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 _PLAYLIST_ID_RE
= r
'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}'
64 def _set_language(self
):
66 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
67 # YouTube sets the expire time to about two months
68 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
70 def _ids_to_results(self
, ids
):
72 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
77 Attempt to log in to YouTube.
78 True is returned if successful or skipped.
79 False is returned if login failed.
81 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
83 (username
, password
) = self
._get
_login
_info
()
84 # No authentication to be performed
86 if self
._LOGIN
_REQUIRED
:
87 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
90 login_page
= self
._download
_webpage
(
91 self
._LOGIN
_URL
, None,
92 note
='Downloading login page',
93 errnote
='unable to fetch login page', fatal
=False)
94 if login_page
is False:
97 login_form
= self
._hidden
_inputs
(login_page
)
100 'checkConnection': 'youtube',
105 login_results
= self
._download
_webpage
(
106 self
._PASSWORD
_CHALLENGE
_URL
, None,
107 note
='Logging in', errnote
='unable to log in', fatal
=False,
108 data
=urlencode_postdata(login_form
))
109 if login_results
is False:
112 error_msg
= self
._html
_search
_regex
(
113 r
'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
114 login_results
, 'error message', default
=None)
116 raise ExtractorError('Unable to login: %s' % error_msg
, expected
=True)
118 if re
.search(r
'id="errormsg_0_Passwd"', login_results
) is not None:
119 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected
=True)
122 # TODO add SMS and phone call support - these require making a request and then prompting the user
124 if re
.search(r
'(?i)<form[^>]+id="challenge"', login_results
) is not None:
125 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
128 self
._downloader
.report_warning(
129 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
130 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
133 tfa_code
= remove_start(tfa_code
, 'G-')
135 tfa_form_strs
= self
._form
_hidden
_inputs
('challenge', login_results
)
137 tfa_form_strs
.update({
142 tfa_data
= urlencode_postdata(tfa_form_strs
)
144 tfa_req
= sanitized_Request(self
._TWOFACTOR
_URL
, tfa_data
)
145 tfa_results
= self
._download
_webpage
(
147 note
='Submitting TFA code', errnote
='unable to submit tfa', fatal
=False)
149 if tfa_results
is False:
152 if re
.search(r
'(?i)<form[^>]+id="challenge"', tfa_results
) is not None:
153 self
._downloader
.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
155 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', tfa_results
) is not None:
156 self
._downloader
.report_warning('unable to log in - did the page structure change?')
158 if re
.search(r
'smsauth-interstitial-reviewsettings', tfa_results
) is not None:
159 self
._downloader
.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
162 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', login_results
) is not None:
163 self
._downloader
.report_warning('unable to log in: bad username or password')
167 def _real_initialize(self
):
168 if self
._downloader
is None:
171 if not self
._login
():
175 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
176 # Extract entries from page with "Load more" button
177 def _entries(self
, page
, playlist_id
):
178 more_widget_html
= content_html
= page
179 for page_num
in itertools
.count(1):
180 for entry
in self
._process
_page
(content_html
):
183 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
187 more
= self
._download
_json
(
188 'https://youtube.com/%s' % mobj
.group('more'), playlist_id
,
189 'Downloading page #%s' % page_num
,
190 transform_source
=uppercase_escape
)
191 content_html
= more
['content_html']
192 if not content_html
.strip():
193 # Some webpages show a "Load more" button but they don't
196 more_widget_html
= more
['load_more_widget_html']
199 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
200 def _process_page(self
, content
):
201 for video_id
, video_title
in self
.extract_videos_from_page(content
):
202 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
204 def extract_videos_from_page(self
, page
):
207 for mobj
in re
.finditer(self
._VIDEO
_RE
, page
):
208 # The link with index 0 is not the first video of the playlist (not sure if still actual)
209 if 'index' in mobj
.groupdict() and mobj
.group('id') == '0':
211 video_id
= mobj
.group('id')
212 video_title
= unescapeHTML(mobj
.group('title'))
214 video_title
= video_title
.strip()
216 idx
= ids_in_page
.index(video_id
)
217 if video_title
and not titles_in_page
[idx
]:
218 titles_in_page
[idx
] = video_title
220 ids_in_page
.append(video_id
)
221 titles_in_page
.append(video_title
)
222 return zip(ids_in_page
, titles_in_page
)
225 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
226 def _process_page(self
, content
):
227 for playlist_id
in orderedSet(re
.findall(
228 r
'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
230 yield self
.url_result(
231 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
233 def _real_extract(self
, url
):
234 playlist_id
= self
._match
_id
(url
)
235 webpage
= self
._download
_webpage
(url
, playlist_id
)
236 title
= self
._og
_search
_title
(webpage
, fatal
=False)
237 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
240 class YoutubeIE(YoutubeBaseInfoExtractor
):
241 IE_DESC
= 'YouTube.com'
242 _VALID_URL
= r
"""(?x)^
244 (?:https?://|//) # http(s):// or protocol-independent URL
245 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
246 (?:www\.)?deturl\.com/www\.youtube\.com/|
247 (?:www\.)?pwnyoutube\.com/|
248 (?:www\.)?yourepeat\.com/|
249 tube\.majestyc\.net/|
250 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
251 (?:.*?\#/)? # handle anchor (#/) redirect urls
252 (?: # the various things that can precede the ID:
253 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
254 |(?: # or the v= param in all its forms
255 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
256 (?:\?|\#!?) # the params delimiter ? or # or #!
257 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
262 youtu\.be| # just youtu.be/xxxx
263 vid\.plus| # or vid.plus/xxxx
264 zwearz\.com/watch| # or zwearz.com/watch/xxxx
266 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
268 )? # all until now is optional -> you can pass the naked ID
269 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
272 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
273 WL # WL are handled by the watch later IE
276 (?(1).+)? # if we found the ID, everything can follow
277 $""" % {'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
}
278 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
280 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
281 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
282 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
283 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
284 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
285 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
286 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
287 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
288 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
289 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
290 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
291 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
292 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
293 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
294 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
295 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
296 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
297 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
301 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
302 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
303 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
304 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
305 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
306 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
307 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
309 # Apple HTTP Live Streaming
310 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
311 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
312 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
313 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
314 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
315 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
316 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
317 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
320 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
321 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
322 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
323 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
324 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
325 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
326 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
327 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
328 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
329 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
330 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
331 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
334 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
335 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
336 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
337 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
338 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
339 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
340 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'preference': -50, 'container': 'm4a_dash'},
343 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
344 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
345 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
346 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
347 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
348 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
349 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
350 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
351 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
352 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
353 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
354 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
355 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
356 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
357 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
358 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
359 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
360 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
361 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
362 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
363 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
364 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
367 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
368 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
370 # Dash webm audio with opus inside
371 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
372 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
373 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
376 '_rtmp': {'protocol': 'rtmp'},
378 _SUBTITLE_FORMATS
= ('ttml', 'vtt')
385 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
389 'title': 'youtube-dl test video "\'/\\Ƥāš',
390 'uploader': 'Philipp Hagemeister',
391 'uploader_id': 'phihag',
392 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
393 'upload_date': '20121002',
394 'license': 'Standard YouTube License',
395 'description': 'test chars: "\'/\\Ƥāš\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 .',
396 'categories': ['Science & Technology'],
397 'tags': ['youtube-dl'],
400 'dislike_count': int,
406 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
407 'note': 'Test generic use_cipher_signature video (#897)',
411 'upload_date': '20120506',
412 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
413 'alt_title': 'I Love It (feat. Charli XCX)',
414 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
415 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
416 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
417 'iconic ep', 'iconic', 'love', 'it'],
419 'uploader': 'Icona Pop',
420 'uploader_id': 'IconaPop',
421 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IconaPop',
422 'license': 'Standard YouTube License',
