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 (
20 compat_urllib_parse_unquote,
21 compat_urllib_parse_unquote_plus,
22 compat_urllib_parse_urlencode,
23 compat_urllib_parse_urlparse,
32 get_element_by_attribute,
52 class YoutubeBaseInfoExtractor(InfoExtractor):
53 """Provide base functions for Youtube extractors"""
54 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
55 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
57 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
58 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
59 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
61 _NETRC_MACHINE = 'youtube'
62 # If True it will raise an error if no login info is provided
63 _LOGIN_REQUIRED = False
65 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}'
67 def _set_language(self):
69 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
70 # YouTube sets the expire time to about two months
71 expire_time=time.time() + 2 * 30 * 24 * 3600)
73 def _ids_to_results(self, ids):
75 self.url_result(vid_id, 'Youtube', video_id=vid_id)
80 Attempt to log in to YouTube.
81 True is returned if successful or skipped.
82 False is returned if login failed.
84 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
86 (username, password) = self._get_login_info()
87 # No authentication to be performed
89 if self._LOGIN_REQUIRED:
90 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
93 login_page = self._download_webpage(
94 self._LOGIN_URL, None,
95 note='Downloading login page',
96 errnote='unable to fetch login page', fatal=False)
97 if login_page is False:
100 login_form = self._hidden_inputs(login_page)
102 def req(url, f_req, note, errnote):
103 data = login_form.copy()
106 'checkConnection': 'youtube',
107 'checkedDomains': 'youtube',
109 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
110 'f.req': json.dumps(f_req),
111 'flowName': 'GlifWebSignIn',
112 'flowEntry': 'ServiceLogin',
114 return self._download_json(
115 url, None, note=note, errnote=errnote,
116 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
118 data=urlencode_postdata(data), headers={
119 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
120 'Google-Accounts-XSRF': 1,
124 self._downloader.report_warning(message)
128 None, [], None, 'US', None, None, 2, False, True,
132 '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',
134 1, [None, None, []], None, None, None, True
139 lookup_results = req(
140 self._LOOKUP_URL, lookup_req,
141 'Looking up account info', 'Unable to look up account info')
143 if lookup_results is False:
146 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
148 warn('Unable to extract user hash')
153 None, 1, None, [1, None, None, None, [password, None, True]],
155 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],
156 1, [None, None, []], None, None, None, True
159 challenge_results = req(
160 self._CHALLENGE_URL, challenge_req,
161 'Logging in', 'Unable to log in')
163 if challenge_results is False:
166 login_res = try_get(challenge_results, lambda x: x[0][5], list)
168 login_msg = try_get(login_res, lambda x: x[5], compat_str)
170 'Unable to login: %s' % 'Invalid password'
171 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
174 res = try_get(challenge_results, lambda x: x[0][-1], list)
176 warn('Unable to extract result entry')
179 tfa = try_get(res, lambda x: x[0][0], list)
181 tfa_str = try_get(tfa, lambda x: x[2], compat_str)
182 if tfa_str == 'TWO_STEP_VERIFICATION':
183 # SEND_SUCCESS - TFA code has been successfully sent to phone
184 # QUOTA_EXCEEDED - reached the limit of TFA codes
185 status = try_get(tfa, lambda x: x[5], compat_str)
186 if status == 'QUOTA_EXCEEDED':
187 warn('Exceeded the limit of TFA codes, try later')
190 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
192 warn('Unable to extract TL')
195 tfa_code = self._get_tfa_info('2-step verification code')
199 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
200 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
203 tfa_code = remove_start(tfa_code, 'G-')
206 user_hash, None, 2, None,
208 9, None, None, None, None, None, None, None,
209 [None, tfa_code, True, 2]
213 self._TFA_URL.format(tl), tfa_req,
214 'Submitting TFA code', 'Unable to submit TFA code')
216 if tfa_results is False:
219 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
221 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
223 'Unable to finish TFA: %s' % 'Invalid TFA code'
224 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
227 check_cookie_url = try_get(
228 tfa_results, lambda x: x[0][-1][2], compat_str)
230 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
232 if not check_cookie_url:
233 warn('Unable to extract CheckCookie URL')
236 check_cookie_results = self._download_webpage(
237 check_cookie_url, None, 'Checking cookie', fatal=False)
239 if check_cookie_results is False:
242 if 'https://myaccount.google.com/' not in check_cookie_results:
243 warn('Unable to log in')
248 def _real_initialize(self):
249 if self._downloader is None:
252 if not self._login():
256 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
257 # Extract entries from page with "Load more" button
258 def _entries(self, page, playlist_id):
259 more_widget_html = content_html = page
260 for page_num in itertools.count(1):
261 for entry in self._process_page(content_html):
264 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
268 more = self._download_json(
269 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
270 'Downloading page #%s' % page_num,
271 transform_source=uppercase_escape)
272 content_html = more['content_html']
273 if not content_html.strip():
274 # Some webpages show a "Load more" button but they don't
277 more_widget_html = more['load_more_widget_html']
280 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
281 def _process_page(self, content):
282 for video_id, video_title in self.extract_videos_from_page(content):
283 yield self.url_result(video_id, 'Youtube', video_id, video_title)
285 def extract_videos_from_page(self, page):
288 for mobj in re.finditer(self._VIDEO_RE, page):
289 # The link with index 0 is not the first video of the playlist (not sure if still actual)
290 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
292 video_id = mobj.group('id')
293 video_title = unescapeHTML(mobj.group('title'))
295 video_title = video_title.strip()
297 idx = ids_in_page.index(video_id)
298 if video_title and not titles_in_page[idx]:
299 titles_in_page[idx] = video_title
301 ids_in_page.append(video_id)
302 titles_in_page.append(video_title)
303 return zip(ids_in_page, titles_in_page)
306 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
307 def _process_page(self, content):
308 for playlist_id in orderedSet(re.findall(
309 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
311 yield self.url_result(
312 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
314 def _real_extract(self, url):
315 playlist_id = self._match_id(url)
316 webpage = self._download_webpage(url, playlist_id)
317 title = self._og_search_title(webpage, fatal=False)
318 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
321 class YoutubeIE(YoutubeBaseInfoExtractor):
322 IE_DESC = 'YouTube.com'
323 _VALID_URL = r"""(?x)^
325 (?:https?://|//) # http(s):// or protocol-independent URL
326 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
327 (?:www\.)?deturl\.com/www\.youtube\.com/|
328 (?:www\.)?pwnyoutube\.com/|
329 (?:www\.)?yourepeat\.com/|
330 tube\.majestyc\.net/|
331 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
332 (?:.*?\#/)? # handle anchor (#/) redirect urls
333 (?: # the various things that can precede the ID:
334 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
335 |(?: # or the v= param in all its forms
336 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
337 (?:\?|\#!?) # the params delimiter ? or # or #!
