3 from __future__ import unicode_literals
13 from .common import InfoExtractor, SearchInfoExtractor
14 from ..jsinterp import JSInterpreter
15 from ..swfinterp import SWFInterpreter
16 from ..compat import (
20 compat_urllib_parse_unquote,
21 compat_urllib_parse_unquote_plus,
22 compat_urllib_parse_urlparse,
23 compat_urllib_request,
32 get_element_by_attribute,
48 class YoutubeBaseInfoExtractor(InfoExtractor):
49 """Provide base functions for Youtube extractors"""
50 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
51 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
52 _NETRC_MACHINE = 'youtube'
53 # If True it will raise an error if no login info is provided
54 _LOGIN_REQUIRED = False
56 def _set_language(self):
58 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
59 # YouTube sets the expire time to about two months
60 expire_time=time.time() + 2 * 30 * 24 * 3600)
62 def _ids_to_results(self, ids):
64 self.url_result(vid_id, 'Youtube', video_id=vid_id)
69 Attempt to log in to YouTube.
70 True is returned if successful or skipped.
71 False is returned if login failed.
73 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
75 (username, password) = self._get_login_info()
76 # No authentication to be performed
78 if self._LOGIN_REQUIRED:
79 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
82 login_page = self._download_webpage(
83 self._LOGIN_URL, None,
84 note='Downloading login page',
85 errnote='unable to fetch login page', fatal=False)
86 if login_page is False:
89 galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"',
90 login_page, 'Login GALX parameter')
94 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
99 'PersistentCookie': 'yes',
101 'bgresponse': 'js_disabled',
102 'checkConnection': '',
103 'checkedDomains': 'youtube',
110 'service': 'youtube',
115 login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('ascii')
117 req = compat_urllib_request.Request(self._LOGIN_URL, login_data)
118 login_results = self._download_webpage(
120 note='Logging in', errnote='unable to log in', fatal=False)
121 if login_results is False:
124 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
125 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
128 # TODO add SMS and phone call support - these require making a request and then prompting the user
130 if re.search(r'(?i)<form[^>]* id="challenge"', login_results) is not None:
131 tfa_code = self._get_tfa_info('2-step verification code')
134 self._downloader.report_warning(
135 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
136 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
139 tfa_code = remove_start(tfa_code, 'G-')
141 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
143 tfa_form_strs.update({
148 tfa_data = compat_urllib_parse.urlencode(encode_dict(tfa_form_strs)).encode('ascii')
150 tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
151 tfa_results = self._download_webpage(
153 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
155 if tfa_results is False:
158 if re.search(r'(?i)<form[^>]* id="challenge"', tfa_results) is not None:
159 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
161 if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
162 self._downloader.report_warning('unable to log in - did the page structure change?')
164 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
165 self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
168 if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
169 self._downloader.report_warning('unable to log in: bad username or password')
173 def _real_initialize(self):
174 if self._downloader is None:
177 if not self._login():
181 class YoutubePlaylistBaseInfoExtractor(InfoExtractor):
182 # Extract the video ids from the playlist pages
183 def _entries(self, page, playlist_id):
184 more_widget_html = content_html = page
185 for page_num in itertools.count(1):
186 for video_id, video_title in self.extract_videos_from_page(content_html):
187 yield self.url_result(
188 video_id, 'Youtube', video_id=video_id,
189 video_title=video_title)
191 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
195 more = self._download_json(
196 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
197 'Downloading page #%s' % page_num,
198 transform_source=uppercase_escape)
199 content_html = more['content_html']
200 if not content_html.strip():
201 # Some webpages show a "Load more" button but they don't
204 more_widget_html = more['load_more_widget_html']
206 def extract_videos_from_page(self, page):
209 for mobj in re.finditer(self._VIDEO_RE, page):
210 # The link with index 0 is not the first video of the playlist (not sure if still actual)
211 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
213 video_id = mobj.group('id')
214 video_title = unescapeHTML(mobj.group('title'))
216 video_title = video_title.strip()
218 idx = ids_in_page.index(video_id)
219 if video_title and not titles_in_page[idx]:
220 titles_in_page[idx] = video_title
222 ids_in_page.append(video_id)
223 titles_in_page.append(video_title)
224 return zip(ids_in_page, titles_in_page)
227 class YoutubeIE(YoutubeBaseInfoExtractor):
228 IE_DESC = 'YouTube.com'
229 _VALID_URL = r"""(?x)^
231 (?:https?://|//) # http(s):// or protocol-independent URL
232 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
233 (?:www\.)?deturl\.com/www\.youtube\.com/|
234 (?:www\.)?pwnyoutube\.com/|
235 (?:www\.)?yourepeat\.com/|
236 tube\.majestyc\.net/|
237 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
238 (?:.*?\#/)? # handle anchor (#/) redirect urls
239 (?: # the various things that can precede the ID:
240 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
241 |(?: # or the v= param in all its forms
242 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
243 (?:\?|\#!?) # the params delimiter ? or # or #!
