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,
53 class YoutubeBaseInfoExtractor(InfoExtractor):
54 """Provide base functions for Youtube extractors"""
55 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
56 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
58 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
59 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
60 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
62 _NETRC_MACHINE = 'youtube'
63 # If True it will raise an error if no login info is provided
64 _LOGIN_REQUIRED = False
66 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}'
68 def _set_language(self):
70 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
71 # YouTube sets the expire time to about two months
72 expire_time=time.time() + 2 * 30 * 24 * 3600)
74 def _ids_to_results(self, ids):
76 self.url_result(vid_id, 'Youtube', video_id=vid_id)
81 Attempt to log in to YouTube.
82 True is returned if successful or skipped.
83 False is returned if login failed.
85 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
87 (username, password) = self._get_login_info()
88 # No authentication to be performed
90 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
91 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
94 login_page = self._download_webpage(
95 self._LOGIN_URL, None,
96 note='Downloading login page',
97 errnote='unable to fetch login page', fatal=False)
98 if login_page is False:
101 login_form = self._hidden_inputs(login_page)
103 def req(url, f_req, note, errnote):
104 data = login_form.copy()
107 'checkConnection': 'youtube',
108 'checkedDomains': 'youtube',
110 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
111 'f.req': json.dumps(f_req),
112 'flowName': 'GlifWebSignIn',
113 'flowEntry': 'ServiceLogin',
115 return self._download_json(
116 url, None, note=note, errnote=errnote,
117 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
119 data=urlencode_postdata(data), headers={
120 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
121 'Google-Accounts-XSRF': 1,
125 self._downloader.report_warning(message)
129 None, [], None, 'US', None, None, 2, False, True,
133 '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',
135 1, [None, None, []], None, None, None, True
140 lookup_results = req(
141 self._LOOKUP_URL, lookup_req,
142 'Looking up account info', 'Unable to look up account info')
144 if lookup_results is False:
147 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
149 warn('Unable to extract user hash')
154 None, 1, None, [1, None, None, None, [password, None, True]],
156 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],
157 1, [None, None, []], None, None, None, True
160 challenge_results = req(
161 self._CHALLENGE_URL, challenge_req,
162 'Logging in', 'Unable to log in')
164 if challenge_results is False:
167 login_res = try_get(challenge_results, lambda x: x[0][5], list)
169 login_msg = try_get(login_res, lambda x: x[5], compat_str)
171 'Unable to login: %s' % 'Invalid password'
172 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
175 res = try_get(challenge_results, lambda x: x[0][-1], list)
177 warn('Unable to extract result entry')
180 tfa = try_get(res, lambda x: x[0][0], list)
182 tfa_str = try_get(tfa, lambda x: x[2], compat_str)
183 if tfa_str == 'TWO_STEP_VERIFICATION':
184 # SEND_SUCCESS - TFA code has been successfully sent to phone
185 # QUOTA_EXCEEDED - reached the limit of TFA codes
186 status = try_get(tfa, lambda x: x[5], compat_str)
187 if status == 'QUOTA_EXCEEDED':
188 warn('Exceeded the limit of TFA codes, try later')
191 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
193 warn('Unable to extract TL')
196 tfa_code = self._get_tfa_info('2-step verification code')
200 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
201 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
204 tfa_code = remove_start(tfa_code, 'G-')
207 user_hash, None, 2, None,
209 9, None, None, None, None, None, None, None,
210 [None, tfa_code, True, 2]
214 self._TFA_URL.format(tl), tfa_req,
215 'Submitting TFA code', 'Unable to submit TFA code')
217 if tfa_results is False:
220 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
222 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
224 'Unable to finish TFA: %s' % 'Invalid TFA code'
225 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
228 check_cookie_url = try_get(
229 tfa_results, lambda x: x[0][-1][2], compat_str)
231 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
233 if not check_cookie_url:
234 warn('Unable to extract CheckCookie URL')
237 check_cookie_results = self._download_webpage(
238 check_cookie_url, None, 'Checking cookie', fatal=False)
240 if check_cookie_results is False:
243 if 'https://myaccount.google.com/' not in check_cookie_results:
244 warn('Unable to log in')
249 def _download_webpage_handle(self, *args, **kwargs):
250 kwargs.setdefault('query', {})['disable_polymer'] = 'true'
251 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
252 *args, **compat_kwargs(kwargs))
254 def _real_initialize(self):
255 if self._downloader is None:
258 if not self._login():
262 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
263 # Extract entries from page with "Load more" button
264 def _entries(self, page, playlist_id):
265 more_widget_html = content_html = page
266 for page_num in itertools.count(1):
267 for entry in self._process_page(content_html):
270 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
274 more = self._download_json(
275 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
276 'Downloading page #%s' % page_num,
277 transform_source=uppercase_escape)
278 content_html = more['content_html']
279 if not content_html.strip():
280 # Some webpages show a "Load more" button but they don't
283 more_widget_html = more['load_more_widget_html']
286 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
287 def _process_page(self, content):
288 for video_id, video_title in self.extract_videos_from_page(content):
289 yield self.url_result(video_id, 'Youtube', video_id, video_title)
291 def extract_videos_from_page(self, page):
294 for mobj in re.finditer(self._VIDEO_RE, page):
295 # The link with index 0 is not the first video of the playlist (not sure if still actual)
296 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
298 video_id = mobj.group('id')
299 video_title = unescapeHTML(mobj.group('title'))
301 video_title = video_title.strip()
303 idx = ids_in_page.index(video_id)
304 if video_title and not titles_in_page[idx]:
305 titles_in_page[idx] = video_title
307 ids_in_page.append(video_id)
308 titles_in_page.append(video_title)
309 return zip(ids_in_page, titles_in_page)
312 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
313 def _process_page(self, content):
314 for playlist_id in orderedSet(re.findall(
315 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
317 yield self.url_result(
318 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
320 def _real_extract(self, url):
321 playlist_id = self._match_id(url)
322 webpage = self._download_webpage(url, playlist_id)
323 title = self._og_search_title(webpage, fatal=False)
324 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
327 class YoutubeIE(YoutubeBaseInfoExtractor):
328 IE_DESC = 'YouTube.com'
329 _VALID_URL = r"""(?x)^
331 (?:https?://|//) # http(s):// or protocol-independent URL
332 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
333 (?:www\.)?deturl\.com/www\.youtube\.com/|
334 (?:www\.)?pwnyoutube\.com/|
335 (?:www\.)?hooktube\.com/|
336 (?:www\.)?yourepeat\.com/|
337 tube\.majestyc\.net/|
338 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
339 (?:.*?\#/)? # handle anchor (#/) redirect urls
340 (?: # the various things that can precede the ID:
341 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
342 |(?: # or the v= param in all its forms
343 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
344 (?:\?|\#!?) # the params delimiter ? or # or #!
