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'},
332 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
333 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'preference': -50, 'container': 'm4a_dash'},
336 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
337 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
338 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
339 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
340 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
341 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
342 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
343 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
344 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
345 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
346 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
347 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
348 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
349 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
350 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
351 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
352 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
353 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
354 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
355 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
356 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
357 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
360 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
361 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
363 # Dash webm audio with opus inside
364 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
365 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
366 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
369 '_rtmp': {'protocol': 'rtmp'},
371 _SUBTITLE_FORMATS
= ('ttml', 'vtt')
376 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
380 'title': 'youtube-dl test video "\'/\\Ƥāš',
381 'uploader': 'Philipp Hagemeister',
382 'uploader_id': 'phihag',
383 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
384 'upload_date': '20121002',
385 'license': 'Standard YouTube License',
386 '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 .',
387 'categories': ['Science & Technology'],
388 'tags': ['youtube-dl'],
391 'dislike_count': int,
397 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
398 'note': 'Test generic use_cipher_signature video (#897)',
402 'upload_date': '20120506',
403 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
404 'alt_title': 'I Love It (feat. Charli XCX)',
405 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
406 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
407 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
408 'iconic ep', 'iconic', 'love', 'it'],
410 'uploader': 'Icona Pop',
411 'uploader_id': 'IconaPop',
412 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IconaPop',
413 'license': 'Standard YouTube License',
414 'creator': 'Icona Pop',
418 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
419 'note': 'Test VEVO video with age protection (#956)',
423 'upload_date': '20130703',
424 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
425 'alt_title': 'Tunnel Vision',
426 'description': 'md5:64249768eec3bc4276236606ea996373',
428 'uploader': 'justintimberlakeVEVO',
429 'uploader_id': 'justintimberlakeVEVO',
430 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
431 'license': 'Standard YouTube License',
432 'creator': 'Justin Timberlake',
437 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
438 'note': 'Embed-only video (#1746)',
442 'upload_date': '20120608',
443 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
444 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
445 'uploader': 'SET India',
446 'uploader_id': 'setindia',
447 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
448 'license': 'Standard YouTube License',
453 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
454 'note': 'Use the first video ID in the URL',
458 'title': 'youtube-dl test video "\'/\\Ƥāš',
459 'uploader': 'Philipp Hagemeister',
460 'uploader_id': 'phihag',
461 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
462 'upload_date': '20121002',
463 'license': 'Standard YouTube License',
464 '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 .',
465 'categories': ['Science & Technology'],
466 'tags': ['youtube-dl'],
469 'dislike_count': int,
472 'skip_download': True,
476 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
477 'note': '256k DASH audio (format 141) via DASH manifest',
481 'upload_date': '20121002',
482 'uploader_id': '8KVIDEO',
483 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
485 'uploader': '8KVIDEO',
486 'license': 'Standard YouTube License',
487 'title': 'UHDTV TEST 8K VIDEO.mp4'
490 'youtube_include_dash_manifest': True,
493 'skip': 'format 141 not served anymore',
495 # DASH manifest with encrypted signature
497 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
501 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
502 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
504 'uploader': 'AfrojackVEVO',
505 'uploader_id': 'AfrojackVEVO',
506 'upload_date': '20131011',
507 'license': 'Standard YouTube License',
510 'youtube_include_dash_manifest': True,
511 'format': '141/bestaudio[ext=m4a]',
514 # JS player signature function name containing $
516 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
520 'title': 'Taylor Swift - Shake It Off',
521 'alt_title': 'Shake It Off',
522 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
524 'uploader': 'TaylorSwiftVEVO',
525 'uploader_id': 'TaylorSwiftVEVO',
526 'upload_date': '20140818',
527 'license': 'Standard YouTube License',
528 'creator': 'Taylor Swift',
531 'youtube_include_dash_manifest': True,
532 'format': '141/bestaudio[ext=m4a]',
537 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
542 'upload_date': '20100909',
543 'uploader': 'The Amazing Atheist',
544 'uploader_id': 'TheAmazingAtheist',
545 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
546 'license': 'Standard YouTube License',
547 'title': 'Burning Everyone\'s Koran',
548 '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',
551 # Normal age-gate video (No vevo, embed allowed)
553 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
557 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
558 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
560 'uploader': 'The Witcher',
561 'uploader_id': 'WitcherGame',
562 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
563 'upload_date': '20140605',
564 'license': 'Standard YouTube License',
568 # Age-gate video with encrypted signature
570 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
574 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
575 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
577 'uploader': 'LloydVEVO',
578 'uploader_id': 'LloydVEVO',
579 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
580 'upload_date': '20110629',
581 'license': 'Standard YouTube License',
585 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
587 'url': '__2ABJjxzNo',
592 'upload_date': '20100430',
593 'uploader_id': 'deadmau5',
594 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
595 'creator': 'deadmau5',
596 'description': 'md5:12c56784b8032162bb936a5f76d55360',
597 'uploader': 'deadmau5',
598 'license': 'Standard YouTube License',
599 'title': 'Deadmau5 - Some Chords (HD)',
600 'alt_title': 'Some Chords',
602 'expected_warnings': [
603 'DASH manifest missing',
606 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
608 'url': 'lqQg6PlCWgI',
613 'upload_date': '20150827',
614 'uploader_id': 'olympic',
615 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
616 'license': 'Standard YouTube License',
617 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