244 (?:.*?&)?? # any other preceding param (like /?s=tuff&v=xxxx)
249 youtu\.be| # just youtu.be/xxxx
250 vid\.plus # or vid.plus/xxxx
252 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
254 )? # all until now is optional -> you can pass the naked ID
255 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
256 (?!.*?&list=) # combined list/video URLs are handled by the playlist IE
257 (?(1).+)? # if we found the ID, everything can follow
259 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
261 '5': {'ext': 'flv', 'width': 400, 'height': 240},
262 '6': {'ext': 'flv', 'width': 450, 'height': 270},
263 '13': {'ext': '3gp'},
264 '17': {'ext': '3gp', 'width': 176, 'height': 144},
265 '18': {'ext': 'mp4', 'width': 640, 'height': 360},
266 '22': {'ext': 'mp4', 'width': 1280, 'height': 720},
267 '34': {'ext': 'flv', 'width': 640, 'height': 360},
268 '35': {'ext': 'flv', 'width': 854, 'height': 480},
269 '36': {'ext': '3gp', 'width': 320, 'height': 240},
270 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080},
271 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072},
272 '43': {'ext': 'webm', 'width': 640, 'height': 360},
273 '44': {'ext': 'webm', 'width': 854, 'height': 480},
274 '45': {'ext': 'webm', 'width': 1280, 'height': 720},
275 '46': {'ext': 'webm', 'width': 1920, 'height': 1080},
276 '59': {'ext': 'mp4', 'width': 854, 'height': 480},
277 '78': {'ext': 'mp4', 'width': 854, 'height': 480},
281 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20},
282 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20},
283 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20},
284 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20},
285 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20},
286 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20},
287 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20},
289 # Apple HTTP Live Streaming
290 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10},
291 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10},
292 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10},
293 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10},
294 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10},
295 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10},
296 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10},
299 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
300 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
301 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
302 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
303 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
304 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
305 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
306 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
307 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'},
308 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'},
309 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'},
312 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
313 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
314 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
317 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
318 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
319 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
320 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
321 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
322 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
323 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'vp9'},
324 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
325 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
326 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
327 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
328 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
329 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
330 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
331 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
332 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
333 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
334 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
335 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
336 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'vp9'},
337 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
340 '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
341 '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
343 # Dash webm audio with opus inside
344 '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
345 '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
346 '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
349 '_rtmp': {'protocol': 'rtmp'},
355 'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&t=1s&end=9',
359 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
360 'uploader': 'Philipp Hagemeister',
361 'uploader_id': 'phihag',
362 'upload_date': '20121002',
363 '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 .',
364 'categories': ['Science & Technology'],
365 'tags': ['youtube-dl'],
367 'dislike_count': int,
373 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY',
374 'note': 'Test generic use_cipher_signature video (#897)',
378 'upload_date': '20120506',
379 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
380 'description': 'md5:782e8651347686cba06e58f71ab51773',
381 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
382 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
383 'iconic ep', 'iconic', 'love', 'it'],
384 'uploader': 'Icona Pop',
385 'uploader_id': 'IconaPop',
389 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
390 'note': 'Test VEVO video with age protection (#956)',
394 'upload_date': '20130703',
395 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
396 'description': 'md5:64249768eec3bc4276236606ea996373',
397 'uploader': 'justintimberlakeVEVO',
398 'uploader_id': 'justintimberlakeVEVO',
403 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
404 'note': 'Embed-only video (#1746)',
408 'upload_date': '20120608',
409 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
410 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
411 'uploader': 'SET India',
412 'uploader_id': 'setindia'
416 'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&v=UxxajLWwzqY',
417 'note': 'Use the first video ID in the URL',
421 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
422 'uploader': 'Philipp Hagemeister',
423 'uploader_id': 'phihag',
424 'upload_date': '20121002',
425 '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 .',
426 'categories': ['Science & Technology'],
427 'tags': ['youtube-dl'],
429 'dislike_count': int,
432 'skip_download': True,
436 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I',
437 'note': '256k DASH audio (format 141) via DASH manifest',
441 'upload_date': '20121002',
442 'uploader_id': '8KVIDEO',
444 'uploader': '8KVIDEO',
445 'title': 'UHDTV TEST 8K VIDEO.mp4'
448 'youtube_include_dash_manifest': True,
452 # DASH manifest with encrypted signature
454 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
458 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
459 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
460 'uploader': 'AfrojackVEVO',
461 'uploader_id': 'AfrojackVEVO',
462 'upload_date': '20131011',
465 'youtube_include_dash_manifest': True,
469 # JS player signature function name containing $
471 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
475 'title': 'Taylor Swift - Shake It Off',
476 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
477 'uploader': 'TaylorSwiftVEVO',
478 'uploader_id': 'TaylorSwiftVEVO',
479 'upload_date': '20140818',
482 'youtube_include_dash_manifest': True,
488 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
492 'upload_date': '20100909',
493 'uploader': 'The Amazing Atheist',
494 'uploader_id': 'TheAmazingAtheist',
495 'title': 'Burning Everyone\'s Koran',
496 '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',
499 # Normal age-gate video (No vevo, embed allowed)
501 'url': 'http://youtube.com/watch?v=HtVdAasjOgU',
505 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
506 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
507 'uploader': 'The Witcher',
508 'uploader_id': 'WitcherGame',
509 'upload_date': '20140605',
513 # Age-gate video with encrypted signature
515 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU',
519 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
520 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
521 'uploader': 'LloydVEVO',
522 'uploader_id': 'LloydVEVO',
523 'upload_date': '20110629',
527 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
529 'url': '__2ABJjxzNo',
533 'upload_date': '20100430',
534 'uploader_id': 'deadmau5',
535 'description': 'md5:12c56784b8032162bb936a5f76d55360',
536 'uploader': 'deadmau5',
537 'title': 'Deadmau5 - Some Chords (HD)',
539 'expected_warnings': [
540 'DASH manifest missing',
543 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
545 'url': 'lqQg6PlCWgI',
549 'upload_date': '20120724',
550 'uploader_id': 'olympic',
551 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
552 'uploader': 'Olympics',
553 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
556 'skip_download': 'requires avconv',
561 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
565 'stretched_ratio': 16 / 9.,
566 'upload_date': '20110310',
567 'uploader_id': 'AllenMeow',
568 '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',
570 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
573 # url_encoded_fmt_stream_map is empty string
575 'url': 'qEJwOuvDf7I',
579 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
581 'upload_date': '20150404',
582 'uploader_id': 'spbelect',
583 'uploader': 'Наблюдатели Петербурга',
586 'skip_download': 'requires avconv',
589 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
591 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
595 'title': 'md5:7b81415841e02ecd4313668cde88737a',
596 'description': 'md5:116377fd2963b81ec4ce64b542173306',
597 'upload_date': '20150625',
598 'uploader_id': 'dorappi2000',
599 'uploader': 'dorappi2000',
600 'formats': 'mincount:33',
603 # DASH manifest with segment_list
605 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
606 'md5': '8ce563a1d667b599d21064e982ab9e31',
610 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
611 'uploader': 'Airtek',
612 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
613 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
614 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
617 'youtube_include_dash_manifest': True,
618 'format': '135', # bestvideo
622 # Multifeed videos (multiple cameras), URL is for Main Camera
623 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
626 'title': 'teamPGP: Rocket League Noob Stream',
627 'description': 'md5:dc7872fb300e143831327f1bae3af010',
633 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
634 'description': 'md5:dc7872fb300e143831327f1bae3af010',
635 'upload_date': '20150721',
636 'uploader': 'Beer Games Beer',
637 'uploader_id': 'beergamesbeer',
643 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
644 'description': 'md5:dc7872fb300e143831327f1bae3af010',
645 'upload_date': '20150721',
646 'uploader': 'Beer Games Beer',
647 'uploader_id': 'beergamesbeer',
653 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
654 'description': 'md5:dc7872fb300e143831327f1bae3af010',
655 'upload_date': '20150721',
656 'uploader': 'Beer Games Beer',
657 'uploader_id': 'beergamesbeer',
663 'title': 'teamPGP: Rocket League Noob Stream (zim)',
664 'description': 'md5:dc7872fb300e143831327f1bae3af010',
665 'upload_date': '20150721',
666 'uploader': 'Beer Games Beer',
667 'uploader_id': 'beergamesbeer',
671 'skip_download': True,
675 'url': 'http://vid.plus/FlRa-iH7PGw',
676 'only_matching': True,
680 def __init__(self, *args, **kwargs):
681 super(YoutubeIE, self).__init__(*args, **kwargs)
682 self._player_cache = {}
684 def report_video_info_webpage_download(self, video_id):
685 """Report attempt to download video info webpage."""