345 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
350 youtu\.be| # just youtu.be/xxxx
351 vid\.plus| # or vid.plus/xxxx
352 zwearz\.com/watch| # or zwearz.com/watch/xxxx
354 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
356 )? # all until now is optional -> you can pass the naked ID
357 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
360 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
361 WL # WL are handled by the watch later IE
364 (?(1).+)? # if we found the ID, everything can follow
365 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
366 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
368 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
369 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
370 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
371 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
372 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
373 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
374 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
375 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
376 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
377 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
378 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
379 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
380 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
381 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
382 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
383 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
384 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
385 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
389 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
390 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
391 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
392 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
393 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
394 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
395 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
397 # Apple HTTP Live Streaming
398 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
399 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
400 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
401 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
402 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
403 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
404 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
405 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
408 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
409 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
410 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
411 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
412 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
413 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
414 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
415 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
416 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
417 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
418 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
419 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
422 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
423 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
424 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
425 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
426 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
427 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
428 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
431 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
432 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
433 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
434 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
435 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
436 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
437 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
438 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
439 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
440 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
441 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
442 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
443 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
444 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
445 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
446 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
447 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
448 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
449 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
450 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
451 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
452 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
455 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
456 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
458 # Dash webm audio with opus inside
459 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
460 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
461 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
464 '_rtmp': {'protocol': 'rtmp'},
466 _SUBTITLE_FORMATS = ('ttml', 'vtt')
473 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
477 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
478 'uploader': 'Philipp Hagemeister',
479 'uploader_id': 'phihag',
480 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
481 'upload_date': '20121002',
482 'license': 'Standard YouTube License',
483 '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 .',
484 'categories': ['Science & Technology'],
485 'tags': ['youtube-dl'],
488 'dislike_count': int,
494 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
495 'note': 'Test generic use_cipher_signature video (#897)',
499 'upload_date': '20120506',
500 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
501 'alt_title': 'I Love It (feat. Charli XCX)',
502 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
503 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
504 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
505 'iconic ep', 'iconic', 'love', 'it'],
507 'uploader': 'Icona Pop',
508 'uploader_id': 'IconaPop',
509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
510 'license': 'Standard YouTube License',
511 'creator': 'Icona Pop',
515 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
516 'note': 'Test VEVO video with age protection (#956)',
520 'upload_date': '20130703',
521 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
522 'alt_title': 'Tunnel Vision',
523 'description': 'md5:64249768eec3bc4276236606ea996373',
525 'uploader': 'justintimberlakeVEVO',
526 'uploader_id': 'justintimberlakeVEVO',
527 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
528 'license': 'Standard YouTube License',
529 'creator': 'Justin Timberlake',
534 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
535 'note': 'Embed-only video (#1746)',
539 'upload_date': '20120608',
540 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
541 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
542 'uploader': 'SET India',
543 'uploader_id': 'setindia',
544 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
545 'license': 'Standard YouTube License',
550 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
551 'note': 'Use the first video ID in the URL',
555 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
556 'uploader': 'Philipp Hagemeister',
557 'uploader_id': 'phihag',
558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
559 'upload_date': '20121002',
560 'license': 'Standard YouTube License',
561 '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 .',
562 'categories': ['Science & Technology'],
563 'tags': ['youtube-dl'],
566 'dislike_count': int,
569 'skip_download': True,
573 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
574 'note': '256k DASH audio (format 141) via DASH manifest',
578 'upload_date': '20121002',
579 'uploader_id': '8KVIDEO',
580 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
582 'uploader': '8KVIDEO',
583 'license': 'Standard YouTube License',
584 'title': 'UHDTV TEST 8K VIDEO.mp4'
587 'youtube_include_dash_manifest': True,
590 'skip': 'format 141 not served anymore',
592 # DASH manifest with encrypted signature
594 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
598 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
599 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
601 'uploader': 'AfrojackVEVO',
602 'uploader_id': 'AfrojackVEVO',
603 'upload_date': '20131011',
604 'license': 'Standard YouTube License',
607 'youtube_include_dash_manifest': True,
608 'format': '141/bestaudio[ext=m4a]',
611 # JS player signature function name containing $
613 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
617 'title': 'Taylor Swift - Shake It Off',
618 'alt_title': 'Shake It Off',
619 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
621 'uploader': 'TaylorSwiftVEVO',
622 'uploader_id': 'TaylorSwiftVEVO',
623 'upload_date': '20140818',
624 'license': 'Standard YouTube License',
625 'creator': 'Taylor Swift',
628 'youtube_include_dash_manifest': True,
629 'format': '141/bestaudio[ext=m4a]',
634 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
639 'upload_date': '20100909',
640 'uploader': 'The Amazing Atheist',
641 'uploader_id': 'TheAmazingAtheist',
642 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
643 'license': 'Standard YouTube License',
644 'title': 'Burning Everyone\'s Koran',
645 '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',
648 # Normal age-gate video (No vevo, embed allowed)
650 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
654 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
655 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
657 'uploader': 'The Witcher',
658 'uploader_id': 'WitcherGame',
659 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
660 'upload_date': '20140605',
661 'license': 'Standard YouTube License',
665 # Age-gate video with encrypted signature
667 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
671 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
672 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
674 'uploader': 'LloydVEVO',
675 'uploader_id': 'LloydVEVO',
676 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
677 'upload_date': '20110629',
678 'license': 'Standard YouTube License',
682 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
683 # YouTube Red ad is not captured for creator
685 'url': '__2ABJjxzNo',
690 'upload_date': '20100430',
691 'uploader_id': 'deadmau5',
692 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
693 'creator': 'deadmau5',
694 'description': 'md5:12c56784b8032162bb936a5f76d55360',
695 'uploader': 'deadmau5',
696 'license': 'Standard YouTube License',
697 'title': 'Deadmau5 - Some Chords (HD)',
698 'alt_title': 'Some Chords',
700 'expected_warnings': [
701 'DASH manifest missing',
704 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
706 'url': 'lqQg6PlCWgI',
711 'upload_date': '20150827',
712 'uploader_id': 'olympic',
713 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
714 'license': 'Standard YouTube License',
715 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
716 'uploader': 'Olympic',
717 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
720 'skip_download': 'requires avconv',
725 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
729 'stretched_ratio': 16 / 9.,
731 'upload_date': '20110310',
732 'uploader_id': 'AllenMeow',
733 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
734 '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',
736 'license': 'Standard YouTube License',
737 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
740 # url_encoded_fmt_stream_map is empty string
742 'url': 'qEJwOuvDf7I',
746 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
748 'upload_date': '20150404',
749 'uploader_id': 'spbelect',
750 'uploader': 'Наблюдатели Петербурга',
753 'skip_download': 'requires avconv',
755 'skip': 'This live event has ended.',
757 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
759 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
763 'title': 'md5:7b81415841e02ecd4313668cde88737a',
764 'description': 'md5:116377fd2963b81ec4ce64b542173306',
766 'upload_date': '20150625',
767 'uploader_id': 'dorappi2000',
768 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
769 'uploader': 'dorappi2000',
770 'license': 'Standard YouTube License',
771 'formats': 'mincount:32',
774 # DASH manifest with segment_list
776 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
777 'md5': '8ce563a1d667b599d21064e982ab9e31',
781 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
782 'uploader': 'Airtek',
783 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
784 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
785 'license': 'Standard YouTube License',
786 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
789 'youtube_include_dash_manifest': True,
790 'format': '135', # bestvideo
792 'skip': 'This live event has ended.',
795 # Multifeed videos (multiple cameras), URL is for Main Camera
796 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
799 'title': 'teamPGP: Rocket League Noob Stream',
800 'description': 'md5:dc7872fb300e143831327f1bae3af010',
806 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
807 'description': 'md5:dc7872fb300e143831327f1bae3af010',
809 'upload_date': '20150721',
810 'uploader': 'Beer Games Beer',
811 'uploader_id': 'beergamesbeer',
812 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
813 'license': 'Standard YouTube License',
819 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
820 'description': 'md5:dc7872fb300e143831327f1bae3af010',
822 'upload_date': '20150721',
823 'uploader': 'Beer Games Beer',
824 'uploader_id': 'beergamesbeer',
825 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
826 'license': 'Standard YouTube License',
832 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
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 (zim)',
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',
856 'skip_download': True,
860 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
861 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
864 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
867 'skip': 'Not multifeed anymore',
870 'url': 'https://vid.plus/FlRa-iH7PGw',
871 'only_matching': True,
874 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
875 'only_matching': True,
878 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
879 # Also tests cut-off URL expansion in video description (see
880 # https://github.com/rg3/youtube-dl/issues/1892,
881 # https://github.com/rg3/youtube-dl/issues/8164)
882 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
886 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
887 'alt_title': 'Dark Walk',
888 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
890 'upload_date': '20151119',
891 'uploader_id': 'IronSoulElf',
892 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
893 'uploader': 'IronSoulElf',
894 'license': 'Standard YouTube License',
895 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
898 'skip_download': True,
902 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
903 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
904 'only_matching': True,
907 # Video with yt:stretch=17:0
908 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
912 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
913 'description': 'md5:ee18a25c350637c8faff806845bddee9',
914 'upload_date': '20151107',
915 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
916 'uploader': 'CH GAMER DROID',
919 'skip_download': True,
921 'skip': 'This video does not exist.',
924 # Video licensed under Creative Commons
925 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
929 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
930 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
932 'upload_date': '20150127',
933 'uploader_id': 'BerkmanCenter',
934 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
935 'uploader': 'The Berkman Klein Center for Internet & Society',
936 'license': 'Creative Commons Attribution license (reuse allowed)',
939 'skip_download': True,
943 # Channel-like uploader_url
944 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
948 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
949 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
951 'upload_date': '20151119',
952 'uploader': 'Bernie 2016',
953 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
954 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
955 'license': 'Creative Commons Attribution license (reuse allowed)',
958 'skip_download': True,
962 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
963 'only_matching': True,
966 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
967 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
968 'only_matching': True,
971 # Rental video preview
972 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
976 'title': 'Piku - Trailer',
977 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
978 'upload_date': '20150811',
979 'uploader': 'FlixMatrix',
980 'uploader_id': 'FlixMatrixKaravan',
981 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
982 'license': 'Standard YouTube License',
985 'skip_download': True,
989 # YouTube Red video with episode data
990 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
994 'title': 'Isolation - Mind Field (Ep 1)',
995 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
997 'upload_date': '20170118',
998 'uploader': 'Vsauce',
999 'uploader_id': 'Vsauce',
1000 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1001 'license': 'Standard YouTube License',
1002 'series': 'Mind Field',
1004 'episode_number': 1,
1007 'skip_download': True,
1009 'expected_warnings': [
1010 'Skipping DASH manifest',
1014 # The following content has been identified by the YouTube community
1015 # as inappropriate or offensive to some audiences.
