3 from __future__
import unicode_literals
14 from .common
import InfoExtractor
, SearchInfoExtractor
15 from ..jsinterp
import JSInterpreter
16 from ..swfinterp
import SWFInterpreter
17 from ..compat
import (
20 compat_urllib_parse_unquote
,
21 compat_urllib_parse_unquote_plus
,
22 compat_urllib_parse_urlencode
,
23 compat_urllib_parse_urlparse
,
32 get_element_by_attribute
,
53 class YoutubeBaseInfoExtractor(InfoExtractor
):
54 """Provide base functions for Youtube extractors"""
55 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
56 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
57 _PASSWORD_CHALLENGE_URL
= 'https://accounts.google.com/signin/challenge/sl/password'
58 _NETRC_MACHINE
= 'youtube'
59 # If True it will raise an error if no login info is provided
60 _LOGIN_REQUIRED
= False
62 def _set_language(self
):
64 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
65 # YouTube sets the expire time to about two months
66 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
68 def _ids_to_results(self
, ids
):
70 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
75 Attempt to log in to YouTube.
76 True is returned if successful or skipped.
77 False is returned if login failed.
79 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
81 (username
, password
) = self
._get
_login
_info
()
82 # No authentication to be performed
84 if self
._LOGIN
_REQUIRED
:
85 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
88 login_page
= self
._download
_webpage
(
89 self
._LOGIN
_URL
, None,
90 note
='Downloading login page',
91 errnote
='unable to fetch login page', fatal
=False)
92 if login_page
is False:
95 login_form
= self
._hidden
_inputs
(login_page
)
98 'checkConnection': 'youtube',
103 login_results
= self
._download
_webpage
(
104 self
._PASSWORD
_CHALLENGE
_URL
, None,
105 note
='Logging in', errnote
='unable to log in', fatal
=False,
106 data
=urlencode_postdata(login_form
))
107 if login_results
is False:
110 error_msg
= self
._html
_search
_regex
(
111 r
'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
112 login_results
, 'error message', default
=None)
114 raise ExtractorError('Unable to login: %s' % error_msg
, expected
=True)
116 if re
.search(r
'id="errormsg_0_Passwd"', login_results
) is not None:
117 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected
=True)
120 # TODO add SMS and phone call support - these require making a request and then prompting the user
122 if re
.search(r
'(?i)<form[^>]+id="challenge"', login_results
) is not None:
123 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
126 self
._downloader
.report_warning(
127 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
128 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
131 tfa_code
= remove_start(tfa_code
, 'G-')
133 tfa_form_strs
= self
._form
_hidden
_inputs
('challenge', login_results
)
135 tfa_form_strs
.update({
140 tfa_data
= urlencode_postdata(tfa_form_strs
)
142 tfa_req
= sanitized_Request(self
._TWOFACTOR
_URL
, tfa_data
)
143 tfa_results
= self
._download
_webpage
(
145 note
='Submitting TFA code', errnote
='unable to submit tfa', fatal
=False)
147 if tfa_results
is False:
150 if re
.search(r
'(?i)<form[^>]+id="challenge"', tfa_results
) is not None:
151 self
._downloader
.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
153 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', tfa_results
) is not None:
154 self
._downloader
.report_warning('unable to log in - did the page structure change?')
156 if re
.search(r
'smsauth-interstitial-reviewsettings', tfa_results
) is not None:
157 self
._downloader
.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
160 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', login_results
) is not None:
161 self
._downloader
.report_warning('unable to log in: bad username or password')
165 def _real_initialize(self
):
166 if self
._downloader
is None:
169 if not self
._login
():
173 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
174 # Extract entries from page with "Load more" button
175 def _entries(self
, page
, playlist_id
):
176 more_widget_html
= content_html
= page
177 for page_num
in itertools
.count(1):
178 for entry
in self
._process
_page
(content_html
):
181 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
185 more
= self
._download
_json
(
186 'https://youtube.com/%s' % mobj
.group('more'), playlist_id
,
187 'Downloading page #%s' % page_num
,
188 transform_source
=uppercase_escape
)
189 content_html
= more
['content_html']
190 if not content_html
.strip():
191 # Some webpages show a "Load more" button but they don't
194 more_widget_html
= more
['load_more_widget_html']
197 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
198 def _process_page(self
, content
):
199 for video_id
, video_title
in self
.extract_videos_from_page(content
):
200 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
202 def extract_videos_from_page(self
, page
):
205 for mobj
in re
.finditer(self
._VIDEO
_RE
, page
):
206 # The link with index 0 is not the first video of the playlist (not sure if still actual)
207 if 'index' in mobj
.groupdict() and mobj
.group('id') == '0':
209 video_id
= mobj
.group('id')
210 video_title
= unescapeHTML(mobj
.group('title'))
212 video_title
= video_title
.strip()
214 idx
= ids_in_page
.index(video_id
)
215 if video_title
and not titles_in_page
[idx
]:
216 titles_in_page
[idx
] = video_title
218 ids_in_page
.append(video_id
)
219 titles_in_page
.append(video_title
)
220 return zip(ids_in_page
, titles_in_page
)
223 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
224 def _process_page(self
, content
):
225 for playlist_id
in orderedSet(re
.findall(
226 r
'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
228 yield self
.url_result(
229 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
231 def _real_extract(self
, url
):
232 playlist_id
= self
._match
_id
(url
)
233 webpage
= self
._download
_webpage
(url
, playlist_id
)
234 title
= self
._og
_search
_title
(webpage
, fatal
=False)
235 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
238 class YoutubeIE(YoutubeBaseInfoExtractor
):
239 IE_DESC
= 'YouTube.com'
240 _VALID_URL
= r
"""(?x)^
242 (?:https?://|//) # http(s):// or protocol-independent URL
243 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
244 (?:www\.)?deturl\.com/www\.youtube\.com/|
245 (?:www\.)?pwnyoutube\.com/|
246 (?:www\.)?yourepeat\.com/|
247 tube\.majestyc\.net/|
248 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
249 (?:.*?\#/)? # handle anchor (#/) redirect urls
250 (?: # the various things that can precede the ID:
251 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
252 |(?: # or the v= param in all its forms
253 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
254 (?:\?|\#!?) # the params delimiter ? or # or #!
255 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
260 youtu\.be| # just youtu.be/xxxx
261 vid\.plus| # or vid.plus/xxxx
262 zwearz\.com/watch| # or zwearz.com/watch/xxxx
264 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
266 )? # all until now is optional -> you can pass the naked ID
267 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
268 (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
269 (?(1).+)? # if we found the ID, everything can follow
271 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
273 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
274 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
275 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
276 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
277 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
278 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
279 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
280 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
281 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
282 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
283 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
284 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
285 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
286 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
287 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
288 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
289 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
290 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
294 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
295 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
296 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
297 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
298 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
299 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
300 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
302 # Apple HTTP Live Streaming
303 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
304 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
305 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
306 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
307 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
308 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
309 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
310 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
313 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
314 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
315 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
316 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
317 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
318 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
319 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
320 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
321 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
322 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40}
,
323 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40}
,
324 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
327 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}
,
328 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}
,
329 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}
,
330 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'}
,
331 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'}
,
334 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
335 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
336 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
337 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
338 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
339 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
340 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40}
,
341 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
342 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
343 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
344 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
345 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
346 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
347 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
348 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
349 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
350 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
351 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
352 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
353 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
354 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
355 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
358 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}
,
359 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}
,
361 # Dash webm audio with opus inside
362 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}
,
363 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}
,
364 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}
,
367 '_rtmp': {'protocol': 'rtmp'}
,
369 _SUBTITLE_FORMATS
= ('ttml', 'vtt')
374 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
378 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
379 'uploader': 'Philipp Hagemeister',
380 'uploader_id': 'phihag',
381 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
382 'upload_date': '20121002',
383 'license': 'Standard YouTube License',
384 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
385 'categories': ['Science & Technology'],
386 'tags': ['youtube-dl'],
389 'dislike_count': int,
395 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
396 'note': 'Test generic use_cipher_signature video (#897)',
400 'upload_date': '20120506',
401 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
402 'alt_title': 'I Love It (feat. Charli XCX)',
403 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
404 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
405 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