686 self.to_screen('%s: Downloading video info webpage' % video_id)
688 def report_information_extraction(self, video_id):
689 """Report attempt to extract video information."""
690 self.to_screen('%s: Extracting video information' % video_id)
692 def report_unavailable_format(self, video_id, format):
693 """Report extracted video URL."""
694 self.to_screen('%s: Format %s not available' % (video_id, format))
696 def report_rtmp_download(self):
697 """Indicate the download will use the RTMP protocol."""
698 self.to_screen('RTMP download detected')
700 def _signature_cache_id(self, example_sig):
701 """ Return a string representation of a signature """
702 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
704 def _extract_signature_function(self, video_id, player_url, example_sig):
706 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?)?\.(?P<ext>[a-z]+)$',
709 raise ExtractorError('Cannot identify player %r' % player_url)
710 player_type = id_m.group('ext')
711 player_id = id_m.group('id')
713 # Read from filesystem cache
714 func_id = '%s_%s_%s' % (
715 player_type, player_id, self._signature_cache_id(example_sig))
716 assert os.path.basename(func_id) == func_id
718 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
719 if cache_spec is not None:
720 return lambda s: ''.join(s[i] for i in cache_spec)
723 'Downloading player %s' % player_url
724 if self._downloader.params.get('verbose') else
725 'Downloading %s player %s' % (player_type, player_id)
727 if player_type == 'js':
728 code = self._download_webpage(
729 player_url, video_id,
731 errnote='Download of %s failed' % player_url)
732 res = self._parse_sig_js(code)
733 elif player_type == 'swf':
734 urlh = self._request_webpage(
735 player_url, video_id,
737 errnote='Download of %s failed' % player_url)
739 res = self._parse_sig_swf(code)
741 assert False, 'Invalid player type %r' % player_type
743 test_string = ''.join(map(compat_chr, range(len(example_sig))))
744 cache_res = res(test_string)
745 cache_spec = [ord(c) for c in cache_res]
747 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
750 def _print_sig_code(self, func, example_sig):
751 def gen_sig_code(idxs):
752 def _genslice(start, end, step):
753 starts = '' if start == 0 else str(start)
754 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
755 steps = '' if step == 1 else (':%d' % step)
756 return 's[%s%s%s]' % (starts, ends, steps)
759 # Quelch pyflakes warnings - start will be set when step is set
760 start = '(Never used)'
761 for i, prev in zip(idxs[1:], idxs[:-1]):
765 yield _genslice(start, prev, step)
768 if i - prev in [-1, 1]:
777 yield _genslice(start, i, step)
779 test_string = ''.join(map(compat_chr, range(len(example_sig))))
780 cache_res = func(test_string)
781 cache_spec = [ord(c) for c in cache_res]
782 expr_code = ' + '.join(gen_sig_code(cache_spec))
783 signature_id_tuple = '(%s)' % (
784 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
785 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
786 ' return %s\n') % (signature_id_tuple, expr_code)
787 self.to_screen('Extracted signature function:\n' + code)
789 def _parse_sig_js(self, jscode):
790 funcname = self._search_regex(
791 r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
792 'Initial JS player signature function name')
794 jsi = JSInterpreter(jscode)
795 initial_function = jsi.extract_function(funcname)
796 return lambda s: initial_function([s])
798 def _parse_sig_swf(self, file_contents):
799 swfi = SWFInterpreter(file_contents)
800 TARGET_CLASSNAME = 'SignatureDecipher'
801 searched_class = swfi.extract_class(TARGET_CLASSNAME)
802 initial_function = swfi.extract_function(searched_class, 'decipher')
803 return lambda s: initial_function([s])
805 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
806 """Turn the encrypted s field into a working signature"""
808 if player_url is None:
809 raise ExtractorError('Cannot decrypt signature without player_url')
811 if player_url.startswith('//'):
812 player_url = 'https:' + player_url
814 player_id = (player_url, self._signature_cache_id(s))
815 if player_id not in self._player_cache:
816 func = self._extract_signature_function(
817 video_id, player_url, s
819 self._player_cache[player_id] = func
820 func = self._player_cache[player_id]
821 if self._downloader.params.get('youtube_print_sig_code'):
822 self._print_sig_code(func, s)
824 except Exception as e:
825 tb = traceback.format_exc()
826 raise ExtractorError(
827 'Signature extraction failed: ' + tb, cause=e)
829 def _get_subtitles(self, video_id, webpage):
831 subs_doc = self._download_xml(
832 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
833 video_id, note=False)
834 except ExtractorError as err:
835 self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
839 for track in subs_doc.findall('track'):
840 lang = track.attrib['lang_code']
841 if lang in sub_lang_list:
844 for ext in ['sbv', 'vtt', 'srt']:
845 params = compat_urllib_parse.urlencode({
849 'name': track.attrib['name'].encode('utf-8'),
852 'url': 'https://www.youtube.com/api/timedtext?' + params,
855 sub_lang_list[lang] = sub_formats
856 if not sub_lang_list:
857 self._downloader.report_warning('video doesn\'t have subtitles')
861 def _get_automatic_captions(self, video_id, webpage):
862 """We need the webpage for getting the captions url, pass it as an
863 argument to speed up the process."""
