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,
53 class YoutubeBaseInfoExtractor(InfoExtractor):
54 """Provide base functions for Youtube extractors"""
55 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
56 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
57 _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
58 _NETRC_MACHINE = 'youtube'
59 # If True it will raise an error if no login info is provided
60 _LOGIN_REQUIRED = False
62 def _set_language(self):
64 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
65 # YouTube sets the expire time to about two months
66 expire_time=time.time() + 2 * 30 * 24 * 3600)
68 def _ids_to_results(self, ids):
70 self.url_result(vid_id, 'Youtube', video_id=vid_id)
75 Attempt to log in to YouTube.
76 True is returned if successful or skipped.
77 False is returned if login failed.
79 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
81 (username, password) = self._get_login_info()
82 # No authentication to be performed
84 if self._LOGIN_REQUIRED:
85 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
88 login_page = self._download_webpage(
89 self._LOGIN_URL, None,
90 note='Downloading login page',
91 errnote='unable to fetch login page', fatal=False)
92 if login_page is False:
95 login_form = self._hidden_inputs(login_page)
98 'checkConnection': 'youtube',
103 login_results = self._download_webpage(
104 self._PASSWORD_CHALLENGE_URL, None,
105 note='Logging in', errnote='unable to log in', fatal=False,
106 data=urlencode_postdata(login_form))
107 if login_results is False:
110 error_msg = self._html_search_regex(
111 r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
112 login_results, 'error message', default=None)
114 raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
116 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
117 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
120 # TODO add SMS and phone call support - these require making a request and then prompting the user
122 if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
123 tfa_code = self._get_tfa_info('2-step verification code')
126 self._downloader.report_warning(
127 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
128 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
131 tfa_code = remove_start(tfa_code, 'G-')
133 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
135 tfa_form_strs.update({
140 tfa_data = urlencode_postdata(tfa_form_strs)
142 tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
143 tfa_results = self._download_webpage(
145 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
147 if tfa_results is False:
150 if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
151 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
153 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
154 self._downloader.report_warning('unable to log in - did the page structure change?')
156 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
157 self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
160 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
161 self._downloader.report_warning('unable to log in: bad username or password')
165 def _real_initialize(self):
166 if self._downloader is None:
169 if not self._login():
173 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
174 # Extract entries from page with "Load more" button
175 def _entries(self, page, playlist_id):
176 more_widget_html = content_html = page
177 for page_num in itertools.count(1):
178 for entry in self._process_page(content_html):
181 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
185 more = self._download_json(
186 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
187 'Downloading page #%s' % page_num,
188 transform_source=uppercase_escape)
189 content_html = more['content_html']
190 if not content_html.strip():
191 # Some webpages show a "Load more" button but they don't
194 more_widget_html = more['load_more_widget_html']
197 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
198 def _process_page(self, content):
199 for video_id, video_title in self.extract_videos_from_page(content):
200 yield self.url_result(video_id, 'Youtube', video_id, video_title)
202 def extract_videos_from_page(self, page):
205 for mobj in re.finditer(self._VIDEO_RE, page):
206 # The link with index 0 is not the first video of the playlist (not sure if still actual)
207 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
209 video_id = mobj.group('id')
210 video_title = unescapeHTML(mobj.group('title'))
212 video_title = video_title.strip()
214 idx = ids_in_page.index(video_id)
215 if video_title and not titles_in_page[idx]:
216 titles_in_page[idx] = video_title
218 ids_in_page.append(video_id)
219 titles_in_page.append(video_title)
220 return zip(ids_in_page, titles_in_page)
223 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
224 def _process_page(self, content):
225 for playlist_id in orderedSet(re.findall(
226 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
228 yield self.url_result(
229 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
231 def _real_extract(self, url):
232 playlist_id = self._match_id(url)
233 webpage = self._download_webpage(url, playlist_id)
234 title = self._og_search_title(webpage, fatal=False)
235 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
238 class YoutubeIE(YoutubeBaseInfoExtractor):
239 IE_DESC = 'YouTube.com'
240 _VALID_URL = r"""(?x)^
242 (?:https?://|//) # http(s):// or protocol-independent URL
243 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
244 (?:www\.)?deturl\.com/www\.youtube\.com/|
245 (?:www\.)?pwnyoutube\.com/|
246 (?:www\.)?yourepeat\.com/|
247 tube\.majestyc\.net/|
248 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
249 (?:.*?\#/)? # handle anchor (#/) redirect urls
250 (?: # the various things that can precede the ID:
251 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
252 |(?: # or the v= param in all its forms
253 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
254 (?:\?|\#!?) # the params delimiter ? or # or #!
255 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
260 youtu\.be| # just youtu.be/xxxx
261 vid\.plus| # or vid.plus/xxxx
262 zwearz\.com/watch| # or zwearz.com/watch/xxxx
264 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
266 )? # all until now is optional -> you can pass the naked ID
267 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
268 (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
269 (?(1).+)? # if we found the ID, everything can follow
271 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
273 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
274 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
275 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
276 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
277 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
278 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
279 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
280 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
281 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
282 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
283 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
284 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
285 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
286 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
287 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
288 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
289 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
290 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
294 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
295 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
296 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
297 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
298 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
299 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
300 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
302 # Apple HTTP Live Streaming
303 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
304 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
305 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
306 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
307 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
308 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
309 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
310 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
313 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
314 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
315 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
316 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
317 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
318 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
319 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
320 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
321 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
322 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
323 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
324 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
327 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
328 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
329 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
330 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
331 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
334 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
335 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
336 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
337 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
338 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
339 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
340 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
341 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
342 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
343 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
344 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
345 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
346 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
347 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
348 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
349 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
350 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
351 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
352 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
353 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
354 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
355 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
358 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
359 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
361 # Dash webm audio with opus inside
362 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
363 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
364 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
367 '_rtmp': {'protocol': 'rtmp'},
369 _SUBTITLE_FORMATS = ('ttml', 'vtt')
374 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
378 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
379 'uploader': 'Philipp Hagemeister',
380 'uploader_id': 'phihag',
381 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
382 'upload_date': '20121002',
383 'license': 'Standard YouTube License',
384 '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 .',
385 'categories': ['Science & Technology'],
386 'tags': ['youtube-dl'],
389 'dislike_count': int,
395 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
396 'note': 'Test generic use_cipher_signature video (#897)',
400 'upload_date': '20120506',
401 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
402 'alt_title': 'I Love It (feat. Charli XCX)',
403 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
404 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
405 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
406 'iconic ep', 'iconic', 'love', 'it'],
408 'uploader': 'Icona Pop',
409 'uploader_id': 'IconaPop',
410 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
411 'license': 'Standard YouTube License',