406 'iconic ep', 'iconic', 'love', 'it'],
408 'uploader': 'Icona Pop',
409 'uploader_id': 'IconaPop',
410 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IconaPop',
411 'license': 'Standard YouTube License',
412 'creator': 'Icona Pop',
416 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
417 'note': 'Test VEVO video with age protection (#956)',
421 'upload_date': '20130703',
422 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
423 'alt_title': 'Tunnel Vision',
424 'description': 'md5:64249768eec3bc4276236606ea996373',
426 'uploader': 'justintimberlakeVEVO',
427 'uploader_id': 'justintimberlakeVEVO',
428 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
429 'license': 'Standard YouTube License',
430 'creator': 'Justin Timberlake',
435 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
436 'note': 'Embed-only video (#1746)',
440 'upload_date': '20120608',
441 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
442 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
443 'uploader': 'SET India',
444 'uploader_id': 'setindia',
445 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
446 'license': 'Standard YouTube License',
451 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
452 'note': 'Use the first video ID in the URL',
456 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
457 'uploader': 'Philipp Hagemeister',
458 'uploader_id': 'phihag',
459 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
460 'upload_date': '20121002',
461 'license': 'Standard YouTube License',
462 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
463 'categories': ['Science & Technology'],
464 'tags': ['youtube-dl'],
467 'dislike_count': int,
470 'skip_download': True,
474 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
475 'note': '256k DASH audio (format 141) via DASH manifest',
479 'upload_date': '20121002',
480 'uploader_id': '8KVIDEO',
481 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
483 'uploader': '8KVIDEO',
484 'license': 'Standard YouTube License',
485 'title': 'UHDTV TEST 8K VIDEO.mp4'
488 'youtube_include_dash_manifest': True,
491 'skip': 'format 141 not served anymore',
493 # DASH manifest with encrypted signature
495 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
499 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
500 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
502 'uploader': 'AfrojackVEVO',
503 'uploader_id': 'AfrojackVEVO',
504 'upload_date': '20131011',
505 'license': 'Standard YouTube License',
508 'youtube_include_dash_manifest': True,
509 'format': '141/bestaudio[ext=m4a]',
512 # JS player signature function name containing $
514 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
518 'title': 'Taylor Swift - Shake It Off',
519 'alt_title': 'Shake It Off',
520 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
522 'uploader': 'TaylorSwiftVEVO',
523 'uploader_id': 'TaylorSwiftVEVO',
524 'upload_date': '20140818',
525 'license': 'Standard YouTube License',
526 'creator': 'Taylor Swift',
529 'youtube_include_dash_manifest': True,
530 'format': '141/bestaudio[ext=m4a]',
535 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
540 'upload_date': '20100909',
541 'uploader': 'The Amazing Atheist',
542 'uploader_id': 'TheAmazingAtheist',
543 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
544 'license': 'Standard YouTube License',
545 'title': 'Burning Everyone\'s Koran',
546 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
549 # Normal age-gate video (No vevo, embed allowed)
551 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
555 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
556 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
558 'uploader': 'The Witcher',
559 'uploader_id': 'WitcherGame',
560 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
561 'upload_date': '20140605',
562 'license': 'Standard YouTube License',
566 # Age-gate video with encrypted signature
568 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
572 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
573 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
575 'uploader': 'LloydVEVO',
576 'uploader_id': 'LloydVEVO',
577 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
578 'upload_date': '20110629',
579 'license': 'Standard YouTube License',
583 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
585 'url': '__2ABJjxzNo',
590 'upload_date': '20100430',
591 'uploader_id': 'deadmau5',
592 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
593 'creator': 'deadmau5',
594 'description': 'md5:12c56784b8032162bb936a5f76d55360',
595 'uploader': 'deadmau5',
596 'license': 'Standard YouTube License',
597 'title': 'Deadmau5 - Some Chords (HD)',
598 'alt_title': 'Some Chords',
600 'expected_warnings': [
601 'DASH manifest missing',
604 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
606 'url': 'lqQg6PlCWgI',
611 'upload_date': '20150827',
612 'uploader_id': 'olympic',
613 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
614 'license': 'Standard YouTube License',
615 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
616 'uploader': 'Olympic',
617 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
620 'skip_download': 'requires avconv',
625 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
629 'stretched_ratio': 16 / 9.,
631 'upload_date': '20110310',
632 'uploader_id': 'AllenMeow',
633 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
634 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
636 'license': 'Standard YouTube License',
637 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
640 # url_encoded_fmt_stream_map is empty string
642 'url': 'qEJwOuvDf7I',
646 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
648 'upload_date': '20150404',
649 'uploader_id': 'spbelect',
650 'uploader': 'Наблюдатели Петербурга',
653 'skip_download': 'requires avconv',
655 'skip': 'This live event has ended.',
657 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
659 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
663 'title': 'md5:7b81415841e02ecd4313668cde88737a',
664 'description': 'md5:116377fd2963b81ec4ce64b542173306',
666 'upload_date': '20150625',
667 'uploader_id': 'dorappi2000',
668 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
669 'uploader': 'dorappi2000',
670 'license': 'Standard YouTube License',
671 'formats': 'mincount:32',
674 # DASH manifest with segment_list
676 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
677 'md5': '8ce563a1d667b599d21064e982ab9e31',
681 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
682 'uploader': 'Airtek',
683 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
684 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
685 'license': 'Standard YouTube License',
686 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
689 'youtube_include_dash_manifest': True,
690 'format': '135', # bestvideo
692 'skip': 'This live event has ended.',
695 # Multifeed videos (multiple cameras), URL is for Main Camera
696 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
699 'title': 'teamPGP: Rocket League Noob Stream',
700 'description': 'md5:dc7872fb300e143831327f1bae3af010',
706 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
707 'description': 'md5:dc7872fb300e143831327f1bae3af010',
709 'upload_date': '20150721',
710 'uploader': 'Beer Games Beer',
711 'uploader_id': 'beergamesbeer',
712 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
713 'license': 'Standard YouTube License',
719 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
720 'description': 'md5:dc7872fb300e143831327f1bae3af010',
722 'upload_date': '20150721',
723 'uploader': 'Beer Games Beer',
724 'uploader_id': 'beergamesbeer',
725 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
726 'license': 'Standard YouTube License',
732 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
733 'description': 'md5:dc7872fb300e143831327f1bae3af010',
735 'upload_date': '20150721',
736 'uploader': 'Beer Games Beer',
737 'uploader_id': 'beergamesbeer',
738 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
739 'license': 'Standard YouTube License',
745 'title': 'teamPGP: Rocket League Noob Stream (zim)',
746 'description': 'md5:dc7872fb300e143831327f1bae3af010',
748 'upload_date': '20150721',
749 'uploader': 'Beer Games Beer',
750 'uploader_id': 'beergamesbeer',
751 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
752 'license': 'Standard YouTube License',
756 'skip_download': True,
760 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
761 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
764 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
767 'skip': 'Not multifeed anymore',
770 'url': 'https://vid.plus/FlRa-iH7PGw',
771 'only_matching': True,
774 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
775 'only_matching': True,
778 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
779 # Also tests cut-off URL expansion in video description (see
780 # https://github.com/rg3/youtube-dl/issues/1892,
781 # https://github.com/rg3/youtube-dl/issues/8164)
782 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
786 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
787 'alt_title': 'Dark Walk',
788 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
790 'upload_date': '20151119',
791 'uploader_id': 'IronSoulElf',
792 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
793 'uploader': 'IronSoulElf',
794 'license': 'Standard YouTube License',
795 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
798 'skip_download': True,
802 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
803 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
804 'only_matching': True,
807 # Video with yt:stretch=17:0
808 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
812 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
813 'description': 'md5:ee18a25c350637c8faff806845bddee9',
814 'upload_date': '20151107',
815 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
816 'uploader': 'CH GAMER DROID',
819 'skip_download': True,
821 'skip': 'This video does not exist.',
824 # Video licensed under Creative Commons
825 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
829 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
830 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
832 'upload_date': '20150127',
833 'uploader_id': 'BerkmanCenter',
834 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
835 'uploader': 'The Berkman Klein Center for Internet & Society',
836 'license': 'Creative Commons Attribution license (reuse allowed)',
839 'skip_download': True,
843 # Channel-like uploader_url
844 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
848 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
849 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
851 'upload_date': '20151119',
852 'uploader': 'Bernie 2016',
853 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
854 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
855 'license': 'Creative Commons Attribution license (reuse allowed)',
858 'skip_download': True,
862 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
863 'only_matching': True,
866 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
867 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
868 'only_matching': True,
871 # Rental video preview
872 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
876 'title': 'Piku - Trailer',
877 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
878 'upload_date': '20150811',
879 'uploader': 'FlixMatrix',
880 'uploader_id': 'FlixMatrixKaravan',
881 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
882 'license': 'Standard YouTube License',
885 'skip_download': True,
889 # YouTube Red video with episode data
890 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
894 'title': 'Isolation - Mind Field (Ep 1)',
895 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
897 'upload_date': '20170118',
898 'uploader': 'Vsauce',
899 'uploader_id': 'Vsauce',
900 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
901 'license': 'Standard YouTube License',
902 'series': 'Mind Field',
907 'skip_download': True,
909 'expected_warnings': [
910 'Skipping DASH manifest',
915 'url': '1t24XAntNCY',
916 'only_matching': True,
920 def __init__(self
, *args
, **kwargs
):
921 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
922 self
._player
_cache
= {}
924 def report_video_info_webpage_download(self
, video_id
):
925 """Report attempt to download video info webpage."""
926 self
.to_screen('%s: Downloading video info webpage' % video_id
)
928 def report_information_extraction(self
, video_id
):
929 """Report attempt to extract video information."""
930 self
.to_screen('%s: Extracting video information' % video_id
)
932 def report_unavailable_format(self
, video_id
, format
):
933 """Report extracted video URL."""