618 'uploader': 'Olympic',
619 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
622 'skip_download': 'requires avconv',
627 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
631 'stretched_ratio': 16 / 9.,
633 'upload_date': '20110310',
634 'uploader_id': 'AllenMeow',
635 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
636 'description': 'made by Wacom from Korea | åå¹&å ę²¹ę·»é by TY\'s Allen | ęč¬heylisa00cavey1001ååøē±ę
ęä¾ę¢åēæ»čÆ',
637 'uploader': 'å«č¾å«',
638 'license': 'Standard YouTube License',
639 'title': '[A-made] č®ę
å¦åå¹ē å¤Ŗå¦ ęå°±ęÆéęØ£ēäŗŗ',
642 # url_encoded_fmt_stream_map is empty string
644 'url': 'qEJwOuvDf7I',
648 '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',
650 'upload_date': '20150404',
651 'uploader_id': 'spbelect',
652 'uploader': 'ŠŠ°Š±Š»ŃŠ“Š°ŃŠµŠ»Šø ŠŠµŃŠµŃŠ±ŃŃŠ³Š°',
655 'skip_download': 'requires avconv',
657 'skip': 'This live event has ended.',
659 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
661 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
665 'title': 'md5:7b81415841e02ecd4313668cde88737a',
666 'description': 'md5:116377fd2963b81ec4ce64b542173306',
668 'upload_date': '20150625',
669 'uploader_id': 'dorappi2000',
670 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
671 'uploader': 'dorappi2000',
672 'license': 'Standard YouTube License',
673 'formats': 'mincount:32',
676 # DASH manifest with segment_list
678 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
679 'md5': '8ce563a1d667b599d21064e982ab9e31',
683 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
684 'uploader': 'Airtek',
685 'description': 'RetransmisiĆ³n en directo de la XVIII media maratĆ³n de Zaragoza.',
686 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
687 'license': 'Standard YouTube License',
688 'title': 'RetransmisiĆ³n XVIII Media maratĆ³n Zaragoza 2015',
691 'youtube_include_dash_manifest': True,
692 'format': '135', # bestvideo
694 'skip': 'This live event has ended.',
697 # Multifeed videos (multiple cameras), URL is for Main Camera
698 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
701 'title': 'teamPGP: Rocket League Noob Stream',
702 'description': 'md5:dc7872fb300e143831327f1bae3af010',
708 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
709 'description': 'md5:dc7872fb300e143831327f1bae3af010',
711 'upload_date': '20150721',
712 'uploader': 'Beer Games Beer',
713 'uploader_id': 'beergamesbeer',
714 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
715 'license': 'Standard YouTube License',
721 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
722 'description': 'md5:dc7872fb300e143831327f1bae3af010',
724 'upload_date': '20150721',
725 'uploader': 'Beer Games Beer',
726 'uploader_id': 'beergamesbeer',
727 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
728 'license': 'Standard YouTube License',
734 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
735 'description': 'md5:dc7872fb300e143831327f1bae3af010',
737 'upload_date': '20150721',
738 'uploader': 'Beer Games Beer',
739 'uploader_id': 'beergamesbeer',
740 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
741 'license': 'Standard YouTube License',
747 'title': 'teamPGP: Rocket League Noob Stream (zim)',
748 'description': 'md5:dc7872fb300e143831327f1bae3af010',
750 'upload_date': '20150721',
751 'uploader': 'Beer Games Beer',
752 'uploader_id': 'beergamesbeer',
753 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
754 'license': 'Standard YouTube License',
758 'skip_download': True,
762 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
763 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
766 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
769 'skip': 'Not multifeed anymore',
772 'url': 'https://vid.plus/FlRa-iH7PGw',
773 'only_matching': True,
776 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
777 'only_matching': True,
780 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
781 # Also tests cut-off URL expansion in video description (see
782 # https://github.com/rg3/youtube-dl/issues/1892,
783 # https://github.com/rg3/youtube-dl/issues/8164)
784 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
788 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
789 'alt_title': 'Dark Walk',
790 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
792 'upload_date': '20151119',
793 'uploader_id': 'IronSoulElf',
794 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
795 'uploader': 'IronSoulElf',
796 'license': 'Standard YouTube License',
797 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
800 'skip_download': True,
804 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
805 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
806 'only_matching': True,
809 # Video with yt:stretch=17:0
810 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
814 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
815 'description': 'md5:ee18a25c350637c8faff806845bddee9',
816 'upload_date': '20151107',
817 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
818 'uploader': 'CH GAMER DROID',
821 'skip_download': True,
823 'skip': 'This video does not exist.',
826 # Video licensed under Creative Commons
827 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
831 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
832 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
834 'upload_date': '20150127',
835 'uploader_id': 'BerkmanCenter',
836 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
837 'uploader': 'The Berkman Klein Center for Internet & Society',
838 'license': 'Creative Commons Attribution license (reuse allowed)',
841 'skip_download': True,
845 # Channel-like uploader_url
846 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
850 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
851 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
853 'upload_date': '20151119',
854 'uploader': 'Bernie 2016',
855 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
856 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
857 'license': 'Creative Commons Attribution license (reuse allowed)',
860 'skip_download': True,
864 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
865 'only_matching': True,
868 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
869 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
870 'only_matching': True,
873 # Rental video preview
874 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
878 'title': 'Piku - Trailer',
879 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
880 'upload_date': '20150811',
881 'uploader': 'FlixMatrix',
882 'uploader_id': 'FlixMatrixKaravan',
883 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
884 'license': 'Standard YouTube License',
887 'skip_download': True,
891 # YouTube Red video with episode data
892 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
896 'title': 'Isolation - Mind Field (Ep 1)',
897 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
899 'upload_date': '20170118',
900 'uploader': 'Vsauce',
901 'uploader_id': 'Vsauce',
902 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
903 'license': 'Standard YouTube License',
904 'series': 'Mind Field',
909 'skip_download': True,
911 'expected_warnings': [
912 'Skipping DASH manifest',
917 'url': '1t24XAntNCY',
918 'only_matching': True,
922 def __init__(self
, *args
, **kwargs
):
923 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
924 self
._player
_cache
= {}
926 def report_video_info_webpage_download(self
, video_id
):
927 """Report attempt to download video info webpage."""
928 self
.to_screen('%s: Downloading video info webpage' % video_id
)
930 def report_information_extraction(self
, video_id
):
931 """Report attempt to extract video information."""
932 self
.to_screen('%s: Extracting video information' % video_id
)
934 def report_unavailable_format(self
, video_id
, format
):
935 """Report extracted video URL."""