1016 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1018 'id': '6SJNVb0GnPI',
1020 'title': 'Race Differences in Intelligence',
1021 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1023 'upload_date': '20140124',
1024 'uploader': 'New Century Foundation',
1025 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1026 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1027 'license': 'Standard YouTube License',
1031 'skip_download': True,
1036 'url': '1t24XAntNCY',
1037 'only_matching': True,
1040 # geo restricted to JP
1041 'url': 'sJL6WA-aGkQ',
1042 'only_matching': True,
1045 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1046 'only_matching': True,
1050 def __init__(self, *args, **kwargs):
1051 super(YoutubeIE, self).__init__(*args, **kwargs)
1052 self._player_cache = {}
1054 def report_video_info_webpage_download(self, video_id):
1055 """Report attempt to download video info webpage."""
1056 self.to_screen('%s: Downloading video info webpage' % video_id)
1058 def report_information_extraction(self, video_id):
1059 """Report attempt to extract video information."""
1060 self.to_screen('%s: Extracting video information' % video_id)
1062 def report_unavailable_format(self, video_id, format):
1063 """Report extracted video URL."""
1064 self.to_screen('%s: Format %s not available' % (video_id, format))
1066 def report_rtmp_download(self):
1067 """Indicate the download will use the RTMP protocol."""
1068 self.to_screen('RTMP download detected')
1070 def _signature_cache_id(self, example_sig):
1071 """ Return a string representation of a signature """
1072 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1074 def _extract_signature_function(self, video_id, player_url, example_sig):
1076 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1079 raise ExtractorError('Cannot identify player %r' % player_url)
1080 player_type = id_m.group('ext')
1081 player_id = id_m.group('id')
1083 # Read from filesystem cache
1084 func_id = '%s_%s_%s' % (
1085 player_type, player_id, self._signature_cache_id(example_sig))
1086 assert os.path.basename(func_id) == func_id
1088 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1089 if cache_spec is not None:
1090 return lambda s: ''.join(s[i] for i in cache_spec)
1093 'Downloading player %s' % player_url
1094 if self._downloader.params.get('verbose') else
1095 'Downloading %s player %s' % (player_type, player_id)
1097 if player_type == 'js':
1098 code = self._download_webpage(
1099 player_url, video_id,
1101 errnote='Download of %s failed' % player_url)
1102 res = self._parse_sig_js(code)
1103 elif player_type == 'swf':
1104 urlh = self._request_webpage(
1105 player_url, video_id,
1107 errnote='Download of %s failed' % player_url)
1109 res = self._parse_sig_swf(code)
1111 assert False, 'Invalid player type %r' % player_type
1113 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1114 cache_res = res(test_string)
1115 cache_spec = [ord(c) for c in cache_res]
1117 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1120 def _print_sig_code(self, func, example_sig):
1121 def gen_sig_code(idxs):
1122 def _genslice(start, end, step):
1123 starts = '' if start == 0 else str(start)
1124 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1125 steps = '' if step == 1 else (':%d' % step)
1126 return 's[%s%s%s]' % (starts, ends, steps)
1129 # Quelch pyflakes warnings - start will be set when step is set
1130 start = '(Never used)'
1131 for i, prev in zip(idxs[1:], idxs[:-1]):
1132 if step is not None:
1133 if i - prev == step:
1135 yield _genslice(start, prev, step)
1138 if i - prev in [-1, 1]:
1143 yield 's[%d]' % prev
1147 yield _genslice(start, i, step)
1149 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1150 cache_res = func(test_string)
1151 cache_spec = [ord(c) for c in cache_res]
1152 expr_code = ' + '.join(gen_sig_code(cache_spec))
1153 signature_id_tuple = '(%s)' % (
1154 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1155 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1156 ' return %s\n') % (signature_id_tuple, expr_code)
1157 self.to_screen('Extracted signature function:\n' + code)
1159 def _parse_sig_js(self, jscode):
1160 funcname = self._search_regex(
1161 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1162 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
1163 jscode, 'Initial JS player signature function name', group='sig')
1165 jsi = JSInterpreter(jscode)
1166 initial_function = jsi.extract_function(funcname)
1167 return lambda s: initial_function([s])
1169 def _parse_sig_swf(self, file_contents):
1170 swfi = SWFInterpreter(file_contents)
1171 TARGET_CLASSNAME = 'SignatureDecipher'
1172 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1173 initial_function = swfi.extract_function(searched_class, 'decipher')
1174 return lambda s: initial_function([s])
1176 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1177 """Turn the encrypted s field into a working signature"""
1179 if player_url is None:
1180 raise ExtractorError('Cannot decrypt signature without player_url')
1182 if player_url.startswith('//'):
1183 player_url = 'https:' + player_url
1184 elif not re.match(r'https?://', player_url):
1185 player_url = compat_urlparse.urljoin(
1186 'https://www.youtube.com', player_url)
1188 player_id = (player_url, self._signature_cache_id(s))
1189 if player_id not in self._player_cache:
1190 func = self._extract_signature_function(
1191 video_id, player_url, s
1193 self._player_cache[player_id] = func
1194 func = self._player_cache[player_id]
1195 if self._downloader.params.get('youtube_print_sig_code'):
1196 self._print_sig_code(func, s)
1198 except Exception as e:
1199 tb = traceback.format_exc()
1200 raise ExtractorError(
1201 'Signature extraction failed: ' + tb, cause=e)
1203 def _get_subtitles(self, video_id, webpage):
1205 subs_doc = self._download_xml(
1206 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1207 video_id, note=False)
1208 except ExtractorError as err:
1209 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1213 for track in subs_doc.findall('track'):
1214 lang = track.attrib['lang_code']
1215 if lang in sub_lang_list:
1218 for ext in self._SUBTITLE_FORMATS:
1219 params = compat_urllib_parse_urlencode({
1223 'name': track.attrib['name'].encode('utf-8'),
1225 sub_formats.append({
1226 'url': 'https://www.youtube.com/api/timedtext?' + params,
1229 sub_lang_list[lang] = sub_formats
1230 if not sub_lang_list:
1231 self._downloader.report_warning('video doesn\'t have subtitles')
1233 return sub_lang_list
1235 def _get_ytplayer_config(self, video_id, webpage):
1237 # User data may contain arbitrary character sequences that may affect
1238 # JSON extraction with regex, e.g. when '};' is contained the second
1239 # regex won't capture the whole JSON. Yet working around by trying more
1240 # concrete regex first keeping in mind proper quoted string handling
1241 # to be implemented in future that will replace this workaround (see
1242 # https://github.com/rg3/youtube-dl/issues/7468,
1243 # https://github.com/rg3/youtube-dl/pull/7599)
1244 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1245 r';ytplayer\.config\s*=\s*({.+?});',
1247 config = self._search_regex(
1248 patterns, webpage, 'ytplayer.config', default=None)
1250 return self._parse_json(
1251 uppercase_escape(config), video_id, fatal=False)
1253 def _get_automatic_captions(self, video_id, webpage):
1254 """We need the webpage for getting the captions url, pass it as an
1255 argument to speed up the process."""