934 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
936 def report_rtmp_download(self
):
937 """Indicate the download will use the RTMP protocol."""
938 self
.to_screen('RTMP download detected')
940 def _signature_cache_id(self
, example_sig
):
941 """ Return a string representation of a signature """
942 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
944 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
946 r
'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
949 raise ExtractorError('Cannot identify player %r' % player_url
)
950 player_type
= id_m
.group('ext')
951 player_id
= id_m
.group('id')
953 # Read from filesystem cache
954 func_id
= '%s_%s_%s' % (
955 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
956 assert os
.path
.basename(func_id
) == func_id
958 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
959 if cache_spec
is not None:
960 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
963 'Downloading player %s' % player_url
964 if self
._downloader
.params
.get('verbose') else
965 'Downloading %s player %s' % (player_type
, player_id
)
967 if player_type
== 'js':
968 code
= self
._download
_webpage
(
969 player_url
, video_id
,
971 errnote
='Download of %s failed' % player_url
)
972 res
= self
._parse
_sig
_js
(code
)
973 elif player_type
== 'swf':
974 urlh
= self
._request
_webpage
(
975 player_url
, video_id
,
977 errnote
='Download of %s failed' % player_url
)
979 res
= self
._parse
_sig
_swf
(code
)
981 assert False, 'Invalid player type %r' % player_type
983 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
984 cache_res
= res(test_string
)
985 cache_spec
= [ord(c
) for c
in cache_res
]
987 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
990 def _print_sig_code(self
, func
, example_sig
):
991 def gen_sig_code(idxs
):
992 def _genslice(start
, end
, step
):
993 starts
= '' if start
== 0 else str(start
)
994 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
995 steps
= '' if step
== 1 else (':%d' % step
)
996 return 's[%s%s%s]' % (starts
, ends
, steps
)
999 # Quelch pyflakes warnings - start will be set when step is set
1000 start
= '(Never used)'
1001 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1002 if step
is not None:
1003 if i
- prev
== step
:
1005 yield _genslice(start
, prev
, step
)
1008 if i
- prev
in [-1, 1]:
1013 yield 's[%d]' % prev
1017 yield _genslice(start
, i
, step
)
1019 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1020 cache_res
= func(test_string
)
1021 cache_spec
= [ord(c
) for c
in cache_res
]
1022 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1023 signature_id_tuple
= '(%s)' % (
1024 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1025 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1026 ' return %s\n') % (signature_id_tuple
, expr_code
)
1027 self
.to_screen('Extracted signature function:\n' + code
)
1029 def _parse_sig_js(self
, jscode
):
1030 funcname
= self
._search
_regex
(
1031 (r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1032 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1033 jscode, 'Initial JS player signature function name
', group='sig
')
1035 jsi = JSInterpreter(jscode)
1036 initial_function = jsi.extract_function(funcname)
1037 return lambda s: initial_function([s])
1039 def _parse_sig_swf(self, file_contents):
1040 swfi = SWFInterpreter(file_contents)
1041 TARGET_CLASSNAME = 'SignatureDecipher
'
1042 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1043 initial_function = swfi.extract_function(searched_class, 'decipher
')
1044 return lambda s: initial_function([s])
1046 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1047 """Turn the encrypted s field into a working signature"""
1049 if player_url is None:
1050 raise ExtractorError('Cannot decrypt signature without player_url
')
1052 if player_url.startswith('//'):
1053 player_url = 'https
:' + player_url
1054 elif not re.match(r'https?
://', player_url):
1055 player_url = compat_urlparse.urljoin(
1056 'https
://www
.youtube
.com
', player_url)
1058 player_id = (player_url, self._signature_cache_id(s))
1059 if player_id not in self._player_cache:
1060 func = self._extract_signature_function(
1061 video_id, player_url, s
1063 self._player_cache[player_id] = func
1064 func = self._player_cache[player_id]
1065 if self._downloader.params.get('youtube_print_sig_code
'):
1066 self._print_sig_code(func, s)
1068 except Exception as e:
1069 tb = traceback.format_exc()
1070 raise ExtractorError(
1071 'Signature extraction failed
: ' + tb, cause=e)
1073 def _get_subtitles(self, video_id, webpage):
1075 subs_doc = self._download_xml(
1076 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1077 video_id, note=False)
1078 except ExtractorError as err:
1079 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1083 for track in subs_doc.findall('track
'):
1084 lang = track.attrib['lang_code
']
1085 if lang in sub_lang_list:
1088 for ext in self._SUBTITLE_FORMATS:
1089 params = compat_urllib_parse_urlencode({
1093 'name
': track.attrib['name
'].encode('utf
-8'),
1095 sub_formats.append({
1096 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1099 sub_lang_list[lang] = sub_formats
1100 if not sub_lang_list:
1101 self._downloader.report_warning('video doesn
\'t have subtitles
')
1103 return sub_lang_list
1105 def _get_ytplayer_config(self, video_id, webpage):
1107 # User data may contain arbitrary character sequences that may affect
1108 # JSON extraction with regex, e.g. when '};' is contained the second
1109 # regex won't capture the whole JSON
. Yet working around by trying more
1110 # concrete regex first keeping in mind proper quoted string handling
1111 # to be implemented in future that will replace this workaround (see
1112 # https://github.com/rg3/youtube-dl/issues/7468,
1113 # https://github.com/rg3/youtube-dl/pull/7599)
1114 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1115 r
';ytplayer\.config\s*=\s*({.+?});',
1117 config
= self
._search
_regex
(
1118 patterns
, webpage
, 'ytplayer.config', default
=None)
1120 return self
._parse
_json
(
1121 uppercase_escape(config
), video_id
, fatal
=False)
1123 def _get_automatic_captions(self
, video_id
, webpage
):
1124 """We need the webpage for getting the captions url, pass it as an
1125 argument to speed up the process."""
1126 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1127 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1128 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1129 if not player_config
:
1130 self
._downloader
.report_warning(err_msg
)
1133 args
= player_config
['args']
1134 caption_url
= args
.get('ttsurl')
1136 timestamp
= args
['timestamp']
1137 # We get the available subtitles
1138 list_params
= compat_urllib_parse_urlencode({
1143 list_url
= caption_url
+ '&' + list_params
1144 caption_list
= self
._download
_xml
(list_url
, video_id
)
1145 original_lang_node
= caption_list
.find('track')
1146 if original_lang_node
is None:
1147 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1149 original_lang
= original_lang_node
.attrib
['lang_code']
1150 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1153 for lang_node
in caption_list
.findall('target'):
1154 sub_lang
= lang_node
.attrib
['lang_code']
1156 for ext
in self
._SUBTITLE
_FORMATS
:
1157 params
= compat_urllib_parse_urlencode({
1158 'lang': original_lang
,
1162 'kind': caption_kind
,
1164 sub_formats
.append({
1165 'url': caption_url
+ '&' + params
,
1168 sub_lang_list
[sub_lang
] = sub_formats
1169 return sub_lang_list
1171 # Some videos don't provide ttsurl but rather caption_tracks and
1172 # caption_translation_languages (e.g. 20LmZk1hakA)
1173 caption_tracks
= args
['caption_tracks']
1174 caption_translation_languages
= args
['caption_translation_languages']
1175 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1176 parsed_caption_url
= compat_urllib_parse_urlparse(caption_url
)
1177 caption_qs
= compat_parse_qs(parsed_caption_url
.query
)
1180 for lang
in caption_translation_languages
.split(','):
1181 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1182 sub_lang
= lang_qs
.get('lc', [None])[0]
1186 for ext
in self
._SUBTITLE
_FORMATS
:
1188 'tlang': [sub_lang
],
1191 sub_url
= compat_urlparse
.urlunparse(parsed_caption_url
._replace
(
1192 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1193 sub_formats
.append({
1197 sub_lang_list
[sub_lang
] = sub_formats
1198 return sub_lang_list
1199 # An extractor error can be raise by the download process if there are
1200 # no automatic captions but there are subtitles
1201 except (KeyError, ExtractorError
):
1202 self
._downloader
.report_warning(err_msg
)
1205 def _mark_watched(self
, video_id
, video_info
):
1206 playback_url
= video_info
.get('videostats_playback_base_url', [None])[0]
1207 if not playback_url
:
1209 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1210 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1212 # cpn generation algorithm is reverse engineered from base.js.
1213 # In fact it works even with dummy cpn.
1214 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1215 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1221 playback_url
= compat_urlparse
.urlunparse(
1222 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1224 self
._download
_webpage
(
1225 playback_url
, video_id
, 'Marking watched',
1226 'Unable to mark watched', fatal
=False)
1229 def extract_id(cls
, url
):
1230 mobj
= re
.match(cls
._VALID
_URL
, url
, re
.VERBOSE
)
1232 raise ExtractorError('Invalid URL: %s' % url
)
1233 video_id
= mobj
.group(2)
1236 def _extract_from_m3u8(self
, manifest_url
, video_id
):
1239 def _get_urls(_manifest
):
1240 lines
= _manifest
.split('\n')
1241 urls
= filter(lambda l
: l
and not l
.startswith('#'),
1244 manifest
= self
._download
_webpage
(manifest_url
, video_id
, 'Downloading formats manifest')
1245 formats_urls
= _get_urls(manifest
)
1246 for format_url
in formats_urls
:
1247 itag
= self
._search
_regex
(r
'itag/(\d+?)/', format_url
, 'itag')
1248 url_map
[itag
] = format_url
1251 def _extract_annotations(self
, video_id
):
1252 url
= 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1253 return self
._download
_webpage
(url
, video_id
, note
='Searching for annotations.', errnote
='Unable to download video annotations.')
