1989 if m_thumb is not None:
1990 video_thumbnail = m_thumb.group(1)
1991 elif 'thumbnail_url' not in video_info:
1992 self._downloader.report_warning('unable to extract video thumbnail')
1993 video_thumbnail = None
1994 else: # don't panic if we can't find it
1995 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1998 upload_date = self._html_search_meta(
1999 'datePublished', video_webpage, 'upload date', default=None)
2001 upload_date = self._search_regex(
2002 [r'(?s)id="eow-date.*?>(.*?)</span>',
2003 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2004 video_webpage, 'upload date', default=None)
2005 upload_date = unified_strdate(upload_date)
2007 video_license = self._html_search_regex(
2008 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2009 video_webpage, 'license', default=None)
2011 m_music = re.search(
2013 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2021 \bhref=["\']/red[^>]*>| # drop possible
2022 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2029 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2030 video_creator = clean_html(m_music.group('creator'))
2032 video_alt_title = video_creator = None
2034 def extract_meta(field):
2035 return self._html_search_regex(
2036 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2037 video_webpage, field, default=None)
2039 track = extract_meta('Song')
2040 artist = extract_meta('Artist')
2042 m_episode = re.search(
2043 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2046 series = unescapeHTML(m_episode.group('series'))
2047 season_number = int(m_episode.group('season'))
2048 episode_number = int(m_episode.group('episode'))
2050 series = season_number = episode_number = None
2052 m_cat_container = self._search_regex(
2053 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2054 video_webpage, 'categories', default=None)
2056 category = self._html_search_regex(
2057 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2059 video_categories = None if category is None else [category]
2061 video_categories = None
2064 unescapeHTML(m.group('content'))
2065 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2067 def _extract_count(count_name):
2068 return str_to_int(self._search_regex(
2069 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2070 % re.escape(count_name),
2071 video_webpage, count_name, default=None))
2073 like_count = _extract_count('like')
2074 dislike_count = _extract_count('dislike')
2076 if view_count is None:
2077 view_count = str_to_int(self._search_regex(
2078 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2079 'view count', default=None))
2082 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2083 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2085 video_duration = try_get(
2086 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2087 if not video_duration:
2088 video_duration = int_or_none(video_details.get('lengthSeconds'))
2089 if not video_duration:
2090 video_duration = parse_duration(self._html_search_meta(
2091 'duration', video_webpage, 'video duration'))
2094 video_annotations = None
2095 if self._downloader.params.get('writeannotations', False):
2096 video_annotations = self._extract_annotations(video_id)
2098 chapters = self._extract_chapters(description_original, video_duration)
2100 # Look for the DASH manifest
2101 if self._downloader.params.get('youtube_include_dash_manifest', True):
2102 dash_mpd_fatal = True
2103 for mpd_url in dash_mpds:
2106 def decrypt_sig(mobj):
2108 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2109 return '/signature/%s' % dec_s
2111 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2113 for df in self._extract_mpd_formats(
2114 mpd_url, video_id, fatal=dash_mpd_fatal,
2115 formats_dict=self._formats):
2116 if not df.get('filesize'):
2117 df['filesize'] = _extract_filesize(df['url'])
2118 # Do not overwrite DASH format found in some previous DASH manifest
2119 if df['format_id'] not in dash_formats:
2120 dash_formats[df['format_id']] = df
2121 # Additional DASH manifests may end up in HTTP Error 403 therefore
2122 # allow them to fail without bug report message if we already have
2123 # some DASH manifest succeeded. This is temporary workaround to reduce
2124 # burst of bug reports until we figure out the reason and whether it
2125 # can be fixed at all.