423 'creator': 'Icona Pop',
427 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
428 'note': 'Test VEVO video with age protection (#956)',
432 'upload_date': '20130703',
433 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
434 'alt_title': 'Tunnel Vision',
435 'description': 'md5:64249768eec3bc4276236606ea996373',
437 'uploader': 'justintimberlakeVEVO',
438 'uploader_id': 'justintimberlakeVEVO',
439 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
440 'license': 'Standard YouTube License',
441 'creator': 'Justin Timberlake',
446 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
447 'note': 'Embed-only video (#1746)',
451 'upload_date': '20120608',
452 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
453 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
454 'uploader': 'SET India',
455 'uploader_id': 'setindia',
456 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
457 'license': 'Standard YouTube License',
462 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
463 'note': 'Use the first video ID in the URL',
467 'title': 'youtube-dl test video "\'/\\Ƥāš',
468 'uploader': 'Philipp Hagemeister',
469 'uploader_id': 'phihag',
470 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
471 'upload_date': '20121002',
472 'license': 'Standard YouTube License',
473 'description': 'test chars: "\'/\\Ƥāš\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 .',
474 'categories': ['Science & Technology'],
475 'tags': ['youtube-dl'],
478 'dislike_count': int,
481 'skip_download': True,
485 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
486 'note': '256k DASH audio (format 141) via DASH manifest',
490 'upload_date': '20121002',
491 'uploader_id': '8KVIDEO',
492 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
494 'uploader': '8KVIDEO',
495 'license': 'Standard YouTube License',
496 'title': 'UHDTV TEST 8K VIDEO.mp4'
499 'youtube_include_dash_manifest': True,
502 'skip': 'format 141 not served anymore',
504 # DASH manifest with encrypted signature
506 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
510 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
511 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
513 'uploader': 'AfrojackVEVO',
514 'uploader_id': 'AfrojackVEVO',
515 'upload_date': '20131011',
516 'license': 'Standard YouTube License',
519 'youtube_include_dash_manifest': True,
520 'format': '141/bestaudio[ext=m4a]',
523 # JS player signature function name containing $
525 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
529 'title': 'Taylor Swift - Shake It Off',
530 'alt_title': 'Shake It Off',
531 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
533 'uploader': 'TaylorSwiftVEVO',
534 'uploader_id': 'TaylorSwiftVEVO',
535 'upload_date': '20140818',
536 'license': 'Standard YouTube License',
537 'creator': 'Taylor Swift',
540 'youtube_include_dash_manifest': True,
541 'format': '141/bestaudio[ext=m4a]',
546 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
551 'upload_date': '20100909',
552 'uploader': 'The Amazing Atheist',
553 'uploader_id': 'TheAmazingAtheist',
554 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
555 'license': 'Standard YouTube License',
556 'title': 'Burning Everyone\'s Koran',
557 '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',
560 # Normal age-gate video (No vevo, embed allowed)
562 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
566 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
567 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
569 'uploader': 'The Witcher',
570 'uploader_id': 'WitcherGame',
571 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
572 'upload_date': '20140605',
573 'license': 'Standard YouTube License',
577 # Age-gate video with encrypted signature
579 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
583 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
584 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
586 'uploader': 'LloydVEVO',
587 'uploader_id': 'LloydVEVO',
588 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
589 'upload_date': '20110629',
590 'license': 'Standard YouTube License',
594 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
596 'url': '__2ABJjxzNo',
601 'upload_date': '20100430',
602 'uploader_id': 'deadmau5',
603 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
604 'creator': 'deadmau5',
605 'description': 'md5:12c56784b8032162bb936a5f76d55360',
606 'uploader': 'deadmau5',
607 'license': 'Standard YouTube License',
608 'title': 'Deadmau5 - Some Chords (HD)',
609 'alt_title': 'Some Chords',
611 'expected_warnings': [
612 'DASH manifest missing',
615 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
617 'url': 'lqQg6PlCWgI',
622 'upload_date': '20150827',
623 'uploader_id': 'olympic',
624 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
625 'license': 'Standard YouTube License',
626 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
627 'uploader': 'Olympic',
628 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
631 'skip_download': 'requires avconv',
636 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
640 'stretched_ratio': 16 / 9.,
642 'upload_date': '20110310',
643 'uploader_id': 'AllenMeow',
644 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
645 'description': 'made by Wacom from Korea | åå¹&å ę²¹ę·»é by TY\'s Allen | ęč¬heylisa00cavey1001ååøē±ę
ęä¾ę¢åēæ»čÆ',
646 'uploader': 'å«č¾å«',
647 'license': 'Standard YouTube License',
648 'title': '[A-made] č®ę
å¦åå¹ē å¤Ŗå¦ ęå°±ęÆéęØ£ēäŗŗ',
651 # url_encoded_fmt_stream_map is empty string
653 'url': 'qEJwOuvDf7I',
657 'title': 'ŠŠ±ŃŃŠ¶Š“ŠµŠ½ŠøŠµ ŃŃŠ“ŠµŠ±Š½Š¾Š¹ ŠæŃŠ°ŠŗŃŠøŠŗŠø ŠæŠ¾ Š²ŃŠ±Š¾ŃŠ°Š¼ 14 ŃŠµŠ½ŃŃŠ±ŃŃ 2014 Š³Š¾Š“Š° Š² Š”Š°Š½ŠŗŃ-ŠŠµŃŠµŃŠ±ŃŃŠ³Šµ',
659 'upload_date': '20150404',
660 'uploader_id': 'spbelect',
661 'uploader': 'ŠŠ°Š±Š»ŃŠ“Š°ŃŠµŠ»Šø ŠŠµŃŠµŃŠ±ŃŃŠ³Š°',
664 'skip_download': 'requires avconv',
666 'skip': 'This live event has ended.',
668 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
670 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
674 'title': 'md5:7b81415841e02ecd4313668cde88737a',
675 'description': 'md5:116377fd2963b81ec4ce64b542173306',
677 'upload_date': '20150625',
678 'uploader_id': 'dorappi2000',
679 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
680 'uploader': 'dorappi2000',
681 'license': 'Standard YouTube License',
682 'formats': 'mincount:32',
685 # DASH manifest with segment_list
687 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
688 'md5': '8ce563a1d667b599d21064e982ab9e31',
692 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
693 'uploader': 'Airtek',
694 'description': 'RetransmisiĆ³n en directo de la XVIII media maratĆ³n de Zaragoza.',
695 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
696 'license': 'Standard YouTube License',
697 'title': 'RetransmisiĆ³n XVIII Media maratĆ³n Zaragoza 2015',
700 'youtube_include_dash_manifest': True,
701 'format': '135', # bestvideo
703 'skip': 'This live event has ended.',
706 # Multifeed videos (multiple cameras), URL is for Main Camera
707 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
710 'title': 'teamPGP: Rocket League Noob Stream',
711 'description': 'md5:dc7872fb300e143831327f1bae3af010',
717 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
718 'description': 'md5:dc7872fb300e143831327f1bae3af010',
720 'upload_date': '20150721',
721 'uploader': 'Beer Games Beer',
722 'uploader_id': 'beergamesbeer',
723 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
724 'license': 'Standard YouTube License',
730 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
731 'description': 'md5:dc7872fb300e143831327f1bae3af010',
733 'upload_date': '20150721',
734 'uploader': 'Beer Games Beer',
735 'uploader_id': 'beergamesbeer',
736 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
737 'license': 'Standard YouTube License',
743 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
744 'description': 'md5:dc7872fb300e143831327f1bae3af010',
746 'upload_date': '20150721',
747 'uploader': 'Beer Games Beer',
748 'uploader_id': 'beergamesbeer',
749 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
750 'license': 'Standard YouTube License',
756 'title': 'teamPGP: Rocket League Noob Stream (zim)',
757 'description': 'md5:dc7872fb300e143831327f1bae3af010',
759 'upload_date': '20150721',
760 'uploader': 'Beer Games Beer',
761 'uploader_id': 'beergamesbeer',
762 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
763 'license': 'Standard YouTube License',
767 'skip_download': True,
771 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
772 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
775 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
778 'skip': 'Not multifeed anymore',
781 'url': 'https://vid.plus/FlRa-iH7PGw',
782 'only_matching': True,
785 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
786 'only_matching': True,
789 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
790 # Also tests cut-off URL expansion in video description (see
791 # https://github.com/rg3/youtube-dl/issues/1892,
792 # https://github.com/rg3/youtube-dl/issues/8164)
793 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
797 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
798 'alt_title': 'Dark Walk',
799 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
801 'upload_date': '20151119',
802 'uploader_id': 'IronSoulElf',
803 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
804 'uploader': 'IronSoulElf',
805 'license': 'Standard YouTube License',
806 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
809 'skip_download': True,
813 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
814 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
815 'only_matching': True,
818 # Video with yt:stretch=17:0
819 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
823 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
824 'description': 'md5:ee18a25c350637c8faff806845bddee9',
825 'upload_date': '20151107',
826 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
827 'uploader': 'CH GAMER DROID',
830 'skip_download': True,
832 'skip': 'This video does not exist.',
835 # Video licensed under Creative Commons
836 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
840 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
841 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
843 'upload_date': '20150127',
844 'uploader_id': 'BerkmanCenter',
845 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
846 'uploader': 'The Berkman Klein Center for Internet & Society',
847 'license': 'Creative Commons Attribution license (reuse allowed)',
850 'skip_download': True,
854 # Channel-like uploader_url
855 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
859 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
860 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
862 'upload_date': '20151119',
863 'uploader': 'Bernie 2016',
864 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
865 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
866 'license': 'Creative Commons Attribution license (reuse allowed)',
869 'skip_download': True,
873 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
874 'only_matching': True,
877 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
878 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
879 'only_matching': True,
882 # Rental video preview
883 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
887 'title': 'Piku - Trailer',
888 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
889 'upload_date': '20150811',
890 'uploader': 'FlixMatrix',
891 'uploader_id': 'FlixMatrixKaravan',
892 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
893 'license': 'Standard YouTube License',
896 'skip_download': True,
900 # YouTube Red video with episode data
901 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
905 'title': 'Isolation - Mind Field (Ep 1)',
906 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
908 'upload_date': '20170118',
909 'uploader': 'Vsauce',
910 'uploader_id': 'Vsauce',
911 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
912 'license': 'Standard YouTube License',
913 'series': 'Mind Field',
918 'skip_download': True,
920 'expected_warnings': [
921 'Skipping DASH manifest',
926 'url': '1t24XAntNCY',
927 'only_matching': True,
930 # geo restricted to JP
931 'url': 'sJL6WA-aGkQ',
932 'only_matching': True,
935 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
936 'only_matching': True,
940 def __init__(self
, *args
, **kwargs
):
941 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
942 self
._player
_cache
= {}
944 def report_video_info_webpage_download(self
, video_id
):
945 """Report attempt to download video info webpage."""