412 'creator': 'Icona Pop',
416 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
417 'note': 'Test VEVO video with age protection (#956)',
421 'upload_date': '20130703',
422 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
423 'alt_title': 'Tunnel Vision',
424 'description': 'md5:64249768eec3bc4276236606ea996373',
426 'uploader': 'justintimberlakeVEVO',
427 'uploader_id': 'justintimberlakeVEVO',
428 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
429 'license': 'Standard YouTube License',
430 'creator': 'Justin Timberlake',
435 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
436 'note': 'Embed-only video (#1746)',
440 'upload_date': '20120608',
441 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
442 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
443 'uploader': 'SET India',
444 'uploader_id': 'setindia',
445 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
446 'license': 'Standard YouTube License',
451 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
452 'note': 'Use the first video ID in the URL',
456 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
457 'uploader': 'Philipp Hagemeister',
458 'uploader_id': 'phihag',
459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
460 'upload_date': '20121002',
461 'license': 'Standard YouTube License',
462 '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 .',
463 'categories': ['Science & Technology'],
464 'tags': ['youtube-dl'],
467 'dislike_count': int,
470 'skip_download': True,
474 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
475 'note': '256k DASH audio (format 141) via DASH manifest',
479 'upload_date': '20121002',
480 'uploader_id': '8KVIDEO',
481 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
483 'uploader': '8KVIDEO',
484 'license': 'Standard YouTube License',
485 'title': 'UHDTV TEST 8K VIDEO.mp4'
488 'youtube_include_dash_manifest': True,
491 'skip': 'format 141 not served anymore',
493 # DASH manifest with encrypted signature
495 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
499 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
500 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
502 'uploader': 'AfrojackVEVO',
503 'uploader_id': 'AfrojackVEVO',
504 'upload_date': '20131011',
505 'license': 'Standard YouTube License',
508 'youtube_include_dash_manifest': True,
509 'format': '141/bestaudio[ext=m4a]',
512 # JS player signature function name containing $
514 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
518 'title': 'Taylor Swift - Shake It Off',
519 'alt_title': 'Shake It Off',
520 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
522 'uploader': 'TaylorSwiftVEVO',
523 'uploader_id': 'TaylorSwiftVEVO',
524 'upload_date': '20140818',
525 'license': 'Standard YouTube License',
526 'creator': 'Taylor Swift',
529 'youtube_include_dash_manifest': True,
530 'format': '141/bestaudio[ext=m4a]',
535 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
540 'upload_date': '20100909',
541 'uploader': 'The Amazing Atheist',
542 'uploader_id': 'TheAmazingAtheist',
543 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
544 'license': 'Standard YouTube License',
545 'title': 'Burning Everyone\'s Koran',
546 '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',
549 # Normal age-gate video (No vevo, embed allowed)
551 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
555 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
556 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
558 'uploader': 'The Witcher',
559 'uploader_id': 'WitcherGame',
560 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
561 'upload_date': '20140605',
562 'license': 'Standard YouTube License',
566 # Age-gate video with encrypted signature
568 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
572 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
573 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
575 'uploader': 'LloydVEVO',
576 'uploader_id': 'LloydVEVO',
577 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
578 'upload_date': '20110629',
579 'license': 'Standard YouTube License',
583 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
585 'url': '__2ABJjxzNo',
590 'upload_date': '20100430',
591 'uploader_id': 'deadmau5',
592 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
593 'creator': 'deadmau5',
594 'description': 'md5:12c56784b8032162bb936a5f76d55360',
595 'uploader': 'deadmau5',
596 'license': 'Standard YouTube License',
597 'title': 'Deadmau5 - Some Chords (HD)',
598 'alt_title': 'Some Chords',
600 'expected_warnings': [
601 'DASH manifest missing',
604 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
606 'url': 'lqQg6PlCWgI',
611 'upload_date': '20150827',
612 'uploader_id': 'olympic',
613 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
614 'license': 'Standard YouTube License',
615 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
616 'uploader': 'Olympic',
617 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
620 'skip_download': 'requires avconv',
625 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
629 'stretched_ratio': 16 / 9.,
631 'upload_date': '20110310',
632 'uploader_id': 'AllenMeow',
633 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
634 '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',
636 'license': 'Standard YouTube License',
637 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
640 # url_encoded_fmt_stream_map is empty string
642 'url': 'qEJwOuvDf7I',
646 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
648 'upload_date': '20150404',
649 'uploader_id': 'spbelect',
650 'uploader': 'Наблюдатели Петербурга',
653 'skip_download': 'requires avconv',
655 'skip': 'This live event has ended.',
657 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
659 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
663 'title': 'md5:7b81415841e02ecd4313668cde88737a',
664 'description': 'md5:116377fd2963b81ec4ce64b542173306',
666 'upload_date': '20150625',
667 'uploader_id': 'dorappi2000',
668 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
669 'uploader': 'dorappi2000',
670 'license': 'Standard YouTube License',
671 'formats': 'mincount:32',
674 # DASH manifest with segment_list
676 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
677 'md5': '8ce563a1d667b599d21064e982ab9e31',
681 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
682 'uploader': 'Airtek',
683 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
684 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
685 'license': 'Standard YouTube License',
686 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
689 'youtube_include_dash_manifest': True,
690 'format': '135', # bestvideo
692 'skip': 'This live event has ended.',
695 # Multifeed videos (multiple cameras), URL is for Main Camera
696 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
699 'title': 'teamPGP: Rocket League Noob Stream',
700 'description': 'md5:dc7872fb300e143831327f1bae3af010',
706 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
707 'description': 'md5:dc7872fb300e143831327f1bae3af010',
709 'upload_date': '20150721',
710 'uploader': 'Beer Games Beer',
711 'uploader_id': 'beergamesbeer',
712 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
713 'license': 'Standard YouTube License',
719 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
720 'description': 'md5:dc7872fb300e143831327f1bae3af010',
722 'upload_date': '20150721',
723 'uploader': 'Beer Games Beer',
724 'uploader_id': 'beergamesbeer',
725 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
726 'license': 'Standard YouTube License',
732 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
733 'description': 'md5:dc7872fb300e143831327f1bae3af010',
735 'upload_date': '20150721',
736 'uploader': 'Beer Games Beer',
737 'uploader_id': 'beergamesbeer',
738 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
739 'license': 'Standard YouTube License',
745 'title': 'teamPGP: Rocket League Noob Stream (zim)',
746 'description': 'md5:dc7872fb300e143831327f1bae3af010',
748 'upload_date': '20150721',
749 'uploader': 'Beer Games Beer',
750 'uploader_id': 'beergamesbeer',
751 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
752 'license': 'Standard YouTube License',
756 'skip_download': True,
760 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
761 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
764 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
767 'skip': 'Not multifeed anymore',
770 'url': 'https://vid.plus/FlRa-iH7PGw',
771 'only_matching': True,
774 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
775 'only_matching': True,
778 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
779 # Also tests cut-off URL expansion in video description (see
780 # https://github.com/rg3/youtube-dl/issues/1892,
781 # https://github.com/rg3/youtube-dl/issues/8164)
782 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
786 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
787 'alt_title': 'Dark Walk',
788 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
790 'upload_date': '20151119',
791 'uploader_id': 'IronSoulElf',
792 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
793 'uploader': 'IronSoulElf',
794 'license': 'Standard YouTube License',
795 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
798 'skip_download': True,
802 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
803 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
804 'only_matching': True,
807 # Video with yt:stretch=17:0
808 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
812 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
813 'description': 'md5:ee18a25c350637c8faff806845bddee9',
814 'upload_date': '20151107',
815 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
816 'uploader': 'CH GAMER DROID',
819 'skip_download': True,
821 'skip': 'This video does not exist.',
824 # Video licensed under Creative Commons
825 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
829 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
830 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
832 'upload_date': '20150127',
833 'uploader_id': 'BerkmanCenter',
834 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
835 'uploader': 'The Berkman Klein Center for Internet & Society',
836 'license': 'Creative Commons Attribution license (reuse allowed)',
839 'skip_download': True,
843 # Channel-like uploader_url
844 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
848 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
849 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
851 'upload_date': '20151119',
852 'uploader': 'Bernie 2016',
853 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
854 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
855 'license': 'Creative Commons Attribution license (reuse allowed)',
858 'skip_download': True,
862 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
863 'only_matching': True,
866 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
867 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
868 'only_matching': True,
871 # Rental video preview
872 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
876 'title': 'Piku - Trailer',
877 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
878 'upload_date': '20150811',
879 'uploader': 'FlixMatrix',
880 'uploader_id': 'FlixMatrixKaravan',
881 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
882 'license': 'Standard YouTube License',
885 'skip_download': True,
889 # YouTube Red video with episode data
890 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
894 'title': 'Isolation - Mind Field (Ep 1)',
895 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
897 'upload_date': '20170118',
898 'uploader': 'Vsauce',
899 'uploader_id': 'Vsauce',
900 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
901 'license': 'Standard YouTube License',
902 'series': 'Mind Field',
907 'skip_download': True,
909 'expected_warnings': [
910 'Skipping DASH manifest',
915 'url': '1t24XAntNCY',
916 'only_matching': True,
920 def __init__(self, *args, **kwargs):
921 super(YoutubeIE, self).__init__(*args, **kwargs)
922 self._player_cache = {}
924 def report_video_info_webpage_download(self, video_id):
925 """Report attempt to download video info webpage."""