2126 dash_mpd_fatal = False
2127 except (ExtractorError, KeyError) as e:
2128 self.report_warning(
2129 'Skipping DASH manifest: %r' % e, video_id)
2131 # Remove the formats we found through non-DASH, they
2132 # contain less info and it can be wrong, because we use
2133 # fixed values (for example the resolution). See
2134 # https://github.com/rg3/youtube-dl/issues/5774 for an
2136 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2137 formats.extend(dash_formats.values())
2139 # Check for malformed aspect ratio
2140 stretched_m = re.search(
2141 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2144 w = float(stretched_m.group('w'))
2145 h = float(stretched_m.group('h'))
2146 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2147 # We will only process correct ratios.
2151 if f.get('vcodec') != 'none':
2152 f['stretched_ratio'] = ratio
2154 self._sort_formats(formats)
2156 self.mark_watched(video_id, video_info, player_response)
2160 'uploader': video_uploader,
2161 'uploader_id': video_uploader_id,
2162 'uploader_url': video_uploader_url,
2163 'channel_id': channel_id,
2164 'channel_url': channel_url,
2165 'upload_date': upload_date,
2166 'license': video_license,
2167 'creator': video_creator or artist,
2168 'title': video_title,
2169 'alt_title': video_alt_title or track,
2170 'thumbnail': video_thumbnail,
2171 'description': video_description,
2172 'categories': video_categories,
2174 'subtitles': video_subtitles,
2175 'automatic_captions': automatic_captions,
2176 'duration': video_duration,
2177 'age_limit': 18 if age_gate else 0,
2178 'annotations': video_annotations,
2179 'chapters': chapters,
2180 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2181 'view_count': view_count,
2182 'like_count': like_count,
2183 'dislike_count': dislike_count,
2184 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
2187 'start_time': start_time,
2188 'end_time': end_time,
2190 'season_number': season_number,
2191 'episode_number': episode_number,
2197 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2198 IE_DESC = 'YouTube.com playlists'
2199 _VALID_URL = r"""(?x)(?:
2209 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2210 \? (?:.*?[&;])*? (?:p|a|list)=
2213 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2216 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2217 # Top tracks, they can also include dots
2223 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2224 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2225 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2226 IE_NAME = 'youtube:playlist'
2228 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2230 'title': 'ytdl test PL',
2231 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2233 'playlist_count': 3,
2235 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2237 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2238 'title': 'YDL_Empty_List',
2240 'playlist_count': 0,
2241 'skip': 'This playlist is private',
2243 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2244 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2246 'title': '29C3: Not my department',
2247 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2249 'playlist_count': 95,
2251 'note': 'issue #673',
2252 'url': 'PLBB231211A4F62143',
2254 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2255 'id': 'PLBB231211A4F62143',
2257 'playlist_mincount': 26,
2259 'note': 'Large playlist',
2260 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2262 'title': 'Uploads from Cauchemar',
2263 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2265 'playlist_mincount': 799,
2267 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2269 'title': 'YDL_safe_search',
2270 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2272 'playlist_count': 2,
2273 'skip': 'This playlist is private',
2276 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2277 'playlist_count': 4,
2280 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2283 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2284 'playlist_mincount': 485,
2286 'title': '2017 華語最新單曲 (2/24更新)',
2287 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2290 'note': 'Embedded SWF player',
2291 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2292 'playlist_count': 4,
2295 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2298 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2299 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2301 'title': 'Uploads from Interstellar Movie',
2302 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2304 'playlist_mincount': 21,
2306 # Playlist URL that does not actually serve a playlist
2307 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2309 'id': 'FqZTN594JQw',
2311 'title': "Smiley's People 01 detective, Adventure Series, Action",
2312 'uploader': 'STREEM',
2313 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2314 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2315 'upload_date': '20150526',
2316 'license': 'Standard YouTube License',
2317 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2318 'categories': ['People & Blogs'],
2322 'dislike_count': int,
2325 'skip_download': True,
2327 'add_ie': [YoutubeIE.ie_key()],
2329 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2331 'id': 'yeWKywCrFtk',
2333 'title': 'Small Scale Baler and Braiding Rugs',
2334 'uploader': 'Backus-Page House Museum',
2335 'uploader_id': 'backuspagemuseum',
2336 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2337 'upload_date': '20161008',
2338 'license': 'Standard YouTube License',
2339 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2340 'categories': ['Nonprofits & Activism'],
2343 'dislike_count': int,
2347 'skip_download': True,
2350 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2351 'only_matching': True,
2353 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2354 'only_matching': True,
2356 # music album playlist
2357 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2358 'only_matching': True,
2360 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2361 'only_matching': True,
2364 def _real_initialize(self):
2367 def _extract_mix(self, playlist_id):
2368 # The mixes are generated from a single video
2369 # the id of the playlist is just 'RD' + video_id
2371 last_id = playlist_id[-11:]
2372 for n in itertools.count(1):
2373 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2374 webpage = self._download_webpage(
2375 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2376 new_ids = orderedSet(re.findall(
2377 r'''(?xs)data-video-username=".*?".*?