936 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
938 def report_rtmp_download(self
):
939 """Indicate the download will use the RTMP protocol."""
940 self
.to_screen('RTMP download detected')
942 def _signature_cache_id(self
, example_sig
):
943 """ Return a string representation of a signature """
944 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
946 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
948 r
'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
951 raise ExtractorError('Cannot identify player %r' % player_url
)
952 player_type
= id_m
.group('ext')
953 player_id
= id_m
.group('id')
955 # Read from filesystem cache
956 func_id
= '%s_%s_%s' % (
957 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
958 assert os
.path
.basename(func_id
) == func_id
960 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
961 if cache_spec
is not None:
962 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
965 'Downloading player %s' % player_url
966 if self
._downloader
.params
.get('verbose') else
967 'Downloading %s player %s' % (player_type
, player_id
)
969 if player_type
== 'js':
970 code
= self
._download
_webpage
(
971 player_url
, video_id
,
973 errnote
='Download of %s failed' % player_url
)
974 res
= self
._parse
_sig
_js
(code
)
975 elif player_type
== 'swf':
976 urlh
= self
._request
_webpage
(
977 player_url
, video_id
,
979 errnote
='Download of %s failed' % player_url
)
981 res
= self
._parse
_sig
_swf
(code
)
983 assert False, 'Invalid player type %r' % player_type
985 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
986 cache_res
= res(test_string
)
987 cache_spec
= [ord(c
) for c
in cache_res
]
989 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
992 def _print_sig_code(self
, func
, example_sig
):
993 def gen_sig_code(idxs
):
994 def _genslice(start
, end
, step
):
995 starts
= '' if start
== 0 else str(start
)
996 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
997 steps
= '' if step
== 1 else (':%d' % step
)
998 return 's[%s%s%s]' % (starts
, ends
, steps
)
1001 # Quelch pyflakes warnings - start will be set when step is set
1002 start
= '(Never used)'
1003 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1004 if step
is not None:
1005 if i
- prev
== step
:
1007 yield _genslice(start
, prev
, step
)
1010 if i
- prev
in [-1, 1]:
1015 yield 's[%d]' % prev
1019 yield _genslice(start
, i
, step
)
1021 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1022 cache_res
= func(test_string
)
1023 cache_spec
= [ord(c
) for c
in cache_res
]
1024 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1025 signature_id_tuple
= '(%s)' % (
1026 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1027 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1028 ' return %s\n') % (signature_id_tuple
, expr_code
)
1029 self
.to_screen('Extracted signature function:\n' + code
)
1031 def _parse_sig_js(self
, jscode
):
1032 funcname
= self
._search
_regex
(
1033 (r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1034 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1035 jscode, 'Initial JS player signature function name
', group='sig
')
1037 jsi = JSInterpreter(jscode)
1038 initial_function = jsi.extract_function(funcname)
1039 return lambda s: initial_function([s])
1041 def _parse_sig_swf(self, file_contents):
1042 swfi = SWFInterpreter(file_contents)
1043 TARGET_CLASSNAME = 'SignatureDecipher
'
1044 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1045 initial_function = swfi.extract_function(searched_class, 'decipher
')
1046 return lambda s: initial_function([s])
1048 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1049 """Turn the encrypted s field into a working signature"""
1051 if player_url is None:
1052 raise ExtractorError('Cannot decrypt signature without player_url
')
1054 if player_url.startswith('//'):
1055 player_url = 'https
:' + player_url
1056 elif not re.match(r'https?
://', player_url):
1057 player_url = compat_urlparse.urljoin(
1058 'https
://www
.youtube
.com
', player_url)
1060 player_id = (player_url, self._signature_cache_id(s))
1061 if player_id not in self._player_cache:
1062 func = self._extract_signature_function(
1063 video_id, player_url, s
1065 self._player_cache[player_id] = func
1066 func = self._player_cache[player_id]
1067 if self._downloader.params.get('youtube_print_sig_code
'):
1068 self._print_sig_code(func, s)
1070 except Exception as e:
1071 tb = traceback.format_exc()
1072 raise ExtractorError(
1073 'Signature extraction failed
: ' + tb, cause=e)
1075 def _get_subtitles(self, video_id, webpage):
1077 subs_doc = self._download_xml(
1078 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1079 video_id, note=False)
1080 except ExtractorError as err:
1081 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1085 for track in subs_doc.findall('track
'):
1086 lang = track.attrib['lang_code
']
1087 if lang in sub_lang_list:
1090 for ext in self._SUBTITLE_FORMATS:
1091 params = compat_urllib_parse_urlencode({
1095 'name
': track.attrib['name
'].encode('utf
-8'),
1097 sub_formats.append({
1098 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1101 sub_lang_list[lang] = sub_formats
1102 if not sub_lang_list:
1103 self._downloader.report_warning('video doesn
\'t have subtitles
')
1105 return sub_lang_list
1107 def _get_ytplayer_config(self, video_id, webpage):
1109 # User data may contain arbitrary character sequences that may affect
1110 # JSON extraction with regex, e.g. when '};' is contained the second
1111 # regex won't capture the whole JSON
. Yet working around by trying more
1112 # concrete regex first keeping in mind proper quoted string handling
1113 # to be implemented in future that will replace this workaround (see
1114 # https://github.com/rg3/youtube-dl/issues/7468,
1115 # https://github.com/rg3/youtube-dl/pull/7599)
1116 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1117 r
';ytplayer\.config\s*=\s*({.+?});',
1119 config
= self
._search
_regex
(
1120 patterns
, webpage
, 'ytplayer.config', default
=None)
1122 return self
._parse
_json
(
1123 uppercase_escape(config
), video_id
, fatal
=False)
1125 def _get_automatic_captions(self
, video_id
, webpage
):
1126 """We need the webpage for getting the captions url, pass it as an
1127 argument to speed up the process."""