1256 self.to_screen('%s: Looking for automatic captions' % video_id)
1257 player_config = self._get_ytplayer_config(video_id, webpage)
1258 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1259 if not player_config:
1260 self._downloader.report_warning(err_msg)
1263 args = player_config['args']
1264 caption_url = args.get('ttsurl')
1266 timestamp = args['timestamp']
1267 # We get the available subtitles
1268 list_params = compat_urllib_parse_urlencode({
1273 list_url = caption_url + '&' + list_params
1274 caption_list = self._download_xml(list_url, video_id)
1275 original_lang_node = caption_list.find('track')
1276 if original_lang_node is None:
1277 self._downloader.report_warning('Video doesn\'t have automatic captions')
1279 original_lang = original_lang_node.attrib['lang_code']
1280 caption_kind = original_lang_node.attrib.get('kind', '')
1283 for lang_node in caption_list.findall('target'):
1284 sub_lang = lang_node.attrib['lang_code']
1286 for ext in self._SUBTITLE_FORMATS:
1287 params = compat_urllib_parse_urlencode({
1288 'lang': original_lang,
1292 'kind': caption_kind,
1294 sub_formats.append({
1295 'url': caption_url + '&' + params,
1298 sub_lang_list[sub_lang] = sub_formats
1299 return sub_lang_list
1301 def make_captions(sub_url, sub_langs):
1302 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1303 caption_qs = compat_parse_qs(parsed_sub_url.query)
1305 for sub_lang in sub_langs:
1307 for ext in self._SUBTITLE_FORMATS:
1309 'tlang': [sub_lang],
1312 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1313 query=compat_urllib_parse_urlencode(caption_qs, True)))
1314 sub_formats.append({
1318 captions[sub_lang] = sub_formats
1321 # New captions format as of 22.06.2017
1322 player_response = args.get('player_response')
1323 if player_response and isinstance(player_response, compat_str):
1324 player_response = self._parse_json(
1325 player_response, video_id, fatal=False)
1327 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1328 base_url = renderer['captionTracks'][0]['baseUrl']
1330 for lang in renderer['translationLanguages']:
1331 lang_code = lang.get('languageCode')
1333 sub_lang_list.append(lang_code)
1334 return make_captions(base_url, sub_lang_list)
1336 # Some videos don't provide ttsurl but rather caption_tracks and
1337 # caption_translation_languages (e.g. 20LmZk1hakA)
1338 # Does not used anymore as of 22.06.2017
1339 caption_tracks = args['caption_tracks']
1340 caption_translation_languages = args['caption_translation_languages']
1341 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1343 for lang in caption_translation_languages.split(','):
1344 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1345 sub_lang = lang_qs.get('lc', [None])[0]
1347 sub_lang_list.append(sub_lang)
1348 return make_captions(caption_url, sub_lang_list)
1349 # An extractor error can be raise by the download process if there are
1350 # no automatic captions but there are subtitles
1351 except (KeyError, IndexError, ExtractorError):
1352 self._downloader.report_warning(err_msg)
1355 def _mark_watched(self, video_id, video_info):
1356 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1357 if not playback_url:
1359 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1360 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1362 # cpn generation algorithm is reverse engineered from base.js.
1363 # In fact it works even with dummy cpn.
1364 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1365 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1371 playback_url = compat_urlparse.urlunparse(
1372 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1374 self._download_webpage(
1375 playback_url, video_id, 'Marking watched',
1376 'Unable to mark watched', fatal=False)
1379 def _extract_urls(webpage):
1380 # Embedded YouTube player
1382 unescapeHTML(mobj.group('url'))
1383 for mobj in re.finditer(r'''(?x)
1393 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1394 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1397 # lazyYT YouTube embed
1398 entries.extend(list(map(
1400 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1402 # Wordpress "YouTube Video Importer" plugin
1403 matches = re.findall(r'''(?x)<div[^>]+
1404 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1405 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1406 entries.extend(m[-1] for m in matches)
1411 def _extract_url(webpage):
1412 urls = YoutubeIE._extract_urls(webpage)
1413 return urls[0] if urls else None
1416 def extract_id(cls, url):
1417 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1419 raise ExtractorError('Invalid URL: %s' % url)
1420 video_id = mobj.group(2)
1423 def _extract_annotations(self, video_id):
1424 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1425 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1428 def _extract_chapters(description, duration):
1431 chapter_lines = re.findall(
1432 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1434 if not chapter_lines:
1437 for next_num, (chapter_line, time_point) in enumerate(
1438 chapter_lines, start=1):
1439 start_time = parse_duration(time_point)
1440 if start_time is None:
1442 if start_time > duration:
1444 end_time = (duration if next_num == len(chapter_lines)
1445 else parse_duration(chapter_lines[next_num][1]))
1446 if end_time is None:
1448 if end_time > duration:
1450 if start_time > end_time:
1452 chapter_title = re.sub(
1453 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1454 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1456 'start_time': start_time,
1457 'end_time': end_time,
1458 'title': chapter_title,
1462 def _real_extract(self, url):
1463 url, smuggled_data = unsmuggle_url(url, {})
1466 'http' if self._downloader.params.get('prefer_insecure', False)
1471 parsed_url = compat_urllib_parse_urlparse(url)
1472 for component in [parsed_url.fragment, parsed_url.query]:
1473 query = compat_parse_qs(component)
1474 if start_time is None and 't' in query:
1475 start_time = parse_duration(query['t'][0])
1476 if start_time is None and 'start' in query:
1477 start_time = parse_duration(query['start'][0])
1478 if end_time is None and 'end' in query:
1479 end_time = parse_duration(query['end'][0])
1481 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1482 mobj = re.search(self._NEXT_URL_RE, url)
1484 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1485 video_id = self.extract_id(url)
1488 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1489 video_webpage = self._download_webpage(url, video_id)
1491 # Attempt to extract SWF player URL
1492 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1493 if mobj is not None:
1494 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1500 def add_dash_mpd(video_info):
1501 dash_mpd = video_info.get('dashmpd')
1502 if dash_mpd and dash_mpd[0] not in dash_mpds:
1503 dash_mpds.append(dash_mpd[0])
1508 def extract_view_count(v_info):
1509 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1512 embed_webpage = None
1513 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1515 # We simulate the access to the video from www.youtube.com/v/{video_id}
1516 # this can be viewed without login into Youtube
1517 url = proto + '://www.youtube.com/embed/%s' % video_id
1518 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1519 data = compat_urllib_parse_urlencode({
1520 'video_id': video_id,
1521 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1522 'sts': self._search_regex(
1523 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1525 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1526 video_info_webpage = self._download_webpage(
1527 video_info_url, video_id,
1528 note='Refetching age-gated info webpage',
1529 errnote='unable to download video info webpage')
1530 video_info = compat_parse_qs(video_info_webpage)
1531 add_dash_mpd(video_info)
1536 # Try looking directly into the video webpage
1537 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1539 args = ytplayer_config['args']
1540 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1541 # Convert to the same format returned by compat_parse_qs
1542 video_info = dict((k, [v]) for k, v in args.items())
1543 add_dash_mpd(video_info)
1544 # Rental video is not rented but preview is available (e.g.