338 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
343 youtu\.be| # just youtu.be/xxxx
344 vid\.plus| # or vid.plus/xxxx
345 zwearz\.com/watch| # or zwearz.com/watch/xxxx
347 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
349 )? # all until now is optional -> you can pass the naked ID
350 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
353 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
354 WL # WL are handled by the watch later IE
357 (?(1).+)? # if we found the ID, everything can follow
358 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
359 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
361 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
362 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
363 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
364 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
365 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
366 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
367 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
368 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
369 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
370 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
371 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
372 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
373 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
374 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
375 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
376 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
377 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
378 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
382 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
383 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
384 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
385 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
386 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
387 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
388 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
390 # Apple HTTP Live Streaming
391 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
392 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
393 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
394 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
395 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
396 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
397 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
398 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
401 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
402 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
403 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
404 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
405 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
406 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
407 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
408 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
409 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
410 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
411 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
412 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
415 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
416 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
417 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
418 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
419 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
420 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
421 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
424 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
425 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
426 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
427 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
428 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
429 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
430 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
431 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
432 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
433 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
434 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
435 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
436 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
437 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
438 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
439 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
440 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
441 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
442 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
443 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
444 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
445 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
448 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
449 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
451 # Dash webm audio with opus inside
452 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
453 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
454 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
457 '_rtmp': {'protocol': 'rtmp'},
459 _SUBTITLE_FORMATS = ('ttml', 'vtt')
466 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
470 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
471 'uploader': 'Philipp Hagemeister',
472 'uploader_id': 'phihag',
473 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
474 'upload_date': '20121002',
475 'license': 'Standard YouTube License',
476 '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 .',
477 'categories': ['Science & Technology'],
478 'tags': ['youtube-dl'],
481 'dislike_count': int,
487 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
488 'note': 'Test generic use_cipher_signature video (#897)',
492 'upload_date': '20120506',
493 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
494 'alt_title': 'I Love It (feat. Charli XCX)',
495 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
496 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
497 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
498 'iconic ep', 'iconic', 'love', 'it'],
500 'uploader': 'Icona Pop',
501 'uploader_id': 'IconaPop',
502 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
503 'license': 'Standard YouTube License',
504 'creator': 'Icona Pop',
508 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
509 'note': 'Test VEVO video with age protection (#956)',
513 'upload_date': '20130703',
514 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
515 'alt_title': 'Tunnel Vision',
516 'description': 'md5:64249768eec3bc4276236606ea996373',
518 'uploader': 'justintimberlakeVEVO',
519 'uploader_id': 'justintimberlakeVEVO',
520 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
521 'license': 'Standard YouTube License',
522 'creator': 'Justin Timberlake',
527 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
528 'note': 'Embed-only video (#1746)',
532 'upload_date': '20120608',
533 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
534 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
535 'uploader': 'SET India',
536 'uploader_id': 'setindia',
537 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
538 'license': 'Standard YouTube License',
543 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
544 'note': 'Use the first video ID in the URL',
548 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
549 'uploader': 'Philipp Hagemeister',
550 'uploader_id': 'phihag',
551 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
552 'upload_date': '20121002',
553 'license': 'Standard YouTube License',
554 '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 .',
555 'categories': ['Science & Technology'],
556 'tags': ['youtube-dl'],
559 'dislike_count': int,
562 'skip_download': True,
566 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
567 'note': '256k DASH audio (format 141) via DASH manifest',
571 'upload_date': '20121002',
572 'uploader_id': '8KVIDEO',
573 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
575 'uploader': '8KVIDEO',
576 'license': 'Standard YouTube License',
577 'title': 'UHDTV TEST 8K VIDEO.mp4'
580 'youtube_include_dash_manifest': True,
583 'skip': 'format 141 not served anymore',
585 # DASH manifest with encrypted signature
587 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
591 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
592 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
594 'uploader': 'AfrojackVEVO',
595 'uploader_id': 'AfrojackVEVO',
596 'upload_date': '20131011',
597 'license': 'Standard YouTube License',
600 'youtube_include_dash_manifest': True,
601 'format': '141/bestaudio[ext=m4a]',
604 # JS player signature function name containing $
606 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
610 'title': 'Taylor Swift - Shake It Off',
611 'alt_title': 'Shake It Off',
612 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
614 'uploader': 'TaylorSwiftVEVO',
615 'uploader_id': 'TaylorSwiftVEVO',
616 'upload_date': '20140818',
617 'license': 'Standard YouTube License',
618 'creator': 'Taylor Swift',
621 'youtube_include_dash_manifest': True,
622 'format': '141/bestaudio[ext=m4a]',
627 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
632 'upload_date': '20100909',
633 'uploader': 'The Amazing Atheist',
634 'uploader_id': 'TheAmazingAtheist',
635 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
636 'license': 'Standard YouTube License',
637 'title': 'Burning Everyone\'s Koran',
638 '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',
641 # Normal age-gate video (No vevo, embed allowed)
643 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
647 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
648 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
650 'uploader': 'The Witcher',
651 'uploader_id': 'WitcherGame',
652 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
653 'upload_date': '20140605',
654 'license': 'Standard YouTube License',
658 # Age-gate video with encrypted signature
660 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
664 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
665 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
667 'uploader': 'LloydVEVO',
668 'uploader_id': 'LloydVEVO',
669 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
670 'upload_date': '20110629',
671 'license': 'Standard YouTube License',
675 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
676 # YouTube Red ad is not captured for creator
678 'url': '__2ABJjxzNo',
683 'upload_date': '20100430',
684 'uploader_id': 'deadmau5',
685 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
686 'creator': 'deadmau5',
687 'description': 'md5:12c56784b8032162bb936a5f76d55360',
688 'uploader': 'deadmau5',
689 'license': 'Standard YouTube License',
690 'title': 'Deadmau5 - Some Chords (HD)',
691 'alt_title': 'Some Chords',
693 'expected_warnings': [
694 'DASH manifest missing',
697 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
699 'url': 'lqQg6PlCWgI',
704 'upload_date': '20150827',
705 'uploader_id': 'olympic',
706 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
707 'license': 'Standard YouTube License',
708 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
709 'uploader': 'Olympic',
710 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
713 'skip_download': 'requires avconv',
718 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
722 'stretched_ratio': 16 / 9.,
724 'upload_date': '20110310',
725 'uploader_id': 'AllenMeow',
726 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
727 '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',
729 'license': 'Standard YouTube License',
730 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
733 # url_encoded_fmt_stream_map is empty string
735 'url': 'qEJwOuvDf7I',
739 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
741 'upload_date': '20150404',
742 'uploader_id': 'spbelect',
743 'uploader': 'Наблюдатели Петербурга',
746 'skip_download': 'requires avconv',
748 'skip': 'This live event has ended.',
750 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
752 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
756 'title': 'md5:7b81415841e02ecd4313668cde88737a',
757 'description': 'md5:116377fd2963b81ec4ce64b542173306',
759 'upload_date': '20150625',
760 'uploader_id': 'dorappi2000',
761 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
762 'uploader': 'dorappi2000',
763 'license': 'Standard YouTube License',
764 'formats': 'mincount:32',
767 # DASH manifest with segment_list
769 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
770 'md5': '8ce563a1d667b599d21064e982ab9e31',
774 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
775 'uploader': 'Airtek',
776 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
777 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
778 'license': 'Standard YouTube License',
779 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
782 'youtube_include_dash_manifest': True,
783 'format': '135', # bestvideo
785 'skip': 'This live event has ended.',
788 # Multifeed videos (multiple cameras), URL is for Main Camera
789 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
792 'title': 'teamPGP: Rocket League Noob Stream',
793 'description': 'md5:dc7872fb300e143831327f1bae3af010',
799 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
800 'description': 'md5:dc7872fb300e143831327f1bae3af010',
802 'upload_date': '20150721',
803 'uploader': 'Beer Games Beer',
804 'uploader_id': 'beergamesbeer',
805 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
806 'license': 'Standard YouTube License',
812 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
813 'description': 'md5:dc7872fb300e143831327f1bae3af010',
815 'upload_date': '20150721',
816 'uploader': 'Beer Games Beer',
817 'uploader_id': 'beergamesbeer',
818 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
819 'license': 'Standard YouTube License',
825 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
826 'description': 'md5:dc7872fb300e143831327f1bae3af010',
828 'upload_date': '20150721',
829 'uploader': 'Beer Games Beer',
830 'uploader_id': 'beergamesbeer',
831 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
832 'license': 'Standard YouTube License',
838 'title': 'teamPGP: Rocket League Noob Stream (zim)',
839 'description': 'md5:dc7872fb300e143831327f1bae3af010',
841 'upload_date': '20150721',
842 'uploader': 'Beer Games Beer',
843 'uploader_id': 'beergamesbeer',
844 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
845 'license': 'Standard YouTube License',
849 'skip_download': True,
853 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
854 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
857 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
860 'skip': 'Not multifeed anymore',
863 'url': 'https://vid.plus/FlRa-iH7PGw',
864 'only_matching': True,
867 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
868 'only_matching': True,
871 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
872 # Also tests cut-off URL expansion in video description (see
873 # https://github.com/rg3/youtube-dl/issues/1892,
874 # https://github.com/rg3/youtube-dl/issues/8164)
875 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
879 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
880 'alt_title': 'Dark Walk',
881 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
883 'upload_date': '20151119',
884 'uploader_id': 'IronSoulElf',
885 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
886 'uploader': 'IronSoulElf',
887 'license': 'Standard YouTube License',
888 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
891 'skip_download': True,
895 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
896 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
897 'only_matching': True,
900 # Video with yt:stretch=17:0
901 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
905 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
906 'description': 'md5:ee18a25c350637c8faff806845bddee9',
907 'upload_date': '20151107',
908 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
909 'uploader': 'CH GAMER DROID',
912 'skip_download': True,
914 'skip': 'This video does not exist.',
917 # Video licensed under Creative Commons
918 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
922 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
923 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
925 'upload_date': '20150127',
926 'uploader_id': 'BerkmanCenter',
927 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
928 'uploader': 'The Berkman Klein Center for Internet & Society',
929 'license': 'Creative Commons Attribution license (reuse allowed)',
932 'skip_download': True,
936 # Channel-like uploader_url
937 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
941 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
942 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
944 'upload_date': '20151119',
945 'uploader': 'Bernie 2016',
946 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
947 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
948 'license': 'Creative Commons Attribution license (reuse allowed)',
951 'skip_download': True,
955 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
956 'only_matching': True,
959 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
960 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
961 'only_matching': True,
964 # Rental video preview
965 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
969 'title': 'Piku - Trailer',
970 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
971 'upload_date': '20150811',
972 'uploader': 'FlixMatrix',
973 'uploader_id': 'FlixMatrixKaravan',
974 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
975 'license': 'Standard YouTube License',
978 'skip_download': True,
982 # YouTube Red video with episode data
983 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
987 'title': 'Isolation - Mind Field (Ep 1)',
988 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
990 'upload_date': '20170118',
991 'uploader': 'Vsauce',
992 'uploader_id': 'Vsauce',
993 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
994 'license': 'Standard YouTube License',
995 'series': 'Mind Field',
1000 'skip_download': True,
1002 'expected_warnings': [
1003 'Skipping DASH manifest',
1007 # The following content has been identified by the YouTube community
1008 # as inappropriate or offensive to some audiences.