1128 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1129 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1130 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1131 if not player_config
:
1132 self
._downloader
.report_warning(err_msg
)
1135 args
= player_config
['args']
1136 caption_url
= args
.get('ttsurl')
1138 timestamp
= args
['timestamp']
1139 # We get the available subtitles
1140 list_params
= compat_urllib_parse_urlencode({
1145 list_url
= caption_url
+ '&' + list_params
1146 caption_list
= self
._download
_xml
(list_url
, video_id
)
1147 original_lang_node
= caption_list
.find('track')
1148 if original_lang_node
is None:
1149 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1151 original_lang
= original_lang_node
.attrib
['lang_code']
1152 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1155 for lang_node
in caption_list
.findall('target'):
1156 sub_lang
= lang_node
.attrib
['lang_code']
1158 for ext
in self
._SUBTITLE
_FORMATS
:
1159 params
= compat_urllib_parse_urlencode({
1160 'lang': original_lang
,
1164 'kind': caption_kind
,
1166 sub_formats
.append({
1167 'url': caption_url
+ '&' + params
,
1170 sub_lang_list
[sub_lang
] = sub_formats
1171 return sub_lang_list
1173 # Some videos don't provide ttsurl but rather caption_tracks and
1174 # caption_translation_languages (e.g. 20LmZk1hakA)
1175 caption_tracks
= args
['caption_tracks']
1176 caption_translation_languages
= args
['caption_translation_languages']
1177 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1178 parsed_caption_url
= compat_urllib_parse_urlparse(caption_url
)
1179 caption_qs
= compat_parse_qs(parsed_caption_url
.query
)
1182 for lang
in caption_translation_languages
.split(','):
1183 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1184 sub_lang
= lang_qs
.get('lc', [None])[0]
1188 for ext
in self
._SUBTITLE
_FORMATS
:
1190 'tlang': [sub_lang
],
1193 sub_url
= compat_urlparse
.urlunparse(parsed_caption_url
._replace
(
1194 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1195 sub_formats
.append({
1199 sub_lang_list
[sub_lang
] = sub_formats
1200 return sub_lang_list
1201 # An extractor error can be raise by the download process if there are
1202 # no automatic captions but there are subtitles
1203 except (KeyError, ExtractorError
):
1204 self
._downloader
.report_warning(err_msg
)
1207 def _mark_watched(self
, video_id
, video_info
):
1208 playback_url
= video_info
.get('videostats_playback_base_url', [None])[0]
1209 if not playback_url
:
1211 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1212 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1214 # cpn generation algorithm is reverse engineered from base.js.
1215 # In fact it works even with dummy cpn.
1216 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1217 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1223 playback_url
= compat_urlparse
.urlunparse(
1224 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1226 self
._download
_webpage
(
1227 playback_url
, video_id
, 'Marking watched',
1228 'Unable to mark watched', fatal
=False)
1231 def extract_id(cls
, url
):
1232 mobj
= re
.match(cls
._VALID
_URL
, url
, re
.VERBOSE
)
1234 raise ExtractorError('Invalid URL: %s' % url
)
1235 video_id
= mobj
.group(2)
1238 def _extract_from_m3u8(self
, manifest_url
, video_id
):
1241 def _get_urls(_manifest
):
1242 lines
= _manifest
.split('\n')
1243 urls
= filter(lambda l
: l
and not l
.startswith('#'),
1246 manifest
= self
._download
_webpage
(manifest_url
, video_id
, 'Downloading formats manifest')
1247 formats_urls
= _get_urls(manifest
)
1248 for format_url
in formats_urls
:
1249 itag
= self
._search
_regex
(r
'itag/(\d+?)/', format_url
, 'itag')
1250 url_map
[itag
] = format_url
1253 def _extract_annotations(self
, video_id
):
1254 url
= 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1255 return self
._download
_webpage
(url
, video_id
, note
='Searching for annotations.', errnote
='Unable to download video annotations.')
1257 def _real_extract(self
, url
):
1258 url
, smuggled_data
= unsmuggle_url(url
, {})
1261 'http' if self
._downloader
.params
.get('prefer_insecure', False)
1266 parsed_url
= compat_urllib_parse_urlparse(url
)
1267 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
1268 query
= compat_parse_qs(component
)
1269 if start_time
is None and 't' in query
:
1270 start_time
= parse_duration(query
['t'][0])
1271 if start_time
is None and 'start' in query
:
1272 start_time
= parse_duration(query
['start'][0])
1273 if end_time
is None and 'end' in query
:
1274 end_time
= parse_duration(query
['end'][0])
1276 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1277 mobj
= re
.search(self
._NEXT
_URL
_RE
, url
)
1279 url
= proto
+ '://www.youtube.com/' + compat_urllib_parse_unquote(mobj
.group(1)).lstrip('/')
1280 video_id
= self
.extract_id(url
)
1283 url
= proto
+ '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1284 video_webpage
= self
._download
_webpage
(url
, video_id
)
1286 # Attempt to extract SWF player URL
1287 mobj
= re
.search(r
'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage
)
1288 if mobj
is not None:
1289 player_url
= re
.sub(r
'\\(.)', r
'\1', mobj
.group(1))
1295 def add_dash_mpd(video_info
):
1296 dash_mpd
= video_info
.get('dashmpd')
1297 if dash_mpd
and dash_mpd
[0] not in dash_mpds
:
1298 dash_mpds
.append(dash_mpd
[0])
1301 embed_webpage
= None
1303 if re
.search(r
'player-age-gate-content">', video_webpage
) is not None:
1305 # We simulate the access to the video from www.youtube.com/v/{video_id}
1306 # this can be viewed without login into Youtube
1307 url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1308 embed_webpage
= self
._download
_webpage
(url
, video_id
, 'Downloading embed webpage')
1309 data
= compat_urllib_parse_urlencode({
1310 'video_id': video_id
,
1311 'eurl': 'https://youtube.googleapis.com/v/' + video_id
,
1312 'sts': self
._search
_regex
(
1313 r
'"sts"\s*:\s*(\d+)', embed_webpage
, 'sts', default
=''),
1315 video_info_url
= proto
+ '://www.youtube.com/get_video_info?' + data
1316 video_info_webpage
= self
._download
_webpage
(
1317 video_info_url
, video_id
,
1318 note
='Refetching age-gated info webpage',
1319 errnote
='unable to download video info webpage')
1320 video_info
= compat_parse_qs(video_info_webpage
)
1321 add_dash_mpd(video_info
)
1325 # Try looking directly into the video webpage
1326 ytplayer_config
= self
._get
_ytplayer
_config
(video_id
, video_webpage
)
1328 args
= ytplayer_config
['args']
1329 if args
.get('url_encoded_fmt_stream_map'):
1330 # Convert to the same format returned by compat_parse_qs
1331 video_info
= dict((k
, [v
]) for k
, v
in args
.items())
1332 add_dash_mpd(video_info
)
1333 # Rental video is not rented but preview is available (e.g.