1545 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1546 # https://github.com/rg3/youtube-dl/issues/10532)
1547 if not video_info and args.get('ypc_vid'):
1548 return self.url_result(
1549 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1550 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1552 sts = ytplayer_config.get('sts')
1553 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1554 # We also try looking in get_video_info since it may contain different dashmpd
1555 # URL that points to a DASH manifest with possibly different itag set (some itags
1556 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1557 # manifest pointed by get_video_info's dashmpd).
1558 # The general idea is to take a union of itags of both DASH manifests (for example
1559 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1560 self.report_video_info_webpage_download(video_id)
1561 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1563 'video_id': video_id,
1573 video_info_webpage = self._download_webpage(
1574 '%s://www.youtube.com/get_video_info' % proto,
1575 video_id, note=False,
1576 errnote='unable to download video info webpage',
1577 fatal=False, query=query)
1578 if not video_info_webpage:
1580 get_video_info = compat_parse_qs(video_info_webpage)
1581 add_dash_mpd(get_video_info)
1582 if view_count is None:
1583 view_count = extract_view_count(get_video_info)
1585 video_info = get_video_info
1586 if 'token' in get_video_info:
1587 # Different get_video_info requests may report different results, e.g.
1588 # some may report video unavailability, but some may serve it without
1589 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1590 # the original webpage as well as el=info and el=embedded get_video_info
1591 # requests report video unavailability due to geo restriction while
1592 # el=detailpage succeeds and returns valid data). This is probably
1593 # due to YouTube measures against IP ranges of hosting providers.
1594 # Working around by preferring the first succeeded video_info containing
1595 # the token if no such video_info yet was found.
1596 if 'token' not in video_info:
1597 video_info = get_video_info
1600 def extract_unavailable_message():
1601 return self._html_search_regex(
1602 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1603 video_webpage, 'unavailable message', default=None)
1605 if 'token' not in video_info:
1606 if 'reason' in video_info:
1607 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1608 regions_allowed = self._html_search_meta(
1609 'regionsAllowed', video_webpage, default=None)
1610 countries = regions_allowed.split(',') if regions_allowed else None
1611 self.raise_geo_restricted(
1612 msg=video_info['reason'][0], countries=countries)
1613 reason = video_info['reason'][0]
1614 if 'Invalid parameters' in reason:
1615 unavailable_message = extract_unavailable_message()
1616 if unavailable_message:
1617 reason = unavailable_message
1618 raise ExtractorError(
1619 'YouTube said: %s' % reason,
1620 expected=True, video_id=video_id)
1622 raise ExtractorError(
1623 '"token" parameter not in video info for unknown reason',
1627 if 'title' in video_info:
1628 video_title = video_info['title'][0]
1630 self._downloader.report_warning('Unable to extract video title')
1634 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1635 if video_description:
1638 redir_url = compat_urlparse.urljoin(url, m.group(1))
1639 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1640 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1641 qs = compat_parse_qs(parsed_redir_url.query)
1647 description_original = video_description = re.sub(r'''(?x)
1649 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1650 (?:title|href)="([^"]+)"\s+
1651 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1655 ''', replace_url, video_description)
1656 video_description = clean_html(video_description)
1658 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1660 video_description = unescapeHTML(fd_mobj.group(1))
1662 video_description = ''
1664 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1665 if not self._downloader.params.get('noplaylist'):
1668 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
1669 for feed in multifeed_metadata_list.split(','):
1670 # Unquote should take place before split on comma (,) since textual
1671 # fields may contain comma as well (see
1672 # https://github.com/rg3/youtube-dl/issues/8536)
1673 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1675 '_type': 'url_transparent',
1676 'ie_key': 'Youtube',
1678 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1679 {'force_singlefeed': True}),
1680 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1682 feed_ids.append(feed_data['id'][0])
1684 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1685 % (', '.join(feed_ids), video_id))
1686 return self.playlist_result(entries, video_id, video_title, video_description)
1687 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1689 if view_count is None:
1690 view_count = extract_view_count(video_info)
1692 # Check for "rental" videos
1693 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1694 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
1696 # Start extracting information
1697 self.report_information_extraction(video_id)
1700 video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str)
1702 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
1704 self._downloader.report_warning('unable to extract uploader name')
1707 video_uploader_id = None
1708 video_uploader_url = None
1710 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1712 if mobj is not None:
1713 video_uploader_id = mobj.group('uploader_id')
1714 video_uploader_url = mobj.group('uploader_url')
1716 self._downloader.report_warning('unable to extract uploader nickname')
1719 # We try first to get a high quality image:
1720 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1721 video_webpage, re.DOTALL)
1722 if m_thumb is not None:
1723 video_thumbnail = m_thumb.group(1)
1724 elif 'thumbnail_url' not in video_info:
1725 self._downloader.report_warning('unable to extract video thumbnail')
1726 video_thumbnail = None
1727 else: # don't panic if we can't find it
1728 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1731 upload_date = self._html_search_meta(
1732 'datePublished', video_webpage, 'upload date', default=None)
1734 upload_date = self._search_regex(
1735 [r'(?s)id="eow-date.*?>(.*?)</span>',
1736 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
1737 video_webpage, 'upload date', default=None)
1738 upload_date = unified_strdate(upload_date)
1740 video_license = self._html_search_regex(
1741 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1742 video_webpage, 'license', default=None)
1744 m_music = re.search(
1746 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
1754 \bhref=["\']/red[^>]*>| # drop possible
1755 >\s*Listen ad-free with YouTube Red # YouTube Red ad
1762 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1763 video_creator = clean_html(m_music.group('creator'))
1765 video_alt_title = video_creator = None
1767 m_episode = re.search(
1768 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1771 series = m_episode.group('series')
1772 season_number = int(m_episode.group('season'))
1773 episode_number = int(m_episode.group('episode'))
1775 series = season_number = episode_number = None
1777 m_cat_container = self._search_regex(
1778 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1779 video_webpage, 'categories', default=None)
1781 category = self._html_search_regex(
1782 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
1784 video_categories = None if category is None else [category]
1786 video_categories = None
1789 unescapeHTML(m.group('content'))
1790 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1792 def _extract_count(count_name):
1793 return str_to_int(self._search_regex(
1794 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1795 % re.escape(count_name),
1796 video_webpage, count_name, default=None))
1798 like_count = _extract_count('like')
1799 dislike_count = _extract_count('dislike')
1802 video_subtitles = self.extract_subtitles(video_id, video_webpage)
1803 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
1805 video_duration = try_get(
1806 video_info, lambda x: int_or_none(x['length_seconds'][0]))
1807 if not video_duration:
1808 video_duration = parse_duration(self._html_search_meta(
1809 'duration', video_webpage, 'video duration'))
1812 video_annotations = None
1813 if self._downloader.params.get('writeannotations', False):
1814 video_annotations = self._extract_annotations(video_id)
1816 chapters = self._extract_chapters(description_original, video_duration)
1818 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1819 self.report_rtmp_download()
1821 'format_id': '_rtmp',
1823 'url': video_info['conn'][0],
1824 'player_url': player_url,
1826 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):
1827 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1828 if 'rtmpe%3Dyes' in encoded_url_map:
1829 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
1831 fmt_list = video_info.get('fmt_list', [''])[0]
1833 for fmt in fmt_list.split(','):
1834 spec = fmt.split('/')
1836 width_height = spec[1].split('x')
1837 if len(width_height) == 2:
1838 formats_spec[spec[0]] = {
1839 'resolution': spec[1],
1840 'width': int_or_none(width_height[0]),
1841 'height': int_or_none(width_height[1]),
1844 for url_data_str in encoded_url_map.split(','):
1845 url_data = compat_parse_qs(url_data_str)
1846 if 'itag' not in url_data or 'url' not in url_data:
1848 format_id = url_data['itag'][0]
1849 url = url_data['url'][0]
1851 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1852 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1853 jsplayer_url_json = self._search_regex(
1855 embed_webpage if age_gate else video_webpage,
1856 'JS player URL (1)', default=None)
1857 if not jsplayer_url_json and not age_gate:
1858 # We need the embed website after all
1859 if embed_webpage is None:
1860 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1861 embed_webpage = self._download_webpage(
1862 embed_url, video_id, 'Downloading embed webpage')
1863 jsplayer_url_json = self._search_regex(
1864 ASSETS_RE, embed_webpage, 'JS player URL')
1866 player_url = json.loads(jsplayer_url_json)
1867 if player_url is None:
1868 player_url_json = self._search_regex(
1869 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1870 video_webpage, 'age gate player URL')
1871 player_url = json.loads(player_url_json)