926 self.to_screen('%s: Downloading video info webpage' % video_id)
928 def report_information_extraction(self, video_id):
929 """Report attempt to extract video information."""
930 self.to_screen('%s: Extracting video information' % video_id)
932 def report_unavailable_format(self, video_id, format):
933 """Report extracted video URL."""
934 self.to_screen('%s: Format %s not available' % (video_id, format))
936 def report_rtmp_download(self):
937 """Indicate the download will use the RTMP protocol."""
938 self.to_screen('RTMP download detected')
940 def _signature_cache_id(self, example_sig):
941 """ Return a string representation of a signature """
942 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
944 def _extract_signature_function(self, video_id, player_url, example_sig):
946 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
949 raise ExtractorError('Cannot identify player %r' % player_url)
950 player_type = id_m.group('ext')
951 player_id = id_m.group('id')
953 # Read from filesystem cache
954 func_id = '%s_%s_%s' % (
955 player_type, player_id, self._signature_cache_id(example_sig))
956 assert os.path.basename(func_id) == func_id
958 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
959 if cache_spec is not None:
960 return lambda s: ''.join(s[i] for i in cache_spec)
963 'Downloading player %s' % player_url
964 if self._downloader.params.get('verbose') else
965 'Downloading %s player %s' % (player_type, player_id)
967 if player_type == 'js':
968 code = self._download_webpage(
969 player_url, video_id,
971 errnote='Download of %s failed' % player_url)
972 res = self._parse_sig_js(code)
973 elif player_type == 'swf':
974 urlh = self._request_webpage(
975 player_url, video_id,
977 errnote='Download of %s failed' % player_url)
979 res = self._parse_sig_swf(code)
981 assert False, 'Invalid player type %r' % player_type
983 test_string = ''.join(map(compat_chr, range(len(example_sig))))
984 cache_res = res(test_string)
985 cache_spec = [ord(c) for c in cache_res]
987 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
990 def _print_sig_code(self, func, example_sig):
991 def gen_sig_code(idxs):
992 def _genslice(start, end, step):
993 starts = '' if start == 0 else str(start)
994 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
995 steps = '' if step == 1 else (':%d' % step)
996 return 's[%s%s%s]' % (starts, ends, steps)
999 # Quelch pyflakes warnings - start will be set when step is set
1000 start = '(Never used)'
1001 for i, prev in zip(idxs[1:], idxs[:-1]):
1002 if step is not None:
1003 if i - prev == step:
1005 yield _genslice(start, prev, step)
1008 if i - prev in [-1, 1]:
1013 yield 's[%d]' % prev
1017 yield _genslice(start, i, step)
1019 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1020 cache_res = func(test_string)
1021 cache_spec = [ord(c) for c in cache_res]
1022 expr_code = ' + '.join(gen_sig_code(cache_spec))
1023 signature_id_tuple = '(%s)' % (
1024 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1025 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1026 ' return %s\n') % (signature_id_tuple, expr_code)
1027 self.to_screen('Extracted signature function:\n' + code)
1029 def _parse_sig_js(self, jscode):
1030 funcname = self._search_regex(
1031 r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
1032 'Initial JS player signature function name')
1034 jsi = JSInterpreter(jscode)
1035 initial_function = jsi.extract_function(funcname)
1036 return lambda s: initial_function([s])
1038 def _parse_sig_swf(self, file_contents):
1039 swfi = SWFInterpreter(file_contents)
1040 TARGET_CLASSNAME = 'SignatureDecipher'
1041 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1042 initial_function = swfi.extract_function(searched_class, 'decipher')
1043 return lambda s: initial_function([s])
1045 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1046 """Turn the encrypted s field into a working signature"""
1048 if player_url is None:
1049 raise ExtractorError('Cannot decrypt signature without player_url')
1051 if player_url.startswith('//'):
1052 player_url = 'https:' + player_url
1054 player_id = (player_url, self._signature_cache_id(s))
1055 if player_id not in self._player_cache:
1056 func = self._extract_signature_function(
1057 video_id, player_url, s
1059 self._player_cache[player_id] = func
1060 func = self._player_cache[player_id]
1061 if self._downloader.params.get('youtube_print_sig_code'):
1062 self._print_sig_code(func, s)
1064 except Exception as e:
1065 tb = traceback.format_exc()
1066 raise ExtractorError(
1067 'Signature extraction failed: ' + tb, cause=e)
1069 def _get_subtitles(self, video_id, webpage):
1071 subs_doc = self._download_xml(
1072 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1073 video_id, note=False)
1074 except ExtractorError as err:
1075 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1079 for track in subs_doc.findall('track'):
1080 lang = track.attrib['lang_code']
1081 if lang in sub_lang_list:
1084 for ext in self._SUBTITLE_FORMATS:
1085 params = compat_urllib_parse_urlencode({
1089 'name': track.attrib['name'].encode('utf-8'),
1091 sub_formats.append({
1092 'url': 'https://www.youtube.com/api/timedtext?' + params,
1095 sub_lang_list[lang] = sub_formats
1096 if not sub_lang_list:
1097 self._downloader.report_warning('video doesn\'t have subtitles')
1099 return sub_lang_list
1101 def _get_ytplayer_config(self, video_id, webpage):
1103 # User data may contain arbitrary character sequences that may affect
1104 # JSON extraction with regex, e.g. when '};' is contained the second
1105 # regex won't capture the whole JSON. Yet working around by trying more
1106 # concrete regex first keeping in mind proper quoted string handling
1107 # to be implemented in future that will replace this workaround (see
1108 # https://github.com/rg3/youtube-dl/issues/7468,
1109 # https://github.com/rg3/youtube-dl/pull/7599)
1110 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1111 r';ytplayer\.config\s*=\s*({.+?});',
1113 config = self._search_regex(
1114 patterns, webpage, 'ytplayer.config', default=None)
1116 return self._parse_json(
1117 uppercase_escape(config), video_id, fatal=False)
1119 def _get_automatic_captions(self, video_id, webpage):
1120 """We need the webpage for getting the captions url, pass it as an
1121 argument to speed up the process."""