1255 def _real_extract(self
, url
):
1256 url
, smuggled_data
= unsmuggle_url(url
, {})
1259 'http' if self
._downloader
.params
.get('prefer_insecure', False)
1264 parsed_url
= compat_urllib_parse_urlparse(url
)
1265 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
1266 query
= compat_parse_qs(component
)
1267 if start_time
is None and 't' in query
:
1268 start_time
= parse_duration(query
['t'][0])
1269 if start_time
is None and 'start' in query
:
1270 start_time
= parse_duration(query
['start'][0])
1271 if end_time
is None and 'end' in query
:
1272 end_time
= parse_duration(query
['end'][0])
1274 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1275 mobj
= re
.search(self
._NEXT
_URL
_RE
, url
)
1277 url
= proto
+ '://www.youtube.com/' + compat_urllib_parse_unquote(mobj
.group(1)).lstrip('/')
1278 video_id
= self
.extract_id(url
)
1281 url
= proto
+ '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1282 video_webpage
= self
._download
_webpage
(url
, video_id
)
1284 # Attempt to extract SWF player URL
1285 mobj
= re
.search(r
'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage
)
1286 if mobj
is not None:
1287 player_url
= re
.sub(r
'\\(.)', r
'\1', mobj
.group(1))
1293 def add_dash_mpd(video_info
):
1294 dash_mpd
= video_info
.get('dashmpd')
1295 if dash_mpd
and dash_mpd
[0] not in dash_mpds
:
1296 dash_mpds
.append(dash_mpd
[0])
1299 embed_webpage
= None
1301 if re
.search(r
'player-age-gate-content">', video_webpage
) is not None:
1303 # We simulate the access to the video from www.youtube.com/v/{video_id}
1304 # this can be viewed without login into Youtube
1305 url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1306 embed_webpage
= self
._download
_webpage
(url
, video_id
, 'Downloading embed webpage')
1307 data
= compat_urllib_parse_urlencode({
1308 'video_id': video_id
,
1309 'eurl': 'https://youtube.googleapis.com/v/' + video_id
,
1310 'sts': self
._search
_regex
(
1311 r
'"sts"\s*:\s*(\d+)', embed_webpage
, 'sts', default
=''),
1313 video_info_url
= proto
+ '://www.youtube.com/get_video_info?' + data
1314 video_info_webpage
= self
._download
_webpage
(
1315 video_info_url
, video_id
,
1316 note
='Refetching age-gated info webpage',
1317 errnote
='unable to download video info webpage')
1318 video_info
= compat_parse_qs(video_info_webpage
)
1319 add_dash_mpd(video_info
)
1323 # Try looking directly into the video webpage
1324 ytplayer_config
= self
._get
_ytplayer
_config
(video_id
, video_webpage
)
1326 args
= ytplayer_config
['args']
1327 if args
.get('url_encoded_fmt_stream_map'):
1328 # Convert to the same format returned by compat_parse_qs
1329 video_info
= dict((k
, [v
]) for k
, v
in args
.items())
1330 add_dash_mpd(video_info
)
1331 # Rental video is not rented but preview is available (e.g.
1332 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1333 # https://github.com/rg3/youtube-dl/issues/10532)
1334 if not video_info
and args
.get('ypc_vid'):
1335 return self
.url_result(
1336 args
['ypc_vid'], YoutubeIE
.ie_key(), video_id
=args
['ypc_vid'])
1337 if args
.get('livestream') == '1' or args
.get('live_playback') == 1:
1339 if not video_info
or self
._downloader
.params
.get('youtube_include_dash_manifest', True):
1340 # We also try looking in get_video_info since it may contain different dashmpd
1341 # URL that points to a DASH manifest with possibly different itag set (some itags
1342 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1343 # manifest pointed by get_video_info's dashmpd).
1344 # The general idea is to take a union of itags of both DASH manifests (for example
1345 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1346 self
.report_video_info_webpage_download(video_id
)
1347 for el_type
in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1349 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1350 % (proto
, video_id
, el_type
))
1351 video_info_webpage
= self
._download
_webpage
(
1353 video_id
, note
=False,
1354 errnote
='unable to download video info webpage')
1355 get_video_info
= compat_parse_qs(video_info_webpage
)
1356 if get_video_info
.get('use_cipher_signature') != ['True']:
1357 add_dash_mpd(get_video_info
)
1359 video_info
= get_video_info
1360 if 'token' in get_video_info
:
1361 # Different get_video_info requests may report different results, e.g.
1362 # some may report video unavailability, but some may serve it without
1363 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1364 # the original webpage as well as el=info and el=embedded get_video_info
1365 # requests report video unavailability due to geo restriction while
1366 # el=detailpage succeeds and returns valid data). This is probably
1367 # due to YouTube measures against IP ranges of hosting providers.
1368 # Working around by preferring the first succeeded video_info containing
1369 # the token if no such video_info yet was found.
1370 if 'token' not in video_info
:
1371 video_info
= get_video_info
1373 if 'token' not in video_info
:
1374 if 'reason' in video_info
:
1375 if 'The uploader has not made this video available in your country.' in video_info
['reason']:
1376 regions_allowed
= self
._html
_search
_meta
('regionsAllowed', video_webpage
, default
=None)
1378 raise ExtractorError('YouTube said: This video is available in %s only' % (
1379 ', '.join(map(ISO3166Utils
.short2full
, regions_allowed
.split(',')))),
1381 raise ExtractorError(
1382 'YouTube said: %s' % video_info
['reason'][0],
1383 expected
=True, video_id
=video_id
)
1385 raise ExtractorError(
1386 '"token" parameter not in video info for unknown reason',
1390 if 'title' in video_info
:
1391 video_title
= video_info
['title'][0]
1393 self
._downloader
.report_warning('Unable to extract video title')
1397 video_description
= get_element_by_id("eow-description", video_webpage
)
1398 if video_description
:
1399 video_description
= re
.sub(r
'''(?x)
1401 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1402 (?:title|href)="([^"]+)"\s+
1403 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1407 ''', r
'\1', video_description
)
1408 video_description
= clean_html(video_description
)
1410 fd_mobj
= re
.search(r
'<meta name="description" content="([^"]+)"', video_webpage
)
1412 video_description
= unescapeHTML(fd_mobj
.group(1))
1414 video_description
= ''
1416 if 'multifeed_metadata_list' in video_info
and not smuggled_data
.get('force_singlefeed', False):
1417 if not self
._downloader
.params
.get('noplaylist'):
1420 multifeed_metadata_list
= video_info
['multifeed_metadata_list'][0]
1421 for feed
in multifeed_metadata_list
.split(','):
1422 # Unquote should take place before split on comma (,) since textual
1423 # fields may contain comma as well (see
1424 # https://github.com/rg3/youtube-dl/issues/8536)
1425 feed_data
= compat_parse_qs(compat_urllib_parse_unquote_plus(feed
))
1427 '_type': 'url_transparent',
1428 'ie_key': 'Youtube',
1430 '%s://www.youtube.com/watch?v=%s' % (proto
, feed_data
['id'][0]),
1431 {'force_singlefeed': True}
),
1432 'title': '%s (%s)' % (video_title
, feed_data
['title'][0]),
1434 feed_ids
.append(feed_data
['id'][0])
1436 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1437 % (', '.join(feed_ids
), video_id
))
1438 return self
.playlist_result(entries
, video_id
, video_title
, video_description
)
1439 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
1441 if 'view_count' in video_info
:
1442 view_count
= int(video_info
['view_count'][0])
1446 # Check for "rental" videos
1447 if 'ypc_video_rental_bar_text' in video_info
and 'author' not in video_info
:
1448 raise ExtractorError('"rental" videos not supported')
1450 # Start extracting information
1451 self
.report_information_extraction(video_id
)
1454 if 'author' not in video_info
:
1455 raise ExtractorError('Unable to extract uploader name')
1456 video_uploader
= compat_urllib_parse_unquote_plus(video_info
['author'][0])
1459 video_uploader_id
= None
1460 video_uploader_url
= None
1462 r
'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1464 if mobj
is not None:
1465 video_uploader_id
= mobj
.group('uploader_id')
1466 video_uploader_url
= mobj
.group('uploader_url')
1468 self
._downloader
.report_warning('unable to extract uploader nickname')
1471 # We try first to get a high quality image:
1472 m_thumb
= re
.search(r