1873 if 'sig' in url_data:
1874 url += '&signature=' + url_data['sig'][0]
1875 elif 's' in url_data:
1876 encrypted_sig = url_data['s'][0]
1878 if self._downloader.params.get('verbose'):
1879 if player_url is None:
1880 player_version = 'unknown'
1881 player_desc = 'unknown'
1883 if player_url.endswith('swf'):
1884 player_version = self._search_regex(
1885 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1886 'flash player', fatal=False)
1887 player_desc = 'flash player %s' % player_version
1889 player_version = self._search_regex(
1890 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1891 r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
1893 'html5 player', fatal=False)
1894 player_desc = 'html5 player %s' % player_version
1896 parts_sizes = self._signature_cache_id(encrypted_sig)
1897 self.to_screen('{%s} signature length %s, %s' %
1898 (format_id, parts_sizes, player_desc))
1900 signature = self._decrypt_signature(
1901 encrypted_sig, video_id, player_url, age_gate)
1902 url += '&signature=' + signature
1903 if 'ratebypass' not in url:
1904 url += '&ratebypass=yes'
1907 'format_id': format_id,
1909 'player_url': player_url,
1911 if format_id in self._formats:
1912 dct.update(self._formats[format_id])
1913 if format_id in formats_spec:
1914 dct.update(formats_spec[format_id])
1916 # Some itags are not included in DASH manifest thus corresponding formats will
1917 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1918 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1919 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1920 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
1923 'filesize': int_or_none(url_data.get('clen', [None])[0]),
1924 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
1927 'fps': int_or_none(url_data.get('fps', [None])[0]),
1928 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
1930 for key, value in more_fields.items():
1933 type_ = url_data.get('type', [None])[0]
1935 type_split = type_.split(';')
1936 kind_ext = type_split[0].split('/')
1937 if len(kind_ext) == 2:
1939 dct['ext'] = mimetype2ext(type_split[0])
1940 if kind in ('audio', 'video'):
1942 for mobj in re.finditer(
1943 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1944 if mobj.group('key') == 'codecs':
1945 codecs = mobj.group('val')
1948 dct.update(parse_codecs(codecs))
1949 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
1950 dct['downloader_options'] = {
1951 # Youtube throttles chunks >~10M
1952 'http_chunk_size': 10485760,
1955 elif video_info.get('hlsvp'):
1956 manifest_url = video_info['hlsvp'][0]
1958 m3u8_formats = self._extract_m3u8_formats(
1959 manifest_url, video_id, 'mp4', fatal=False)
1960 for a_format in m3u8_formats:
1961 itag = self._search_regex(
1962 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1964 a_format['format_id'] = itag
1965 if itag in self._formats:
1966 dct = self._formats[itag].copy()
1967 dct.update(a_format)
1969 a_format['player_url'] = player_url
1970 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1971 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1972 formats.append(a_format)
1974 error_message = clean_html(video_info.get('reason', [None])[0])
1975 if not error_message:
1976 error_message = extract_unavailable_message()
1978 raise ExtractorError(error_message, expected=True)
1979 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
1981 # Look for the DASH manifest
1982 if self._downloader.params.get('youtube_include_dash_manifest', True):
1983 dash_mpd_fatal = True
1984 for mpd_url in dash_mpds:
1987 def decrypt_sig(mobj):
1989 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1990 return '/signature/%s' % dec_s
1992 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
1994 for df in self._extract_mpd_formats(
1995 mpd_url, video_id, fatal=dash_mpd_fatal,
1996 formats_dict=self._formats):
1997 # Do not overwrite DASH format found in some previous DASH manifest
1998 if df['format_id'] not in dash_formats:
1999 dash_formats[df['format_id']] = df
2000 # Additional DASH manifests may end up in HTTP Error 403 therefore
2001 # allow them to fail without bug report message if we already have
2002 # some DASH manifest succeeded. This is temporary workaround to reduce
2003 # burst of bug reports until we figure out the reason and whether it
2004 # can be fixed at all.
2005 dash_mpd_fatal = False
2006 except (ExtractorError, KeyError) as e:
2007 self.report_warning(
2008 'Skipping DASH manifest: %r' % e, video_id)
2010 # Remove the formats we found through non-DASH, they
2011 # contain less info and it can be wrong, because we use
2012 # fixed values (for example the resolution). See
2013 # https://github.com/rg3/youtube-dl/issues/5774 for an
2015 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2016 formats.extend(dash_formats.values())
2018 # Check for malformed aspect ratio
2019 stretched_m = re.search(
2020 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2023 w = float(stretched_m.group('w'))
2024 h = float(stretched_m.group('h'))
2025 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2026 # We will only process correct ratios.
2030 if f.get('vcodec') != 'none':
2031 f['stretched_ratio'] = ratio
2033 self._sort_formats(formats)
2035 self.mark_watched(video_id, video_info)
2039 'uploader': video_uploader,
2040 'uploader_id': video_uploader_id,
2041 'uploader_url': video_uploader_url,
2042 'upload_date': upload_date,
2043 'license': video_license,
2044 'creator': video_creator,
2045 'title': video_title,
2046 'alt_title': video_alt_title,
2047 'thumbnail': video_thumbnail,
2048 'description': video_description,
2049 'categories': video_categories,
2051 'subtitles': video_subtitles,
2052 'automatic_captions': automatic_captions,
2053 'duration': video_duration,
2054 'age_limit': 18 if age_gate else 0,
2055 'annotations': video_annotations,
2056 'chapters': chapters,
2057 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2058 'view_count': view_count,
2059 'like_count': like_count,
2060 'dislike_count': dislike_count,
2061 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
2064 'start_time': start_time,
2065 'end_time': end_time,
2067 'season_number': season_number,
2068 'episode_number': episode_number,
2072 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2073 IE_DESC = 'YouTube.com playlists'
2074 _VALID_URL = r"""(?x)(?:
2080 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2081 \? (?:.*?[&;])*? (?:p|a|list)=
2084 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2087 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
2088 # Top tracks, they can also include dots
2094 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2095 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2096 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2097 IE_NAME = 'youtube:playlist'
2099 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2101 'title': 'ytdl test PL',
2102 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2104 'playlist_count': 3,
2106 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2108 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2109 'title': 'YDL_Empty_List',
2111 'playlist_count': 0,
2112 'skip': 'This playlist is private',
2114 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2115 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2117 'title': '29C3: Not my department',
2118 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2120 'playlist_count': 95,
2122 'note': 'issue #673',
2123 'url': 'PLBB231211A4F62143',
2125 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2126 'id': 'PLBB231211A4F62143',
2128 'playlist_mincount': 26,
2130 'note': 'Large playlist',
2131 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2133 'title': 'Uploads from Cauchemar',
2134 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2136 'playlist_mincount': 799,
2138 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2140 'title': 'YDL_safe_search',
2141 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2143 'playlist_count': 2,
2144 'skip': 'This playlist is private',
2147 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2148 'playlist_count': 4,
2151 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2154 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2155 'playlist_mincount': 485,
2157 'title': '2017 華語最新單曲 (2/24更新)',
2158 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2161 'note': 'Embedded SWF player',
2162 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2163 'playlist_count': 4,
2166 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2169 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2170 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2172 'title': 'Uploads from Interstellar Movie',
2173 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2175 'playlist_mincount': 21,
2177 # Playlist URL that does not actually serve a playlist
2178 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2180 'id': 'FqZTN594JQw',
2182 'title': "Smiley's People 01 detective, Adventure Series, Action",
2183 'uploader': 'STREEM',
2184 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2185 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2186 'upload_date': '20150526',
2187 'license': 'Standard YouTube License',
2188 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2189 'categories': ['People & Blogs'],
2192 'dislike_count': int,
2195 'skip_download': True,
2197 'add_ie': [YoutubeIE.ie_key()],
2199 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2201 'id': 'yeWKywCrFtk',
2203 'title': 'Small Scale Baler and Braiding Rugs',
2204 'uploader': 'Backus-Page House Museum',
2205 'uploader_id': 'backuspagemuseum',
2206 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2207 'upload_date': '20161008',
2208 'license': 'Standard YouTube License',
2209 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2210 'categories': ['Nonprofits & Activism'],
2213 'dislike_count': int,
2217 'skip_download': True,
2220 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2221 'only_matching': True,
2223 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2224 'only_matching': True,
2227 def _real_initialize(self):
2230 def _extract_mix(self, playlist_id):
2231 # The mixes are generated from a single video
2232 # the id of the playlist is just 'RD' + video_id
2234 last_id = playlist_id[-11:]
2235 for n in itertools.count(1):
2236 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2237 webpage = self._download_webpage(
2238 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2239 new_ids = orderedSet(re.findall(
2240 r'''(?xs)data-video-username=".*?".*?