1122 self.to_screen('%s: Looking for automatic captions' % video_id)
1123 player_config = self._get_ytplayer_config(video_id, webpage)
1124 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1125 if not player_config:
1126 self._downloader.report_warning(err_msg)
1129 args = player_config['args']
1130 caption_url = args.get('ttsurl')
1132 timestamp = args['timestamp']
1133 # We get the available subtitles
1134 list_params = compat_urllib_parse_urlencode({
1139 list_url = caption_url + '&' + list_params
1140 caption_list = self._download_xml(list_url, video_id)
1141 original_lang_node = caption_list.find('track')
1142 if original_lang_node is None:
1143 self._downloader.report_warning('Video doesn\'t have automatic captions')
1145 original_lang = original_lang_node.attrib['lang_code']
1146 caption_kind = original_lang_node.attrib.get('kind', '')
1149 for lang_node in caption_list.findall('target'):
1150 sub_lang = lang_node.attrib['lang_code']
1152 for ext in self._SUBTITLE_FORMATS:
1153 params = compat_urllib_parse_urlencode({
1154 'lang': original_lang,
1158 'kind': caption_kind,
1160 sub_formats.append({
1161 'url': caption_url + '&' + params,
1164 sub_lang_list[sub_lang] = sub_formats
1165 return sub_lang_list
1167 # Some videos don't provide ttsurl but rather caption_tracks and
1168 # caption_translation_languages (e.g. 20LmZk1hakA)
1169 caption_tracks = args['caption_tracks']
1170 caption_translation_languages = args['caption_translation_languages']
1171 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1172 parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
1173 caption_qs = compat_parse_qs(parsed_caption_url.query)
1176 for lang in caption_translation_languages.split(','):
1177 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1178 sub_lang = lang_qs.get('lc', [None])[0]
1182 for ext in self._SUBTITLE_FORMATS:
1184 'tlang': [sub_lang],
1187 sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
1188 query=compat_urllib_parse_urlencode(caption_qs, True)))
1189 sub_formats.append({
1193 sub_lang_list[sub_lang] = sub_formats
1194 return sub_lang_list
1195 # An extractor error can be raise by the download process if there are
1196 # no automatic captions but there are subtitles
1197 except (KeyError, ExtractorError):
1198 self._downloader.report_warning(err_msg)
1201 def _mark_watched(self, video_id, video_info):
1202 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1203 if not playback_url:
1205 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1206 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1208 # cpn generation algorithm is reverse engineered from base.js.
1209 # In fact it works even with dummy cpn.
1210 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1211 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1217 playback_url = compat_urlparse.urlunparse(
1218 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1220 self._download_webpage(
1221 playback_url, video_id, 'Marking watched',
1222 'Unable to mark watched', fatal=False)
1225 def extract_id(cls, url):
1226 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1228 raise ExtractorError('Invalid URL: %s' % url)
1229 video_id = mobj.group(2)
1232 def _extract_from_m3u8(self, manifest_url, video_id):
1235 def _get_urls(_manifest):
1236 lines = _manifest.split('\n')
1237 urls = filter(lambda l: l and not l.startswith('#'),
1240 manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
1241 formats_urls = _get_urls(manifest)
1242 for format_url in formats_urls:
1243 itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
1244 url_map[itag] = format_url
1247 def _extract_annotations(self, video_id):
1248 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1249 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1251 def _real_extract(self, url):
1252 url, smuggled_data = unsmuggle_url(url, {})
1255 'http' if self._downloader.params.get('prefer_insecure', False)
1260 parsed_url = compat_urllib_parse_urlparse(url)
1261 for component in [parsed_url.fragment, parsed_url.query]:
1262 query = compat_parse_qs(component)
1263 if start_time is None and 't' in query:
1264 start_time = parse_duration(query['t'][0])
1265 if start_time is None and 'start' in query:
1266 start_time = parse_duration(query['start'][0])
1267 if end_time is None and 'end' in query:
1268 end_time = parse_duration(query['end'][0])
1270 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1271 mobj = re.search(self._NEXT_URL_RE, url)
1273 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1274 video_id = self.extract_id(url)
1277 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1278 video_webpage = self._download_webpage(url, video_id)
1280 # Attempt to extract SWF player URL
1281 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1282 if mobj is not None:
1283 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1289 def add_dash_mpd(video_info):
1290 dash_mpd = video_info.get('dashmpd')
1291 if dash_mpd and dash_mpd[0] not in dash_mpds:
1292 dash_mpds.append(dash_mpd[0])
1295 embed_webpage = None
1297 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1299 # We simulate the access to the video from www.youtube.com/v/{video_id}
1300 # this can be viewed without login into Youtube
1301 url = proto + '://www.youtube.com/embed/%s' % video_id
1302 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1303 data = compat_urllib_parse_urlencode({
1304 'video_id': video_id,
1305 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1306 'sts': self._search_regex(
1307 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1309 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1310 video_info_webpage = self._download_webpage(
1311 video_info_url, video_id,
1312 note='Refetching age-gated info webpage',
1313 errnote='unable to download video info webpage')
1314 video_info = compat_parse_qs(video_info_webpage)
1315 add_dash_mpd(video_info)
1319 # Try looking directly into the video webpage
1320 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1322 args = ytplayer_config['args']
1323 if args.get('url_encoded_fmt_stream_map'):
1324 # Convert to the same format returned by compat_parse_qs
1325 video_info = dict((k, [v]) for k, v in args.items())
1326 add_dash_mpd(video_info)
1327 # Rental video is not rented but preview is available (e.g.
1328 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1329 # https://github.com/rg3/youtube-dl/issues/10532)
1330 if not video_info and args.get('ypc_vid'):
1331 return self.url_result(
1332 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1333 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1335 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1336 # We also try looking in get_video_info since it may contain different dashmpd
1337 # URL that points to a DASH manifest with possibly different itag set (some itags
1338 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1339 # manifest pointed by get_video_info's dashmpd).
1340 # The general idea is to take a union of itags of both DASH manifests (for example
1341 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1342 self.report_video_info_webpage_download(video_id)
1343 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1345 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1346 % (proto, video_id, el_type))
1347 video_info_webpage = self._download_webpage(
1349 video_id, note=False,
1350 errnote='unable to download video info webpage')
1351 get_video_info = compat_parse_qs(video_info_webpage)
1352 if get_video_info.get('use_cipher_signature') != ['True']:
1353 add_dash_mpd(get_video_info)
1355 video_info = get_video_info
1356 if 'token' in get_video_info:
1357 # Different get_video_info requests may report different results, e.g.
1358 # some may report video unavailability, but some may serve it without
1359 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1360 # the original webpage as well as el=info and el=embedded get_video_info
1361 # requests report video unavailability due to geo restriction while
1362 # el=detailpage succeeds and returns valid data). This is probably
1363 # due to YouTube measures against IP ranges of hosting providers.
1364 # Working around by preferring the first succeeded video_info containing
1365 # the token if no such video_info yet was found.