2378 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2380 # Fetch new pages until all the videos are repeated, it seems that
2381 # there are always 51 unique videos.
2382 new_ids = [_id for _id in new_ids if _id not in ids]
2388 url_results = self._ids_to_results(ids)
2390 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2392 search_title('playlist-title') or
2393 search_title('title long-title') or
2394 search_title('title'))
2395 title = clean_html(title_span)
2397 return self.playlist_result(url_results, playlist_id, title)
2399 def _extract_playlist(self, playlist_id):
2400 url = self._TEMPLATE_URL % playlist_id
2401 page = self._download_webpage(url, playlist_id)
2403 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2404 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2405 match = match.strip()
2406 # Check if the playlist exists or is private
2407 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2409 reason = mobj.group('reason')
2410 message = 'This playlist %s' % reason
2411 if 'private' in reason:
2412 message += ', use --username or --netrc to access it'
2414 raise ExtractorError(message, expected=True)
2415 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2416 raise ExtractorError(
2417 'Invalid parameters. Maybe URL is incorrect.',
2419 elif re.match(r'[^<]*Choose your language[^<]*', match):
2422 self.report_warning('Youtube gives an alert message: ' + match)
2424 playlist_title = self._html_search_regex(
2425 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2426 page, 'title', default=None)
2428 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2429 uploader = self._search_regex(
2430 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2431 page, 'uploader', default=None)
2433 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2436 uploader_id = mobj.group('uploader_id')
2437 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2439 uploader_id = uploader_url = None
2443 if not playlist_title:
2445 # Some playlist URLs don't actually serve a playlist (e.g.
2446 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2447 next(self._entries(page, playlist_id))
2448 except StopIteration:
2451 playlist = self.playlist_result(
2452 self._entries(page, playlist_id), playlist_id, playlist_title)
2454 'uploader': uploader,
2455 'uploader_id': uploader_id,
2456 'uploader_url': uploader_url,
2459 return has_videos, playlist
2461 def _check_download_just_video(self, url, playlist_id):
2462 # Check if it's a video-specific URL
2463 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2464 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2465 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2466 'video id', default=None)
2468 if self._downloader.params.get('noplaylist'):
2469 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2470 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2472 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2473 return video_id, None
2476 def _real_extract(self, url):
2477 # Extract playlist id
2478 mobj = re.match(self._VALID_URL, url)
2480 raise ExtractorError('Invalid URL: %s' % url)
2481 playlist_id = mobj.group(1) or mobj.group(2)
2483 video_id, video = self._check_download_just_video(url, playlist_id)
2487 if playlist_id.startswith(('RD', 'UL', 'PU')):
2488 # Mixes require a custom extraction process
2489 return self._extract_mix(playlist_id)
2491 has_videos, playlist = self._extract_playlist(playlist_id)
2492 if has_videos or not video_id:
2495 # Some playlist URLs don't actually serve a playlist (see
2496 # https://github.com/rg3/youtube-dl/issues/10537).
2497 # Fallback to plain video extraction if there is a video id
2498 # along with playlist id.