2241 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2243 # Fetch new pages until all the videos are repeated, it seems that
2244 # there are always 51 unique videos.
2245 new_ids = [_id for _id in new_ids if _id not in ids]
2251 url_results = self._ids_to_results(ids)
2253 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2255 search_title('playlist-title') or
2256 search_title('title long-title') or
2257 search_title('title'))
2258 title = clean_html(title_span)
2260 return self.playlist_result(url_results, playlist_id, title)
2262 def _extract_playlist(self, playlist_id):
2263 url = self._TEMPLATE_URL % playlist_id
2264 page = self._download_webpage(url, playlist_id)
2266 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2267 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2268 match = match.strip()
2269 # Check if the playlist exists or is private
2270 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2272 reason = mobj.group('reason')
2273 message = 'This playlist %s' % reason
2274 if 'private' in reason:
2275 message += ', use --username or --netrc to access it'
2277 raise ExtractorError(message, expected=True)
2278 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2279 raise ExtractorError(
2280 'Invalid parameters. Maybe URL is incorrect.',
2282 elif re.match(r'[^<]*Choose your language[^<]*', match):
2285 self.report_warning('Youtube gives an alert message: ' + match)
2287 playlist_title = self._html_search_regex(
2288 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2289 page, 'title', default=None)
2291 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2292 uploader = self._search_regex(
2293 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2294 page, 'uploader', default=None)
2296 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2299 uploader_id = mobj.group('uploader_id')
2300 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2302 uploader_id = uploader_url = None
2306 if not playlist_title:
2308 # Some playlist URLs don't actually serve a playlist (e.g.
2309 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2310 next(self._entries(page, playlist_id))
2311 except StopIteration:
2314 playlist = self.playlist_result(
2315 self._entries(page, playlist_id), playlist_id, playlist_title)
2317 'uploader': uploader,
2318 'uploader_id': uploader_id,
2319 'uploader_url': uploader_url,
2322 return has_videos, playlist
2324 def _check_download_just_video(self, url, playlist_id):
2325 # Check if it's a video-specific URL
2326 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2327 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2328 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2329 'video id', default=None)
2331 if self._downloader.params.get('noplaylist'):
2332 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2333 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2335 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2336 return video_id, None
2339 def _real_extract(self, url):
2340 # Extract playlist id
2341 mobj = re.match(self._VALID_URL, url)
2343 raise ExtractorError('Invalid URL: %s' % url)
2344 playlist_id = mobj.group(1) or mobj.group(2)
2346 video_id, video = self._check_download_just_video(url, playlist_id)
2350 if playlist_id.startswith(('RD', 'UL', 'PU')):
2351 # Mixes require a custom extraction process
2352 return self._extract_mix(playlist_id)
2354 has_videos, playlist = self._extract_playlist(playlist_id)
2355 if has_videos or not video_id:
2358 # Some playlist URLs don't actually serve a playlist (see
2359 # https://github.com/rg3/youtube-dl/issues/10537).
2360 # Fallback to plain video extraction if there is a video id
2361 # along with playlist id.
2362 return self.url_result(video_id, 'Youtube', video_id=video_id)
2365 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2366 IE_DESC = 'YouTube.com channels'
2367 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2368 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2369 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2370 IE_NAME = 'youtube:channel'
2372 'note': 'paginated channel',
2373 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2374 'playlist_mincount': 91,
2376 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2377 'title': 'Uploads from lex will',
2380 'note': 'Age restricted channel',
2381 # from https://www.youtube.com/user/DeusExOfficial
2382 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2383 'playlist_mincount': 64,
2385 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2386 'title': 'Uploads from Deus Ex',
2391 def suitable(cls, url):
2392 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2393 else super(YoutubeChannelIE, cls).suitable(url))
2395 def _build_template_url(self, url, channel_id):
2396 return self._TEMPLATE_URL % channel_id
2398 def _real_extract(self, url):
2399 channel_id = self._match_id(url)
2401 url = self._build_template_url(url, channel_id)
2403 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2404 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2405 # otherwise fallback on channel by page extraction
2406 channel_page = self._download_webpage(
2407 url + '?view=57', channel_id,
2408 'Downloading channel page', fatal=False)
2409 if channel_page is False:
2410 channel_playlist_id = False
2412 channel_playlist_id = self._html_search_meta(
2413 'channelId', channel_page, 'channel id', default=None)
2414 if not channel_playlist_id:
2415 channel_url = self._html_search_meta(
2416 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2417 channel_page, 'channel url', default=None)
2419 channel_playlist_id = self._search_regex(
2420 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2421 channel_url, 'channel id', default=None)
2422 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2423 playlist_id = 'UU' + channel_playlist_id[2:]
2424 return self.url_result(
2425 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2427 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2428 autogenerated = re.search(r'''(?x)
2430 channel-header-autogenerated-label|
2431 yt-channel-title-autogenerated
2432 )[^"]*"''', channel_page) is not None
2435 # The videos are contained in a single page
2436 # the ajax pages can't be used, they are empty
2439 video_id, 'Youtube', video_id=video_id,
2440 video_title=video_title)
2441 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2442 return self.playlist_result(entries, channel_id)
2445 next(self._entries(channel_page, channel_id))
2446 except StopIteration:
2447 alert_message = self._html_search_regex(
2448 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2449 channel_page, 'alert', default=None, group='alert')
2451 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2453 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2456 class YoutubeUserIE(YoutubeChannelIE):
2457 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2458 _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_-]+)'
2459 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2460 IE_NAME = 'youtube:user'
2463 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2464 'playlist_mincount': 320,
2466 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2467 'title': 'Uploads from The Linux Foundation',
2470 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2471 # but not https://www.youtube.com/user/12minuteathlete/videos
2472 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2473 'playlist_mincount': 249,
2475 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2476 'title': 'Uploads from 12 Minute Athlete',
2479 'url': 'ytuser:phihag',
2480 'only_matching': True,
2482 'url': 'https://www.youtube.com/c/gametrailers',
2483 'only_matching': True,
2485 'url': 'https://www.youtube.com/gametrailers',
2486 'only_matching': True,
2488 # This channel is not available, geo restricted to JP
2489 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2490 'only_matching': True,
2494 def suitable(cls, url):
2495 # Don't return True if the url can be extracted with other youtube
2496 # extractor, the regex would is too permissive and it would match.