1334 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1335 # https://github.com/rg3/youtube-dl/issues/10532)
1336 if not video_info
and args
.get('ypc_vid'):
1337 return self
.url_result(
1338 args
['ypc_vid'], YoutubeIE
.ie_key(), video_id
=args
['ypc_vid'])
1339 if args
.get('livestream') == '1' or args
.get('live_playback') == 1:
1341 if not video_info
or self
._downloader
.params
.get('youtube_include_dash_manifest', True):
1342 # We also try looking in get_video_info since it may contain different dashmpd
1343 # URL that points to a DASH manifest with possibly different itag set (some itags
1344 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1345 # manifest pointed by get_video_info's dashmpd).
1346 # The general idea is to take a union of itags of both DASH manifests (for example
1347 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1348 self
.report_video_info_webpage_download(video_id
)
1349 for el_type
in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1351 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1352 % (proto
, video_id
, el_type
))
1353 video_info_webpage
= self
._download
_webpage
(
1355 video_id
, note
=False,
1356 errnote
='unable to download video info webpage')
1357 get_video_info
= compat_parse_qs(video_info_webpage
)
1358 if get_video_info
.get('use_cipher_signature') != ['True']:
1359 add_dash_mpd(get_video_info
)
1361 video_info
= get_video_info
1362 if 'token' in get_video_info
:
1363 # Different get_video_info requests may report different results, e.g.
1364 # some may report video unavailability, but some may serve it without
1365 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1366 # the original webpage as well as el=info and el=embedded get_video_info
1367 # requests report video unavailability due to geo restriction while
1368 # el=detailpage succeeds and returns valid data). This is probably
1369 # due to YouTube measures against IP ranges of hosting providers.
1370 # Working around by preferring the first succeeded video_info containing
1371 # the token if no such video_info yet was found.
1372 if 'token' not in video_info
:
1373 video_info
= get_video_info
1375 if 'token' not in video_info
:
1376 if 'reason' in video_info
:
1377 if 'The uploader has not made this video available in your country.' in video_info
['reason']:
1378 regions_allowed
= self
._html
_search
_meta
('regionsAllowed', video_webpage
, default
=None)
1380 raise ExtractorError('YouTube said: This video is available in %s only' % (
1381 ', '.join(map(ISO3166Utils
.short2full
, regions_allowed
.split(',')))),
1383 raise ExtractorError(
1384 'YouTube said: %s' % video_info
['reason'][0],
1385 expected
=True, video_id
=video_id
)
1387 raise ExtractorError(
1388 '"token" parameter not in video info for unknown reason',
1392 if 'title' in video_info
:
1393 video_title
= video_info
['title'][0]
1395 self
._downloader
.report_warning('Unable to extract video title')
1399 video_description
= get_element_by_id("eow-description", video_webpage
)
1400 if video_description
:
1401 video_description
= re
.sub(r
'''(?x)
1403 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1404 (?:title|href)="([^"]+)"\s+
1405 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1409 ''', r
'\1', video_description
)
1410 video_description
= clean_html(video_description
)
1412 fd_mobj
= re
.search(r
'<meta name="description" content="([^"]+)"', video_webpage
)
1414 video_description
= unescapeHTML(fd_mobj
.group(1))
1416 video_description
= ''
1418 if 'multifeed_metadata_list' in video_info
and not smuggled_data
.get('force_singlefeed', False):
1419 if not self
._downloader
.params
.get('noplaylist'):
1422 multifeed_metadata_list
= video_info
['multifeed_metadata_list'][0]
1423 for feed
in multifeed_metadata_list
.split(','):
1424 # Unquote should take place before split on comma (,) since textual
1425 # fields may contain comma as well (see
1426 # https://github.com/rg3/youtube-dl/issues/8536)
1427 feed_data
= compat_parse_qs(compat_urllib_parse_unquote_plus(feed
))
1429 '_type': 'url_transparent',
1430 'ie_key': 'Youtube',
1432 '%s://www.youtube.com/watch?v=%s' % (proto
, feed_data
['id'][0]),
1433 {'force_singlefeed': True}),
1434 'title': '%s (%s)' % (video_title
, feed_data
['title'][0]),
1436 feed_ids
.append(feed_data
['id'][0])
1438 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1439 % (', '.join(feed_ids
), video_id
))
1440 return self
.playlist_result(entries
, video_id
, video_title
, video_description
)
1441 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
1443 if 'view_count' in video_info
:
1444 view_count
= int(video_info
['view_count'][0])
1448 # Check for "rental" videos
1449 if 'ypc_video_rental_bar_text' in video_info
and 'author' not in video_info
:
1450 raise ExtractorError('"rental" videos not supported')
1452 # Start extracting information
1453 self
.report_information_extraction(video_id
)
1456 if 'author' not in video_info
:
1457 raise ExtractorError('Unable to extract uploader name')
1458 video_uploader
= compat_urllib_parse_unquote_plus(video_info
['author'][0])
1461 video_uploader_id
= None
1462 video_uploader_url
= None
1464 r
'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1466 if mobj
is not None:
1467 video_uploader_id
= mobj
.group('uploader_id')
1468 video_uploader_url