864 self.to_screen('%s: Looking for automatic captions' % video_id)
865 mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
866 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
868 self._downloader.report_warning(err_msg)
870 player_config = json.loads(mobj.group(1))
872 args = player_config['args']
873 caption_url = args['ttsurl']
874 timestamp = args['timestamp']
875 # We get the available subtitles
876 list_params = compat_urllib_parse.urlencode({
881 list_url = caption_url + '&' + list_params
882 caption_list = self._download_xml(list_url, video_id)
883 original_lang_node = caption_list.find('track')
884 if original_lang_node is None:
885 self._downloader.report_warning('Video doesn\'t have automatic captions')
887 original_lang = original_lang_node.attrib['lang_code']
888 caption_kind = original_lang_node.attrib.get('kind', '')
891 for lang_node in caption_list.findall('target'):
892 sub_lang = lang_node.attrib['lang_code']
894 for ext in ['sbv', 'vtt', 'srt']:
895 params = compat_urllib_parse.urlencode({
896 'lang': original_lang,
900 'kind': caption_kind,
903 'url': caption_url + '&' + params,
906 sub_lang_list[sub_lang] = sub_formats
908 # An extractor error can be raise by the download process if there are
909 # no automatic captions but there are subtitles
910 except (KeyError, ExtractorError):
911 self._downloader.report_warning(err_msg)
915 def extract_id(cls, url):
916 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
918 raise ExtractorError('Invalid URL: %s' % url)
919 video_id = mobj.group(2)
922 def _extract_from_m3u8(self, manifest_url, video_id):
925 def _get_urls(_manifest):
926 lines = _manifest.split('\n')
927 urls = filter(lambda l: l and not l.startswith('#'),
930 manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
931 formats_urls = _get_urls(manifest)
932 for format_url in formats_urls:
933 itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
934 url_map[itag] = format_url
937 def _extract_annotations(self, video_id):
938 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
939 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
941 def _parse_dash_manifest(
942 self, video_id, dash_manifest_url, player_url, age_gate, fatal=True):
943 def decrypt_sig(mobj):
945 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
946 return '/signature/%s' % dec_s
947 dash_manifest_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, dash_manifest_url)
948 dash_doc = self._download_xml(
949 dash_manifest_url, video_id,
950 note='Downloading DASH manifest',
951 errnote='Could not download DASH manifest',
954 if dash_doc is False:
958 for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'):
959 mime_type = a.attrib.get('mimeType')
960 for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'):
961 url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
964 if mime_type == 'text/vtt':
965 # TODO implement WebVTT downloading
967 elif mime_type.startswith('audio/') or mime_type.startswith('video/'):
968 segment_list = r.find('{urn:mpeg:DASH:schema:MPD:2011}SegmentList')
969 format_id = r.attrib['id']
970 video_url = url_el.text
971 filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
973 'format_id': format_id,
975 'width': int_or_none(r.attrib.get('width')),
976 'height': int_or_none(r.attrib.get('height')),
977 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
978 'asr': int_or_none(r.attrib.get('audioSamplingRate')),
979 'filesize': filesize,
980 'fps': int_or_none(r.attrib.get('frameRate')),
982 if segment_list is not None:
984 'initialization_url': segment_list.find('{urn:mpeg:DASH:schema:MPD:2011}Initialization').attrib['sourceURL'],
985 'segment_urls': [segment.attrib.get('media') for segment in segment_list.findall('{urn:mpeg:DASH:schema:MPD:2011}SegmentURL')],
986 'protocol': 'http_dash_segments',
989 existing_format = next(
991 if fo['format_id'] == format_id)
992 except StopIteration:
993 full_info = self._formats.get(format_id, {}).copy()
995 codecs = r.attrib.get('codecs')
997 if full_info.get('acodec') == 'none' and 'vcodec' not in full_info:
998 full_info['vcodec'] = codecs
999 elif full_info.get('vcodec') == 'none' and 'acodec' not in full_info:
1000 full_info['acodec'] = codecs
1001 formats.append(full_info)
1003 existing_format.update(f)
1005 self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
1008 def _real_extract(self, url):
1009 url, smuggled_data = unsmuggle_url(url, {})
1012 'http' if self._downloader.params.get('prefer_insecure', False)
1017 parsed_url = compat_urllib_parse_urlparse(url)
1018 for component in [parsed_url.fragment, parsed_url.query]:
1019 query = compat_parse_qs(component)
1020 if start_time is None and 't' in query:
1021 start_time = parse_duration(query['t'][0])
1022 if start_time is None and 'start' in query:
1023 start_time = parse_duration(query['start'][0])
1024 if end_time is None and 'end' in query:
1025 end_time = parse_duration(query['end'][0])
1027 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1028 mobj = re.search(self._NEXT_URL_RE, url)
1030 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1031 video_id = self.extract_id(url)
1034 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1035 video_webpage = self._download_webpage(url, video_id)
1037 # Attempt to extract SWF player URL
1038 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1039 if mobj is not None:
1040 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1046 def add_dash_mpd(video_info):
1047 dash_mpd = video_info.get('dashmpd')
1048 if dash_mpd and dash_mpd[0] not in dash_mpds:
1049 dash_mpds.append(dash_mpd[0])
1052 embed_webpage = None
1054 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1056 # We simulate the access to the video from www.youtube.com/v/{video_id}
1057 # this can be viewed without login into Youtube
1058 url = proto + '://www.youtube.com/embed/%s' % video_id
1059 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1060 data = compat_urllib_parse.urlencode({
1061 'video_id': video_id,
1062 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1063 'sts': self._search_regex(
1064 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1066 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1067 video_info_webpage = self._download_webpage(
1068 video_info_url, video_id,
1069 note='Refetching age-gated info webpage',
1070 errnote='unable to download video info webpage')
1071 video_info = compat_parse_qs(video_info_webpage)
1072 add_dash_mpd(video_info)
1076 # Try looking directly into the video webpage
1077 mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
1079 json_code = uppercase_escape(mobj.group(1))
1080 ytplayer_config = json.loads(json_code)
1081 args = ytplayer_config['args']
1082 if args.get('url_encoded_fmt_stream_map'):
1083 # Convert to the same format returned by compat_parse_qs
1084 video_info = dict((k, [v]) for k, v in args.items())
1085 add_dash_mpd(video_info)
1086 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1088 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1089 # We also try looking in get_video_info since it may contain different dashmpd
1090 # URL that points to a DASH manifest with possibly different itag set (some itags
1091 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1092 # manifest pointed by get_video_info's dashmpd).