'<span itemprop="thumbnail".*?href="(.*?)">',
1473 video_webpage
, re
.DOTALL
)
1474 if m_thumb
is not None:
1475 video_thumbnail
= m_thumb
.group(1)
1476 elif 'thumbnail_url' not in video_info
:
1477 self
._downloader
.report_warning('unable to extract video thumbnail')
1478 video_thumbnail
= None
1479 else: # don't panic if we can't find it
1480 video_thumbnail
= compat_urllib_parse_unquote_plus(video_info
['thumbnail_url'][0])
1483 upload_date
= self
._html
_search
_meta
(
1484 'datePublished', video_webpage
, 'upload date', default
=None)
1486 upload_date
= self
._search
_regex
(
1487 [r
'(?s)id="eow-date.*?>(.*?)</span>',
1488 r
'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1489 video_webpage
, 'upload date', default
=None)
1491 upload_date
= ' '.join(re
.sub(r
'[/,-]', r
' ', mobj
.group(1)).split())
1492 upload_date
= unified_strdate(upload_date
)
1494 video_license
= self
._html
_search
_regex
(
1495 r
'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1496 video_webpage
, 'license', default
=None)
1498 m_music
= re
.search(
1499 r
'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1502 video_alt_title
= remove_quotes(unescapeHTML(m_music
.group('title')))
1503 video_creator
= clean_html(m_music
.group('creator'))
1505 video_alt_title
= video_creator
= None
1507 m_episode
= re
.search(
1508 r
'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1511 series
= m_episode
.group('series')
1512 season_number
= int(m_episode
.group('season'))
1513 episode_number
= int(m_episode
.group('episode'))
1515 series
= season_number
= episode_number
= None
1517 m_cat_container
= self
._search
_regex
(
1518 r
'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1519 video_webpage
, 'categories', default
=None)
1521 category
= self
._html
_search
_regex
(
1522 r
'(?s)<a[^<]+>(.*?)</a>', m_cat_container
, 'category',
1524 video_categories
= None if category
is None else [category
]
1526 video_categories
= None
1529 unescapeHTML(m
.group('content'))
1530 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), video_webpage
)]
1532 def _extract_count(count_name
):
1533 return str_to_int(self
._search
_regex
(
1534 r
'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1535 % re
.escape(count_name
),
1536 video_webpage
, count_name
, default
=None))
1538 like_count
= _extract_count('like')
1539 dislike_count
= _extract_count('dislike')
1542 video_subtitles
= self
.extract_subtitles(video_id
, video_webpage
)
1543 automatic_captions
= self
.extract_automatic_captions(video_id
, video_webpage
)
1545 video_duration
= try_get(
1546 video_info
, lambda x
: int_or_none(x
['length_seconds'][0]))
1547 if not video_duration
:
1548 video_duration
= parse_duration(self
._html
_search
_meta
(
1549 'duration', video_webpage
, 'video duration'))
1552 video_annotations
= None
1553 if self
._downloader
.params
.get('writeannotations', False):
1554 video_annotations
= self
._extract
_annotations
(video_id
)
1556 def _map_to_format_list(urlmap
):
1558 for itag
, video_real_url
in urlmap
.items():
1561 'url': video_real_url
,
1562 'player_url': player_url
,
1564 if itag
in self
._formats
:
1565 dct
.update(self
._formats
[itag
])
1569 if 'conn' in video_info
and video_info
['conn'][0].startswith('rtmp'):
1570 self
.report_rtmp_download()
1572 'format_id': '_rtmp',
1574 'url': video_info
['conn'][0],
1575 'player_url': player_url
,
1577 elif len(video_info
.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info
.get('adaptive_fmts', [''])[0]) >= 1:
1578 encoded_url_map
= video_info
.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info
.get('adaptive_fmts', [''])[0]
1579 if 'rtmpe%3Dyes' in encoded_url_map
:
1580 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected
=True)
1582 fmt_list
= video_info
.get('fmt_list', [''])[0]
1584 for fmt
in fmt_list
.split(','):
1585 spec
= fmt
.split('/')
1587 width_height
= spec
[1].split('x')
1588 if len(width_height
) == 2:
1589 formats_spec
[spec
[0]] = {
1590 'resolution': spec
[1],
1591 'width': int_or_none(width_height
[0]),
1592 'height': int_or_none(width_height
[1]),
1595 for url_data_str
in encoded_url_map
.split(','):
1596 url_data
= compat_parse_qs(url_data_str
)
1597 if 'itag' not in url_data
or 'url' not in url_data
:
1599 format_id
= url_data
['itag'][0]
1600 url
= url_data
['url'][0]
1602 if 'sig' in url_data
:
1603 url
+= '&signature=' + url_data
['sig'][0]
1604 elif 's' in url_data
:
1605 encrypted_sig
= url_data
['s'][0]
1606 ASSETS_RE
= r
'"assets":.+?"js":\s*("[^"]+")'
1608 jsplayer_url_json
= self
._search
_regex
(
1610 embed_webpage
if age_gate
else video_webpage
,
1611 'JS player URL (1)', default
=None)
1612 if not jsplayer_url_json
and not age_gate
:
1613 # We need the embed website after all
1614 if embed_webpage
is None:
1615 embed_url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1616 embed_webpage
= self
._download
_webpage
(
1617 embed_url
, video_id
, 'Downloading embed webpage')
1618 jsplayer_url_json
= self
._search
_regex
(
1619 ASSETS_RE
, embed_webpage
, 'JS player URL')
1621 player_url
= json
.loads(jsplayer_url_json
)
1622 if player_url
is None:
1623 player_url_json
= self
._search
_regex
(
1624 r
'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1625 video_webpage
, 'age gate player URL')
1626 player_url
= json
.loads(player_url_json
)
1628 if self
._downloader
.params
.get('verbose'):
1629 if player_url
is None:
1630 player_version
= 'unknown'
1631 player_desc
= 'unknown'
1633 if player_url
.endswith('swf'):
1634 player_version
= self
._search
_regex
(
1635 r
'-(.+?)(?:/watch_as3)?\.swf$', player_url
,
1636 'flash player', fatal
=False)
1637 player_desc
= 'flash player %s' % player_version
1639 player_version
= self
._search
_regex
(
1640 [r
'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r
'(?:www|player)-([^/]+)/base\.js'],
1642 'html5 player', fatal
=False)
1643 player_desc
= 'html5 player %s' % player_version
1645 parts_sizes
= self
._signature
_cache
_id
(encrypted_sig
)
1646 self
.to_screen('{%s} signature length %s, %s' %
1647 (format_id
, parts_sizes
, player_desc
))
1649 signature
= self
._decrypt
_signature
(
1650 encrypted_sig
, video_id
, player_url
, age_gate
)
1651 url
+= '&signature=' + signature
1652 if 'ratebypass' not in url
:
1653 url
+= '&ratebypass=yes'
1656 'format_id': format_id
,
1658 'player_url': player_url
,
1660 if format_id
in self
._formats
:
1661 dct
.update(self
._formats
[format_id
])
1662 if format_id
in formats_spec
:
1663 dct
.update(formats_spec
[format_id
])
1665 # Some itags are not included in DASH manifest thus corresponding formats will
1666 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1667 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1668 mobj
= re
.search(r
'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data
.get('size', [''])[0])
1669 width
, height
= (int(mobj
.group('width')), int(mobj
.group('height'))) if mobj
else (None, None)
1672 'filesize': int_or_none(url_data
.get('clen', [None])[0]),
1673 'tbr': float_or_none(url_data
.get('bitrate', [None])[0], 1000),
1676 'fps': int_or_none(url_data
.get('fps', [None])[0]),
1677 'format_note': url_data
.get('quality_label', [None])[0] or url_data
.get('quality', [None])[0],
1679 for key
, value
in more_fields
.items():
1682 type_
= url_data
.get('type', [None])[0]
1684 type_split
= type_
.split(';')
1685 kind_ext
= type_split
[0].split('/')
1686 if len(kind_ext
) == 2:
1688 dct
['ext'] = mimetype2ext(type_split
[0])
1689 if kind
in ('audio', 'video'):
1691 for mobj
in re
.finditer(
1692 r
'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
1693 if mobj.group('key
') == 'codecs
':
1694 codecs = mobj.group('val
')
1697 codecs = codecs.split(',')
1698 if len(codecs) == 2:
1699 acodec, vcodec = codecs[1], codecs[0]
1701 acodec, vcodec = (codecs[0], 'none
') if kind == 'audio
' else ('none
', codecs[0])
1707 elif video_info.get('hlsvp
'):
1708 manifest_url = video_info['hlsvp
'][0]
1709 url_map = self._extract_from_m3u8(manifest_url, video_id)
1710 formats = _map_to_format_list(url_map)
1711 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1712 for a_format in formats:
1713 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
1715 unavailable_message = self._html_search_regex(
1716 r'(?s
)<h1
[^
>]+id="unavailable-message"[^
>]*>(.+?