= mobj
.group('uploader_url')
1470 self
._downloader
.report_warning('unable to extract uploader nickname')
1473 # We try first to get a high quality image:
1474 m_thumb
= re
.search(r
'<span itemprop="thumbnail".*?href="(.*?)">',
1475 video_webpage
, re
.DOTALL
)
1476 if m_thumb
is not None:
1477 video_thumbnail
= m_thumb
.group(1)
1478 elif 'thumbnail_url' not in video_info
:
1479 self
._downloader
.report_warning('unable to extract video thumbnail')
1480 video_thumbnail
= None
1481 else: # don't panic if we can't find it
1482 video_thumbnail
= compat_urllib_parse_unquote_plus(video_info
['thumbnail_url'][0])
1485 upload_date
= self
._html
_search
_meta
(
1486 'datePublished', video_webpage
, 'upload date', default
=None)
1488 upload_date
= self
._search
_regex
(
1489 [r
'(?s)id="eow-date.*?>(.*?)</span>',
1490 r
'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1491 video_webpage
, 'upload date', default
=None)
1493 upload_date
= ' '.join(re
.sub(r
'[/,-]', r
' ', mobj
.group(1)).split())
1494 upload_date
= unified_strdate(upload_date
)
1496 video_license
= self
._html
_search
_regex
(
1497 r
'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1498 video_webpage
, 'license', default
=None)
1500 m_music
= re
.search(
1501 r
'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1504 video_alt_title
= remove_quotes(unescapeHTML(m_music
.group('title')))
1505 video_creator
= clean_html(m_music
.group('creator'))
1507 video_alt_title
= video_creator
= None
1509 m_episode
= re
.search(
1510 r
'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*ā¢\s*E(?P<episode>\d+)</span>',
1513 series
= m_episode
.group('series')
1514 season_number
= int(m_episode
.group('season'))
1515 episode_number
= int(m_episode
.group('episode'))
1517 series
= season_number
= episode_number
= None
1519 m_cat_container
= self
._search
_regex
(
1520 r
'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1521 video_webpage
, 'categories', default
=None)
1523 category
= self
._html
_search
_regex
(
1524 r
'(?s)<a[^<]+>(.*?)</a>', m_cat_container
, 'category',
1526 video_categories
= None if category
is None else [category
]
1528 video_categories
= None
1531 unescapeHTML(m
.group('content'))
1532 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), video_webpage
)]
1534 def _extract_count(count_name
):
1535 return str_to_int(self
._search
_regex
(
1536 r
'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1537 % re
.escape(count_name
),
1538 video_webpage
, count_name
, default
=None))
1540 like_count
= _extract_count('like')
1541 dislike_count
= _extract_count('dislike')
1544 video_subtitles
= self
.extract_subtitles(video_id
, video_webpage
)
1545 automatic_captions
= self
.extract_automatic_captions(video_id
, video_webpage
)
1547 video_duration
= try_get(
1548 video_info
, lambda x
: int_or_none(x
['length_seconds'][0]))
1549 if not video_duration
:
1550 video_duration
= parse_duration(self
._html
_search
_meta
(
1551 'duration', video_webpage
, 'video duration'))
1554 video_annotations
= None
1555 if self
._downloader
.params
.get('writeannotations', False):
1556 video_annotations
= self
._extract
_annotations
(video_id
)
1558 def _map_to_format_list(urlmap
):
1560 for itag
, video_real_url
in urlmap
.items():
1563 'url': video_real_url
,
1564 'player_url': player_url
,
1566 if itag
in self
._formats
:
1567 dct
.update(self
._formats
[itag
])
1571 if 'conn' in video_info
and video_info
['conn'][0].startswith('rtmp'):
1572 self
.report_rtmp_download()
1574 'format_id': '_rtmp',
1576 'url': video_info
['conn'][0],
1577 'player_url': player_url
,
1579 elif len(video_info
.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info
.get('adaptive_fmts', [''])[0]) >= 1:
1580 encoded_url_map
= video_info
.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info
.get('adaptive_fmts', [''])[0]
1581 if 'rtmpe%3Dyes' in encoded_url_map
:
1582 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected
=True)
1584 fmt_list
= video_info
.get('fmt_list', [''])[0]
1586 for fmt
in fmt_list
.split(','):
1587 spec
= fmt
.split('/')
1589 width_height
= spec
[1].split('x')
1590 if len(width_height
) == 2:
1591 formats_spec
[spec
[0]] = {
1592 'resolution': spec
[1],
1593 'width': int_or_none(width_height
[0]),
1594 'height': int_or_none(width_height
[1]),
1597 for url_data_str
in encoded_url_map
.split(','):
1598 url_data
= compat_parse_qs(url_data_str
)
1599 if 'itag' not in url_data
or 'url' not in url_data
:
1601 format_id
= url_data
['itag'][0]
1602 url
= url_data
['url'][0]
1604 if 'sig' in url_data
:
1605 url
+= '&signature=' + url_data
['sig'][0]
1606 elif 's' in url_data
:
1607 encrypted_sig
= url_data
['s'][0]
1608 ASSETS_RE
= r
'"assets":.+?"js":\s*("[^"]+")'
1610 jsplayer_url_json
= self
._search
_regex
(
1612 embed_webpage
if age_gate
else video_webpage
,
1613 'JS player URL (1)', default
=None)
1614 if not jsplayer_url_json
and not age_gate
:
1615 # We need the embed website after all
1616 if embed_webpage
is None:
1617 embed_url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1618 embed_webpage
= self
._download
_webpage
(
1619 embed_url
, video_id
, 'Downloading embed webpage')
1620 jsplayer_url_json
= self
._search
_regex
(
1621 ASSETS_RE
, embed_webpage
, 'JS player URL')
1623 player_url
= json
.loads(jsplayer_url_json