1009 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1011 'id': '6SJNVb0GnPI',
1013 'title': 'Race Differences in Intelligence',
1014 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1016 'upload_date': '20140124',
1017 'uploader': 'New Century Foundation',
1018 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1019 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1020 'license': 'Standard YouTube License',
1024 'skip_download': True,
1029 'url': '1t24XAntNCY',
1030 'only_matching': True,
1033 # geo restricted to JP
1034 'url': 'sJL6WA-aGkQ',
1035 'only_matching': True,
1038 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1039 'only_matching': True,
1043 def __init__(self, *args, **kwargs):
1044 super(YoutubeIE, self).__init__(*args, **kwargs)
1045 self._player_cache = {}
1047 def report_video_info_webpage_download(self, video_id):
1048 """Report attempt to download video info webpage."""
1049 self.to_screen('%s: Downloading video info webpage' % video_id)
1051 def report_information_extraction(self, video_id):
1052 """Report attempt to extract video information."""
1053 self.to_screen('%s: Extracting video information' % video_id)
1055 def report_unavailable_format(self, video_id, format):
1056 """Report extracted video URL."""
1057 self.to_screen('%s: Format %s not available' % (video_id, format))
1059 def report_rtmp_download(self):
1060 """Indicate the download will use the RTMP protocol."""
1061 self.to_screen('RTMP download detected')
1063 def _signature_cache_id(self, example_sig):
1064 """ Return a string representation of a signature """
1065 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1067 def _extract_signature_function(self, video_id, player_url, example_sig):
1069 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1072 raise ExtractorError('Cannot identify player %r' % player_url)
1073 player_type = id_m.group('ext')
1074 player_id = id_m.group('id')
1076 # Read from filesystem cache
1077 func_id = '%s_%s_%s' % (
1078 player_type, player_id, self._signature_cache_id(example_sig))
1079 assert os.path.basename(func_id) == func_id
1081 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1082 if cache_spec is not None:
1083 return lambda s: ''.join(s[i] for i in cache_spec)
1086 'Downloading player %s' % player_url
1087 if self._downloader.params.get('verbose') else
1088 'Downloading %s player %s' % (player_type, player_id)
1090 if player_type == 'js':
1091 code = self._download_webpage(
1092 player_url, video_id,
1094 errnote='Download of %s failed' % player_url)
1095 res = self._parse_sig_js(code)
1096 elif player_type == 'swf':
1097 urlh = self._request_webpage(
1098 player_url, video_id,
1100 errnote='Download of %s failed' % player_url)
1102 res = self._parse_sig_swf(code)
1104 assert False, 'Invalid player type %r' % player_type
1106 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1107 cache_res = res(test_string)
1108 cache_spec = [ord(c) for c in cache_res]
1110 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1113 def _print_sig_code(self, func, example_sig):
1114 def gen_sig_code(idxs):
1115 def _genslice(start, end, step):
1116 starts = '' if start == 0 else str(start)
1117 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1118 steps = '' if step == 1 else (':%d' % step)
1119 return 's[%s%s%s]' % (starts, ends, steps)
1122 # Quelch pyflakes warnings - start will be set when step is set
1123 start = '(Never used)'
1124 for i, prev in zip(idxs[1:], idxs[:-1]):
1125 if step is not None:
1126 if i - prev == step:
1128 yield _genslice(start, prev, step)
1131 if i - prev in [-1, 1]:
1136 yield 's[%d]' % prev
1140 yield _genslice(start, i, step)
1142 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1143 cache_res = func(test_string)
1144 cache_spec = [ord(c) for c in cache_res]
1145 expr_code = ' + '.join(gen_sig_code(cache_spec))
1146 signature_id_tuple = '(%s)' % (
1147 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1148 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1149 ' return %s\n') % (signature_id_tuple, expr_code)
1150 self.to_screen('Extracted signature function:\n' + code)
1152 def _parse_sig_js(self, jscode):
1153 funcname = self._search_regex(
1154 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1155 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
1156 jscode, 'Initial JS player signature function name', group='sig')
1158 jsi = JSInterpreter(jscode)
1159 initial_function = jsi.extract_function(funcname)
1160 return lambda s: initial_function([s])
1162 def _parse_sig_swf(self, file_contents):
1163 swfi = SWFInterpreter(file_contents)
1164 TARGET_CLASSNAME = 'SignatureDecipher'
1165 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1166 initial_function = swfi.extract_function(searched_class, 'decipher')
1167 return lambda s: initial_function([s])
1169 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1170 """Turn the encrypted s field into a working signature"""
1172 if player_url is None:
1173 raise ExtractorError('Cannot decrypt signature without player_url')
1175 if player_url.startswith('//'):
1176 player_url = 'https:' + player_url
1177 elif not re.match(r'https?://', player_url):
1178 player_url = compat_urlparse.urljoin(
1179 'https://www.youtube.com', player_url)
1181 player_id = (player_url, self._signature_cache_id(s))
1182 if player_id not in self._player_cache:
1183 func = self._extract_signature_function(
1184 video_id, player_url, s
1186 self._player_cache[player_id] = func
1187 func = self._player_cache[player_id]
1188 if self._downloader.params.get('youtube_print_sig_code'):
1189 self._print_sig_code(func, s)
1191 except Exception as e:
1192 tb = traceback.format_exc()
1193 raise ExtractorError(
1194 'Signature extraction failed: ' + tb, cause=e)
1196 def _get_subtitles(self, video_id, webpage):
1198 subs_doc = self._download_xml(
1199 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1200 video_id, note=False)
1201 except ExtractorError as err:
1202 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1206 for track in subs_doc.findall('track'):
1207 lang = track.attrib['lang_code']
1208 if lang in sub_lang_list:
1211 for ext in self._SUBTITLE_FORMATS:
1212 params = compat_urllib_parse_urlencode({
1216 'name': track.attrib['name'].encode('utf-8'),
1218 sub_formats.append({
1219 'url': 'https://www.youtube.com/api/timedtext?' + params,
1222 sub_lang_list[lang] = sub_formats
1223 if not sub_lang_list:
1224 self._downloader.report_warning('video doesn\'t have subtitles')
1226 return sub_lang_list
1228 def _get_ytplayer_config(self, video_id, webpage):
1230 # User data may contain arbitrary character sequences that may affect
1231 # JSON extraction with regex, e.g. when '};' is contained the second
1232 # regex won't capture the whole JSON. Yet working around by trying more
1233 # concrete regex first keeping in mind proper quoted string handling
1234 # to be implemented in future that will replace this workaround (see
1235 # https://github.com/rg3/youtube-dl/issues/7468,
1236 # https://github.com/rg3/youtube-dl/pull/7599)
1237 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1238 r';ytplayer\.config\s*=\s*({.+?});',
1240 config = self._search_regex(
1241 patterns, webpage, 'ytplayer.config', default=None)
1243 return self._parse_json(
1244 uppercase_escape(config), video_id, fatal=False)
1246 def _get_automatic_captions(self, video_id, webpage):
1247 """We need the webpage for getting the captions url, pass it as an
1248 argument to speed up the process."""