)</h1
>',
1717 video_webpage, 'unavailable message
', default=None)
1718 if unavailable_message:
1719 raise ExtractorError(unavailable_message, expected=True)
1720 raise ExtractorError('no conn
, hlsvp
or url_encoded_fmt_stream_map information found
in video info
')
1722 # Look for the DASH manifest
1723 if self._downloader.params.get('youtube_include_dash_manifest
', True):
1724 dash_mpd_fatal = True
1725 for mpd_url in dash_mpds:
1728 def decrypt_sig(mobj):
1730 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1731 return '/signature
/%s' % dec_s
1733 mpd_url = re.sub(r'/s
/([a
-fA
-F0
-9\
.]+)', decrypt_sig, mpd_url)
1735 for df in self._extract_mpd_formats(
1736 mpd_url, video_id, fatal=dash_mpd_fatal,
1737 formats_dict=self._formats):
1738 # Do not overwrite DASH format found in some previous DASH manifest
1739 if df['format_id
'] not in dash_formats:
1740 dash_formats[df['format_id
']] = df
1741 # Additional DASH manifests may end up in HTTP Error 403 therefore
1742 # allow them to fail without bug report message if we already have
1743 # some DASH manifest succeeded. This is temporary workaround to reduce
1744 # burst of bug reports until we figure out the reason and whether it
1745 # can be fixed at all.
1746 dash_mpd_fatal = False
1747 except (ExtractorError, KeyError) as e:
1748 self.report_warning(
1749 'Skipping DASH manifest
: %r' % e, video_id)
1751 # Remove the formats we found through non-DASH, they
1752 # contain less info and it can be wrong, because we use
1753 # fixed values (for example the resolution). See
1754 # https://github.com/rg3/youtube-dl/issues/5774 for an
1756 formats = [f for f in formats if f['format_id
'] not in dash_formats.keys()]
1757 formats.extend(dash_formats.values())
1759 # Check for malformed aspect ratio
1760 stretched_m = re.search(
1761 r'<meta\s
+property="og:video:tag".*?content
="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1764 w = float(stretched_m.group('w
'))
1765 h = float(stretched_m.group('h
'))
1766 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1767 # We will only process correct ratios.
1771 if f.get('vcodec
') != 'none
':
1772 f['stretched_ratio
'] = ratio
1774 self._sort_formats(formats)
1776 self.mark_watched(video_id, video_info)
1780 'uploader
': video_uploader,
1781 'uploader_id
': video_uploader_id,
1782 'uploader_url
': video_uploader_url,
1783 'upload_date
': upload_date,
1784 'license
': video_license,
1785 'creator
': video_creator,
1786 'title
': video_title,
1787 'alt_title
': video_alt_title,
1788 'thumbnail
': video_thumbnail,
1789 'description
': video_description,
1790 'categories
': video_categories,
1792 'subtitles
': video_subtitles,
1793 'automatic_captions
': automatic_captions,
1794 'duration
': video_duration,
1795 'age_limit
': 18 if age_gate else 0,
1796 'annotations
': video_annotations,
1797 'webpage_url
': proto + '://www
.youtube
.com
/watch?v
=%s' % video_id,
1798 'view_count
': view_count,
1799 'like_count
': like_count,
1800 'dislike_count
': dislike_count,
1801 'average_rating
': float_or_none(video_info.get('avg_rating
', [None])[0]),
1804 'start_time
': start_time,
1805 'end_time
': end_time,
1807 'season_number
': season_number,
1808 'episode_number
': episode_number,
1812 class YoutubeSharedVideoIE(InfoExtractor):
1813 _VALID_URL = r'(?
:https?
:)?
//(?
:www\
.)?youtube\
.com
/shared
\?.*\bci
=(?P
<id>[0-9A
-Za
-z_
-]{11}
)'
1814 IE_NAME = 'youtube
:shared
'
1817 'url
': 'https
://www
.youtube
.com
/shared?ci
=1nEzmT
-M4fU
',
1819 'id': 'uPDB5I9wfp8
',
1821 'title
': 'Pocoyo
: 90 minutos de episódios completos Português para crianç
as - PARTE
3',
1822 'description
': 'md5
:d9e4d9346a2dfff4c7dc4c8cec0f546d
',
1823 'upload_date
': '20160219',
1824 'uploader
': 'Pocoyo
- Portuguê
s (BR
)',
1825 'uploader_id
': 'PocoyoBrazil
',
1827 'add_ie
': ['Youtube
'],
1829 # There are already too many Youtube downloads
1830 'skip_download
': True,
1834 def _real_extract(self, url):
1835 video_id = self._match_id(url)
1837 webpage = self._download_webpage(url, video_id)
1839 real_video_id = self._html_search_meta(
1840 'videoId
', webpage, 'YouTube video
id', fatal=True)
1842 return self.url_result(real_video_id, YoutubeIE.ie_key())
1845 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1846 IE_DESC = 'YouTube
.com playlists
'
1847 _VALID_URL = r"""(?x)(?:
1853 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1854 \? (?:.*?[&;])*? (?:p|a|list)=
1857 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1860 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
1861 # Top tracks, they can also include dots
1866 ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
1868 _TEMPLATE_URL = 'https
://www
.youtube
.com
/playlist?
list=%s&disable_polymer
=true
'
1869 _VIDEO_RE = r'href
="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index
=(?P
<index
>\d
+)(?
:[^
>]+>(?P
<title
>[^
<]+))?
'
1870 IE_NAME = 'youtube
:playlist
'
1872 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1874 'title
': 'ytdl test PL
',
1875 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1877 'playlist_count
': 3,
1879 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1881 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1882 'title
': 'YDL_Empty_List
',
1884 'playlist_count
': 0,
1885 'skip
': 'This playlist
is private
',
1887 'note
': 'Playlist
with deleted
videos (#651). As a bonus, the video #51 is also twice in this list.',
1888 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1890 'title': '29C3: Not my department',
1891 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1893 'playlist_count': 95,
1895 'note': 'issue #673',
1896 'url': 'PLBB231211A4F62143',
1898 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1899 'id': 'PLBB231211A4F62143',
1901 'playlist_mincount': 26,
1903 'note': 'Large playlist',
1904 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1906 'title': 'Uploads from Cauchemar',
1907 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1909 'playlist_mincount': 799,
1911 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1913 'title': 'YDL_safe_search',
1914 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1916 'playlist_count': 2,
1917 'skip': 'This playlist is private',
1920 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1921 'playlist_count': 4,
1924 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1927 'note': 'Embedded SWF player',
1928 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1929 'playlist_count': 4,
1932 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1935 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1936 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1938 'title': 'Uploads from Interstellar Movie',
1939 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1941 'playlist_mincount': 21,
1943 # Playlist URL that does not actually serve a playlist
1944 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1946 'id': 'FqZTN594JQw',
1948 'title': "Smiley's People 01 detective, Adventure Series, Action",
1949 'uploader': 'STREEM',
1950 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1951 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1952 'upload_date': '20150526',
1953 'license': 'Standard YouTube License',
1954 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1955 'categories': ['People & Blogs'],
1958 'dislike_count': int,
1961 'skip_download': True,
1963 'add_ie': [YoutubeIE
.ie_key()],
1965 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1967 'id': 'yeWKywCrFtk',
1969 'title': 'Small Scale Baler and Braiding Rugs',
1970 'uploader': 'Backus-Page House Museum',
1971 'uploader_id': 'backuspagemuseum',
1972 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1973 'upload_date': '20161008',
1974 'license': 'Standard YouTube License',
1975 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1976 'categories': ['Nonprofits & Activism'],
1979 'dislike_count': int,
1983 'skip_download': True,
1986 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1987 'only_matching': True,
1989 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
1990 'only_matching': True,
1993 def _real_initialize(self
):
1996 def _extract_mix(self
, playlist_id
):
1997 # The mixes are generated from a single video
1998 # the id of the playlist is just 'RD' + video_id
2000 last_id
= playlist_id
[-11:]
2001 for n
in itertools
.count(1):
2002 url
= 'https://youtube.com/watch?v=%s&list=%s' % (last_id
, playlist_id
)
2003 webpage
= self
._download
_webpage
(
2004 url
, playlist_id
, 'Downloading page {0} of Youtube mix'.format(n
))
2005 new_ids
= orderedSet(re
.findall(
2006 r
'''(?xs)data-video-username=".*?".*?
2007 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re
.escape(playlist_id
),
2009 # Fetch new pages until all the videos are repeated, it seems that
2010 # there are always 51 unique videos.