2499 return self.url_result(video_id, 'Youtube', video_id=video_id)
2502 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2503 IE_DESC = 'YouTube.com channels'
2504 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2505 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2506 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2507 IE_NAME = 'youtube:channel'
2509 'note': 'paginated channel',
2510 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2511 'playlist_mincount': 91,
2513 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2514 'title': 'Uploads from lex will',
2517 'note': 'Age restricted channel',
2518 # from https://www.youtube.com/user/DeusExOfficial
2519 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2520 'playlist_mincount': 64,
2522 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2523 'title': 'Uploads from Deus Ex',
2526 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2527 'only_matching': True,
2531 def suitable(cls, url):
2532 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2533 else super(YoutubeChannelIE, cls).suitable(url))
2535 def _build_template_url(self, url, channel_id):
2536 return self._TEMPLATE_URL % channel_id
2538 def _real_extract(self, url):
2539 channel_id = self._match_id(url)
2541 url = self._build_template_url(url, channel_id)
2543 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2544 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2545 # otherwise fallback on channel by page extraction
2546 channel_page = self._download_webpage(
2547 url + '?view=57', channel_id,
2548 'Downloading channel page', fatal=False)
2549 if channel_page is False:
2550 channel_playlist_id = False
2552 channel_playlist_id = self._html_search_meta(
2553 'channelId', channel_page, 'channel id', default=None)
2554 if not channel_playlist_id:
2555 channel_url = self._html_search_meta(
2556 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2557 channel_page, 'channel url', default=None)
2559 channel_playlist_id = self._search_regex(
2560 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2561 channel_url, 'channel id', default=None)
2562 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2563 playlist_id = 'UU' + channel_playlist_id[2:]
2564 return self.url_result(
2565 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2567 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2568 autogenerated = re.search(r'''(?x)
2570 channel-header-autogenerated-label|
2571 yt-channel-title-autogenerated
2572 )[^"]*"''', channel_page) is not None
2575 # The videos are contained in a single page
2576 # the ajax pages can't be used, they are empty
2579 video_id, 'Youtube', video_id=video_id,
2580 video_title=video_title)
2581 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2582 return self.playlist_result(entries, channel_id)
2585 next(self._entries(channel_page, channel_id))
2586 except StopIteration:
2587 alert_message = self._html_search_regex(
2588 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2589 channel_page, 'alert', default=None, group='alert')
2591 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2593 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2596 class YoutubeUserIE(YoutubeChannelIE):
2597 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2598 _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_-]+)'
2599 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2600 IE_NAME = 'youtube:user'
2603 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2604 'playlist_mincount': 320,
2606 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2607 'title': 'Uploads from The Linux Foundation',
2610 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2611 # but not https://www.youtube.com/user/12minuteathlete/videos
2612 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2613 'playlist_mincount': 249,
2615 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2616 'title': 'Uploads from 12 Minute Athlete',
2619 'url': 'ytuser:phihag',
2620 'only_matching': True,
2622 'url': 'https://www.youtube.com/c/gametrailers',
2623 'only_matching': True,
2625 'url': 'https://www.youtube.com/gametrailers',
2626 'only_matching': True,
2628 # This channel is not available, geo restricted to JP
2629 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2630 'only_matching': True,
2634 def suitable(cls, url):
2635 # Don't return True if the url can be extracted with other youtube
2636 # extractor, the regex would is too permissive and it would match.