1093 # The general idea is to take a union of itags of both DASH manifests (for example
1094 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1095 self.report_video_info_webpage_download(video_id)
1096 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1098 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1099 % (proto, video_id, el_type))
1100 video_info_webpage = self._download_webpage(
1102 video_id, note=False,
1103 errnote='unable to download video info webpage')
1104 get_video_info = compat_parse_qs(video_info_webpage)
1105 if get_video_info.get('use_cipher_signature') != ['True']:
1106 add_dash_mpd(get_video_info)
1108 video_info = get_video_info
1109 if 'token' in get_video_info:
1110 # Different get_video_info requests may report different results, e.g.
1111 # some may report video unavailability, but some may serve it without
1112 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1113 # the original webpage as well as el=info and el=embedded get_video_info
1114 # requests report video unavailability due to geo restriction while
1115 # el=detailpage succeeds and returns valid data). This is probably
1116 # due to YouTube measures against IP ranges of hosting providers.
1117 # Working around by preferring the first succeeded video_info containing
1118 # the token if no such video_info yet was found.
1119 if 'token' not in video_info:
1120 video_info = get_video_info
1122 if 'token' not in video_info:
1123 if 'reason' in video_info:
1124 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1125 regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
1127 raise ExtractorError('YouTube said: This video is available in %s only' % (
1128 ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
1130 raise ExtractorError(
1131 'YouTube said: %s' % video_info['reason'][0],
1132 expected=True, video_id=video_id)
1134 raise ExtractorError(
1135 '"token" parameter not in video info for unknown reason',
1139 if 'title' in video_info:
1140 video_title = video_info['title'][0]
1142 self._downloader.report_warning('Unable to extract video title')
1146 video_description = get_element_by_id("eow-description", video_webpage)
1147 if video_description:
1148 video_description = re.sub(r'''(?x)
1150 (?:[a-zA-Z-]+="[^"]+"\s+)*?
1152 (?:[a-zA-Z-]+="[^"]+"\s+)*?
1153 class="yt-uix-redirect-link"\s*>
1156 ''', r'\1', video_description)
1157 video_description = clean_html(video_description)
1159 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1161 video_description = unescapeHTML(fd_mobj.group(1))
1163 video_description = ''
1165 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1166 if not self._downloader.params.get('noplaylist'):
1169 multifeed_metadata_list = compat_urllib_parse_unquote_plus(video_info['multifeed_metadata_list'][0])
1170 for feed in multifeed_metadata_list.split(','):
1171 feed_data = compat_parse_qs(feed)
1173 '_type': 'url_transparent',
1174 'ie_key': 'Youtube',
1176 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1177 {'force_singlefeed': True}),
1178 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1180 feed_ids.append(feed_data['id'][0])
1182 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1183 % (', '.join(feed_ids), video_id))
1184 return self.playlist_result(entries, video_id, video_title, video_description)
1185 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1187 if 'view_count' in video_info:
1188 view_count = int(video_info['view_count'][0])
1192 # Check for "rental" videos
1193 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1194 raise ExtractorError('"rental" videos not supported')
1196 # Start extracting information
1197 self.report_information_extraction(video_id)
1200 if 'author' not in video_info:
1201 raise ExtractorError('Unable to extract uploader name')
1202 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
1205 video_uploader_id = None
1206 mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
1207 if mobj is not None:
1208 video_uploader_id = mobj.group(1)
1210 self._downloader.report_warning('unable to extract uploader nickname')
1213 # We try first to get a high quality image:
1214 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1215 video_webpage, re.DOTALL)
1216 if m_thumb is not None:
1217 video_thumbnail = m_thumb.group(1)
1218 elif 'thumbnail_url' not in video_info:
1219 self._downloader.report_warning('unable to extract video thumbnail')
1220 video_thumbnail = None
1221 else: # don't panic if we can't find it
1222 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1225 upload_date = self._html_search_meta(
1226 'datePublished', video_webpage, 'upload date', default=None)
1228 upload_date = self._search_regex(
1229 [r'(?s)id="eow-date.*?>(.*?)</span>',
1230 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1231 video_webpage, 'upload date', default=None)
1233 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1234 upload_date = unified_strdate(upload_date)
1236 m_cat_container = self._search_regex(
1237 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1238 video_webpage, 'categories', default=None)
1240 category = self._html_search_regex(
1241 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
1243 video_categories = None if category is None else [category]
1245 video_categories = None
1248 unescapeHTML(m.group('content'))
1249 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1251 def _extract_count(count_name):
1252 return str_to_int(self._search_regex(
1253 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1254 % re.escape(count_name),
1255 video_webpage, count_name, default=None))
1257 like_count = _extract_count('like')
1258 dislike_count = _extract_count('dislike')
1261 video_subtitles = self.extract_subtitles(video_id, video_webpage)
1262 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
1264 if 'length_seconds' not in video_info:
1265 self._downloader.report_warning('unable to extract video duration')
1266 video_duration = None
1268 video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
1271 video_annotations = None
1272 if self._downloader.params.get('writeannotations', False):
1273 video_annotations = self._extract_annotations(video_id)
1275 def _map_to_format_list(urlmap):
1277 for itag, video_real_url in urlmap.items():
1280 'url': video_real_url,
1281 'player_url': player_url,
1283 if itag in self._formats:
1284 dct.update(self._formats[itag])
1288 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1289 self.report_rtmp_download()
1291 'format_id': '_rtmp',
1293 'url': video_info['conn'][0],
1294 'player_url': player_url,
1296 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
1297 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1298 if 'rtmpe%3Dyes' in encoded_url_map:
1299 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
1301 for url_data_str in encoded_url_map.split(','):
1302 url_data = compat_parse_qs(url_data_str)
1303 if 'itag' not in url_data or 'url' not in url_data:
1305 format_id = url_data['itag'][0]
1306 url = url_data['url'][0]
1308 if 'sig' in url_data:
1309 url += '&signature=' + url_data['sig'][0]
1310 elif 's' in url_data:
1311 encrypted_sig = url_data['s'][0]
1312 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1314 jsplayer_url_json = self._search_regex(
1316 embed_webpage if age_gate else video_webpage,
1317 'JS player URL (1)', default=None)
1318 if not jsplayer_url_json and not age_gate:
1319 # We need the embed website after all
1320 if embed_webpage is None:
1321 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1322 embed_webpage = self._download_webpage(
1323 embed_url, video_id, 'Downloading embed webpage')
1324 jsplayer_url_json = self._search_regex(
1325 ASSETS_RE, embed_webpage, 'JS player URL')
1327 player_url = json.loads(jsplayer_url_json)