946 self
.to_screen('%s: Downloading video info webpage' % video_id
)
948 def report_information_extraction(self
, video_id
):
949 """Report attempt to extract video information."""
950 self
.to_screen('%s: Extracting video information' % video_id
)
952 def report_unavailable_format(self
, video_id
, format
):
953 """Report extracted video URL."""
954 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
956 def report_rtmp_download(self
):
957 """Indicate the download will use the RTMP protocol."""
958 self
.to_screen('RTMP download detected')
960 def _signature_cache_id(self
, example_sig
):
961 """ Return a string representation of a signature """
962 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
964 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
966 r
'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
969 raise ExtractorError('Cannot identify player %r' % player_url
)
970 player_type
= id_m
.group('ext')
971 player_id
= id_m
.group('id')
973 # Read from filesystem cache
974 func_id
= '%s_%s_%s' % (
975 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
976 assert os
.path
.basename(func_id
) == func_id
978 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
979 if cache_spec
is not None:
980 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
983 'Downloading player %s' % player_url
984 if self
._downloader
.params
.get('verbose') else
985 'Downloading %s player %s' % (player_type
, player_id
)
987 if player_type
== 'js':
988 code
= self
._download
_webpage
(
989 player_url
, video_id
,
991 errnote
='Download of %s failed' % player_url
)
992 res
= self
._parse
_sig
_js
(code
)
993 elif player_type
== 'swf':
994 urlh
= self
._request
_webpage
(
995 player_url
, video_id
,
997 errnote
='Download of %s failed' % player_url
)
999 res
= self
._parse
_sig
_swf
(code
)
1001 assert False, 'Invalid player type %r' % player_type
1003 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1004 cache_res
= res(test_string
)
1005 cache_spec
= [ord(c
) for c
in cache_res
]
1007 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1010 def _print_sig_code(self
, func
, example_sig
):
1011 def gen_sig_code(idxs
):
1012 def _genslice(start
, end
, step
):
1013 starts
= '' if start
== 0 else str(start
)
1014 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1015 steps
= '' if step
== 1 else (':%d' % step
)
1016 return 's[%s%s%s]' % (starts
, ends
, steps
)
1019 # Quelch pyflakes warnings - start will be set when step is set
1020 start
= '(Never used)'
1021 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1022 if step
is not None:
1023 if i
- prev
== step
:
1025 yield _genslice(start
, prev
, step
)
1028 if i
- prev
in [-1, 1]:
1033 yield 's[%d]' % prev
1037 yield _genslice(start
, i
, step
)
1039 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1040 cache_res
= func(test_string
)
1041 cache_spec
= [ord(c
) for c
in cache_res
]
1042 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1043 signature_id_tuple
= '(%s)' % (
1044 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1045 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1046 ' return %s\n') % (signature_id_tuple
, expr_code
)
1047 self
.to_screen('Extracted signature function:\n' + code
)
1049 def _parse_sig_js(self
, jscode
):
1050 funcname
= self
._search
_regex
(
1051 (r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1052 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1053 jscode, 'Initial JS player signature function name
', group='sig
')
1055 jsi = JSInterpreter(jscode)
1056 initial_function = jsi.extract_function(funcname)
1057 return lambda s: initial_function([s])
1059 def _parse_sig_swf(self, file_contents):
1060 swfi = SWFInterpreter(file_contents)
1061 TARGET_CLASSNAME = 'SignatureDecipher
'
1062 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1063 initial_function = swfi.extract_function(searched_class, 'decipher
')
1064 return lambda s: initial_function([s])
1066 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1067 """Turn the encrypted s field into a working signature"""
1069 if player_url is None:
1070 raise ExtractorError('Cannot decrypt signature without player_url
')
1072 if player_url.startswith('//'):
1073 player_url = 'https
:' + player_url
1074 elif not re.match(r'https?
://', player_url):
1075 player_url = compat_urlparse.urljoin(
1076 'https
://www
.youtube
.com
', player_url)
1078 player_id = (player_url, self._signature_cache_id(s))
1079 if player_id not in self._player_cache:
1080 func = self._extract_signature_function(
1081 video_id, player_url, s
1083 self._player_cache[player_id] = func
1084 func = self._player_cache[player_id]
1085 if self._downloader.params.get('youtube_print_sig_code
'):
1086 self._print_sig_code(func, s)
1088 except Exception as e:
1089 tb = traceback.format_exc()
1090 raise ExtractorError(
1091 'Signature extraction failed
: ' + tb, cause=e)
1093 def _get_subtitles(self, video_id, webpage):
1095 subs_doc = self._download_xml(
1096 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1097 video_id, note=False)
1098 except ExtractorError as err:
1099 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1103 for track in subs_doc.findall('track
'):
1104 lang = track.attrib['lang_code
']
1105 if lang in sub_lang_list:
1108 for ext in self._SUBTITLE_FORMATS:
1109 params = compat_urllib_parse_urlencode({
1113 'name
': track.attrib['name
'].encode('utf
-8'),
1115 sub_formats.append({
1116 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1119 sub_lang_list[lang] = sub_formats
1120 if not sub_lang_list:
1121 self._downloader.report_warning('video doesn
\'t have subtitles
')
1123 return sub_lang_list
1125 def _get_ytplayer_config(self, video_id, webpage):
1127 # User data may contain arbitrary character sequences that may affect
1128 # JSON extraction with regex, e.g. when '};' is contained the second
1129 # regex won't capture the whole JSON
. Yet working around by trying more
1130 # concrete regex first keeping in mind proper quoted string handling
1131 # to be implemented in future that will replace this workaround (see
1132 # https://github.com/rg3/youtube-dl/issues/7468,
1133 # https://github.com/rg3/youtube-dl/pull/7599)
1134 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1135 r
';ytplayer\.config\s*=\s*({.+?});',
1137 config
= self
._search
_regex
(
1138 patterns
, webpage
, 'ytplayer.config', default
=None)
1140 return self
._parse
_json
(
1141 uppercase_escape(config
), video_id
, fatal
=False)
1143 def _get_automatic_captions(self
, video_id
, webpage
):
1144 """We need the webpage for getting the captions url, pass it as an
1145 argument to speed up the process."""
1146 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1147 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1148 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1149 if not player_config
:
1150 self
._downloader
.report_warning(err_msg
)
1153 args
= player_config
['args']
1154 caption_url
= args
.get('ttsurl')
1156 timestamp
= args
['timestamp']
1157 # We get the available subtitles
1158 list_params
= compat_urllib_parse_urlencode({
1163 list_url
= caption_url
+ '&' + list_params
1164 caption_list
= self
._download
_xml
(list_url
, video_id
)
1165 original_lang_node
= caption_list
.find('track')
1166 if original_lang_node
is None:
1167 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1169 original_lang
= original_lang_node
.attrib
['lang_code']
1170 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1173 for lang_node
in caption_list
.findall('target'):
1174 sub_lang
= lang_node
.attrib
['lang_code']
1176 for ext
in self
._SUBTITLE
_FORMATS
:
1177 params
= compat_urllib_parse_urlencode({
1178 'lang': original_lang
,
1182 'kind': caption_kind
,
1184 sub_formats
.append({
1185 'url': caption_url
+ '&' + params
,
1188 sub_lang_list
[sub_lang
] = sub_formats
1189 return sub_lang_list
1191 # Some videos don't provide ttsurl but rather caption_tracks and
1192 # caption_translation_languages (e.g. 20LmZk1hakA)
1193 caption_tracks
= args
['caption_tracks']
1194 caption_translation_languages
= args
['caption_translation_languages']
1195 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1196 parsed_caption_url
= compat_urllib_parse_urlparse(caption_url
)
1197 caption_qs
= compat_parse_qs(parsed_caption_url
.query
)
1200 for lang
in caption_translation_languages
.split(','):
1201 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1202 sub_lang
= lang_qs
.get('lc', [None])[0]
1206 for ext
in self
._SUBTITLE
_FORMATS
:
1208 'tlang': [sub_lang
],
1211 sub_url
= compat_urlparse
.urlunparse(parsed_caption_url
._replace
(
1212 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1213 sub_formats
.append({
1217 sub_lang_list
[sub_lang
] = sub_formats
1218 return sub_lang_list
1219 # An extractor error can be raise by the download process if there are
1220 # no automatic captions but there are subtitles
1221 except (KeyError, ExtractorError
):
1222 self
._downloader
.report_warning(err_msg
)
1225 def _mark_watched(self
, video_id
, video_info
):
1226 playback_url
= video_info
.get('videostats_playback_base_url', [None])[0]
1227 if not playback_url
:
1229 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1230 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1232 # cpn generation algorithm is reverse engineered from base.js.
1233 # In fact it works even with dummy cpn.