2637 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2638 if any(ie.suitable(url) for ie in other_yt_ies):
2641 return super(YoutubeUserIE, cls).suitable(url)
2643 def _build_template_url(self, url, channel_id):
2644 mobj = re.match(self._VALID_URL, url)
2645 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2648 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2649 IE_DESC = 'YouTube.com live streams'
2650 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2651 IE_NAME = 'youtube:live'
2654 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2656 'id': 'a48o2S1cPoo',
2658 'title': 'The Young Turks - Live Main Show',
2659 'uploader': 'The Young Turks',
2660 'uploader_id': 'TheYoungTurks',
2661 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2662 'upload_date': '20150715',
2663 'license': 'Standard YouTube License',
2664 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2665 'categories': ['News & Politics'],
2666 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2668 'dislike_count': int,
2671 'skip_download': True,
2674 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2675 'only_matching': True,
2677 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2678 'only_matching': True,
2680 'url': 'https://www.youtube.com/TheYoungTurks/live',
2681 'only_matching': True,
2684 def _real_extract(self, url):
2685 mobj = re.match(self._VALID_URL, url)
2686 channel_id = mobj.group('id')
2687 base_url = mobj.group('base_url')
2688 webpage = self._download_webpage(url, channel_id, fatal=False)
2690 page_type = self._og_search_property(
2691 'type', webpage, 'page type', default='')
2692 video_id = self._html_search_meta(
2693 'videoId', webpage, 'video id', default=None)
2694 if page_type.startswith('video') and video_id and re.match(
2695 r'^[0-9A-Za-z_-]{11}$', video_id):
2696 return self.url_result(video_id, YoutubeIE.ie_key())
2697 return self.url_result(base_url)
2700 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2701 IE_DESC = 'YouTube.com user/channel playlists'
2702 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2703 IE_NAME = 'youtube:playlists'
2706 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2707 'playlist_mincount': 4,
2709 'id': 'ThirstForScience',
2710 'title': 'Thirst for Science',
2713 # with "Load more" button
2714 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2715 'playlist_mincount': 70,
2718 'title': 'Игорь Клейнер',
2721 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2722 'playlist_mincount': 17,
2724 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2725 'title': 'Chem Player',
2730 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2731 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2734 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2735 IE_DESC = 'YouTube.com searches'
2736 # there doesn't appear to be a real limit, for example if you search for
2737 # 'python' you get more than 8.000.000 results
2738 _MAX_RESULTS = float('inf')
2739 IE_NAME = 'youtube:search'
2740 _SEARCH_KEY = 'ytsearch'
2741 _EXTRA_QUERY_ARGS = {}
2744 def _get_n_results(self, query, n):
2745 """Get a specified number of results for a query"""
2751 'search_query': query.encode('utf-8'),
2753 url_query.update(self._EXTRA_QUERY_ARGS)
2754 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2756 for pagenum in itertools.count(1):
2757 data = self._download_json(
2758 result_url, video_id='query "%s"' % query,
2759 note='Downloading page %s' % pagenum,
2760 errnote='Unable to download API page',
2761 query={'spf': 'navigate'})
2762 html_content = data[1]['body']['content']
2764 if 'class="search-message' in html_content:
2765 raise ExtractorError(
2766 '[youtube] No video results', expected=True)
2768 new_videos = list(self._process_page(html_content))
2769 videos += new_videos
2770 if not new_videos or len(videos) > limit:
2772 next_link = self._html_search_regex(
2773 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2774 html_content, 'next link', default=None)
2775 if next_link is None:
2777 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2781 return self.playlist_result(videos, query)
2784 class YoutubeSearchDateIE(YoutubeSearchIE):
2785 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2786 _SEARCH_KEY = 'ytsearchdate'
2787 IE_DESC = 'YouTube.com searches, newest videos first'
2788 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2791 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
2792 IE_DESC = 'YouTube.com search URLs'
2793 IE_NAME = 'youtube:search_url'
2794 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2796 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2797 'playlist_mincount': 5,
2799 'title': 'youtube-dl test video',
2802 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2803 'only_matching': True,
2806 def _real_extract(self, url):
2807 mobj = re.match(self._VALID_URL, url)
2808 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2809 webpage = self._download_webpage(url, query)
2810 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2813 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2814 IE_DESC = 'YouTube.com (multi-season) shows'