1328 if player_url is None:
1329 player_url_json = self._search_regex(
1330 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1331 video_webpage, 'age gate player URL')
1332 player_url = json.loads(player_url_json)
1334 if self._downloader.params.get('verbose'):
1335 if player_url is None:
1336 player_version = 'unknown'
1337 player_desc = 'unknown'
1339 if player_url.endswith('swf'):
1340 player_version = self._search_regex(
1341 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1342 'flash player', fatal=False)
1343 player_desc = 'flash player %s' % player_version
1345 player_version = self._search_regex(
1346 r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1348 'html5 player', fatal=False)
1349 player_desc = 'html5 player %s' % player_version
1351 parts_sizes = self._signature_cache_id(encrypted_sig)
1352 self.to_screen('{%s} signature length %s, %s' %
1353 (format_id, parts_sizes, player_desc))
1355 signature = self._decrypt_signature(
1356 encrypted_sig, video_id, player_url, age_gate)
1357 url += '&signature=' + signature
1358 if 'ratebypass' not in url:
1359 url += '&ratebypass=yes'
1361 # Some itags are not included in DASH manifest thus corresponding formats will
1362 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1363 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1364 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1365 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
1367 'format_id': format_id,
1369 'player_url': player_url,
1370 'filesize': int_or_none(url_data.get('clen', [None])[0]),
1371 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
1374 'fps': int_or_none(url_data.get('fps', [None])[0]),
1375 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
1377 type_ = url_data.get('type', [None])[0]
1379 type_split = type_.split(';')
1380 kind_ext = type_split[0].split('/')
1381 if len(kind_ext) == 2:
1382 kind, ext = kind_ext
1384 if kind in ('audio', 'video'):
1386 for mobj in re.finditer(
1387 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1388 if mobj.group('key') == 'codecs':
1389 codecs = mobj.group('val')
1392 codecs = codecs.split(',')
1393 if len(codecs) == 2:
1394 acodec, vcodec = codecs[0], codecs[1]
1396 acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
1401 if format_id in self._formats:
1402 dct.update(self._formats[format_id])
1404 elif video_info.get('hlsvp'):
1405 manifest_url = video_info['hlsvp'][0]
1406 url_map = self._extract_from_m3u8(manifest_url, video_id)
1407 formats = _map_to_format_list(url_map)
1409 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
1411 # Look for the DASH manifest
1412 if self._downloader.params.get('youtube_include_dash_manifest', True):
1413 dash_mpd_fatal = True
1414 for dash_manifest_url in dash_mpds:
1417 for df in self._parse_dash_manifest(
1418 video_id, dash_manifest_url, player_url, age_gate, dash_mpd_fatal):
1419 # Do not overwrite DASH format found in some previous DASH manifest
1420 if df['format_id'] not in dash_formats:
1421 dash_formats[df['format_id']] = df
1422 # Additional DASH manifests may end up in HTTP Error 403 therefore
1423 # allow them to fail without bug report message if we already have
1424 # some DASH manifest succeeded. This is temporary workaround to reduce
1425 # burst of bug reports until we figure out the reason and whether it
1426 # can be fixed at all.
1427 dash_mpd_fatal = False
1428 except (ExtractorError, KeyError) as e:
1429 self.report_warning(
1430 'Skipping DASH manifest: %r' % e, video_id)
1432 # Remove the formats we found through non-DASH, they
1433 # contain less info and it can be wrong, because we use
1434 # fixed values (for example the resolution). See
1435 # https://github.com/rg3/youtube-dl/issues/5774 for an
1437 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
1438 formats.extend(dash_formats.values())
1440 # Check for malformed aspect ratio
1441 stretched_m = re.search(
1442 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1445 ratio = float(stretched_m.group('w')) / float(stretched_m.group('h'))
1447 if f.get('vcodec') != 'none':
1448 f['stretched_ratio'] = ratio
1450 self._sort_formats(formats)
1454 'uploader': video_uploader,
1455 'uploader_id': video_uploader_id,
1456 'upload_date': upload_date,
1457 'title': video_title,
1458 'thumbnail': video_thumbnail,
1459 'description': video_description,
1460 'categories': video_categories,
1462 'subtitles': video_subtitles,
1463 'automatic_captions': automatic_captions,
1464 'duration': video_duration,
1465 'age_limit': 18 if age_gate else 0,
1466 'annotations': video_annotations,
1467 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
1468 'view_count': view_count,
1469 'like_count': like_count,
1470 'dislike_count': dislike_count,
1471 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
1474 'start_time': start_time,
1475 'end_time': end_time,
1479 class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtractor):
1480 IE_DESC = 'YouTube.com playlists'
1481 _VALID_URL = r"""(?x)(?:
1486 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1487 \? (?:.*?&)*? (?:p|a|list)=
1491 (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
1492 # Top tracks, they can also include dots
1497 ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
1499 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
1500 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
1501 IE_NAME = 'youtube:playlist'
1503 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1505 'title': 'ytdl test PL',
1506 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1508 'playlist_count': 3,
1510 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1512 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1513 'title': 'YDL_Empty_List',
1515 'playlist_count': 0,
1517 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1518 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1520 'title': '29C3: Not my department',
1521 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1523 'playlist_count': 95,
1525 'note': 'issue #673',
1526 'url': 'PLBB231211A4F62143',
1528 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1529 'id': 'PLBB231211A4F62143',
1531 'playlist_mincount': 26,
1533 'note': 'Large playlist',
1534 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1536 'title': 'Uploads from Cauchemar',
1537 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1539 'playlist_mincount': 799,
1541 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1543 'title': 'YDL_safe_search',
1544 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1546 'playlist_count': 2,
1549 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1550 'playlist_count': 4,
1553 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1556 'note': 'Embedded SWF player',
1557 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1558 'playlist_count': 4,
1561 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1564 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1565 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1567 'title': 'Uploads from Interstellar Movie',
1568 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1570 'playlist_mincout': 21,
1573 def _real_initialize(self):
1576 def _extract_mix(self, playlist_id):
1577 # The mixes are generated from a single video
1578 # the id of the playlist is just 'RD' + video_id
1579 url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
1580 webpage = self._download_webpage(
1581 url, playlist_id, 'Downloading Youtube mix')
1582 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
1584 search_title('playlist-title') or
1585 search_title('title long-title') or
1586 search_title('title'))
1587 title = clean_html(title_span)
1588 ids = orderedSet(re.findall(
1589 r'''(?xs)data-video-username=".*?".*?