1249 self.to_screen('%s: Looking for automatic captions' % video_id)
1250 player_config = self._get_ytplayer_config(video_id, webpage)
1251 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1252 if not player_config:
1253 self._downloader.report_warning(err_msg)
1256 args = player_config['args']
1257 caption_url = args.get('ttsurl')
1259 timestamp = args['timestamp']
1260 # We get the available subtitles
1261 list_params = compat_urllib_parse_urlencode({
1266 list_url = caption_url + '&' + list_params
1267 caption_list = self._download_xml(list_url, video_id)
1268 original_lang_node = caption_list.find('track')
1269 if original_lang_node is None:
1270 self._downloader.report_warning('Video doesn\'t have automatic captions')
1272 original_lang = original_lang_node.attrib['lang_code']
1273 caption_kind = original_lang_node.attrib.get('kind', '')
1276 for lang_node in caption_list.findall('target'):
1277 sub_lang = lang_node.attrib['lang_code']
1279 for ext in self._SUBTITLE_FORMATS:
1280 params = compat_urllib_parse_urlencode({
1281 'lang': original_lang,
1285 'kind': caption_kind,
1287 sub_formats.append({
1288 'url': caption_url + '&' + params,
1291 sub_lang_list[sub_lang] = sub_formats
1292 return sub_lang_list
1294 def make_captions(sub_url, sub_langs):
1295 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1296 caption_qs = compat_parse_qs(parsed_sub_url.query)
1298 for sub_lang in sub_langs:
1300 for ext in self._SUBTITLE_FORMATS:
1302 'tlang': [sub_lang],
1305 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1306 query=compat_urllib_parse_urlencode(caption_qs, True)))
1307 sub_formats.append({
1311 captions[sub_lang] = sub_formats
1314 # New captions format as of 22.06.2017
1315 player_response = args.get('player_response')
1316 if player_response and isinstance(player_response, compat_str):
1317 player_response = self._parse_json(
1318 player_response, video_id, fatal=False)
1320 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1321 base_url = renderer['captionTracks'][0]['baseUrl']
1323 for lang in renderer['translationLanguages']:
1324 lang_code = lang.get('languageCode')
1326 sub_lang_list.append(lang_code)
1327 return make_captions(base_url, sub_lang_list)
1329 # Some videos don't provide ttsurl but rather caption_tracks and
1330 # caption_translation_languages (e.g. 20LmZk1hakA)
1331 # Does not used anymore as of 22.06.2017
1332 caption_tracks = args['caption_tracks']
1333 caption_translation_languages = args['caption_translation_languages']
1334 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1336 for lang in caption_translation_languages.split(','):
1337 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1338 sub_lang = lang_qs.get('lc', [None])[0]
1340 sub_lang_list.append(sub_lang)
1341 return make_captions(caption_url, sub_lang_list)
1342 # An extractor error can be raise by the download process if there are
1343 # no automatic captions but there are subtitles
1344 except (KeyError, IndexError, ExtractorError):
1345 self._downloader.report_warning(err_msg)
1348 def _mark_watched(self, video_id, video_info):
1349 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1350 if not playback_url:
1352 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1353 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1355 # cpn generation algorithm is reverse engineered from base.js.
1356 # In fact it works even with dummy cpn.
1357 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1358 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1364 playback_url = compat_urlparse.urlunparse(
1365 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1367 self._download_webpage(
1368 playback_url, video_id, 'Marking watched',
1369 'Unable to mark watched', fatal=False)
1372 def extract_id(cls, url):
1373 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1375 raise ExtractorError('Invalid URL: %s' % url)
1376 video_id = mobj.group(2)
1379 def _extract_annotations(self, video_id):
1380 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1381 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1384 def _extract_chapters(description, duration):
1387 chapter_lines = re.findall(
1388 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1390 if not chapter_lines:
1393 for next_num, (chapter_line, time_point) in enumerate(
1394 chapter_lines, start=1):
1395 start_time = parse_duration(time_point)
1396 if start_time is None:
1398 if start_time > duration:
1400 end_time = (duration if next_num == len(chapter_lines)
1401 else parse_duration(chapter_lines[next_num][1]))
1402 if end_time is None:
1404 if end_time > duration:
1406 if start_time > end_time:
1408 chapter_title = re.sub(
1409 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1410 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1412 'start_time': start_time,
1413 'end_time': end_time,
1414 'title': chapter_title,
1418 def _real_extract(self, url):
1419 url, smuggled_data = unsmuggle_url(url, {})
1422 'http' if self._downloader.params.get('prefer_insecure', False)
1427 parsed_url = compat_urllib_parse_urlparse(url)
1428 for component in [parsed_url.fragment, parsed_url.query]:
1429 query = compat_parse_qs(component)
1430 if start_time is None and 't' in query:
1431 start_time = parse_duration(query['t'][0])
1432 if start_time is None and 'start' in query:
1433 start_time = parse_duration(query['start'][0])
1434 if end_time is None and 'end' in query:
1435 end_time = parse_duration(query['end'][0])
1437 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1438 mobj = re.search(self._NEXT_URL_RE, url)
1440 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1441 video_id = self.extract_id(url)
1444 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1445 video_webpage = self._download_webpage(url, video_id)
1447 # Attempt to extract SWF player URL
1448 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1449 if mobj is not None:
1450 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1456 def add_dash_mpd(video_info):
1457 dash_mpd = video_info.get('dashmpd')
1458 if dash_mpd and dash_mpd[0] not in dash_mpds:
1459 dash_mpds.append(dash_mpd[0])
1464 def extract_view_count(v_info):
1465 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1468 embed_webpage = None
1469 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1471 # We simulate the access to the video from www.youtube.com/v/{video_id}
1472 # this can be viewed without login into Youtube
1473 url = proto + '://www.youtube.com/embed/%s' % video_id
1474 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1475 data = compat_urllib_parse_urlencode({
1476 'video_id': video_id,
1477 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1478 'sts': self._search_regex(
1479 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1481 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1482 video_info_webpage = self._download_webpage(
1483 video_info_url, video_id,
1484 note='Refetching age-gated info webpage',
1485 errnote='unable to download video info webpage')
1486 video_info = compat_parse_qs(video_info_webpage)
1487 add_dash_mpd(video_info)
1492 # Try looking directly into the video webpage
1493 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1495 args = ytplayer_config['args']
1496 if args.get('url_encoded_fmt_stream_map'):
1497 # Convert to the same format returned by compat_parse_qs
1498 video_info = dict((k, [v]) for k, v in args.items())
1499 add_dash_mpd(video_info)
1500 # Rental video is not rented but preview is available (e.g.