2815 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2816 IE_NAME = 'youtube:show'
2818 'url': 'https://www.youtube.com/show/airdisasters',
2819 'playlist_mincount': 5,
2821 'id': 'airdisasters',
2822 'title': 'Air Disasters',
2826 def _real_extract(self, url):
2827 playlist_id = self._match_id(url)
2828 return super(YoutubeShowIE, self)._real_extract(
2829 'https://www.youtube.com/show/%s/playlists' % playlist_id)
2832 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
2834 Base class for feed extractors
2835 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2837 _LOGIN_REQUIRED = True
2841 return 'youtube:%s' % self._FEED_NAME
2843 def _real_initialize(self):
2846 def _entries(self, page):
2847 # The extraction process is the same as for playlists, but the regex
2848 # for the video ids doesn't contain an index
2850 more_widget_html = content_html = page
2851 for page_num in itertools.count(1):
2852 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
2854 # 'recommended' feed has infinite 'load more' and each new portion spins
2855 # the same videos in (sometimes) slightly different order, so we'll check
2856 # for unicity and break when portion has no new videos
2857 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
2863 for entry in self._ids_to_results(new_ids):
2866 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2870 more = self._download_json(
2871 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2872 'Downloading page #%s' % page_num,
2873 transform_source=uppercase_escape)
2874 content_html = more['content_html']
2875 more_widget_html = more['load_more_widget_html']
2877 def _real_extract(self, url):
2878 page = self._download_webpage(
2879 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
2880 self._PLAYLIST_TITLE)
2881 return self.playlist_result(
2882 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
2885 class YoutubeWatchLaterIE(YoutubePlaylistIE):
2886 IE_NAME = 'youtube:watchlater'
2887 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2888 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2891 'url': 'https://www.youtube.com/playlist?list=WL',
2892 'only_matching': True,
2894 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2895 'only_matching': True,
2898 def _real_extract(self, url):
2899 _, video = self._check_download_just_video(url, 'WL')
2902 _, playlist = self._extract_playlist('WL')
2906 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
2907 IE_NAME = 'youtube:favorites'
2908 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2909 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2910 _LOGIN_REQUIRED = True
2912 def _real_extract(self, url):
2913 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2914 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
2915 return self.url_result(playlist_id, 'YoutubePlaylist')
2918 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2919 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2920 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2921 _FEED_NAME = 'recommended'
2922 _PLAYLIST_TITLE = 'Youtube Recommended videos'
2925 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2926 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2927 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2928 _FEED_NAME = 'subscriptions'
2929 _PLAYLIST_TITLE = 'Youtube Subscriptions'
2932 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2933 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
2934 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2935 _FEED_NAME = 'history'
2936 _PLAYLIST_TITLE = 'Youtube History'
2939 class YoutubeTruncatedURLIE(InfoExtractor):
2940 IE_NAME = 'youtube:truncated_url'
2941 IE_DESC = False # Do not list
2942 _VALID_URL = r'''(?x)
2944 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2947 annotation_id=annotation_[^&]+|
2953 attribution_link\?a=[^&]+
2959 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2960 'only_matching': True,
2962 'url': 'https://www.youtube.com/watch?',
2963 'only_matching': True,
2965 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2966 'only_matching': True,
2968 'url': 'https://www.youtube.com/watch?feature=foo',
2969 'only_matching': True,
2971 'url': 'https://www.youtube.com/watch?hl=en-GB',
2972 'only_matching': True,
2974 'url': 'https://www.youtube.com/watch?t=2372',
2975 'only_matching': True,
2978 def _real_extract(self, url):
2979 raise ExtractorError(
2980 'Did you forget to quote the URL? Remember that & is a meta '
2981 'character in most shells, so you want to put the URL in quotes, '
2983 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2984 ' or simply youtube-dl BaW_jenozKc .',
2988 class YoutubeTruncatedIDIE(InfoExtractor):
2989 IE_NAME = 'youtube:truncated_id'
2990 IE_DESC = False # Do not list
2991 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2994 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2995 'only_matching': True,
2998 def _real_extract(self, url):
2999 video_id = self._match_id(url)
3000 raise ExtractorError(
3001 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),