1590 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
1592 url_results = self._ids_to_results(ids)
1594 return self.playlist_result(url_results, playlist_id, title)
1596 def _extract_playlist(self, playlist_id):
1597 url = self._TEMPLATE_URL % playlist_id
1598 page = self._download_webpage(url, playlist_id)
1600 for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
1601 match = match.strip()
1602 # Check if the playlist exists or is private
1603 if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
1604 raise ExtractorError(
1605 'The playlist doesn\'t exist or is private, use --username or '
1606 '--netrc to access it.',
1608 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
1609 raise ExtractorError(
1610 'Invalid parameters. Maybe URL is incorrect.',
1612 elif re.match(r'[^<]*Choose your language[^<]*', match):
1615 self.report_warning('Youtube gives an alert message: ' + match)
1617 playlist_title = self._html_search_regex(
1618 r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
1621 return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title)
1623 def _real_extract(self, url):
1624 # Extract playlist id
1625 mobj = re.match(self._VALID_URL, url)
1627 raise ExtractorError('Invalid URL: %s' % url)
1628 playlist_id = mobj.group(1) or mobj.group(2)
1630 # Check if it's a video-specific URL
1631 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
1632 if 'v' in query_dict:
1633 video_id = query_dict['v'][0]
1634 if self._downloader.params.get('noplaylist'):
1635 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1636 return self.url_result(video_id, 'Youtube', video_id=video_id)
1638 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
1640 if playlist_id.startswith('RD') or playlist_id.startswith('UL'):
1641 # Mixes require a custom extraction process
1642 return self._extract_mix(playlist_id)
1644 return self._extract_playlist(playlist_id)
1647 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
1648 IE_DESC = 'YouTube.com channels'
1649 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
1650 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
1651 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
1652 IE_NAME = 'youtube:channel'
1654 'note': 'paginated channel',
1655 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
1656 'playlist_mincount': 91,
1658 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
1659 'title': 'Uploads from lex will',
1662 'note': 'Age restricted channel',
1663 # from https://www.youtube.com/user/DeusExOfficial
1664 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
1665 'playlist_mincount': 64,
1667 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
1668 'title': 'Uploads from Deus Ex',
1672 def _real_extract(self, url):
1673 channel_id = self._match_id(url)
1675 url = self._TEMPLATE_URL % channel_id
1677 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
1678 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
1679 # otherwise fallback on channel by page extraction
1680 channel_page = self._download_webpage(
1681 url + '?view=57', channel_id,
1682 'Downloading channel page', fatal=False)
1683 if channel_page is False:
1684 channel_playlist_id = False
1686 channel_playlist_id = self._html_search_meta(
1687 'channelId', channel_page, 'channel id', default=None)
1688 if not channel_playlist_id:
1689 channel_playlist_id = self._search_regex(
1690 r'data-(?:channel-external-|yt)id="([^"]+)"',
1691 channel_page, 'channel id', default=None)
1692 if channel_playlist_id and channel_playlist_id.startswith('UC'):
1693 playlist_id = 'UU' + channel_playlist_id[2:]
1694 return self.url_result(
1695 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
1697 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
1698 autogenerated = re.search(r'''(?x)
1700 channel-header-autogenerated-label|
1701 yt-channel-title-autogenerated
1702 )[^"]*"''', channel_page) is not None
1705 # The videos are contained in a single page
1706 # the ajax pages can't be used, they are empty
1709 video_id, 'Youtube', video_id=video_id,
1710 video_title=video_title)
1711 for video_id, video_title in self.extract_videos_from_page(channel_page)]
1712 return self.playlist_result(entries, channel_id)
1714 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
1717 class YoutubeUserIE(YoutubeChannelIE):
1718 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
1719 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
1720 _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
1721 IE_NAME = 'youtube:user'
1724 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
1725 'playlist_mincount': 320,
1727 'title': 'TheLinuxFoundation',
1730 'url': 'ytuser:phihag',
1731 'only_matching': True,
1735 def suitable(cls, url):
1736 # Don't return True if the url can be extracted with other youtube
1737 # extractor, the regex would is too permissive and it would match.