1234 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1235 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1241 playback_url
= compat_urlparse
.urlunparse(
1242 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1244 self
._download
_webpage
(
1245 playback_url
, video_id
, 'Marking watched',
1246 'Unable to mark watched', fatal
=False)
1249 def extract_id(cls
, url
):
1250 mobj
= re
.match(cls
._VALID
_URL
, url
, re
.VERBOSE
)
1252 raise ExtractorError('Invalid URL: %s' % url
)
1253 video_id
= mobj
.group(2)
1256 def _extract_from_m3u8(self
, manifest_url
, video_id
):
1259 def _get_urls(_manifest
):
1260 lines
= _manifest
.split('\n')
1261 urls
= filter(lambda l
: l
and not l
.startswith('#'),
1264 manifest
= self
._download
_webpage
(manifest_url
, video_id
, 'Downloading formats manifest')
1265 formats_urls
= _get_urls(manifest
)
1266 for format_url
in formats_urls
:
1267 itag
= self
._search
_regex
(r
'itag/(\d+?)/', format_url
, 'itag')
1268 url_map
[itag
] = format_url
1271 def _extract_annotations(self
, video_id
):
1272 url
= 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1273 return self
._download
_webpage
(url
, video_id
, note
='Searching for annotations.', errnote
='Unable to download video annotations.')
1275 def _real_extract(self
, url
):
1276 url
, smuggled_data
= unsmuggle_url(url
, {})
1279 'http' if self
._downloader
.params
.get('prefer_insecure', False)
1284 parsed_url
= compat_urllib_parse_urlparse(url
)
1285 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
1286 query
= compat_parse_qs(component
)
1287 if start_time
is None and 't' in query
:
1288 start_time
= parse_duration(query
['t'][0])
1289 if start_time
is None and 'start' in query
:
1290 start_time
= parse_duration(query
['start'][0])
1291 if end_time
is None and 'end' in query
:
1292 end_time
= parse_duration(query
['end'][0])
1294 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1295 mobj
= re
.search(self
._NEXT
_URL
_RE
, url
)
1297 url
= proto
+ '://www.youtube.com/' + compat_urllib_parse_unquote(mobj
.group(1)).lstrip('/')
1298 video_id
= self
.extract_id(url
)
1301 url
= proto
+ '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1302 video_webpage
= self
._download
_webpage
(url
, video_id
)
1304 # Attempt to extract SWF player URL
1305 mobj
= re
.search(r
'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage
)
1306 if mobj
is not None:
1307 player_url
= re
.sub(r
'\\(.)', r
'\1', mobj
.group(1))
1313 def add_dash_mpd(video_info
):
1314 dash_mpd
= video_info
.get('dashmpd')
1315 if dash_mpd
and dash_mpd
[0] not in dash_mpds
:
1316 dash_mpds
.append(dash_mpd
[0])
1319 embed_webpage
= None
1321 if re
.search(r
'player-age-gate-content">', video_webpage
) is not None:
1323 # We simulate the access to the video from www.youtube.com/v/{video_id}
1324 # this can be viewed without login into Youtube
1325 url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1326 embed_webpage
= self
._download
_webpage
(url
, video_id
, 'Downloading embed webpage')
1327 data
= compat_urllib_parse_urlencode({
1328 'video_id': video_id
,
1329 'eurl': 'https://youtube.googleapis.com/v/' + video_id
,
1330 'sts': self
._search
_regex
(
1331 r
'"sts"\s*:\s*(\d+)', embed_webpage
, 'sts', default
=''),
1333 video_info_url
= proto
+ '://www.youtube.com/get_video_info?' + data
1334 video_info_webpage
= self
._download
_webpage
(
1335 video_info_url
, video_id
,
1336 note
='Refetching age-gated info webpage',
1337 errnote
='unable to download video info webpage')
1338 video_info
= compat_parse_qs(video_info_webpage
)
1339 add_dash_mpd(video_info
)
1343 # Try looking directly into the video webpage
1344 ytplayer_config
= self
._get
_ytplayer
_config
(video_id
, video_webpage
)
1346 args
= ytplayer_config
['args']
1347 if args
.get('url_encoded_fmt_stream_map'):
1348 # Convert to the same format returned by compat_parse_qs
1349 video_info
= dict((k
, [v
]) for k
, v
in args
.items())
1350 add_dash_mpd(video_info
)
1351 # Rental video is not rented but preview is available (e.g.
1352 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1353 # https://github.com/rg3/youtube-dl/issues/10532)
1354 if not video_info
and args
.get('ypc_vid'):
1355 return self
.url_result(
1356 args
['ypc_vid'], YoutubeIE
.ie_key(), video_id
=args
['ypc_vid'])
1357 if args
.get('livestream') == '1' or args
.get('live_playback') == 1:
1359 if not video_info
or self
._downloader
.params
.get('youtube_include_dash_manifest', True):
1360 # We also try looking in get_video_info since it may contain different dashmpd
1361 # URL that points to a DASH manifest with possibly different itag set (some itags
1362 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1363 # manifest pointed by get_video_info's dashmpd).
1364 # The general idea is to take a union of itags of both DASH manifests (for example
1365 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1366 self
.report_video_info_webpage_download(video_id
)
1367 for el_type
in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1369 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1370 % (proto
, video_id
, el_type
))
1371 video_info_webpage
= self
._download
_webpage
(
1373 video_id
, note
=False,
1374 errnote
='unable to download video info webpage')
1375 get_video_info
= compat_parse_qs(video_info_webpage
)
1376 if get_video_info
.get('use_cipher_signature') != ['True']:
1377 add_dash_mpd(get_video_info
)
1379 video_info
= get_video_info
1380 if 'token' in get_video_info
:
1381 # Different get_video_info requests may report different results, e.g.
1382 # some may report video unavailability, but some may serve it without
1383 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1384 # the original webpage as well as el=info and el=embedded get_video_info
1385 # requests report video unavailability due to geo restriction while
1386 # el=detailpage succeeds and returns valid data). This is probably
1387 # due to YouTube measures against IP ranges of hosting providers.
1388 # Working around by preferring the first succeeded video_info containing
1389 # the token if no such video_info yet was found.
1390 if 'token' not in video_info
:
1391 video_info
= get_video_info
1393 if 'token' not in video_info
:
1394 if 'reason' in video_info
:
1395 if 'The uploader has not made this video available in your country.' in video_info
['reason']:
1396 regions_allowed
= self
._html
_search
_meta
(
1397 'regionsAllowed', video_webpage
, default
=None)
1398 countries
= regions_allowed
.split(',') if regions_allowed
else None
1399 self
.raise_geo_restricted(
1400 msg
=video_info
['reason'][0], countries
=countries
)
1401 raise ExtractorError(
1402 'YouTube said: %s' % video_info
['reason'][0],
1403 expected
=True, video_id
=video_id
)
1405 raise ExtractorError(
1406 '"token" parameter not in video info for unknown reason',
1410 if 'title' in video_info
:
1411 video_title
= video_info
['title'][0]
1413 self
._downloader
.report_warning('Unable to extract video title')
1417 video_description
= get_element_by_id("eow-description", video_webpage
)
1418 if video_description
:
1419 video_description
= re
.sub(r
'''(?x)
1421 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1422 (?:title|href)="([^"]+)"\s+
1423 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1427 ''', r
'\1', video_description
)
1428 video_description
= clean_html(video_description
)
1430 fd_mobj
= re
.search(r
'<meta name="description" content="([^"]+)"', video_webpage
)
1432 video_description
= unescapeHTML(fd_mobj
.group(1))
1434 video_description
= ''
1436 if 'multifeed_metadata_list' in video_info
and not smuggled_data
.get('force_singlefeed', False):
1437 if not self
._downloader
.params
.get('noplaylist'):
1440 multifeed_metadata_list
= video_info
['multifeed_metadata_list'][0]
1441 for feed
in multifeed_metadata_list
.split(','):
1442 # Unquote should take place before split on comma (,) since textual
1443 # fields may contain comma as well (see
1444 # https://github.com/rg3/youtube-dl/issues/8536)
1445 feed_data
= compat_parse_qs(compat_urllib_parse_unquote_plus(feed
))
1447 '_type': 'url_transparent',
1448 'ie_key': 'Youtube',
1450 '%s://www.youtube.com/watch?v=%s' % (proto
, feed_data
['id'][0]),
1451 {'force_singlefeed': True}),
1452 'title': '%s (%s)' % (video_title
, feed_data
['title'][0]),
1454 feed_ids
.append(feed_data
['id'][0])
1456 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1457 % (', '.join(feed_ids
), video_id
))
1458 return self
.playlist_result(entries
, video_id
, video_title
, video_description
)
1459 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
1461 if 'view_count' in video_info
:
1462 view_count
= int(video_info
['view_count'][0])
1466 # Check for "rental" videos
1467 if 'ypc_video_rental_bar_text' in video_info
and 'author' not in video_info
:
1468 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected
=True)
1470 # Start extracting information
1471 self
.report_information_extraction(video_id
)
1474 if 'author' not in video_info
:
1475 raise ExtractorError('Unable to extract uploader name')
1476 video_uploader
= compat_urllib_parse_unquote_plus(video_info
['author'][0])
1479 video_uploader_id
= None
1480 video_uploader_url
= None
1482 r
'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1484 if mobj
is not None:
1485 video_uploader_id
= mobj
.group('uploader_id')
1486 video_uploader_url
= mobj
.group('uploader_url')
1488 self
._downloader
.report_warning('unable to extract uploader nickname')
1491 # We try first to get a high quality image:
1492 m_thumb
= re
.search(r
'<span itemprop="thumbnail".*?href="(.*?)">',
1493 video_webpage
, re
.DOTALL
)
1494 if m_thumb
is not None:
1495 video_thumbnail
= m_thumb
.group(1)
1496 elif 'thumbnail_url' not in video_info
:
1497 self
._downloader
.report_warning('unable to extract video thumbnail')
1498 video_thumbnail
= None
1499 else: # don't panic if we can't find it
1500 video_thumbnail
= compat_urllib_parse_unquote_plus(video_info
['thumbnail_url'][0])
1503 upload_date
= self
._html
_search
_meta
(
1504 'datePublished', video_webpage
, 'upload date', default
=None)
1506 upload_date
= self
._search
_regex
(
1507 [r
'(?s)id="eow-date.*?>(.*?)</span>',
1508 r
'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1509 video_webpage
, 'upload date', default
=None)
1511 upload_date
= ' '.join(re
.sub(r
'[/,-]', r
' ', mobj
.group(1)).split())
1512 upload_date
= unified_strdate(upload_date
)
1514 video_license
= self
._html
_search
_regex
(
1515 r
'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1516 video_webpage
, 'license', default
=None)
1518 m_music
= re
.search(
1519 r
'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1522 video_alt_title
= remove_quotes(unescapeHTML(m_music
.group('title')))
1523 video_creator
= clean_html(m_music
.group('creator'))
1525 video_alt_title
= video_creator
= None
1527 m_episode
= re
.search(
1528 r
'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*ā¢\s*E(?P<episode>\d+)</span>',
1531 series
= m_episode
.group('series')
1532 season_number
= int(m_episode
.group('season'))
1533 episode_number
= int(m_episode
.group('episode'))
1535 series
= season_number
= episode_number
= None
1537 m_cat_container
= self
._search
_regex
(
1538 r
'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1539 video_webpage
, 'categories', default
=None)
1541 category
= self
._html
_search
_regex
(
1542 r
'(?s)<a[^<]+>(.*?)</a>', m_cat_container
, 'category',
1544 video_categories
= None if category
is None else [category
]
1546 video_categories
= None
1549 unescapeHTML(m
.group('content'))
1550 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), video_webpage
)]
1552 def _extract_count(count_name
):
1553 return str_to_int(self
._search
_regex
(
1554 r
'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1555 % re
.escape(count_name
),
1556 video_webpage
, count_name
, default
=None))
1558 like_count
= _extract_count('like')
1559 dislike_count
= _extract_count('dislike')
1562 video_subtitles
= self
.extract_subtitles(video_id
, video_webpage
)
1563 automatic_captions
= self
.extract_automatic_captions(video_id
, video_webpage
)
1565 video_duration
= try_get(
1566 video_info
, lambda x
: int_or_none(x
['length_seconds'][0]))
1567 if not video_duration
:
1568 video_duration
= parse_duration(self
._html
_search
_meta
(
1569 'duration', video_webpage
, 'video duration'))
1572 video_annotations
= None
1573 if self
._downloader
.params
.get('writeannotations', False):
1574 video_annotations
= self
._extract
_annotations
(video_id
)
1576 def _map_to_format_list(urlmap
):
1578 for itag
, video_real_url
in urlmap
.items():
1581 'url': video_real_url
,
1582 'player_url': player_url
,
1584 if itag
in self
._formats
:
1585 dct
.update(self
._formats
[itag
])
1589 if 'conn' in video_info
and video_info
['conn'][0].startswith('rtmp'):
1590 self
.report_rtmp_download()
1592 'format_id': '_rtmp',
1594 'url': video_info
['conn'][0],
1595 'player_url': player_url
,
1597 elif len(video_info
.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info
.get('adaptive_fmts', [''])[0]) >= 1:
1598 encoded_url_map
= video_info
.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info
.get('adaptive_fmts', [''])[0]
1599 if 'rtmpe%3Dyes' in encoded_url_map
:
1600 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected
=True)
1602 fmt_list
= video_info
.get('fmt_list', [''])[0]
1604 for fmt
in fmt_list
.split(','):
1605 spec
= fmt
.split('/')
1607 width_height
= spec
[1].split('x')
1608 if len(width_height
) == 2:
1609 formats_spec
[spec
[0]] = {
1610 'resolution': spec
[1],
1611 'width': int_or_none(width_height
[0]),
1612 'height': int_or_none(width_height
[1]),
1615 for url_data_str
in encoded_url_map
.split(','):
1616 url_data
= compat_parse_qs(url_data_str
)
1617 if 'itag' not in url_data
or 'url' not in url_data
:
1619 format_id
= url_data
['itag'][0]
1620 url
= url_data
['url'][0]
1622 if 'sig' in url_data
:
1623 url
+= '&signature=' + url_data
['sig'][0]
1624 elif 's' in url_data
:
1625 encrypted_sig
= url_data
['s'][0]
1626 ASSETS_RE
= r
'"assets":.+?"js":\s*("[^"]+")'
1628 jsplayer_url_json
= self
._search
_regex
(
1630 embed_webpage
if age_gate
else video_webpage
,
1631 'JS player URL (1)', default
=None)
1632 if not jsplayer_url_json
and not age_gate
:
1633 # We need the embed website after all
1634 if embed_webpage
is None:
1635 embed_url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1636 embed_webpage
= self
._download
_webpage
(
1637 embed_url
, video_id
, 'Downloading embed webpage')
1638 jsplayer_url_json
= self
._search
_regex
(
1639 ASSETS_RE
, embed_webpage
, 'JS player URL')
1641 player_url
= json
.loads(jsplayer_url_json
)
1642 if player_url
is None:
1643 player_url_json
= self
._search
_regex
(
1644 r
'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1645 video_webpage
, 'age gate player URL')
1646 player_url
= json
.loads(player_url_json
)
1648 if self
._downloader
.params
.get('verbose'):
1649 if player_url
is None:
1650 player_version
= 'unknown'
1651 player_desc
= 'unknown'
1653 if player_url
.endswith('swf'):
1654 player_version
= self
._search
_regex
(
1655 r
'-(.+?)(?:/watch_as3)?\.swf$', player_url
,
1656 'flash player', fatal
=False)
1657 player_desc
= 'flash player %s' % player_version
1659 player_version
= self
._search
_regex
(
1660 [r
'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r
'(?:www|player)-([^/]+)/base\.js'],
1662 'html5 player', fatal
=False)
1663 player_desc
= 'html5 player %s' % player_version
1665 parts_sizes
= self
._signature
_cache
_id
(encrypted_sig
)
1666 self
.to_screen('{%s} signature length %s, %s' %
1667 (format_id
, parts_sizes
, player_desc
))
1669 signature
= self
._decrypt
_signature
(
1670 encrypted_sig
, video_id
, player_url
, age_gate
)
1671 url
+= '&signature=' + signature
1672 if 'ratebypass' not in url
:
1673 url
+= '&ratebypass=yes'
1676 'format_id': format_id
,
1678 'player_url': player_url
,
1680 if format_id
in self
._formats
:
1681 dct
.update(self
._formats
[format_id
])
1682 if format_id
in formats_spec
:
1683 dct
.update(formats_spec
[format_id
])
1685 # Some itags are not included in DASH manifest thus corresponding formats will
1686 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1687 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1688 mobj
= re
.search(r
'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data
.get('size', [''])[0])
1689 width
, height
= (int(mobj
.group('width')), int(mobj
.group('height'))) if mobj
else (None, None)
1692 'filesize': int_or_none(url_data
.get('clen', [None])[0]),
1693 'tbr': float_or_none(url_data
.get('bitrate', [None])[0], 1000),
1696 'fps': int_or_none(url_data
.get('fps', [None])[0]),
1697 'format_note': url_data
.get('quality_label', [None])[0] or url_data
.get('quality', [None])[0],
1699 for key
, value
in more_fields
.items():
1702 type_
= url_data
.get('type', [None])[0]
1704 type_split
= type_
.split(';')
1705 kind_ext
= type_split
[0].split('/')
1706 if len(kind_ext
) == 2:
1708 dct
['ext'] = mimetype2ext(type_split
[0])
1709 if kind
in ('audio', 'video'):
1711 for mobj
in re
.finditer(
1712 r
'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
1713 if mobj.group('key
') == 'codecs
':
1714 codecs = mobj.group('val
')
1717 dct.update(parse_codecs(codecs))
1719 elif video_info.get('hlsvp
'):
1720 manifest_url = video_info['hlsvp
'][0]
1721 url_map = self._extract_from_m3u8(manifest_url, video_id)
1722 formats = _map_to_format_list(url_map)
1723 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1724 for a_format in formats:
1725 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
1727 unavailable_message = self._html_search_regex(
1728 r'(?s
)<h1
[^
>]+id="unavailable-message"[^
>]*>(.+?