1366 if 'token' not in video_info:
1367 video_info = get_video_info
1369 if 'token' not in video_info:
1370 if 'reason' in video_info:
1371 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1372 regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
1374 raise ExtractorError('YouTube said: This video is available in %s only' % (
1375 ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
1377 raise ExtractorError(
1378 'YouTube said: %s' % video_info['reason'][0],
1379 expected=True, video_id=video_id)
1381 raise ExtractorError(
1382 '"token" parameter not in video info for unknown reason',
1386 if 'title' in video_info:
1387 video_title = video_info['title'][0]
1389 self._downloader.report_warning('Unable to extract video title')
1393 video_description = get_element_by_id("eow-description", video_webpage)
1394 if video_description:
1395 video_description = re.sub(r'''(?x)
1397 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1398 (?:title|href)="([^"]+)"\s+
1399 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1403 ''', r'\1', video_description)
1404 video_description = clean_html(video_description)
1406 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1408 video_description = unescapeHTML(fd_mobj.group(1))
1410 video_description = ''
1412 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1413 if not self._downloader.params.get('noplaylist'):
1416 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
1417 for feed in multifeed_metadata_list.split(','):
1418 # Unquote should take place before split on comma (,) since textual
1419 # fields may contain comma as well (see
1420 # https://github.com/rg3/youtube-dl/issues/8536)
1421 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1423 '_type': 'url_transparent',
1424 'ie_key': 'Youtube',
1426 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1427 {'force_singlefeed': True}),
1428 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1430 feed_ids.append(feed_data['id'][0])
1432 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1433 % (', '.join(feed_ids), video_id))
1434 return self.playlist_result(entries, video_id, video_title, video_description)
1435 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1437 if 'view_count' in video_info:
1438 view_count = int(video_info['view_count'][0])
1442 # Check for "rental" videos
1443 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1444 raise ExtractorError('"rental" videos not supported')
1446 # Start extracting information
1447 self.report_information_extraction(video_id)
1450 if 'author' not in video_info:
1451 raise ExtractorError('Unable to extract uploader name')
1452 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
1455 video_uploader_id = None
1456 video_uploader_url = None
1458 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1460 if mobj is not None:
1461 video_uploader_id = mobj.group('uploader_id')
1462 video_uploader_url = mobj.group('uploader_url')
1464 self._downloader.report_warning('unable to extract uploader nickname')
1467 # We try first to get a high quality image:
1468 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1469 video_webpage, re.DOTALL)
1470 if m_thumb is not None:
1471 video_thumbnail = m_thumb.group(1)
1472 elif 'thumbnail_url' not in video_info:
1473 self._downloader.report_warning('unable to extract video thumbnail')
1474 video_thumbnail = None
1475 else: # don't panic if we can't find it
1476 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1479 upload_date = self._html_search_meta(
1480 'datePublished', video_webpage, 'upload date', default=None)
1482 upload_date = self._search_regex(
1483 [r'(?s)id="eow-date.*?>(.*?)</span>',
1484 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1485 video_webpage, 'upload date', default=None)
1487 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1488 upload_date = unified_strdate(upload_date)
1490 video_license = self._html_search_regex(
1491 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1492 video_webpage, 'license', default=None)
1494 m_music = re.search(
1495 r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1498 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1499 video_creator = clean_html(m_music.group('creator'))
1501 video_alt_title = video_creator = None
1503 m_episode = re.search(
1504 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1507 series = m_episode.group('series')
1508 season_number = int(m_episode.group('season'))
1509 episode_number = int(m_episode.group('episode'))
1511 series = season_number = episode_number = None
1513 m_cat_container = self._search_regex(
1514 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1515 video_webpage, 'categories', default=None)
1517 category = self._html_search_regex(
1518 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
1520 video_categories = None if category is None else [category]
1522 video_categories = None
1525 unescapeHTML(m.group('content'))
1526 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1528 def _extract_count(count_name):
1529 return str_to_int(self._search_regex(
1530 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1531 % re.escape(count_name),
1532 video_webpage, count_name, default=None))
1534 like_count = _extract_count('like')
1535 dislike_count = _extract_count('dislike')
1538 video_subtitles = self.extract_subtitles(video_id, video_webpage)
1539 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
1541 video_duration = try_get(
1542 video_info, lambda x: int_or_none(x['length_seconds'][0]))
1543 if not video_duration:
1544 video_duration = parse_duration(self._html_search_meta(
1545 'duration', video_webpage, 'video duration'))
1548 video_annotations = None
1549 if self._downloader.params.get('writeannotations', False):
1550 video_annotations = self._extract_annotations(video_id)
1552 def _map_to_format_list(urlmap):
1554 for itag, video_real_url in urlmap.items():
1557 'url': video_real_url,
1558 'player_url': player_url,
1560 if itag in self._formats:
1561 dct.update(self._formats[itag])
1565 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1566 self.report_rtmp_download()
1568 'format_id': '_rtmp',
1570 'url': video_info['conn'][0],
1571 'player_url': player_url,
1573 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
1574 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1575 if 'rtmpe%3Dyes' in encoded_url_map:
1576 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
1578 fmt_list = video_info.get('fmt_list', [''])[0]
1580 for fmt in fmt_list.split(','):
1581 spec = fmt.split('/')
1583 width_height = spec[1].split('x')
1584 if len(width_height) == 2:
1585 formats_spec[spec[0]] = {
1586 'resolution': spec[1],
1587 'width': int_or_none(width_height[0]),
1588 'height': int_or_none(width_height[1]),
1591 for url_data_str in encoded_url_map.split(','):
1592 url_data = compat_parse_qs(url_data_str)
1593 if 'itag' not in url_data or 'url' not in url_data:
1595 format_id = url_data['itag'][0]
1596 url = url_data['url'][0]
1598 if 'sig' in url_data:
1599 url += '&signature=' + url_data['sig'][0]
1600 elif 's' in url_data:
1601 encrypted_sig = url_data['s'][0]
1602 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1604 jsplayer_url_json = self._search_regex(
1606 embed_webpage if age_gate else video_webpage,
1607 'JS player URL (1)', default=None)
1608 if not jsplayer_url_json and not age_gate:
1609 # We need the embed website after all
1610 if embed_webpage is None:
1611 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1612 embed_webpage = self._download_webpage(
1613 embed_url, video_id, 'Downloading embed webpage')
1614 jsplayer_url_json = self._search_regex(
1615 ASSETS_RE, embed_webpage, 'JS player URL')
1617 player_url = json.loads(jsplayer_url_json)
1618 if player_url is None:
1619 player_url_json = self._search_regex(
1620 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1621 video_webpage, 'age gate player URL')
1622 player_url = json.loads(player_url_json)
1624 if self._downloader.params.get('verbose'):
1625 if player_url is None:
1626 player_version = 'unknown'
1627 player_desc = 'unknown'
1629 if player_url.endswith('swf'):
1630 player_version = self._search_regex(
1631 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1632 'flash player', fatal=False)
1633 player_desc = 'flash player %s' % player_version
1635 player_version = self._search_regex(
1636 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
1638 'html5 player', fatal=False)
1639 player_desc = 'html5 player %s' % player_version
1641 parts_sizes = self._signature_cache_id(encrypted_sig)
1642 self.to_screen('{%s} signature length %s, %s' %
1643 (format_id, parts_sizes, player_desc))
1645 signature = self._decrypt_signature(
1646 encrypted_sig, video_id, player_url, age_gate)
1647 url += '&signature=' + signature
1648 if 'ratebypass' not in url:
1649 url += '&ratebypass=yes'
1652 'format_id': format_id,
1654 'player_url': player_url,
1656 if format_id in self._formats:
1657 dct.update(self._formats[format_id])
1658 if format_id in formats_spec:
1659 dct.update(formats_spec[format_id])
1661 # Some itags are not included in DASH manifest thus corresponding formats will
1662 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1663 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1664 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1665 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