2497 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2498 if any(ie.suitable(url) for ie in other_yt_ies):
2501 return super(YoutubeUserIE, cls).suitable(url)
2503 def _build_template_url(self, url, channel_id):
2504 mobj = re.match(self._VALID_URL, url)
2505 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2508 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2509 IE_DESC = 'YouTube.com live streams'
2510 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2511 IE_NAME = 'youtube:live'
2514 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2516 'id': 'a48o2S1cPoo',
2518 'title': 'The Young Turks - Live Main Show',
2519 'uploader': 'The Young Turks',
2520 'uploader_id': 'TheYoungTurks',
2521 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2522 'upload_date': '20150715',
2523 'license': 'Standard YouTube License',
2524 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2525 'categories': ['News & Politics'],
2526 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2528 'dislike_count': int,
2531 'skip_download': True,
2534 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2535 'only_matching': True,
2537 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2538 'only_matching': True,
2540 'url': 'https://www.youtube.com/TheYoungTurks/live',
2541 'only_matching': True,
2544 def _real_extract(self, url):
2545 mobj = re.match(self._VALID_URL, url)
2546 channel_id = mobj.group('id')
2547 base_url = mobj.group('base_url')
2548 webpage = self._download_webpage(url, channel_id, fatal=False)
2550 page_type = self._og_search_property(
2551 'type', webpage, 'page type', default='')
2552 video_id = self._html_search_meta(
2553 'videoId', webpage, 'video id', default=None)
2554 if page_type.startswith('video') and video_id and re.match(
2555 r'^[0-9A-Za-z_-]{11}$', video_id):
2556 return self.url_result(video_id, YoutubeIE.ie_key())
2557 return self.url_result(base_url)
2560 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2561 IE_DESC = 'YouTube.com user/channel playlists'
2562 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2563 IE_NAME = 'youtube:playlists'
2566 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2567 'playlist_mincount': 4,
2569 'id': 'ThirstForScience',
2570 'title': 'Thirst for Science',
2573 # with "Load more" button
2574 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2575 'playlist_mincount': 70,
2578 'title': 'Игорь Клейнер',
2581 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2582 'playlist_mincount': 17,
2584 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2585 'title': 'Chem Player',
2590 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2591 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2594 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2595 IE_DESC = 'YouTube.com searches'
2596 # there doesn't appear to be a real limit, for example if you search for
2597 # 'python' you get more than 8.000.000 results
2598 _MAX_RESULTS = float('inf')
2599 IE_NAME = 'youtube:search'
2600 _SEARCH_KEY = 'ytsearch'
2601 _EXTRA_QUERY_ARGS = {}
2604 def _get_n_results(self, query, n):
2605 """Get a specified number of results for a query"""
2611 'search_query': query.encode('utf-8'),
2613 url_query.update(self._EXTRA_QUERY_ARGS)
2614 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2616 for pagenum in itertools.count(1):
2617 data = self._download_json(
2618 result_url, video_id='query "%s"' % query,
2619 note='Downloading page %s' % pagenum,
2620 errnote='Unable to download API page',
2621 query={'spf': 'navigate'})
2622 html_content = data[1]['body']['content']
2624 if 'class="search-message' in html_content:
2625 raise ExtractorError(
2626 '[youtube] No video results', expected=True)
2628 new_videos = list(self._process_page(html_content))
2629 videos += new_videos
2630 if not new_videos or len(videos) > limit:
2632 next_link = self._html_search_regex(
2633 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2634 html_content, 'next link', default=None)
2635 if next_link is None:
2637 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2641 return self.playlist_result(videos, query)
2644 class YoutubeSearchDateIE(YoutubeSearchIE):
2645 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2646 _SEARCH_KEY = 'ytsearchdate'
2647 IE_DESC = 'YouTube.com searches, newest videos first'
2648 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2651 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
2652 IE_DESC = 'YouTube.com search URLs'
2653 IE_NAME = 'youtube:search_url'
2654 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2656 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2657 'playlist_mincount': 5,
2659 'title': 'youtube-dl test video',
2662 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2663 'only_matching': True,
2666 def _real_extract(self, url):
2667 mobj = re.match(self._VALID_URL, url)
2668 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2669 webpage = self._download_webpage(url, query)
2670 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2673 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2674 IE_DESC = 'YouTube.com (multi-season) shows'
2675 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2676 IE_NAME = 'youtube:show'
2678 'url': 'https://www.youtube.com/show/airdisasters',
2679 'playlist_mincount': 5,
2681 'id': 'airdisasters',
2682 'title': 'Air Disasters',
2686 def _real_extract(self, url):
2687 playlist_id = self._match_id(url)
2688 return super(YoutubeShowIE, self)._real_extract(
2689 'https://www.youtube.com/show/%s/playlists' % playlist_id)
2692 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
2694 Base class for feed extractors
2695 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2697 _LOGIN_REQUIRED = True
2701 return 'youtube:%s' % self._FEED_NAME
2703 def _real_initialize(self):
2706 def _entries(self, page):
2707 # The extraction process is the same as for playlists, but the regex
2708 # for the video ids doesn't contain an index
2710 more_widget_html = content_html = page
2711 for page_num in itertools.count(1):
2712 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
2714 # 'recommended' feed has infinite 'load more' and each new portion spins
2715 # the same videos in (sometimes) slightly different order, so we'll check
2716 # for unicity and break when portion has no new videos
2717 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
2723 for entry in self._ids_to_results(new_ids):
2726 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2730 more = self._download_json(
2731 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2732 'Downloading page #%s' % page_num,
2733 transform_source=uppercase_escape)
2734 content_html = more['content_html']
2735 more_widget_html = more['load_more_widget_html']
2737 def _real_extract(self, url):
2738 page = self._download_webpage(
2739 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
2740 self._PLAYLIST_TITLE)
2741 return self.playlist_result(
2742 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
2745 class YoutubeWatchLaterIE(YoutubePlaylistIE):
2746 IE_NAME = 'youtube:watchlater'
2747 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2748 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2751 'url': 'https://www.youtube.com/playlist?list=WL',
2752 'only_matching': True,
2754 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2755 'only_matching': True,
2758 def _real_extract(self, url):
2759 _, video = self._check_download_just_video(url, 'WL')
2762 _, playlist = self._extract_playlist('WL')
2766 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
2767 IE_NAME = 'youtube:favorites'
2768 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2769 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2770 _LOGIN_REQUIRED = True
2772 def _real_extract(self, url):
2773 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2774 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
2775 return self.url_result(playlist_id, 'YoutubePlaylist')
2778 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2779 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2780 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2781 _FEED_NAME = 'recommended'
2782 _PLAYLIST_TITLE = 'Youtube Recommended videos'
2785 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2786 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2787 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2788 _FEED_NAME = 'subscriptions'
2789 _PLAYLIST_TITLE = 'Youtube Subscriptions'
2792 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2793 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
2794 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2795 _FEED_NAME = 'history'
2796 _PLAYLIST_TITLE = 'Youtube History'
2799 class YoutubeTruncatedURLIE(InfoExtractor):
2800 IE_NAME = 'youtube:truncated_url'
2801 IE_DESC = False # Do not list
2802 _VALID_URL = r'''(?x)
2804 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2807 annotation_id=annotation_[^&]+|
2813 attribution_link\?a=[^&]+
2819 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2820 'only_matching': True,
2822 'url': 'https://www.youtube.com/watch?',
2823 'only_matching': True,
2825 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2826 'only_matching': True,
2828 'url': 'https://www.youtube.com/watch?feature=foo',
2829 'only_matching': True,
2831 'url': 'https://www.youtube.com/watch?hl=en-GB',
2832 'only_matching': True,
2834 'url': 'https://www.youtube.com/watch?t=2372',
2835 'only_matching': True,
2838 def _real_extract(self, url):
2839 raise ExtractorError(
2840 'Did you forget to quote the URL? Remember that & is a meta '
2841 'character in most shells, so you want to put the URL in quotes, '
2843 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2844 ' or simply youtube-dl BaW_jenozKc .',
2848 class YoutubeTruncatedIDIE(InfoExtractor):
2849 IE_NAME = 'youtube:truncated_id'
2850 IE_DESC = False # Do not list
2851 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2854 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2855 'only_matching': True,
2858 def _real_extract(self, url):
2859 video_id = self._match_id(url)
2860 raise ExtractorError(
2861 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),