)</h1
>',
1729 video_webpage, 'unavailable message
', default=None)
1730 if unavailable_message:
1731 raise ExtractorError(unavailable_message, expected=True)
1732 raise ExtractorError('no conn
, hlsvp
or url_encoded_fmt_stream_map information found
in video info
')
1734 # Look for the DASH manifest
1735 if self._downloader.params.get('youtube_include_dash_manifest
', True):
1736 dash_mpd_fatal = True
1737 for mpd_url in dash_mpds:
1740 def decrypt_sig(mobj):
1742 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1743 return '/signature
/%s' % dec_s
1745 mpd_url = re.sub(r'/s
/([a
-fA
-F0
-9\
.]+)', decrypt_sig, mpd_url)
1747 for df in self._extract_mpd_formats(
1748 mpd_url, video_id, fatal=dash_mpd_fatal,
1749 formats_dict=self._formats):
1750 # Do not overwrite DASH format found in some previous DASH manifest
1751 if df['format_id
'] not in dash_formats:
1752 dash_formats[df['format_id
']] = df
1753 # Additional DASH manifests may end up in HTTP Error 403 therefore
1754 # allow them to fail without bug report message if we already have
1755 # some DASH manifest succeeded. This is temporary workaround to reduce
1756 # burst of bug reports until we figure out the reason and whether it
1757 # can be fixed at all.
1758 dash_mpd_fatal = False
1759 except (ExtractorError, KeyError) as e:
1760 self.report_warning(
1761 'Skipping DASH manifest
: %r' % e, video_id)
1763 # Remove the formats we found through non-DASH, they
1764 # contain less info and it can be wrong, because we use
1765 # fixed values (for example the resolution). See
1766 # https://github.com/rg3/youtube-dl/issues/5774 for an
1768 formats = [f for f in formats if f['format_id
'] not in dash_formats.keys()]
1769 formats.extend(dash_formats.values())
1771 # Check for malformed aspect ratio
1772 stretched_m = re.search(
1773 r'<meta\s
+property="og:video:tag".*?content
="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1776 w = float(stretched_m.group('w
'))
1777 h = float(stretched_m.group('h
'))
1778 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1779 # We will only process correct ratios.
1783 if f.get('vcodec
') != 'none
':
1784 f['stretched_ratio
'] = ratio
1786 self._sort_formats(formats)
1788 self.mark_watched(video_id, video_info)
1792 'uploader
': video_uploader,
1793 'uploader_id
': video_uploader_id,
1794 'uploader_url
': video_uploader_url,
1795 'upload_date
': upload_date,
1796 'license
': video_license,
1797 'creator
': video_creator,
1798 'title
': video_title,
1799 'alt_title
': video_alt_title,
1800 'thumbnail
': video_thumbnail,
1801 'description
': video_description,
1802 'categories
': video_categories,
1804 'subtitles
': video_subtitles,
1805 'automatic_captions
': automatic_captions,
1806 'duration
': video_duration,
1807 'age_limit
': 18 if age_gate else 0,
1808 'annotations
': video_annotations,
1809 'webpage_url
': proto + '://www
.youtube
.com
/watch?v
=%s' % video_id,
1810 'view_count
': view_count,
1811 'like_count
': like_count,
1812 'dislike_count
': dislike_count,
1813 'average_rating
': float_or_none(video_info.get('avg_rating
', [None])[0]),
1816 'start_time
': start_time,
1817 'end_time
': end_time,
1819 'season_number
': season_number,
1820 'episode_number
': episode_number,
1824 class YoutubeSharedVideoIE(InfoExtractor):
1825 _VALID_URL = r'(?
:https?
:)?
//(?
:www\
.)?youtube\
.com
/shared
\?.*\bci
=(?P
<id>[0-9A
-Za
-z_
-]{11}
)'
1826 IE_NAME = 'youtube
:shared
'
1829 'url
': 'https
://www
.youtube
.com
/shared?ci
=1nEzmT
-M4fU
',
1831 'id': 'uPDB5I9wfp8
',
1833 'title
': 'Pocoyo
: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧ
as - PARTE
3',
1834 'description
': 'md5
:d9e4d9346a2dfff4c7dc4c8cec0f546d
',
1835 'upload_date
': '20160219',
1836 'uploader
': 'Pocoyo
- PortuguĆŖ
s (BR
)',
1837 'uploader_id
': 'PocoyoBrazil
',
1839 'add_ie
': ['Youtube
'],
1841 # There are already too many Youtube downloads
1842 'skip_download
': True,
1846 def _real_extract(self, url):
1847 video_id = self._match_id(url)
1849 webpage = self._download_webpage(url, video_id)
1851 real_video_id = self._html_search_meta(
1852 'videoId
', webpage, 'YouTube video
id', fatal=True)
1854 return self.url_result(real_video_id, YoutubeIE.ie_key())
1857 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1858 IE_DESC = 'YouTube
.com playlists
'
1859 _VALID_URL = r"""(?x)(?:
1865 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
1866 \? (?:.*?[&;])*? (?:p|a|list)=
1869 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1872 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
1873 # Top tracks, they can also include dots
1879 )""" % {'playlist_id
': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
1880 _TEMPLATE_URL = 'https
://www
.youtube
.com
/playlist?
list=%s&disable_polymer
=true
'
1881 _VIDEO_RE = r'href
="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index
=(?P
<index
>\d
+)(?
:[^
>]+>(?P
<title
>[^
<]+))?
'
1882 IE_NAME = 'youtube
:playlist
'
1884 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1886 'title
': 'ytdl test PL
',
1887 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1889 'playlist_count
': 3,
1891 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1893 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1894 'title
': 'YDL_Empty_List
',
1896 'playlist_count
': 0,
1897 'skip
': 'This playlist
is private
',
1899 'note
': 'Playlist
with deleted
videos (#651). As a bonus, the video #51 is also twice in this list.',
1900 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1902 'title': '29C3: Not my department',
1903 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1905 'playlist_count': 95,
1907 'note': 'issue #673',
1908 'url': 'PLBB231211A4F62143',
1910 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1911 'id': 'PLBB231211A4F62143',
1913 'playlist_mincount': 26,
1915 'note': 'Large playlist',
1916 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1918 'title': 'Uploads from Cauchemar',
1919 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1921 'playlist_mincount': 799,
1923 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1925 'title': 'YDL_safe_search',
1926 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1928 'playlist_count': 2,
1929 'skip': 'This playlist is private',
1932 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1933 'playlist_count': 4,
1936 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1939 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1940 'playlist_mincount': 485,
1942 'title': '2017 čÆčŖęę°å®ę² (2/24ę“ę°)',
1943 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1946 'note': 'Embedded SWF player',
1947 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1948 'playlist_count': 4,
1951 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1954 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1955 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1957 'title': 'Uploads from Interstellar Movie',
1958 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1960 'playlist_mincount': 21,
1962 # Playlist URL that does not actually serve a playlist
1963 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1965 'id': 'FqZTN594JQw',
1967 'title': "Smiley's People 01 detective, Adventure Series, Action",
1968 'uploader': 'STREEM',
1969 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1970 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1971 'upload_date': '20150526',
1972 'license': 'Standard YouTube License',
1973 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1974 'categories': ['People & Blogs'],
1977 'dislike_count': int,
1980 'skip_download': True,
1982 'add_ie': [YoutubeIE
.ie_key()],
1984 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1986 'id': 'yeWKywCrFtk',
1988 'title': 'Small Scale Baler and Braiding Rugs',
1989 'uploader': 'Backus-Page House Museum',
1990 'uploader_id': 'backuspagemuseum',
1991 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1992 'upload_date': '20161008',
1993 'license': 'Standard YouTube License',
1994 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1995 'categories': ['Nonprofits & Activism'],
1998 'dislike_count': int,
2002 'skip_download': True,
2005 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2006 'only_matching': True,
2008 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2009 'only_matching': True,
2012 def _real_initialize(self
):
2015 def _extract_mix(self
, playlist_id
):
2016 # The mixes are generated from a single video
2017 # the id of the playlist is just 'RD' + video_id
2019 last_id
= playlist_id
[-11:]
2020 for n
in itertools
.count(1):
2021 url
= 'https://youtube.com/watch?v=%s&list=%s' % (last_id
, playlist_id
)
2022 webpage
= self
._download
_webpage
(
2023 url
, playlist_id
, 'Downloading page {0} of Youtube mix'.format(n
))
2024 new_ids
= orderedSet(re
.findall(
2025 r
'''(?xs)data-video-username=".*?".*?
2026 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re
.escape(playlist_id
),
2028 # Fetch new pages until all the videos are repeated, it seems that
2029 # there are always 51 unique videos.