1668 'filesize': int_or_none(url_data.get('clen', [None])[0]),
1669 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
1672 'fps': int_or_none(url_data.get('fps', [None])[0]),
1673 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
1675 for key, value in more_fields.items():
1678 type_ = url_data.get('type', [None])[0]
1680 type_split = type_.split(';')
1681 kind_ext = type_split[0].split('/')
1682 if len(kind_ext) == 2:
1684 dct['ext'] = mimetype2ext(type_split[0])
1685 if kind in ('audio', 'video'):
1687 for mobj in re.finditer(
1688 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1689 if mobj.group('key') == 'codecs':
1690 codecs = mobj.group('val')
1693 codecs = codecs.split(',')
1694 if len(codecs) == 2:
1695 acodec, vcodec = codecs[1], codecs[0]
1697 acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
1703 elif video_info.get('hlsvp'):
1704 manifest_url = video_info['hlsvp'][0]
1705 url_map = self._extract_from_m3u8(manifest_url, video_id)
1706 formats = _map_to_format_list(url_map)
1707 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1708 for a_format in formats:
1709 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1711 unavailable_message = self._html_search_regex(
1712 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1713 video_webpage, 'unavailable message', default=None)
1714 if unavailable_message:
1715 raise ExtractorError(unavailable_message, expected=True)
1716 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
1718 # Look for the DASH manifest
1719 if self._downloader.params.get('youtube_include_dash_manifest', True):
1720 dash_mpd_fatal = True
1721 for mpd_url in dash_mpds:
1724 def decrypt_sig(mobj):
1726 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1727 return '/signature/%s' % dec_s
1729 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
1731 for df in self._extract_mpd_formats(
1732 mpd_url, video_id, fatal=dash_mpd_fatal,
1733 formats_dict=self._formats):
1734 # Do not overwrite DASH format found in some previous DASH manifest
1735 if df['format_id'] not in dash_formats:
1736 dash_formats[df['format_id']] = df
1737 # Additional DASH manifests may end up in HTTP Error 403 therefore
1738 # allow them to fail without bug report message if we already have
1739 # some DASH manifest succeeded. This is temporary workaround to reduce
1740 # burst of bug reports until we figure out the reason and whether it
1741 # can be fixed at all.
1742 dash_mpd_fatal = False
1743 except (ExtractorError, KeyError) as e:
1744 self.report_warning(
1745 'Skipping DASH manifest: %r' % e, video_id)
1747 # Remove the formats we found through non-DASH, they
1748 # contain less info and it can be wrong, because we use
1749 # fixed values (for example the resolution). See
1750 # https://github.com/rg3/youtube-dl/issues/5774 for an
1752 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
1753 formats.extend(dash_formats.values())
1755 # Check for malformed aspect ratio
1756 stretched_m = re.search(
1757 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1760 w = float(stretched_m.group('w'))
1761 h = float(stretched_m.group('h'))
1762 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1763 # We will only process correct ratios.
1767 if f.get('vcodec') != 'none':
1768 f['stretched_ratio'] = ratio
1770 self._sort_formats(formats)
1772 self.mark_watched(video_id, video_info)
1776 'uploader': video_uploader,
1777 'uploader_id': video_uploader_id,
1778 'uploader_url': video_uploader_url,
1779 'upload_date': upload_date,
1780 'license': video_license,
1781 'creator': video_creator,
1782 'title': video_title,
1783 'alt_title': video_alt_title,
1784 'thumbnail': video_thumbnail,
1785 'description': video_description,
1786 'categories': video_categories,
1788 'subtitles': video_subtitles,
1789 'automatic_captions': automatic_captions,
1790 'duration': video_duration,
1791 'age_limit': 18 if age_gate else 0,
1792 'annotations': video_annotations,
1793 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
1794 'view_count': view_count,
1795 'like_count': like_count,
1796 'dislike_count': dislike_count,
1797 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
1800 'start_time': start_time,
1801 'end_time': end_time,
1803 'season_number': season_number,
1804 'episode_number': episode_number,
1808 class YoutubeSharedVideoIE(InfoExtractor):
1809 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
1810 IE_NAME = 'youtube:shared'
1813 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1815 'id': 'uPDB5I9wfp8',
1817 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1818 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1819 'upload_date': '20160219',
1820 'uploader': 'Pocoyo - Português (BR)',
1821 'uploader_id': 'PocoyoBrazil',
1823 'add_ie': ['Youtube'],
1825 # There are already too many Youtube downloads
1826 'skip_download': True,
1830 def _real_extract(self, url):
1831 video_id = self._match_id(url)
1833 webpage = self._download_webpage(url, video_id)
1835 real_video_id = self._html_search_meta(
1836 'videoId', webpage, 'YouTube video id', fatal=True)
1838 return self.url_result(real_video_id, YoutubeIE.ie_key())
1841 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1842 IE_DESC = 'YouTube.com playlists'
1843 _VALID_URL = r"""(?x)(?:
1849 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1850 \? (?:.*?[&;])*? (?:p|a|list)=
1853 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1856 (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
1857 # Top tracks, they can also include dots
1862 ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
1864 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
1865 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
1866 IE_NAME = 'youtube:playlist'
1868 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1870 'title': 'ytdl test PL',
1871 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1873 'playlist_count': 3,
1875 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1877 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1878 'title': 'YDL_Empty_List',
1880 'playlist_count': 0,
1881 'skip': 'This playlist is private',
1883 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1884 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1886 'title': '29C3: Not my department',
1887 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1889 'playlist_count': 95,
1891 'note': 'issue #673',
1892 'url': 'PLBB231211A4F62143',
1894 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1895 'id': 'PLBB231211A4F62143',
1897 'playlist_mincount': 26,
1899 'note': 'Large playlist',
1900 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1902 'title': 'Uploads from Cauchemar',
1903 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1905 'playlist_mincount': 799,
1907 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1909 'title': 'YDL_safe_search',
1910 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1912 'playlist_count': 2,
1913 'skip': 'This playlist is private',
1916 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1917 'playlist_count': 4,
1920 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1923 'note': 'Embedded SWF player',
1924 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1925 'playlist_count': 4,
1928 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1931 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1932 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1934 'title': 'Uploads from Interstellar Movie',
1935 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1937 'playlist_mincount': 21,
1939 # Playlist URL that does not actually serve a playlist
1940 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1942 'id': 'FqZTN594JQw',
1944 'title': "Smiley's People 01 detective, Adventure Series, Action",
1945 'uploader': 'STREEM',
1946 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1947 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1948 'upload_date': '20150526',
1949 'license': 'Standard YouTube License',
1950 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1951 'categories': ['People & Blogs'],
1954 'dislike_count': int,
1957 'skip_download': True,
1959 'add_ie': [YoutubeIE.ie_key()],
1961 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1963 'id': 'yeWKywCrFtk',
1965 'title': 'Small Scale Baler and Braiding Rugs',
1966 'uploader': 'Backus-Page House Museum',
1967 'uploader_id': 'backuspagemuseum',
1968 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1969 'upload_date': '20161008',
1970 'license': 'Standard YouTube License',
1971 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1972 'categories': ['Nonprofits & Activism'],
1975 'dislike_count': int,
1979 'skip_download': True,
1982 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1983 'only_matching': True,
1986 def _real_initialize(self):
1989 def _extract_mix(self, playlist_id):
1990 # The mixes are generated from a single video
1991 # the id of the playlist is just 'RD' + video_id
1993 last_id = playlist_id[-11:]
1994 for n in itertools.count(1):
1995 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
1996 webpage = self._download_webpage(
1997 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
1998 new_ids = orderedSet(re.findall(
1999 r'''(?xs)data-video-username=".*?".*?