1501 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1502 # https://github.com/rg3/youtube-dl/issues/10532)
1503 if not video_info and args.get('ypc_vid'):
1504 return self.url_result(
1505 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1506 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1508 sts = ytplayer_config.get('sts')
1509 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1510 # We also try looking in get_video_info since it may contain different dashmpd
1511 # URL that points to a DASH manifest with possibly different itag set (some itags
1512 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1513 # manifest pointed by get_video_info's dashmpd).
1514 # The general idea is to take a union of itags of both DASH manifests (for example
1515 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1516 self.report_video_info_webpage_download(video_id)
1517 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1519 'video_id': video_id,
1529 video_info_webpage = self._download_webpage(
1530 '%s://www.youtube.com/get_video_info' % proto,
1531 video_id, note=False,
1532 errnote='unable to download video info webpage',
1533 fatal=False, query=query)
1534 if not video_info_webpage:
1536 get_video_info = compat_parse_qs(video_info_webpage)
1537 add_dash_mpd(get_video_info)
1538 if view_count is None:
1539 view_count = extract_view_count(get_video_info)
1541 video_info = get_video_info
1542 if 'token' in get_video_info:
1543 # Different get_video_info requests may report different results, e.g.
1544 # some may report video unavailability, but some may serve it without
1545 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1546 # the original webpage as well as el=info and el=embedded get_video_info
1547 # requests report video unavailability due to geo restriction while
1548 # el=detailpage succeeds and returns valid data). This is probably
1549 # due to YouTube measures against IP ranges of hosting providers.
1550 # Working around by preferring the first succeeded video_info containing
1551 # the token if no such video_info yet was found.
1552 if 'token' not in video_info:
1553 video_info = get_video_info
1555 if 'token' not in video_info:
1556 if 'reason' in video_info:
1557 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1558 regions_allowed = self._html_search_meta(
1559 'regionsAllowed', video_webpage, default=None)
1560 countries = regions_allowed.split(',') if regions_allowed else None
1561 self.raise_geo_restricted(
1562 msg=video_info['reason'][0], countries=countries)
1563 raise ExtractorError(
1564 'YouTube said: %s' % video_info['reason'][0],
1565 expected=True, video_id=video_id)
1567 raise ExtractorError(
1568 '"token" parameter not in video info for unknown reason',
1572 if 'title' in video_info:
1573 video_title = video_info['title'][0]
1575 self._downloader.report_warning('Unable to extract video title')
1579 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1580 if video_description:
1581 description_original = video_description = re.sub(r'''(?x)
1583 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1584 (?:title|href)="([^"]+)"\s+
1585 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1589 ''', r'\1', video_description)
1590 video_description = clean_html(video_description)
1592 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1594 video_description = unescapeHTML(fd_mobj.group(1))
1596 video_description = ''
1598 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1599 if not self._downloader.params.get('noplaylist'):
1602 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
1603 for feed in multifeed_metadata_list.split(','):
1604 # Unquote should take place before split on comma (,) since textual
1605 # fields may contain comma as well (see
1606 # https://github.com/rg3/youtube-dl/issues/8536)
1607 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1609 '_type': 'url_transparent',
1610 'ie_key': 'Youtube',
1612 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1613 {'force_singlefeed': True}),
1614 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1616 feed_ids.append(feed_data['id'][0])
1618 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1619 % (', '.join(feed_ids), video_id))
1620 return self.playlist_result(entries, video_id, video_title, video_description)
1621 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1623 if view_count is None:
1624 view_count = extract_view_count(video_info)
1626 # Check for "rental" videos
1627 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1628 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
1630 # Start extracting information
1631 self.report_information_extraction(video_id)
1634 if 'author' not in video_info:
1635 raise ExtractorError('Unable to extract uploader name')
1636 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
1639 video_uploader_id = None
1640 video_uploader_url = None
1642 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1644 if mobj is not None:
1645 video_uploader_id = mobj.group('uploader_id')
1646 video_uploader_url = mobj.group('uploader_url')
1648 self._downloader.report_warning('unable to extract uploader nickname')
1651 # We try first to get a high quality image:
1652 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1653 video_webpage, re.DOTALL)
1654 if m_thumb is not None:
1655 video_thumbnail = m_thumb.group(1)
1656 elif 'thumbnail_url' not in video_info:
1657 self._downloader.report_warning('unable to extract video thumbnail')
1658 video_thumbnail = None
1659 else: # don't panic if we can't find it
1660 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1663 upload_date = self._html_search_meta(
1664 'datePublished', video_webpage, 'upload date', default=None)
1666 upload_date = self._search_regex(
1667 [r'(?s)id="eow-date.*?>(.*?)</span>',
1668 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1669 video_webpage, 'upload date', default=None)
1671 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1672 upload_date = unified_strdate(upload_date)
1674 video_license = self._html_search_regex(
1675 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1676 video_webpage, 'license', default=None)
1678 m_music = re.search(
1680 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
1688 \bhref=["\']/red[^>]*>| # drop possible
1689 >\s*Listen ad-free with YouTube Red # YouTube Red ad
1696 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1697 video_creator = clean_html(m_music.group('creator'))
1699 video_alt_title = video_creator = None
1701 m_episode = re.search(
1702 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1705 series = m_episode.group('series')
1706 season_number = int(m_episode.group('season'))
1707 episode_number = int(m_episode.group('episode'))
1709 series = season_number = episode_number = None
1711 m_cat_container = self._search_regex(
1712 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1713 video_webpage, 'categories', default=None)
1715 category = self._html_search_regex(
1716 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
1718 video_categories = None if category is None else [category]
1720 video_categories = None
1723 unescapeHTML(m.group('content'))
1724 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1726 def _extract_count(count_name):
1727 return str_to_int(self._search_regex(
1728 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1729 % re.escape(count_name),
1730 video_webpage, count_name, default=None))
1732 like_count = _extract_count('like')
1733 dislike_count = _extract_count('dislike')
1736 video_subtitles = self.extract_subtitles(video_id, video_webpage)
1737 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
1739 video_duration = try_get(
1740 video_info, lambda x: int_or_none(x['length_seconds'][0]))
1741 if not video_duration:
1742 video_duration = parse_duration(self._html_search_meta(
1743 'duration', video_webpage, 'video duration'))
1746 video_annotations = None
1747 if self._downloader.params.get('writeannotations', False):
1748 video_annotations = self._extract_annotations(video_id)
1750 chapters = self._extract_chapters(description_original, video_duration)
1752 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1753 self.report_rtmp_download()
1755 'format_id': '_rtmp',
1757 'url': video_info['conn'][0],
1758 'player_url': player_url,
1760 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
1761 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1762 if 'rtmpe%3Dyes' in encoded_url_map:
1763 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
1765 fmt_list = video_info.get('fmt_list', [''])[0]
1767 for fmt in fmt_list.split(','):
1768 spec = fmt.split('/')
1770 width_height = spec[1].split('x')
1771 if len(width_height) == 2:
1772 formats_spec[spec[0]] = {
1773 'resolution': spec[1],
1774 'width': int_or_none(width_height[0]),
1775 'height': int_or_none(width_height[1]),
1778 for url_data_str in encoded_url_map.split(','):
1779 url_data = compat_parse_qs(url_data_str)
1780 if 'itag' not in url_data or 'url' not in url_data:
1782 format_id = url_data['itag'][0]
1783 url = url_data['url'][0]
1785 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1786 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1787 jsplayer_url_json = self._search_regex(
1789 embed_webpage if age_gate else video_webpage,
1790 'JS player URL (1)', default=None)
1791 if not jsplayer_url_json and not age_gate:
1792 # We need the embed website after all
1793 if embed_webpage is None:
1794 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1795 embed_webpage = self._download_webpage(
1796 embed_url, video_id, 'Downloading embed webpage')
1797 jsplayer_url_json = self._search_regex(
1798 ASSETS_RE, embed_webpage, 'JS player URL')
1800 player_url = json.loads(jsplayer_url_json)
1801 if player_url is None:
1802 player_url_json = self._search_regex(
1803 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1804 video_webpage, 'age gate player URL')
1805 player_url = json.loads(player_url_json)
1807 if 'sig' in url_data:
1808 url += '&signature=' + url_data['sig'][0]
1809 elif 's' in url_data:
1810 encrypted_sig = url_data['s'][0]
1812 if self._downloader.params.get('verbose'):
1813 if player_url is None:
1814 player_version = 'unknown'
1815 player_desc = 'unknown'
1817 if player_url.endswith('swf'):
1818 player_version = self._search_regex(
1819 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1820 'flash player', fatal=False)
1821 player_desc = 'flash player %s' % player_version
1823 player_version = self._search_regex(
1824 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1825 r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
1827 'html5 player', fatal=False)