2030 new_ids
= [_id
for _id
in new_ids
if _id
not in ids
]
2036 url_results
= self
._ids
_to
_results
(ids
)
2038 search_title
= lambda class_name
: get_element_by_attribute('class', class_name
, webpage
)
2040 search_title('playlist-title') or
2041 search_title('title long-title') or
2042 search_title('title'))
2043 title
= clean_html(title_span
)
2045 return self
.playlist_result(url_results
, playlist_id
, title
)
2047 def _extract_playlist(self
, playlist_id
):
2048 url
= self
._TEMPLATE
_URL
% playlist_id
2049 page
= self
._download
_webpage
(url
, playlist_id
)
2051 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2052 for match
in re
.findall(r
'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page
):
2053 match
= match
.strip()
2054 # Check if the playlist exists or is private
2055 mobj
= re
.match(r
'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match
)
2057 reason
= mobj
.group('reason')
2058 message
= 'This playlist %s' % reason
2059 if 'private' in reason
:
2060 message
+= ', use --username or --netrc to access it'
2062 raise ExtractorError(message
, expected
=True)
2063 elif re
.match(r
'[^<]*Invalid parameters[^<]*', match
):
2064 raise ExtractorError(
2065 'Invalid parameters. Maybe URL is incorrect.',
2067 elif re
.match(r
'[^<]*Choose your language[^<]*', match
):
2070 self
.report_warning('Youtube gives an alert message: ' + match
)
2072 playlist_title
= self
._html
_search
_regex
(
2073 r
'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2074 page
, 'title', default
=None)
2078 if not playlist_title
:
2080 # Some playlist URLs don't actually serve a playlist (e.g.
2081 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2082 next(self
._entries
(page
, playlist_id
))
2083 except StopIteration:
2086 return has_videos
, self
.playlist_result(
2087 self
._entries
(page
, playlist_id
), playlist_id
, playlist_title
)
2089 def _check_download_just_video(self
, url
, playlist_id
):
2090 # Check if it's a video-specific URL
2091 query_dict
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
2092 video_id
= query_dict
.get('v', [None])[0] or self
._search
_regex
(
2093 r
'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url
,
2094 'video id', default
=None)
2096 if self
._downloader
.params
.get('noplaylist'):
2097 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
2098 return video_id
, self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2100 self
.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id
, video_id
))
2101 return video_id
, None
2104 def _real_extract(self
, url
):
2105 # Extract playlist id
2106 mobj
= re
.match(self
._VALID
_URL
, url
)
2108 raise ExtractorError('Invalid URL: %s' % url
)
2109 playlist_id
= mobj
.group(1) or mobj
.group(2)
2111 video_id
, video
= self
._check
_download
_just
_video
(url
, playlist_id
)
2115 if playlist_id
.startswith(('RD', 'UL', 'PU')):
2116 # Mixes require a custom extraction process
2117 return self
._extract
_mix
(playlist_id
)
2119 has_videos
, playlist
= self
._extract
_playlist
(playlist_id
)
2120 if has_videos
or not video_id
:
2123 # Some playlist URLs don't actually serve a playlist (see
2124 # https://github.com/rg3/youtube-dl/issues/10537).
2125 # Fallback to plain video extraction if there is a video id
2126 # along with playlist id.
2127 return self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2130 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor
):
2131 IE_DESC
= 'YouTube.com channels'
2132 _VALID_URL
= r
'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2133 _TEMPLATE_URL
= 'https://www.youtube.com/channel/%s/videos'
2134 _VIDEO_RE
= r
'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2135 IE_NAME
= 'youtube:channel'
2137 'note': 'paginated channel',
2138 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2139 'playlist_mincount': 91,
2141 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2142 'title': 'Uploads from lex will',
2145 'note': 'Age restricted channel',
2146 # from https://www.youtube.com/user/DeusExOfficial
2147 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2148 'playlist_mincount': 64,
2150 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2151 'title': 'Uploads from Deus Ex',
2156 def suitable(cls
, url
):
2157 return (False if YoutubePlaylistsIE
.suitable(url
) or YoutubeLiveIE
.suitable(url
)
2158 else super(YoutubeChannelIE
, cls
).suitable(url
))
2160 def _build_template_url(self
, url
, channel_id
):
2161 return self
._TEMPLATE
_URL
% channel_id
2163 def _real_extract(self
, url
):
2164 channel_id
= self
._match
_id
(url
)
2166 url
= self
._build
_template
_url
(url
, channel_id
)
2168 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2169 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2170 # otherwise fallback on channel by page extraction
2171 channel_page
= self
._download
_webpage
(
2172 url
+ '?view=57', channel_id
,
2173 'Downloading channel page', fatal
=False)
2174 if channel_page
is False:
2175 channel_playlist_id
= False
2177 channel_playlist_id
= self
._html
_search
_meta
(
2178 'channelId', channel_page
, 'channel id', default
=None)
2179 if not channel_playlist_id
:
2180 channel_url
= self
._html
_search
_meta
(
2181 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2182 channel_page
, 'channel url', default
=None)
2184 channel_playlist_id
= self
._search
_regex
(
2185 r
'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2186 channel_url
, 'channel id', default
=None)
2187 if channel_playlist_id
and channel_playlist_id
.startswith('UC'):
2188 playlist_id
= 'UU' + channel_playlist_id
[2:]
2189 return self
.url_result(
2190 compat_urlparse
.urljoin(url
, '/playlist?list=%s' % playlist_id
), 'YoutubePlaylist')
2192 channel_page
= self
._download
_webpage
(url
, channel_id
, 'Downloading page #1')
2193 autogenerated
= re
.search(r
'''(?x)
2195 channel-header-autogenerated-label|
2196 yt-channel-title-autogenerated
2197 )[^"]*"''', channel_page
) is not None
2200 # The videos are contained in a single page
2201 # the ajax pages can't be used, they are empty
2204 video_id
, 'Youtube', video_id
=video_id
,
2205 video_title
=video_title
)
2206 for video_id
, video_title
in self
.extract_videos_from_page(channel_page
)]
2207 return self
.playlist_result(entries
, channel_id
)
2210 next(self
._entries
(channel_page
, channel_id
))
2211 except StopIteration:
2212 alert_message
= self
._html
_search
_regex
(
2213 r
'(?s)<div[^>]+class=(["\']).*?
\byt
-alert
-message
\b.*?\
1[^
>]*>(?P
<alert
>[^
<]+)</div
>',
2214 channel_page, 'alert
', default=None, group='alert
')
2216 raise ExtractorError('Youtube said
: %s' % alert_message, expected=True)
2218 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2221 class YoutubeUserIE(YoutubeChannelIE):
2222 IE_DESC = 'YouTube
.com user
videos (URL
or "ytuser" keyword
)'
2223 _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_-]+)'
2224 _TEMPLATE_URL = 'https
://www
.youtube
.com
/%s/%s/videos
'
2225 IE_NAME = 'youtube
:user
'
2228 'url
': 'https
://www
.youtube
.com
/user
/TheLinuxFoundation
',
2229 'playlist_mincount
': 320,
2231 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ
',
2232 'title
': 'Uploads
from The Linux Foundation
',
2235 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2236 # but not https://www.youtube.com/user/12minuteathlete/videos
2237 'url
': 'https
://www
.youtube
.com
/c
/12minuteathlete
/videos
',
2238 'playlist_mincount
': 249,
2240 'id': 'UUVjM
-zV6_opMDx7WYxnjZiQ
',
2241 'title
': 'Uploads
from 12 Minute Athlete
',
2244 'url
': 'ytuser
:phihag
',
2245 'only_matching
': True,
2247 'url
': 'https
://www
.youtube
.com
/c
/gametrailers
',
2248 'only_matching
': True,
2250 'url
': 'https
://www
.youtube
.com
/gametrailers
',
2251 'only_matching
': True,
2253 # This channel is not available, geo restricted to JP
2254 'url
': 'https
://www
.youtube
.com
/user
/kananishinoSMEJ
/videos
',
2255 'only_matching
': True,
2259 def suitable(cls, url):
2260 # Don't
return True if the url can be extracted
with other youtube
2261 # extractor, the regex would is too permissive and it would match.