)
1624 if player_url
is None:
1625 player_url_json
= self
._search
_regex
(
1626 r
'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1627 video_webpage
, 'age gate player URL')
1628 player_url
= json
.loads(player_url_json
)
1630 if self
._downloader
.params
.get('verbose'):
1631 if player_url
is None:
1632 player_version
= 'unknown'
1633 player_desc
= 'unknown'
1635 if player_url
.endswith('swf'):
1636 player_version
= self
._search
_regex
(
1637 r
'-(.+?)(?:/watch_as3)?\.swf$', player_url
,
1638 'flash player', fatal
=False)
1639 player_desc
= 'flash player %s' % player_version
1641 player_version
= self
._search
_regex
(
1642 [r
'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r
'(?:www|player)-([^/]+)/base\.js'],
1644 'html5 player', fatal
=False)
1645 player_desc
= 'html5 player %s' % player_version
1647 parts_sizes
= self
._signature
_cache
_id
(encrypted_sig
)
1648 self
.to_screen('{%s} signature length %s, %s' %
1649 (format_id
, parts_sizes
, player_desc
))
1651 signature
= self
._decrypt
_signature
(
1652 encrypted_sig
, video_id
, player_url
, age_gate
)
1653 url
+= '&signature=' + signature
1654 if 'ratebypass' not in url
:
1655 url
+= '&ratebypass=yes'
1658 'format_id': format_id
,
1660 'player_url': player_url
,
1662 if format_id
in self
._formats
:
1663 dct
.update(self
._formats
[format_id
])
1664 if format_id
in formats_spec
:
1665 dct
.update(formats_spec
[format_id
])
1667 # Some itags are not included in DASH manifest thus corresponding formats will
1668 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1669 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1670 mobj
= re
.search(r
'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data
.get('size', [''])[0])
1671 width
, height
= (int(mobj
.group('width')), int(mobj
.group('height'))) if mobj
else (None, None)
1674 'filesize': int_or_none(url_data
.get('clen', [None])[0]),
1675 'tbr': float_or_none(url_data
.get('bitrate', [None])[0], 1000),
1678 'fps': int_or_none(url_data
.get('fps', [None])[0]),
1679 'format_note': url_data
.get('quality_label', [None])[0] or url_data
.get('quality', [None])[0],
1681 for key
, value
in more_fields
.items():
1684 type_
= url_data
.get('type', [None])[0]
1686 type_split
= type_
.split(';')
1687 kind_ext
= type_split
[0].split('/')
1688 if len(kind_ext
) == 2:
1690 dct
['ext'] = mimetype2ext(type_split
[0])
1691 if kind
in ('audio', 'video'):
1693 for mobj
in re
.finditer(
1694 r
'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
1695 if mobj.group('key
') == 'codecs
':
1696 codecs = mobj.group('val
')
1699 codecs = codecs.split(',')
1700 if len(codecs) == 2:
1701 acodec, vcodec = codecs[1], codecs[0]
1703 acodec, vcodec = (codecs[0], 'none
') if kind == 'audio
' else ('none
', codecs[0])
1709 elif video_info.get('hlsvp
'):
1710 manifest_url = video_info['hlsvp
'][0]
1711 url_map = self._extract_from_m3u8(manifest_url, video_id)
1712 formats = _map_to_format_list(url_map)
1713 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1714 for a_format in formats:
1715 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
1717 unavailable_message = self._html_search_regex(
1718 r'(?s
)<h1
[^
>]+id="unavailable-message"[^
>]*>(.+?
)</h1
>',
1719 video_webpage, 'unavailable message
', default=None)
1720 if unavailable_message:
1721 raise ExtractorError(unavailable_message, expected=True)
1722 raise ExtractorError('no conn
, hlsvp
or url_encoded_fmt_stream_map information found
in video info
')
1724 # Look for the DASH manifest
1725 if self._downloader.params.get('youtube_include_dash_manifest
', True):
1726 dash_mpd_fatal = True
1727 for mpd_url in dash_mpds:
1730 def decrypt_sig(mobj):
1732 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1733 return '/signature
/%s' % dec_s
1735 mpd_url = re.sub(r'/s
/([a
-fA
-F0
-9\
.]+)', decrypt_sig, mpd_url)
1737 for df in self._extract_mpd_formats(
1738 mpd_url, video_id, fatal=dash_mpd_fatal,
1739 formats_dict=self._formats):
1740 # Do not overwrite DASH format found in some previous DASH manifest
1741 if df['format_id
'] not in dash_formats:
1742 dash_formats[df['format_id
']] = df
1743 # Additional DASH manifests may end up in HTTP Error 403 therefore
1744 # allow them to fail without bug report message if we already have
1745 # some DASH manifest succeeded. This is temporary workaround to reduce
1746 # burst of bug reports until we figure out the reason and whether it
1747 # can be fixed at all.
1748 dash_mpd_fatal = False
1749 except (ExtractorError, KeyError) as e:
1750 self.report_warning(
1751 'Skipping DASH manifest
: %r' % e, video_id)
1753 # Remove the formats we found through non-DASH, they
1754 # contain less info and it can be wrong, because we use
1755 # fixed values (for example the resolution). See
1756 # https://github.com/rg3/youtube-dl/issues/5774 for an
1758 formats = [f for f in formats if f['format_id
'] not in dash_formats.keys()]
1759 formats.extend(dash_formats.values())
1761 # Check for malformed aspect ratio
1762 stretched_m = re.search(
1763 r'<meta\s
+property="og:video:tag".*?content
="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1766 w = float(stretched_m.group('w
'))
1767 h = float(stretched_m.group('h
'))
1768 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1769 # We will only process correct ratios.