2000 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2002 # Fetch new pages until all the videos are repeated, it seems that
2003 # there are always 51 unique videos.
2004 new_ids = [_id for _id in new_ids if _id not in ids]
2010 url_results = self._ids_to_results(ids)
2012 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2014 search_title('playlist-title') or
2015 search_title('title long-title') or
2016 search_title('title'))
2017 title = clean_html(title_span)
2019 return self.playlist_result(url_results, playlist_id, title)
2021 def _extract_playlist(self, playlist_id):
2022 url = self._TEMPLATE_URL % playlist_id
2023 page = self._download_webpage(url, playlist_id)
2025 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2026 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2027 match = match.strip()
2028 # Check if the playlist exists or is private
2029 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2031 reason = mobj.group('reason')
2032 message = 'This playlist %s' % reason
2033 if 'private' in reason:
2034 message += ', use --username or --netrc to access it'
2036 raise ExtractorError(message, expected=True)
2037 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2038 raise ExtractorError(
2039 'Invalid parameters. Maybe URL is incorrect.',
2041 elif re.match(r'[^<]*Choose your language[^<]*', match):
2044 self.report_warning('Youtube gives an alert message: ' + match)
2046 playlist_title = self._html_search_regex(
2047 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2048 page, 'title', default=None)
2052 if not playlist_title:
2054 # Some playlist URLs don't actually serve a playlist (e.g.
2055 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2056 next(self._entries(page, playlist_id))
2057 except StopIteration:
2060 return has_videos, self.playlist_result(
2061 self._entries(page, playlist_id), playlist_id, playlist_title)
2063 def _check_download_just_video(self, url, playlist_id):
2064 # Check if it's a video-specific URL
2065 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2066 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2067 r'(?:^|//)youtu\.be/([0-9A-Za-z_-]{11})', url,
2068 'video id', default=None)
2070 if self._downloader.params.get('noplaylist'):
2071 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2072 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2074 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2075 return video_id, None
2078 def _real_extract(self, url):
2079 # Extract playlist id
2080 mobj = re.match(self._VALID_URL, url)
2082 raise ExtractorError('Invalid URL: %s' % url)
2083 playlist_id = mobj.group(1) or mobj.group(2)
2085 video_id, video = self._check_download_just_video(url, playlist_id)
2089 if playlist_id.startswith(('RD', 'UL', 'PU')):
2090 # Mixes require a custom extraction process
2091 return self._extract_mix(playlist_id)
2093 has_videos, playlist = self._extract_playlist(playlist_id)
2094 if has_videos or not video_id:
2097 # Some playlist URLs don't actually serve a playlist (see
2098 # https://github.com/rg3/youtube-dl/issues/10537).
2099 # Fallback to plain video extraction if there is a video id
2100 # along with playlist id.
2101 return self.url_result(video_id, 'Youtube', video_id=video_id)
2104 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2105 IE_DESC = 'YouTube.com channels'
2106 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2107 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2108 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2109 IE_NAME = 'youtube:channel'
2111 'note': 'paginated channel',
2112 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2113 'playlist_mincount': 91,
2115 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2116 'title': 'Uploads from lex will',
2119 'note': 'Age restricted channel',
2120 # from https://www.youtube.com/user/DeusExOfficial
2121 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2122 'playlist_mincount': 64,
2124 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2125 'title': 'Uploads from Deus Ex',
2130 def suitable(cls, url):
2131 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2132 else super(YoutubeChannelIE, cls).suitable(url))
2134 def _build_template_url(self, url, channel_id):
2135 return self._TEMPLATE_URL % channel_id
2137 def _real_extract(self, url):
2138 channel_id = self._match_id(url)
2140 url = self._build_template_url(url, channel_id)
2142 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2143 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2144 # otherwise fallback on channel by page extraction
2145 channel_page = self._download_webpage(
2146 url + '?view=57', channel_id,
2147 'Downloading channel page', fatal=False)
2148 if channel_page is False:
2149 channel_playlist_id = False
2151 channel_playlist_id = self._html_search_meta(
2152 'channelId', channel_page, 'channel id', default=None)
2153 if not channel_playlist_id:
2154 channel_url = self._html_search_meta(
2155 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2156 channel_page, 'channel url', default=None)
2158 channel_playlist_id = self._search_regex(
2159 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2160 channel_url, 'channel id', default=None)
2161 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2162 playlist_id = 'UU' + channel_playlist_id[2:]
2163 return self.url_result(
2164 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2166 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2167 autogenerated = re.search(r'''(?x)
2169 channel-header-autogenerated-label|
2170 yt-channel-title-autogenerated
2171 )[^"]*"''', channel_page) is not None
2174 # The videos are contained in a single page
2175 # the ajax pages can't be used, they are empty
2178 video_id, 'Youtube', video_id=video_id,
2179 video_title=video_title)
2180 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2181 return self.playlist_result(entries, channel_id)
2184 next(self._entries(channel_page, channel_id))
2185 except StopIteration:
2186 alert_message = self._html_search_regex(
2187 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2188 channel_page, 'alert', default=None, group='alert')
2190 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2192 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2195 class YoutubeUserIE(YoutubeChannelIE):
2196 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2197 _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_-]+)'
2198 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2199 IE_NAME = 'youtube:user'
2202 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2203 'playlist_mincount': 320,
2205 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2206 'title': 'Uploads from The Linux Foundation',
2209 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2210 # but not https://www.youtube.com/user/12minuteathlete/videos
2211 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2212 'playlist_mincount': 249,
2214 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2215 'title': 'Uploads from 12 Minute Athlete',
2218 'url': 'ytuser:phihag',
2219 'only_matching': True,
2221 'url': 'https://www.youtube.com/c/gametrailers',
2222 'only_matching': True,
2224 'url': 'https://www.youtube.com/gametrailers',
2225 'only_matching': True,
2227 # This channel is not available.
2228 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2229 'only_matching': True,
2233 def suitable(cls, url):
2234 # Don't return True if the url can be extracted with other youtube
2235 # extractor, the regex would is too permissive and it would match.