2262 other_yt_ies
= iter(klass
for (name
, klass
) in globals().items() if name
.startswith('Youtube') and name
.endswith('IE') and klass
is not cls
)
2263 if any(ie
.suitable(url
) for ie
in other_yt_ies
):
2266 return super(YoutubeUserIE
, cls
).suitable(url
)
2268 def _build_template_url(self
, url
, channel_id
):
2269 mobj
= re
.match(self
._VALID
_URL
, url
)
2270 return self
._TEMPLATE
_URL
% (mobj
.group('user') or 'user', mobj
.group('id'))
2273 class YoutubeLiveIE(YoutubeBaseInfoExtractor
):
2274 IE_DESC
= 'YouTube.com live streams'
2275 _VALID_URL
= r
'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2276 IE_NAME
= 'youtube:live'
2279 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2281 'id': 'a48o2S1cPoo',
2283 'title': 'The Young Turks - Live Main Show',
2284 'uploader': 'The Young Turks',
2285 'uploader_id': 'TheYoungTurks',
2286 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2287 'upload_date': '20150715',
2288 'license': 'Standard YouTube License',
2289 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2290 'categories': ['News & Politics'],
2291 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2293 'dislike_count': int,
2296 'skip_download': True,
2299 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2300 'only_matching': True,
2302 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2303 'only_matching': True,
2305 'url': 'https://www.youtube.com/TheYoungTurks/live',
2306 'only_matching': True,
2309 def _real_extract(self
, url
):
2310 mobj
= re
.match(self
._VALID
_URL
, url
)
2311 channel_id
= mobj
.group('id')
2312 base_url
= mobj
.group('base_url')
2313 webpage
= self
._download
_webpage
(url
, channel_id
, fatal
=False)
2315 page_type
= self
._og
_search
_property
(
2316 'type', webpage
, 'page type', default
=None)
2317 video_id
= self
._html
_search
_meta
(
2318 'videoId', webpage
, 'video id', default
=None)
2319 if page_type
== 'video' and video_id
and re
.match(r
'^[0-9A-Za-z_-]{11}$', video_id
):
2320 return self
.url_result(video_id
, YoutubeIE
.ie_key())
2321 return self
.url_result(base_url
)
2324 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor
):
2325 IE_DESC
= 'YouTube.com user/channel playlists'
2326 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2327 IE_NAME
= 'youtube:playlists'
2330 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2331 'playlist_mincount': 4,
2333 'id': 'ThirstForScience',
2334 'title': 'Thirst for Science',
2337 # with "Load more" button
2338 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2339 'playlist_mincount': 70,
2342 'title': 'ŠŠ³Š¾ŃŃ ŠŠ»ŠµŠ¹Š½ŠµŃ',
2345 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2346 'playlist_mincount': 17,
2348 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2349 'title': 'Chem Player',
2354 class YoutubeSearchIE(SearchInfoExtractor
, YoutubePlaylistIE
):
2355 IE_DESC
= 'YouTube.com searches'
2356 # there doesn't appear to be a real limit, for example if you search for
2357 # 'python' you get more than 8.000.000 results
2358 _MAX_RESULTS
= float('inf')
2359 IE_NAME
= 'youtube:search'
2360 _SEARCH_KEY
= 'ytsearch'
2361 _EXTRA_QUERY_ARGS
= {}
2364 def _get_n_results(self
, query
, n
):
2365 """Get a specified number of results for a query"""
2371 'search_query': query
.encode('utf-8'),
2373 url_query
.update(self
._EXTRA
_QUERY
_ARGS
)
2374 result_url
= 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query
)
2376 for pagenum
in itertools
.count(1):
2377 data
= self
._download
_json
(
2378 result_url
, video_id
='query "%s"' % query
,
2379 note
='Downloading page %s' % pagenum
,
2380 errnote
='Unable to download API page',
2381 query
={'spf': 'navigate'})
2382 html_content
= data
[1]['body']['content']
2384 if 'class="search-message' in html_content
:
2385 raise ExtractorError(
2386 '[youtube] No video results', expected
=True)
2388 new_videos
= self
._ids
_to
_results
(orderedSet(re
.findall(
2389 r
'href="/watch\?v=(.{11})', html_content
)))
2390 videos
+= new_videos
2391 if not new_videos
or len(videos
) > limit
:
2393 next_link
= self
._html
_search
_regex
(
2394 r
'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2395 html_content
, 'next link', default
=None)
2396 if next_link
is None:
2398 result_url
= compat_urlparse
.urljoin('https://www.youtube.com/', next_link
)
2402 return self
.playlist_result(videos
, query
)
2405 class YoutubeSearchDateIE(YoutubeSearchIE
):
2406 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
2407 _SEARCH_KEY
= 'ytsearchdate'
2408 IE_DESC
= 'YouTube.com searches, newest videos first'
2409 _EXTRA_QUERY_ARGS
= {'search_sort': 'video_date_uploaded'}
2412 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor
):
2413 IE_DESC
= 'YouTube.com search URLs'
2414 IE_NAME
= 'youtube:search_url'
2415 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2416 _VIDEO_RE
= r
'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2418 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2419 'playlist_mincount': 5,
2421 'title': 'youtube-dl test video',
2424 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2425 'only_matching': True,
2428 def _real_extract(self
, url
):
2429 mobj
= re
.match(self
._VALID
_URL
, url
)
2430 query
= compat_urllib_parse_unquote_plus(mobj
.group('query'))
2431 webpage
= self
._download
_webpage
(url
, query
)
2432 return self
.playlist_result(self
._process
_page
(webpage
), playlist_title
=query
)
2435 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor
):
2436 IE_DESC
= 'YouTube.com (multi-season) shows'
2437 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2438 IE_NAME
= 'youtube:show'
2440 'url': 'https://www.youtube.com/show/airdisasters',
2441 'playlist_mincount': 5,
2443 'id': 'airdisasters',
2444 'title': 'Air Disasters',
2448 def _real_extract(self
, url
):
2449 playlist_id
= self
._match
_id
(url
)
2450 return super(YoutubeShowIE
, self
)._real
_extract
(
2451 'https://www.youtube.com/show/%s/playlists' % playlist_id
)
2454 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor
):
2456 Base class for feed extractors
2457 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2459 _LOGIN_REQUIRED
= True
2463 return 'youtube:%s' % self
._FEED
_NAME
2465 def _real_initialize(self
):
2468 def _real_extract(self
, url
):
2469 page
= self
._download
_webpage
(
2470 'https://www.youtube.com/feed/%s' % self
._FEED
_NAME
, self
._PLAYLIST
_TITLE
)
2472 # The extraction process is the same as for playlists, but the regex
2473 # for the video ids doesn't contain an index
2475 more_widget_html
= content_html
= page
2476 for page_num
in itertools
.count(1):
2477 matches
= re
.findall(r
'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html
)
2479 # 'recommended' feed has infinite 'load more' and each new portion spins
2480 # the same videos in (sometimes) slightly different order, so we'll check
2481 # for unicity and break when portion has no new videos
2482 new_ids
= filter(lambda video_id
: video_id
not in ids
, orderedSet(matches
))
2488 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
2492 more
= self
._download
_json
(
2493 'https://youtube.com/%s' % mobj
.group('more'), self
._PLAYLIST
_TITLE
,
2494 'Downloading page #%s' % page_num
,
2495 transform_source
=uppercase_escape
)
2496 content_html
= more
['content_html']
2497 more_widget_html
= more
['load_more_widget_html']
2499 return self
.playlist_result(
2500 self
._ids
_to
_results
(ids
), playlist_title
=self
._PLAYLIST
_TITLE
)
2503 class YoutubeWatchLaterIE(YoutubePlaylistIE
):
2504 IE_NAME
= 'youtube:watchlater'
2505 IE_DESC
= 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2506 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2509 'url': 'https://www.youtube.com/playlist?list=WL',
2510 'only_matching': True,
2512 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2513 'only_matching': True,
2516 def _real_extract(self
, url
):
2517 _
, video
= self
._check
_download
_just
_video
(url
, 'WL')
2520 _
, playlist
= self
._extract
_playlist
('WL')
2524 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
2525 IE_NAME
= 'youtube:favorites'
2526 IE_DESC
= 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2527 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2528 _LOGIN_REQUIRED
= True
2530 def _real_extract(self
, url
):
2531 webpage
= self
._download
_webpage
('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2532 playlist_id
= self
._search
_regex
(r
'list=(.+?)["&]', webpage
, 'favourites playlist id')
2533 return self
.url_result(playlist_id
, 'YoutubePlaylist')
2536 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
2537 IE_DESC
= 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2538 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2539 _FEED_NAME
= 'recommended'
2540 _PLAYLIST_TITLE
= 'Youtube Recommended videos'
2543 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
2544 IE_DESC
= 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2545 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2546 _FEED_NAME
= 'subscriptions'
2547 _PLAYLIST_TITLE
= 'Youtube Subscriptions'
2550 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
2551 IE_DESC
= 'Youtube watch history, ":ythistory" for short (requires authentication)'
2552 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2553 _FEED_NAME
= 'history'
2554 _PLAYLIST_TITLE
= 'Youtube History'
2557 class YoutubeTruncatedURLIE(InfoExtractor
):
2558 IE_NAME
= 'youtube:truncated_url'
2559 IE_DESC
= False # Do not list
2560 _VALID_URL
= r
'''(?x)
2562 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2565 annotation_id=annotation_[^&]+|
2571 attribution_link\?a=[^&]+
2577 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2578 'only_matching': True,
2580 'url': 'https://www.youtube.com/watch?',
2581 'only_matching': True,
2583 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2584 'only_matching': True,
2586 'url': 'https://www.youtube.com/watch?feature=foo',
2587 'only_matching': True,
2589 'url': 'https://www.youtube.com/watch?hl=en-GB',
2590 'only_matching': True,
2592 'url': 'https://www.youtube.com/watch?t=2372',
2593 'only_matching': True,
2596 def _real_extract(self
, url
):
2597 raise ExtractorError(
2598 'Did you forget to quote the URL? Remember that & is a meta '
2599 'character in most shells, so you want to put the URL in quotes, '
2601 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2602 ' or simply youtube-dl BaW_jenozKc .',
2606 class YoutubeTruncatedIDIE(InfoExtractor
):
2607 IE_NAME
= 'youtube:truncated_id'
2608 IE_DESC
= False # Do not list
2609 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2612 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2613 'only_matching': True,
2616 def _real_extract(self
, url
):
2617 video_id
= self
._match
_id
(url
)
2618 raise ExtractorError(
2619 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id
, url
),