2011 new_ids
= [_id
for _id
in new_ids
if _id
not in ids
]
2017 url_results
= self
._ids
_to
_results
(ids
)
2019 search_title
= lambda class_name
: get_element_by_attribute('class', class_name
, webpage
)
2021 search_title('playlist-title') or
2022 search_title('title long-title') or
2023 search_title('title'))
2024 title
= clean_html(title_span
)
2026 return self
.playlist_result(url_results
, playlist_id
, title
)
2028 def _extract_playlist(self
, playlist_id
):
2029 url
= self
._TEMPLATE
_URL
% playlist_id
2030 page
= self
._download
_webpage
(url
, playlist_id
)
2032 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2033 for match
in re
.findall(r
'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page
):
2034 match
= match
.strip()
2035 # Check if the playlist exists or is private
2036 mobj
= re
.match(r
'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match
)
2038 reason
= mobj
.group('reason')
2039 message
= 'This playlist %s' % reason
2040 if 'private' in reason
:
2041 message
+= ', use --username or --netrc to access it'
2043 raise ExtractorError(message
, expected
=True)
2044 elif re
.match(r
'[^<]*Invalid parameters[^<]*', match
):
2045 raise ExtractorError(
2046 'Invalid parameters. Maybe URL is incorrect.',
2048 elif re
.match(r
'[^<]*Choose your language[^<]*', match
):
2051 self
.report_warning('Youtube gives an alert message: ' + match
)
2053 playlist_title
= self
._html
_search
_regex
(
2054 r
'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2055 page
, 'title', default
=None)
2059 if not playlist_title
:
2061 # Some playlist URLs don't actually serve a playlist (e.g.
2062 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2063 next(self
._entries
(page
, playlist_id
))
2064 except StopIteration:
2067 return has_videos
, self
.playlist_result(
2068 self
._entries
(page
, playlist_id
), playlist_id
, playlist_title
)
2070 def _check_download_just_video(self
, url
, playlist_id
):
2071 # Check if it's a video-specific URL
2072 query_dict
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
2073 video_id
= query_dict
.get('v', [None])[0] or self
._search
_regex
(
2074 r
'(?:^|//)youtu\.be/([0-9A-Za-z_-]{11})', url
,
2075 'video id', default
=None)
2077 if self
._downloader
.params
.get('noplaylist'):
2078 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
2079 return video_id
, self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2081 self
.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id
, video_id
))
2082 return video_id
, None
2085 def _real_extract(self
, url
):
2086 # Extract playlist id
2087 mobj
= re
.match(self
._VALID
_URL
, url
)
2089 raise ExtractorError('Invalid URL: %s' % url
)
2090 playlist_id
= mobj
.group(1) or mobj
.group(2)
2092 video_id
, video
= self
._check
_download
_just
_video
(url
, playlist_id
)
2096 if playlist_id
.startswith(('RD', 'UL', 'PU')):
2097 # Mixes require a custom extraction process
2098 return self
._extract
_mix
(playlist_id
)
2100 has_videos
, playlist
= self
._extract
_playlist
(playlist_id
)
2101 if has_videos
or not video_id
:
2104 # Some playlist URLs don't actually serve a playlist (see
2105 # https://github.com/rg3/youtube-dl/issues/10537).
2106 # Fallback to plain video extraction if there is a video id
2107 # along with playlist id.
2108 return self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2111 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor
):
2112 IE_DESC
= 'YouTube.com channels'
2113 _VALID_URL
= r
'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2114 _TEMPLATE_URL
= 'https://www.youtube.com/channel/%s/videos'
2115 _VIDEO_RE
= r
'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2116 IE_NAME
= 'youtube:channel'
2118 'note': 'paginated channel',
2119 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2120 'playlist_mincount': 91,
2122 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2123 'title': 'Uploads from lex will',
2126 'note': 'Age restricted channel',
2127 # from https://www.youtube.com/user/DeusExOfficial
2128 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2129 'playlist_mincount': 64,
2131 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2132 'title': 'Uploads from Deus Ex',
2137 def suitable(cls
, url
):
2138 return (False if YoutubePlaylistsIE
.suitable(url
) or YoutubeLiveIE
.suitable(url
)
2139 else super(YoutubeChannelIE
, cls
).suitable(url
))
2141 def _build_template_url(self
, url
, channel_id
):
2142 return self
._TEMPLATE
_URL
% channel_id
2144 def _real_extract(self
, url
):
2145 channel_id
= self
._match
_id
(url
)
2147 url
= self
._build
_template
_url
(url
, channel_id
)
2149 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2150 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2151 # otherwise fallback on channel by page extraction
2152 channel_page
= self
._download
_webpage
(
2153 url
+ '?view=57', channel_id
,
2154 'Downloading channel page', fatal
=False)
2155 if channel_page
is False:
2156 channel_playlist_id
= False
2158 channel_playlist_id
= self
._html
_search
_meta
(
2159 'channelId', channel_page
, 'channel id', default
=None)
2160 if not channel_playlist_id
:
2161 channel_url
= self
._html
_search
_meta
(
2162 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2163 channel_page
, 'channel url', default
=None)
2165 channel_playlist_id
= self
._search
_regex
(
2166 r
'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2167 channel_url
, 'channel id', default
=None)
2168 if channel_playlist_id
and channel_playlist_id
.startswith('UC'):
2169 playlist_id
= 'UU' + channel_playlist_id
[2:]
2170 return self
.url_result(
2171 compat_urlparse
.urljoin(url
, '/playlist?list=%s' % playlist_id
), 'YoutubePlaylist')
2173 channel_page
= self
._download
_webpage
(url
, channel_id
, 'Downloading page #1')
2174 autogenerated
= re
.search(r
'''(?x)
2176 channel-header-autogenerated-label|
2177 yt-channel-title-autogenerated
2178 )[^"]*"''', channel_page
) is not None
2181 # The videos are contained in a single page
2182 # the ajax pages can't be used, they are empty
2185 video_id
, 'Youtube', video_id
=video_id
,
2186 video_title
=video_title
)
2187 for video_id
, video_title
in self
.extract_videos_from_page(channel_page
)]
2188 return self
.playlist_result(entries
, channel_id
)
2191 next(self
._entries
(channel_page
, channel_id
))
2192 except StopIteration:
2193 alert_message
= self
._html
_search
_regex
(
2194 r
'(?s)<div[^>]+class=(["\']).*?
\byt
-alert
-message
\b.*?\
1[^
>]*>(?P
<alert
>[^
<]+)</div
>',
2195 channel_page, 'alert
', default=None, group='alert
')
2197 raise ExtractorError('Youtube said
: %s' % alert_message, expected=True)
2199 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2202 class YoutubeUserIE(YoutubeChannelIE):
2203 IE_DESC = 'YouTube
.com user
videos (URL
or "ytuser" keyword
)'
2204 _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_-]+)'
2205 _TEMPLATE_URL = 'https
://www
.youtube
.com
/%s/%s/videos
'
2206 IE_NAME = 'youtube
:user
'
2209 'url
': 'https
://www
.youtube
.com
/user
/TheLinuxFoundation
',
2210 'playlist_mincount
': 320,
2212 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ
',
2213 'title
': 'Uploads
from The Linux Foundation
',
2216 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2217 # but not https://www.youtube.com/user/12minuteathlete/videos
2218 'url
': 'https
://www
.youtube
.com
/c
/12minuteathlete
/videos
',
2219 'playlist_mincount
': 249,
2221 'id': 'UUVjM
-zV6_opMDx7WYxnjZiQ
',
2222 'title
': 'Uploads
from 12 Minute Athlete
',
2225 'url
': 'ytuser
:phihag
',
2226 'only_matching
': True,
2228 'url
': 'https
://www
.youtube
.com
/c
/gametrailers
',
2229 'only_matching
': True,
2231 'url
': 'https
://www
.youtube
.com
/gametrailers
',
2232 'only_matching
': True,
2234 # This channel is not available.
2235 'url
': 'https
://www
.youtube
.com
/user
/kananishinoSMEJ
/videos
',
2236 'only_matching
': True,
2240 def suitable(cls, url):
2241 # Don't
return True if the url can be extracted
with other youtube
2242 # extractor, the regex would is too permissive and it would match.