1828 player_desc = 'html5 player %s' % player_version
1830 parts_sizes = self._signature_cache_id(encrypted_sig)
1831 self.to_screen('{%s} signature length %s, %s' %
1832 (format_id, parts_sizes, player_desc))
1834 signature = self._decrypt_signature(
1835 encrypted_sig, video_id, player_url, age_gate)
1836 url += '&signature=' + signature
1837 if 'ratebypass' not in url:
1838 url += '&ratebypass=yes'
1841 'format_id': format_id,
1843 'player_url': player_url,
1845 if format_id in self._formats:
1846 dct.update(self._formats[format_id])
1847 if format_id in formats_spec:
1848 dct.update(formats_spec[format_id])
1850 # Some itags are not included in DASH manifest thus corresponding formats will
1851 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1852 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1853 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1854 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
1857 'filesize': int_or_none(url_data.get('clen', [None])[0]),
1858 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
1861 'fps': int_or_none(url_data.get('fps', [None])[0]),
1862 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
1864 for key, value in more_fields.items():
1867 type_ = url_data.get('type', [None])[0]
1869 type_split = type_.split(';')
1870 kind_ext = type_split[0].split('/')
1871 if len(kind_ext) == 2:
1873 dct['ext'] = mimetype2ext(type_split[0])
1874 if kind in ('audio', 'video'):
1876 for mobj in re.finditer(
1877 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1878 if mobj.group('key') == 'codecs':
1879 codecs = mobj.group('val')
1882 dct.update(parse_codecs(codecs))
1884 elif video_info.get('hlsvp'):
1885 manifest_url = video_info['hlsvp'][0]
1887 m3u8_formats = self._extract_m3u8_formats(
1888 manifest_url, video_id, 'mp4', fatal=False)
1889 for a_format in m3u8_formats:
1890 itag = self._search_regex(
1891 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1893 a_format['format_id'] = itag
1894 if itag in self._formats:
1895 dct = self._formats[itag].copy()
1896 dct.update(a_format)
1898 a_format['player_url'] = player_url
1899 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1900 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1901 formats.append(a_format)
1903 unavailable_message = self._html_search_regex(
1904 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1905 video_webpage, 'unavailable message', default=None)
1906 if unavailable_message:
1907 raise ExtractorError(unavailable_message, expected=True)
1908 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
1910 # Look for the DASH manifest
1911 if self._downloader.params.get('youtube_include_dash_manifest', True):
1912 dash_mpd_fatal = True
1913 for mpd_url in dash_mpds:
1916 def decrypt_sig(mobj):
1918 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1919 return '/signature/%s' % dec_s
1921 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
1923 for df in self._extract_mpd_formats(
1924 mpd_url, video_id, fatal=dash_mpd_fatal,
1925 formats_dict=self._formats):
1926 # Do not overwrite DASH format found in some previous DASH manifest
1927 if df['format_id'] not in dash_formats:
1928 dash_formats[df['format_id']] = df
1929 # Additional DASH manifests may end up in HTTP Error 403 therefore
1930 # allow them to fail without bug report message if we already have
1931 # some DASH manifest succeeded. This is temporary workaround to reduce
1932 # burst of bug reports until we figure out the reason and whether it
1933 # can be fixed at all.
1934 dash_mpd_fatal = False
1935 except (ExtractorError, KeyError) as e:
1936 self.report_warning(
1937 'Skipping DASH manifest: %r' % e, video_id)
1939 # Remove the formats we found through non-DASH, they
1940 # contain less info and it can be wrong, because we use
1941 # fixed values (for example the resolution). See
1942 # https://github.com/rg3/youtube-dl/issues/5774 for an
1944 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
1945 formats.extend(dash_formats.values())
1947 # Check for malformed aspect ratio
1948 stretched_m = re.search(
1949 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1952 w = float(stretched_m.group('w'))
1953 h = float(stretched_m.group('h'))
1954 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1955 # We will only process correct ratios.
1959 if f.get('vcodec') != 'none':
1960 f['stretched_ratio'] = ratio
1962 self._sort_formats(formats)
1964 self.mark_watched(video_id, video_info)
1968 'uploader': video_uploader,
1969 'uploader_id': video_uploader_id,
1970 'uploader_url': video_uploader_url,
1971 'upload_date': upload_date,
1972 'license': video_license,
1973 'creator': video_creator,
1974 'title': video_title,
1975 'alt_title': video_alt_title,
1976 'thumbnail': video_thumbnail,
1977 'description': video_description,
1978 'categories': video_categories,
1980 'subtitles': video_subtitles,
1981 'automatic_captions': automatic_captions,
1982 'duration': video_duration,
1983 'age_limit': 18 if age_gate else 0,
1984 'annotations': video_annotations,
1985 'chapters': chapters,
1986 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
1987 'view_count': view_count,
1988 'like_count': like_count,
1989 'dislike_count': dislike_count,
1990 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
1993 'start_time': start_time,
1994 'end_time': end_time,
1996 'season_number': season_number,
1997 'episode_number': episode_number,
2001 class YoutubeSharedVideoIE(InfoExtractor):
2002 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
2003 IE_NAME = 'youtube:shared'
2006 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
2008 'id': 'uPDB5I9wfp8',
2010 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
2011 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
2012 'upload_date': '20160219',
2013 'uploader': 'Pocoyo - Português (BR)',
2014 'uploader_id': 'PocoyoBrazil',
2016 'add_ie': ['Youtube'],
2018 # There are already too many Youtube downloads
2019 'skip_download': True,
2023 def _real_extract(self, url):
2024 video_id = self._match_id(url)
2026 webpage = self._download_webpage(url, video_id)
2028 real_video_id = self._html_search_meta(
2029 'videoId', webpage, 'YouTube video id', fatal=True)
2031 return self.url_result(real_video_id, YoutubeIE.ie_key())
2034 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2035 IE_DESC = 'YouTube.com playlists'
2036 _VALID_URL = r"""(?x)(?:
2042 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2043 \? (?:.*?[&;])*? (?:p|a|list)=
2046 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2049 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
2050 # Top tracks, they can also include dots
2056 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2057 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
2058 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2059 IE_NAME = 'youtube:playlist'
2061 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2063 'title': 'ytdl test PL',
2064 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2066 'playlist_count': 3,
2068 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2070 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2071 'title': 'YDL_Empty_List',
2073 'playlist_count': 0,
2074 'skip': 'This playlist is private',
2076 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2077 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2079 'title': '29C3: Not my department',
2080 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2082 'playlist_count': 95,
2084 'note': 'issue #673',
2085 'url': 'PLBB231211A4F62143',
2087 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2088 'id': 'PLBB231211A4F62143',
2090 'playlist_mincount': 26,
2092 'note': 'Large playlist',
2093 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2095 'title': 'Uploads from Cauchemar',
2096 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2098 'playlist_mincount': 799,
2100 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2102 'title': 'YDL_safe_search',
2103 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2105 'playlist_count': 2,
2106 'skip': 'This playlist is private',
2109 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2110 'playlist_count': 4,
2113 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2116 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2117 'playlist_mincount': 485,
2119 'title': '2017 華語最新單曲 (2/24更新)',
2120 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2123 'note': 'Embedded SWF player',
2124 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2125 'playlist_count': 4,
2128 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2131 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2132 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2134 'title': 'Uploads from Interstellar Movie',
2135 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2137 'playlist_mincount': 21,
2139 # Playlist URL that does not actually serve a playlist
2140 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2142 'id': 'FqZTN594JQw',
2144 'title': "Smiley's People 01 detective, Adventure Series, Action",
2145 'uploader': 'STREEM',
2146 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2147 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2148 'upload_date': '20150526',
2149 'license': 'Standard YouTube License',
2150 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2151 'categories': ['People & Blogs'],
2154 'dislike_count': int,
2157 'skip_download': True,
2159 'add_ie': [YoutubeIE.ie_key()],
2161 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2163 'id': 'yeWKywCrFtk',
2165 'title': 'Small Scale Baler and Braiding Rugs',
2166 'uploader': 'Backus-Page House Museum',
2167 'uploader_id': 'backuspagemuseum',
2168 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2169 'upload_date': '20161008',
2170 'license': 'Standard YouTube License',
2171 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2172 'categories': ['Nonprofits & Activism'],
2175 'dislike_count': int,
2179 'skip_download': True,
2182 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2183 'only_matching': True,
2185 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2186 'only_matching': True,
2189 def _real_initialize(self):
2192 def _extract_mix(self, playlist_id):
2193 # The mixes are generated from a single video
2194 # the id of the playlist is just 'RD' + video_id
2196 last_id = playlist_id[-11:]
2197 for n in itertools.count(1):
2198 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2199 webpage = self._download_webpage(
2200 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2201 new_ids = orderedSet(re.findall(
2202 r'''(?xs)data-video-username=".*?".*?