1738 other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls)
1739 if any(ie.suitable(url) for ie in other_ies):
1742 return super(YoutubeUserIE, cls).suitable(url)
1745 class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
1746 IE_DESC = 'YouTube.com searches'
1747 # there doesn't appear to be a real limit, for example if you search for
1748 # 'python' you get more than 8.000.000 results
1749 _MAX_RESULTS = float('inf')
1750 IE_NAME = 'youtube:search'
1751 _SEARCH_KEY = 'ytsearch'
1752 _EXTRA_QUERY_ARGS = {}
1755 def _get_n_results(self, query, n):
1756 """Get a specified number of results for a query"""
1761 for pagenum in itertools.count(1):
1763 'search_query': query.encode('utf-8'),
1767 url_query.update(self._EXTRA_QUERY_ARGS)
1768 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse.urlencode(url_query)
1769 data = self._download_json(
1770 result_url, video_id='query "%s"' % query,
1771 note='Downloading page %s' % pagenum,
1772 errnote='Unable to download API page')
1773 html_content = data[1]['body']['content']
1775 if 'class="search-message' in html_content:
1776 raise ExtractorError(
1777 '[youtube] No video results', expected=True)
1779 new_videos = self._ids_to_results(orderedSet(re.findall(
1780 r'href="/watch\?v=(.{11})', html_content)))
1781 videos += new_videos
1782 if not new_videos or len(videos) > limit:
1787 return self.playlist_result(videos, query)
1790 class YoutubeSearchDateIE(YoutubeSearchIE):
1791 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
1792 _SEARCH_KEY = 'ytsearchdate'
1793 IE_DESC = 'YouTube.com searches, newest videos first'
1794 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
1797 class YoutubeSearchURLIE(InfoExtractor):
1798 IE_DESC = 'YouTube.com search URLs'
1799 IE_NAME = 'youtube:search_url'
1800 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)'
1802 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
1803 'playlist_mincount': 5,
1805 'title': 'youtube-dl test video',
1809 def _real_extract(self, url):
1810 mobj = re.match(self._VALID_URL, url)
1811 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
1813 webpage = self._download_webpage(url, query)
1814 result_code = self._search_regex(
1815 r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML')
1817 part_codes = re.findall(
1818 r'(?s)<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*>(.*?)</h3>', result_code)
1820 for part_code in part_codes:
1821 part_title = self._html_search_regex(
1822 [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False)
1823 part_url_snippet = self._html_search_regex(
1824 r'(?s)href="([^"]+)"', part_code, 'item URL')
1825 part_url = compat_urlparse.urljoin(
1826 'https://www.youtube.com/', part_url_snippet)
1830 'title': part_title,
1834 '_type': 'playlist',
1840 class YoutubeShowIE(InfoExtractor):
1841 IE_DESC = 'YouTube.com (multi-season) shows'
1842 _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
1843 IE_NAME = 'youtube:show'
1845 'url': 'https://www.youtube.com/show/airdisasters',
1846 'playlist_mincount': 5,
1848 'id': 'airdisasters',
1849 'title': 'Air Disasters',
1853 def _real_extract(self, url):
1854 mobj = re.match(self._VALID_URL, url)
1855 playlist_id = mobj.group('id')
1856 webpage = self._download_webpage(
1857 'https://www.youtube.com/show/%s/playlists' % playlist_id, playlist_id, 'Downloading show webpage')
1858 # There's one playlist for each season of the show
1859 m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage))
1860 self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons)))
1863 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist')
1864 for season in m_seasons
1866 title = self._og_search_title(webpage, fatal=False)
1869 '_type': 'playlist',
1876 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
1878 Base class for feed extractors
1879 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
1881 _LOGIN_REQUIRED = True
1885 return 'youtube:%s' % self._FEED_NAME
1887 def _real_initialize(self):
1890 def _real_extract(self, url):
1891 page = self._download_webpage(
1892 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
1894 # The extraction process is the same as for playlists, but the regex
1895 # for the video ids doesn't contain an index
1897 more_widget_html = content_html = page
1898 for page_num in itertools.count(1):
1899 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
1901 # 'recommended' feed has infinite 'load more' and each new portion spins
1902 # the same videos in (sometimes) slightly different order, so we'll check
1903 # for unicity and break when portion has no new videos
1904 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
1910 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
1914 more = self._download_json(
1915 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
1916 'Downloading page #%s' % page_num,
1917 transform_source=uppercase_escape)
1918 content_html = more['content_html']
1919 more_widget_html = more['load_more_widget_html']
1921 return self.playlist_result(
1922 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
1925 class YoutubeWatchLaterIE(YoutubePlaylistIE):
1926 IE_NAME = 'youtube:watchlater'
1927 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
1928 _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater'
1930 _TESTS = [] # override PlaylistIE tests
1932 def _real_extract(self, url):
1933 return self._extract_playlist('WL')
1936 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
1937 IE_NAME = 'youtube:favorites'
1938 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
1939 _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
1940 _LOGIN_REQUIRED = True
1942 def _real_extract(self, url):
1943 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
1944 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
1945 return self.url_result(playlist_id, 'YoutubePlaylist')
1948 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
1949 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
1950 _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
1951 _FEED_NAME = 'recommended'
1952 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1955 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
1956 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
1957 _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
1958 _FEED_NAME = 'subscriptions'
1959 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1962 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
1963 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
1964 _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
1965 _FEED_NAME = 'history'
1966 _PLAYLIST_TITLE = 'Youtube History'
1969 class YoutubeTruncatedURLIE(InfoExtractor):
1970 IE_NAME = 'youtube:truncated_url'
1971 IE_DESC = False # Do not list
1972 _VALID_URL = r'''(?x)
1974 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
1977 annotation_id=annotation_[^&]+|
1983 attribution_link\?a=[^&]+
1989 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041',
1990 'only_matching': True,
1992 'url': 'http://www.youtube.com/watch?',
1993 'only_matching': True,
1995 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
1996 'only_matching': True,
1998 'url': 'https://www.youtube.com/watch?feature=foo',
1999 'only_matching': True,
2001 'url': 'https://www.youtube.com/watch?hl=en-GB',
2002 'only_matching': True,
2004 'url': 'https://www.youtube.com/watch?t=2372',
2005 'only_matching': True,
2008 def _real_extract(self, url):
2009 raise ExtractorError(
2010 'Did you forget to quote the URL? Remember that & is a meta '
2011 'character in most shells, so you want to put the URL in quotes, '
2013 '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2014 ' or simply youtube-dl BaW_jenozKc .',
2018 class YoutubeTruncatedIDIE(InfoExtractor):
2019 IE_NAME = 'youtube:truncated_id'
2020 IE_DESC = False # Do not list
2021 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2024 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2025 'only_matching': True,
2028 def _real_extract(self, url):
2029 video_id = self._match_id(url)
2030 raise ExtractorError(
2031 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),