2243 other_yt_ies
= iter(klass
for (name
, klass
) in globals().items() if name
.startswith('Youtube') and name
.endswith('IE') and klass
is not cls
)
2244 if any(ie
.suitable(url
) for ie
in other_yt_ies
):
2247 return super(YoutubeUserIE
, cls
).suitable(url
)
2249 def _build_template_url(self
, url
, channel_id
):
2250 mobj
= re
.match(self
._VALID
_URL
, url
)
2251 return self
._TEMPLATE
_URL
% (mobj
.group('user') or 'user', mobj
.group('id'))
2254 class YoutubeLiveIE(YoutubeBaseInfoExtractor
):
2255 IE_DESC
= 'YouTube.com live streams'
2256 _VALID_URL
= r
'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2257 IE_NAME
= 'youtube:live'
2260 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2262 'id': 'a48o2S1cPoo',
2264 'title': 'The Young Turks - Live Main Show',
2265 'uploader': 'The Young Turks',
2266 'uploader_id': 'TheYoungTurks',
2267 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2268 'upload_date': '20150715',
2269 'license': 'Standard YouTube License',
2270 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2271 'categories': ['News & Politics'],
2272 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2274 'dislike_count': int,
2277 'skip_download': True,
2280 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2281 'only_matching': True,
2283 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2284 'only_matching': True,
2286 'url': 'https://www.youtube.com/TheYoungTurks/live',
2287 'only_matching': True,
2290 def _real_extract(self
, url
):
2291 mobj
= re
.match(self
._VALID
_URL
, url
)
2292 channel_id
= mobj
.group('id')
2293 base_url
= mobj
.group('base_url')
2294 webpage
= self
._download
_webpage
(url
, channel_id
, fatal
=False)
2296 page_type
= self
._og
_search
_property
(
2297 'type', webpage
, 'page type', default
=None)
2298 video_id
= self
._html
_search
_meta
(
2299 'videoId', webpage
, 'video id', default
=None)
2300 if page_type
== 'video' and video_id
and re
.match(r
'^[0-9A-Za-z_-]{11}$', video_id
):
2301 return self
.url_result(video_id
, YoutubeIE
.ie_key())
2302 return self
.url_result(base_url
)
2305 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor
):
2306 IE_DESC
= 'YouTube.com user/channel playlists'
2307 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2308 IE_NAME
= 'youtube:playlists'
2311 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2312 'playlist_mincount': 4,
2314 'id': 'ThirstForScience',
2315 'title': 'Thirst for Science',
2318 # with "Load more" button
2319 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2320 'playlist_mincount': 70,
2323 'title': 'Игорь Клейнер',
2326 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2327 'playlist_mincount': 17,
2329 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2330 'title': 'Chem Player',
2335 class YoutubeSearchIE(SearchInfoExtractor
, YoutubePlaylistIE
):
2336 IE_DESC
= 'YouTube.com searches'
2337 # there doesn't appear to be a real limit, for example if you search for
2338 # 'python' you get more than 8.000.000 results
2339 _MAX_RESULTS
= float('inf')
2340 IE_NAME
= 'youtube:search'
2341 _SEARCH_KEY
= 'ytsearch'
2342 _EXTRA_QUERY_ARGS
= {}
2345 def _get_n_results(self
, query
, n
):
2346 """Get a specified number of results for a query"""
2352 'search_query': query
.encode('utf-8'),
2354 url_query
.update(self
._EXTRA
_QUERY
_ARGS
)
2355 result_url
= 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query
)
2357 for pagenum
in itertools
.count(1):
2358 data
= self
._download
_json
(
2359 result_url
, video_id
='query "%s"' % query
,
2360 note
='Downloading page %s' % pagenum
,
2361 errnote
='Unable to download API page',
2362 query
={'spf': 'navigate'}
)
2363 html_content
= data
[1]['body']['content']
2365 if 'class="search-message' in html_content
:
2366 raise ExtractorError(
2367 '[youtube] No video results', expected
=True)
2369 new_videos
= self
._ids
_to
_results
(orderedSet(re
.findall(
2370 r
'href="/watch\?v=(.{11})', html_content
)))
2371 videos
+= new_videos
2372 if not new_videos
or len(videos
) > limit
:
2374 next_link
= self
._html
_search
_regex
(
2375 r
'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2376 html_content
, 'next link', default
=None)
2377 if next_link
is None:
2379 result_url
= compat_urlparse
.urljoin('https://www.youtube.com/', next_link
)
2383 return self
.playlist_result(videos
, query
)
2386 class YoutubeSearchDateIE(YoutubeSearchIE
):
2387 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
2388 _SEARCH_KEY
= 'ytsearchdate'
2389 IE_DESC
= 'YouTube.com searches, newest videos first'
2390 _EXTRA_QUERY_ARGS
= {'search_sort': 'video_date_uploaded'}
2393 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor
):
2394 IE_DESC
= 'YouTube.com search URLs'
2395 IE_NAME
= 'youtube:search_url'
2396 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2397 _VIDEO_RE
= r
'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2399 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2400 'playlist_mincount': 5,
2402 'title': 'youtube-dl test video',
2405 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2406 'only_matching': True,
2409 def _real_extract(self
, url
):
2410 mobj
= re
.match(self
._VALID
_URL
, url
)
2411 query
= compat_urllib_parse_unquote_plus(mobj
.group('query'))
2412 webpage
= self
._download
_webpage
(url
, query
)
2413 return self
.playlist_result(self
._process
_page
(webpage
), playlist_title
=query
)
2416 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor
):
2417 IE_DESC
= 'YouTube.com (multi-season) shows'
2418 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2419 IE_NAME
= 'youtube:show'
2421 'url': 'https://www.youtube.com/show/airdisasters',
2422 'playlist_mincount': 5,
2424 'id': 'airdisasters',
2425 'title': 'Air Disasters',
2429 def _real_extract(self
, url
):
2430 playlist_id
= self
._match
_id
(url
)
2431 return super(YoutubeShowIE
, self
)._real
_extract
(
2432 'https://www.youtube.com/show/%s/playlists' % playlist_id
)
2435 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor
):
2437 Base class for feed extractors
2438 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2440 _LOGIN_REQUIRED
= True
2444 return 'youtube:%s' % self
._FEED
_NAME
2446 def _real_initialize(self
):
2449 def _real_extract(self
, url
):
2450 page
= self
._download
_webpage
(
2451 'https://www.youtube.com/feed/%s' % self
._FEED
_NAME
, self
._PLAYLIST
_TITLE
)
2453 # The extraction process is the same as for playlists, but the regex
2454 # for the video ids doesn't contain an index
2456 more_widget_html
= content_html
= page
2457 for page_num
in itertools
.count(1):
2458 matches
= re
.findall(r
'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html
)
2460 # 'recommended' feed has infinite 'load more' and each new portion spins
2461 # the same videos in (sometimes) slightly different order, so we'll check
2462 # for unicity and break when portion has no new videos
2463 new_ids
= filter(lambda video_id
: video_id
not in ids
, orderedSet(matches
))
2469 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
2473 more
= self
._download
_json
(
2474 'https://youtube.com/%s' % mobj
.group('more'), self
._PLAYLIST
_TITLE
,
2475 'Downloading page #%s' % page_num
,
2476 transform_source
=uppercase_escape
)
2477 content_html
= more
['content_html']
2478 more_widget_html
= more
['load_more_widget_html']
2480 return self
.playlist_result(
2481 self
._ids
_to
_results
(ids
), playlist_title
=self
._PLAYLIST
_TITLE
)
2484 class YoutubeWatchLaterIE(YoutubePlaylistIE
):
2485 IE_NAME
= 'youtube:watchlater'
2486 IE_DESC
= 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2487 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2490 'url': 'https://www.youtube.com/playlist?list=WL',
2491 'only_matching': True,
2493 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2494 'only_matching': True,
2497 def _real_extract(self
, url
):
2498 _
, video
= self
._check
_download
_just
_video
(url
, 'WL')
2501 _
, playlist
= self
._extract
_playlist
('WL')
2505 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
2506 IE_NAME
= 'youtube:favorites'
2507 IE_DESC
= 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2508 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2509 _LOGIN_REQUIRED
= True
2511 def _real_extract(self
, url
):
2512 webpage
= self
._download
_webpage
('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2513 playlist_id
= self
._search
_regex
(r
'list=(.+?)["&]', webpage
, 'favourites playlist id')
2514 return self
.url_result(playlist_id
, 'YoutubePlaylist')
2517 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
2518 IE_DESC
= 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2519 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2520 _FEED_NAME
= 'recommended'
2521 _PLAYLIST_TITLE
= 'Youtube Recommended videos'
2524 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
2525 IE_DESC
= 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2526 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2527 _FEED_NAME
= 'subscriptions'
2528 _PLAYLIST_TITLE
= 'Youtube Subscriptions'
2531 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
2532 IE_DESC
= 'Youtube watch history, ":ythistory" for short (requires authentication)'
2533 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2534 _FEED_NAME
= 'history'
2535 _PLAYLIST_TITLE
= 'Youtube History'
2538 class YoutubeTruncatedURLIE(InfoExtractor
):
2539 IE_NAME
= 'youtube:truncated_url'
2540 IE_DESC
= False # Do not list
2541 _VALID_URL
= r
'''(?x)
2543 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2546 annotation_id=annotation_[^&]+|
2552 attribution_link\?a=[^&]+
2558 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2559 'only_matching': True,
2561 'url': 'https://www.youtube.com/watch?',
2562 'only_matching': True,
2564 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2565 'only_matching': True,
2567 'url': 'https://www.youtube.com/watch?feature=foo',
2568 'only_matching': True,
2570 'url': 'https://www.youtube.com/watch?hl=en-GB',
2571 'only_matching': True,
2573 'url': 'https://www.youtube.com/watch?t=2372',
2574 'only_matching': True,
2577 def _real_extract(self
, url
):
2578 raise ExtractorError(
2579 'Did you forget to quote the URL? Remember that & is a meta '
2580 'character in most shells, so you want to put the URL in quotes, '
2582 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2583 ' or simply youtube-dl BaW_jenozKc .',
2587 class YoutubeTruncatedIDIE(InfoExtractor
):
2588 IE_NAME
= 'youtube:truncated_id'
2589 IE_DESC
= False # Do not list
2590 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2593 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2594 'only_matching': True,
2597 def _real_extract(self
, url
):
2598 video_id
= self
._match
_id
(url
)
2599 raise ExtractorError(
2600 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id
, url
),