2203 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2205 # Fetch new pages until all the videos are repeated, it seems that
2206 # there are always 51 unique videos.
2207 new_ids = [_id for _id in new_ids if _id not in ids]
2213 url_results = self._ids_to_results(ids)
2215 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2217 search_title('playlist-title') or
2218 search_title('title long-title') or
2219 search_title('title'))
2220 title = clean_html(title_span)
2222 return self.playlist_result(url_results, playlist_id, title)
2224 def _extract_playlist(self, playlist_id):
2225 url = self._TEMPLATE_URL % playlist_id
2226 page = self._download_webpage(url, playlist_id)
2228 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2229 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2230 match = match.strip()
2231 # Check if the playlist exists or is private
2232 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2234 reason = mobj.group('reason')
2235 message = 'This playlist %s' % reason
2236 if 'private' in reason:
2237 message += ', use --username or --netrc to access it'
2239 raise ExtractorError(message, expected=True)
2240 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2241 raise ExtractorError(
2242 'Invalid parameters. Maybe URL is incorrect.',
2244 elif re.match(r'[^<]*Choose your language[^<]*', match):
2247 self.report_warning('Youtube gives an alert message: ' + match)
2249 playlist_title = self._html_search_regex(
2250 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2251 page, 'title', default=None)
2255 if not playlist_title:
2257 # Some playlist URLs don't actually serve a playlist (e.g.
2258 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2259 next(self._entries(page, playlist_id))
2260 except StopIteration:
2263 return has_videos, self.playlist_result(
2264 self._entries(page, playlist_id), playlist_id, playlist_title)
2266 def _check_download_just_video(self, url, playlist_id):
2267 # Check if it's a video-specific URL
2268 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2269 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2270 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2271 'video id', default=None)
2273 if self._downloader.params.get('noplaylist'):
2274 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2275 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2277 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2278 return video_id, None
2281 def _real_extract(self, url):
2282 # Extract playlist id
2283 mobj = re.match(self._VALID_URL, url)
2285 raise ExtractorError('Invalid URL: %s' % url)
2286 playlist_id = mobj.group(1) or mobj.group(2)
2288 video_id, video = self._check_download_just_video(url, playlist_id)
2292 if playlist_id.startswith(('RD', 'UL', 'PU')):
2293 # Mixes require a custom extraction process
2294 return self._extract_mix(playlist_id)
2296 has_videos, playlist = self._extract_playlist(playlist_id)
2297 if has_videos or not video_id:
2300 # Some playlist URLs don't actually serve a playlist (see
2301 # https://github.com/rg3/youtube-dl/issues/10537).
2302 # Fallback to plain video extraction if there is a video id
2303 # along with playlist id.
2304 return self.url_result(video_id, 'Youtube', video_id=video_id)
2307 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2308 IE_DESC = 'YouTube.com channels'
2309 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2310 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2311 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2312 IE_NAME = 'youtube:channel'
2314 'note': 'paginated channel',
2315 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2316 'playlist_mincount': 91,
2318 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2319 'title': 'Uploads from lex will',
2322 'note': 'Age restricted channel',
2323 # from https://www.youtube.com/user/DeusExOfficial
2324 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2325 'playlist_mincount': 64,
2327 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2328 'title': 'Uploads from Deus Ex',
2333 def suitable(cls, url):
2334 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2335 else super(YoutubeChannelIE, cls).suitable(url))
2337 def _build_template_url(self, url, channel_id):
2338 return self._TEMPLATE_URL % channel_id
2340 def _real_extract(self, url):
2341 channel_id = self._match_id(url)
2343 url = self._build_template_url(url, channel_id)
2345 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2346 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2347 # otherwise fallback on channel by page extraction
2348 channel_page = self._download_webpage(
2349 url + '?view=57', channel_id,
2350 'Downloading channel page', fatal=False)
2351 if channel_page is False:
2352 channel_playlist_id = False
2354 channel_playlist_id = self._html_search_meta(
2355 'channelId', channel_page, 'channel id', default=None)
2356 if not channel_playlist_id:
2357 channel_url = self._html_search_meta(
2358 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2359 channel_page, 'channel url', default=None)
2361 channel_playlist_id = self._search_regex(
2362 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2363 channel_url, 'channel id', default=None)
2364 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2365 playlist_id = 'UU' + channel_playlist_id[2:]
2366 return self.url_result(
2367 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2369 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2370 autogenerated = re.search(r'''(?x)
2372 channel-header-autogenerated-label|
2373 yt-channel-title-autogenerated
2374 )[^"]*"''', channel_page) is not None
2377 # The videos are contained in a single page
2378 # the ajax pages can't be used, they are empty
2381 video_id, 'Youtube', video_id=video_id,
2382 video_title=video_title)
2383 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2384 return self.playlist_result(entries, channel_id)
2387 next(self._entries(channel_page, channel_id))
2388 except StopIteration:
2389 alert_message = self._html_search_regex(
2390 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2391 channel_page, 'alert', default=None, group='alert')
2393 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2395 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2398 class YoutubeUserIE(YoutubeChannelIE):
2399 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2400 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
2401 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2402 IE_NAME = 'youtube:user'
2405 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2406 'playlist_mincount': 320,
2408 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2409 'title': 'Uploads from The Linux Foundation',
2412 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2413 # but not https://www.youtube.com/user/12minuteathlete/videos
2414 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2415 'playlist_mincount': 249,
2417 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2418 'title': 'Uploads from 12 Minute Athlete',
2421 'url': 'ytuser:phihag',
2422 'only_matching': True,
2424 'url': 'https://www.youtube.com/c/gametrailers',
2425 'only_matching': True,
2427 'url': 'https://www.youtube.com/gametrailers',
2428 'only_matching': True,
2430 # This channel is not available, geo restricted to JP
2431 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2432 'only_matching': True,
2436 def suitable(cls, url):
2437 # Don't return True if the url can be extracted with other youtube
2438 # extractor, the regex would is too permissive and it would match.