2236 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2237 if any(ie.suitable(url) for ie in other_yt_ies):
2240 return super(YoutubeUserIE, cls).suitable(url)
2242 def _build_template_url(self, url, channel_id):
2243 mobj = re.match(self._VALID_URL, url)
2244 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2247 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2248 IE_DESC = 'YouTube.com live streams'
2249 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2250 IE_NAME = 'youtube:live'
2253 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2255 'id': 'a48o2S1cPoo',
2257 'title': 'The Young Turks - Live Main Show',
2258 'uploader': 'The Young Turks',
2259 'uploader_id': 'TheYoungTurks',
2260 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2261 'upload_date': '20150715',
2262 'license': 'Standard YouTube License',
2263 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2264 'categories': ['News & Politics'],
2265 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2267 'dislike_count': int,
2270 'skip_download': True,
2273 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2274 'only_matching': True,
2276 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2277 'only_matching': True,
2279 'url': 'https://www.youtube.com/TheYoungTurks/live',
2280 'only_matching': True,
2283 def _real_extract(self, url):
2284 mobj = re.match(self._VALID_URL, url)
2285 channel_id = mobj.group('id')
2286 base_url = mobj.group('base_url')
2287 webpage = self._download_webpage(url, channel_id, fatal=False)
2289 page_type = self._og_search_property(
2290 'type', webpage, 'page type', default=None)
2291 video_id = self._html_search_meta(
2292 'videoId', webpage, 'video id', default=None)
2293 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2294 return self.url_result(video_id, YoutubeIE.ie_key())
2295 return self.url_result(base_url)
2298 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2299 IE_DESC = 'YouTube.com user/channel playlists'
2300 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2301 IE_NAME = 'youtube:playlists'
2304 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2305 'playlist_mincount': 4,
2307 'id': 'ThirstForScience',
2308 'title': 'Thirst for Science',
2311 # with "Load more" button
2312 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2313 'playlist_mincount': 70,
2316 'title': 'Игорь Клейнер',
2319 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2320 'playlist_mincount': 17,
2322 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2323 'title': 'Chem Player',
2328 class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
2329 IE_DESC = 'YouTube.com searches'
2330 # there doesn't appear to be a real limit, for example if you search for
2331 # 'python' you get more than 8.000.000 results
2332 _MAX_RESULTS = float('inf')
2333 IE_NAME = 'youtube:search'
2334 _SEARCH_KEY = 'ytsearch'
2335 _EXTRA_QUERY_ARGS = {}
2338 def _get_n_results(self, query, n):
2339 """Get a specified number of results for a query"""
2344 for pagenum in itertools.count(1):
2346 'search_query': query.encode('utf-8'),
2350 url_query.update(self._EXTRA_QUERY_ARGS)
2351 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2352 data = self._download_json(
2353 result_url, video_id='query "%s"' % query,
2354 note='Downloading page %s' % pagenum,
2355 errnote='Unable to download API page')
2356 html_content = data[1]['body']['content']
2358 if 'class="search-message' in html_content:
2359 raise ExtractorError(
2360 '[youtube] No video results', expected=True)
2362 new_videos = self._ids_to_results(orderedSet(re.findall(
2363 r'href="/watch\?v=(.{11})', html_content)))
2364 videos += new_videos
2365 if not new_videos or len(videos) > limit:
2370 return self.playlist_result(videos, query)
2373 class YoutubeSearchDateIE(YoutubeSearchIE):
2374 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2375 _SEARCH_KEY = 'ytsearchdate'
2376 IE_DESC = 'YouTube.com searches, newest videos first'
2377 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2380 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
2381 IE_DESC = 'YouTube.com search URLs'
2382 IE_NAME = 'youtube:search_url'
2383 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2384 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2386 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2387 'playlist_mincount': 5,
2389 'title': 'youtube-dl test video',
2392 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2393 'only_matching': True,
2396 def _real_extract(self, url):
2397 mobj = re.match(self._VALID_URL, url)
2398 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2399 webpage = self._download_webpage(url, query)
2400 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2403 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2404 IE_DESC = 'YouTube.com (multi-season) shows'
2405 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2406 IE_NAME = 'youtube:show'
2408 'url': 'https://www.youtube.com/show/airdisasters',
2409 'playlist_mincount': 5,
2411 'id': 'airdisasters',
2412 'title': 'Air Disasters',
2416 def _real_extract(self, url):
2417 playlist_id = self._match_id(url)
2418 return super(YoutubeShowIE, self)._real_extract(
2419 'https://www.youtube.com/show/%s/playlists' % playlist_id)
2422 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
2424 Base class for feed extractors
2425 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2427 _LOGIN_REQUIRED = True
2431 return 'youtube:%s' % self._FEED_NAME
2433 def _real_initialize(self):
2436 def _real_extract(self, url):
2437 page = self._download_webpage(
2438 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2440 # The extraction process is the same as for playlists, but the regex
2441 # for the video ids doesn't contain an index
2443 more_widget_html = content_html = page
2444 for page_num in itertools.count(1):
2445 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
2447 # 'recommended' feed has infinite 'load more' and each new portion spins
2448 # the same videos in (sometimes) slightly different order, so we'll check
2449 # for unicity and break when portion has no new videos
2450 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2456 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2460 more = self._download_json(
2461 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2462 'Downloading page #%s' % page_num,
2463 transform_source=uppercase_escape)
2464 content_html = more['content_html']
2465 more_widget_html = more['load_more_widget_html']
2467 return self.playlist_result(
2468 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2471 class YoutubeWatchLaterIE(YoutubePlaylistIE):
2472 IE_NAME = 'youtube:watchlater'
2473 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2474 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2477 'url': 'https://www.youtube.com/playlist?list=WL',
2478 'only_matching': True,
2480 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2481 'only_matching': True,
2484 def _real_extract(self, url):
2485 _, video = self._check_download_just_video(url, 'WL')
2488 _, playlist = self._extract_playlist('WL')
2492 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
2493 IE_NAME = 'youtube:favorites'
2494 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2495 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2496 _LOGIN_REQUIRED = True
2498 def _real_extract(self, url):
2499 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2500 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
2501 return self.url_result(playlist_id, 'YoutubePlaylist')
2504 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2505 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2506 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2507 _FEED_NAME = 'recommended'
2508 _PLAYLIST_TITLE = 'Youtube Recommended videos'
2511 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2512 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2513 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2514 _FEED_NAME = 'subscriptions'
2515 _PLAYLIST_TITLE = 'Youtube Subscriptions'
2518 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2519 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
2520 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2521 _FEED_NAME = 'history'
2522 _PLAYLIST_TITLE = 'Youtube History'
2525 class YoutubeTruncatedURLIE(InfoExtractor):
2526 IE_NAME = 'youtube:truncated_url'
2527 IE_DESC = False # Do not list
2528 _VALID_URL = r'''(?x)
2530 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2533 annotation_id=annotation_[^&]+|
2539 attribution_link\?a=[^&]+
2545 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2546 'only_matching': True,
2548 'url': 'https://www.youtube.com/watch?',
2549 'only_matching': True,
2551 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2552 'only_matching': True,
2554 'url': 'https://www.youtube.com/watch?feature=foo',
2555 'only_matching': True,
2557 'url': 'https://www.youtube.com/watch?hl=en-GB',
2558 'only_matching': True,
2560 'url': 'https://www.youtube.com/watch?t=2372',
2561 'only_matching': True,
2564 def _real_extract(self, url):
2565 raise ExtractorError(
2566 'Did you forget to quote the URL? Remember that & is a meta '
2567 'character in most shells, so you want to put the URL in quotes, '
2569 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2570 ' or simply youtube-dl BaW_jenozKc .',
2574 class YoutubeTruncatedIDIE(InfoExtractor):
2575 IE_NAME = 'youtube:truncated_id'
2576 IE_DESC = False # Do not list
2577 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2580 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2581 'only_matching': True,
2584 def _real_extract(self, url):
2585 video_id = self._match_id(url)
2586 raise ExtractorError(
2587 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),