2439 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2440 if any(ie.suitable(url) for ie in other_yt_ies):
2443 return super(YoutubeUserIE, cls).suitable(url)
2445 def _build_template_url(self, url, channel_id):
2446 mobj = re.match(self._VALID_URL, url)
2447 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2450 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2451 IE_DESC = 'YouTube.com live streams'
2452 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2453 IE_NAME = 'youtube:live'
2456 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2458 'id': 'a48o2S1cPoo',
2460 'title': 'The Young Turks - Live Main Show',
2461 'uploader': 'The Young Turks',
2462 'uploader_id': 'TheYoungTurks',
2463 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2464 'upload_date': '20150715',
2465 'license': 'Standard YouTube License',
2466 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2467 'categories': ['News & Politics'],
2468 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2470 'dislike_count': int,
2473 'skip_download': True,
2476 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2477 'only_matching': True,
2479 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2480 'only_matching': True,
2482 'url': 'https://www.youtube.com/TheYoungTurks/live',
2483 'only_matching': True,
2486 def _real_extract(self, url):
2487 mobj = re.match(self._VALID_URL, url)
2488 channel_id = mobj.group('id')
2489 base_url = mobj.group('base_url')
2490 webpage = self._download_webpage(url, channel_id, fatal=False)
2492 page_type = self._og_search_property(
2493 'type', webpage, 'page type', default=None)
2494 video_id = self._html_search_meta(
2495 'videoId', webpage, 'video id', default=None)
2496 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2497 return self.url_result(video_id, YoutubeIE.ie_key())
2498 return self.url_result(base_url)
2501 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2502 IE_DESC = 'YouTube.com user/channel playlists'
2503 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2504 IE_NAME = 'youtube:playlists'
2507 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2508 'playlist_mincount': 4,
2510 'id': 'ThirstForScience',
2511 'title': 'Thirst for Science',
2514 # with "Load more" button
2515 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2516 'playlist_mincount': 70,
2519 'title': 'Игорь Клейнер',
2522 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2523 'playlist_mincount': 17,
2525 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2526 'title': 'Chem Player',
2531 class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
2532 IE_DESC = 'YouTube.com searches'
2533 # there doesn't appear to be a real limit, for example if you search for
2534 # 'python' you get more than 8.000.000 results
2535 _MAX_RESULTS = float('inf')
2536 IE_NAME = 'youtube:search'
2537 _SEARCH_KEY = 'ytsearch'
2538 _EXTRA_QUERY_ARGS = {}
2541 def _get_n_results(self, query, n):
2542 """Get a specified number of results for a query"""
2548 'search_query': query.encode('utf-8'),
2550 url_query.update(self._EXTRA_QUERY_ARGS)
2551 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2553 for pagenum in itertools.count(1):
2554 data = self._download_json(
2555 result_url, video_id='query "%s"' % query,
2556 note='Downloading page %s' % pagenum,
2557 errnote='Unable to download API page',
2558 query={'spf': 'navigate'})
2559 html_content = data[1]['body']['content']
2561 if 'class="search-message' in html_content:
2562 raise ExtractorError(
2563 '[youtube] No video results', expected=True)
2565 new_videos = self._ids_to_results(orderedSet(re.findall(
2566 r'href="/watch\?v=(.{11})', html_content)))
2567 videos += new_videos
2568 if not new_videos or len(videos) > limit:
2570 next_link = self._html_search_regex(
2571 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2572 html_content, 'next link', default=None)
2573 if next_link is None:
2575 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2579 return self.playlist_result(videos, query)
2582 class YoutubeSearchDateIE(YoutubeSearchIE):
2583 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2584 _SEARCH_KEY = 'ytsearchdate'
2585 IE_DESC = 'YouTube.com searches, newest videos first'
2586 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2589 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
2590 IE_DESC = 'YouTube.com search URLs'
2591 IE_NAME = 'youtube:search_url'
2592 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2593 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2595 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2596 'playlist_mincount': 5,
2598 'title': 'youtube-dl test video',
2601 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2602 'only_matching': True,
2605 def _real_extract(self, url):
2606 mobj = re.match(self._VALID_URL, url)
2607 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2608 webpage = self._download_webpage(url, query)
2609 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2612 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2613 IE_DESC = 'YouTube.com (multi-season) shows'
2614 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2615 IE_NAME = 'youtube:show'
2617 'url': 'https://www.youtube.com/show/airdisasters',
2618 'playlist_mincount': 5,
2620 'id': 'airdisasters',
2621 'title': 'Air Disasters',
2625 def _real_extract(self, url):
2626 playlist_id = self._match_id(url)
2627 return super(YoutubeShowIE, self)._real_extract(
2628 'https://www.youtube.com/show/%s/playlists' % playlist_id)
2631 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
2633 Base class for feed extractors
2634 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2636 _LOGIN_REQUIRED = True
2640 return 'youtube:%s' % self._FEED_NAME
2642 def _real_initialize(self):
2645 def _real_extract(self, url):
2646 page = self._download_webpage(
2647 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2649 # The extraction process is the same as for playlists, but the regex
2650 # for the video ids doesn't contain an index
2652 more_widget_html = content_html = page
2653 for page_num in itertools.count(1):
2654 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
2656 # 'recommended' feed has infinite 'load more' and each new portion spins
2657 # the same videos in (sometimes) slightly different order, so we'll check
2658 # for unicity and break when portion has no new videos
2659 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2665 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2669 more = self._download_json(
2670 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2671 'Downloading page #%s' % page_num,
2672 transform_source=uppercase_escape)
2673 content_html = more['content_html']
2674 more_widget_html = more['load_more_widget_html']
2676 return self.playlist_result(
2677 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2680 class YoutubeWatchLaterIE(YoutubePlaylistIE):
2681 IE_NAME = 'youtube:watchlater'
2682 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2683 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2686 'url': 'https://www.youtube.com/playlist?list=WL',
2687 'only_matching': True,
2689 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2690 'only_matching': True,
2693 def _real_extract(self, url):
2694 _, video = self._check_download_just_video(url, 'WL')
2697 _, playlist = self._extract_playlist('WL')
2701 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
2702 IE_NAME = 'youtube:favorites'
2703 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2704 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2705 _LOGIN_REQUIRED = True
2707 def _real_extract(self, url):
2708 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2709 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
2710 return self.url_result(playlist_id, 'YoutubePlaylist')
2713 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2714 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2715 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2716 _FEED_NAME = 'recommended'
2717 _PLAYLIST_TITLE = 'Youtube Recommended videos'
2720 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2721 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2722 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2723 _FEED_NAME = 'subscriptions'
2724 _PLAYLIST_TITLE = 'Youtube Subscriptions'
2727 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2728 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
2729 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2730 _FEED_NAME = 'history'
2731 _PLAYLIST_TITLE = 'Youtube History'
2734 class YoutubeTruncatedURLIE(InfoExtractor):
2735 IE_NAME = 'youtube:truncated_url'
2736 IE_DESC = False # Do not list
2737 _VALID_URL = r'''(?x)
2739 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2742 annotation_id=annotation_[^&]+|
2748 attribution_link\?a=[^&]+
2754 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2755 'only_matching': True,
2757 'url': 'https://www.youtube.com/watch?',
2758 'only_matching': True,
2760 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2761 'only_matching': True,
2763 'url': 'https://www.youtube.com/watch?feature=foo',
2764 'only_matching': True,
2766 'url': 'https://www.youtube.com/watch?hl=en-GB',
2767 'only_matching': True,
2769 'url': 'https://www.youtube.com/watch?t=2372',
2770 'only_matching': True,
2773 def _real_extract(self, url):
2774 raise ExtractorError(
2775 'Did you forget to quote the URL? Remember that & is a meta '
2776 'character in most shells, so you want to put the URL in quotes, '
2778 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2779 ' or simply youtube-dl BaW_jenozKc .',
2783 class YoutubeTruncatedIDIE(InfoExtractor):
2784 IE_NAME = 'youtube:truncated_id'
2785 IE_DESC = False # Do not list
2786 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2789 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2790 'only_matching': True,
2793 def _real_extract(self, url):
2794 video_id = self._match_id(url)
2795 raise ExtractorError(
2796 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),