1773 if f.get('vcodec
') != 'none
':
1774 f['stretched_ratio
'] = ratio
1776 self._sort_formats(formats)
1778 self.mark_watched(video_id, video_info)
1782 'uploader
': video_uploader,
1783 'uploader_id
': video_uploader_id,
1784 'uploader_url
': video_uploader_url,
1785 'upload_date
': upload_date,
1786 'license
': video_license,
1787 'creator
': video_creator,
1788 'title
': video_title,
1789 'alt_title
': video_alt_title,
1790 'thumbnail
': video_thumbnail,
1791 'description
': video_description,
1792 'categories
': video_categories,
1794 'subtitles
': video_subtitles,
1795 'automatic_captions
': automatic_captions,
1796 'duration
': video_duration,
1797 'age_limit
': 18 if age_gate else 0,
1798 'annotations
': video_annotations,
1799 'webpage_url
': proto + '://www
.youtube
.com
/watch?v
=%s' % video_id,
1800 'view_count
': view_count,
1801 'like_count
': like_count,
1802 'dislike_count
': dislike_count,
1803 'average_rating
': float_or_none(video_info.get('avg_rating
', [None])[0]),
1806 'start_time
': start_time,
1807 'end_time
': end_time,
1809 'season_number
': season_number,
1810 'episode_number
': episode_number,
1814 class YoutubeSharedVideoIE(InfoExtractor):
1815 _VALID_URL = r'(?
:https?
:)?
//(?
:www\
.)?youtube\
.com
/shared
\?.*\bci
=(?P
<id>[0-9A
-Za
-z_
-]{11}
)'
1816 IE_NAME = 'youtube
:shared
'
1819 'url
': 'https
://www
.youtube
.com
/shared?ci
=1nEzmT
-M4fU
',
1821 'id': 'uPDB5I9wfp8
',
1823 'title
': 'Pocoyo
: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧ
as - PARTE
3',
1824 'description
': 'md5
:d9e4d9346a2dfff4c7dc4c8cec0f546d
',
1825 'upload_date
': '20160219',
1826 'uploader
': 'Pocoyo
- PortuguĆŖ
s (BR
)',
1827 'uploader_id
': 'PocoyoBrazil
',
1829 'add_ie
': ['Youtube
'],
1831 # There are already too many Youtube downloads
1832 'skip_download
': True,
1836 def _real_extract(self, url):
1837 video_id = self._match_id(url)
1839 webpage = self._download_webpage(url, video_id)
1841 real_video_id = self._html_search_meta(
1842 'videoId
', webpage, 'YouTube video
id', fatal=True)
1844 return self.url_result(real_video_id, YoutubeIE.ie_key())
1847 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1848 IE_DESC = 'YouTube
.com playlists
'
1849 _VALID_URL = r"""(?x)(?:
1855 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1856 \? (?:.*?[&;])*? (?:p|a|list)=
1859 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1862 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
1863 # Top tracks, they can also include dots
1868 ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
1870 _TEMPLATE_URL = 'https
://www
.youtube
.com
/playlist?
list=%s&disable_polymer
=true
'
1871 _VIDEO_RE = r'href
="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index
=(?P
<index
>\d
+)(?
:[^
>]+>(?P
<title
>[^
<]+))?
'
1872 IE_NAME = 'youtube
:playlist
'
1874 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1876 'title
': 'ytdl test PL
',
1877 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1879 'playlist_count
': 3,
1881 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1883 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1884 'title
': 'YDL_Empty_List
',
1886 'playlist_count
': 0,
1887 'skip
': 'This playlist
is private
',
1889 'note
': 'Playlist
with deleted
videos (#651). As a bonus, the video #51 is also twice in this list.',
1890 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1892 'title': '29C3: Not my department',
1893 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1895 'playlist_count': 95,
1897 'note': 'issue #673',
1898 'url': 'PLBB231211A4F62143',
1900 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1901 'id': 'PLBB231211A4F62143',
1903 'playlist_mincount': 26,
1905 'note': 'Large playlist',
1906 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1908 'title': 'Uploads from Cauchemar',
1909 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1911 'playlist_mincount': 799,
1913 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1915 'title': 'YDL_safe_search',
1916 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1918 'playlist_count': 2,
1919 'skip': 'This playlist is private',
1922 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1923 'playlist_count': 4,
1926 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1929 'note': 'Embedded SWF player',
1930 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1931 'playlist_count': 4,
1934 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1937 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1938 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1940 'title': 'Uploads from Interstellar Movie',
1941 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1943 'playlist_mincount': 21,
1945 # Playlist URL that does not actually serve a playlist
1946 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1948 'id': 'FqZTN594JQw',
1950 'title': "Smiley's People 01 detective, Adventure Series, Action",
1951 'uploader': 'STREEM',
1952 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1953 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1954 'upload_date': '20150526',
1955 'license': 'Standard YouTube License',
1956 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1957 'categories': ['People & Blogs'],
1960 'dislike_count': int,
1963 'skip_download': True,
1965 'add_ie': [YoutubeIE
.ie_key()],
1967 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1969 'id': 'yeWKywCrFtk',
1971 'title': 'Small Scale Baler and Braiding Rugs',
1972 'uploader': 'Backus-Page House Museum',
1973 'uploader_id': 'backuspagemuseum',
1974 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1975 'upload_date': '20161008',
1976 'license': 'Standard YouTube License',
1977 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1978 'categories': ['Nonprofits & Activism'],
1981 'dislike_count': int,
1985 'skip_download': True,
1988 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1989 'only_matching': True,
1991 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
1992 'only_matching': True,
1995 def _real_initialize(self
):
1998 def _extract_mix(self
, playlist_id
):
1999 # The mixes are generated from a single video
2000 # the id of the playlist is just 'RD' + video_id
2002 last_id
= playlist_id
[-11:]
2003 for n
in itertools
.count(1):
2004 url
= 'https://youtube.com/watch?v=%s&list=%s' % (last_id
, playlist_id
)
2005 webpage
= self
._download
_webpage
(
2006 url
, playlist_id
, 'Downloading page {0} of Youtube mix'.format(n
))
2007 new_ids
= orderedSet(re
.findall(
2008 r
'''(?xs)data-video-username=".*?".*?
2009 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re
.escape(playlist_id
),
2011 # Fetch new pages until all the videos are repeated, it seems that
2012 # there are always 51 unique videos.
2013 new_ids
= [_id
for _id
in new_ids
if _id
not in ids
]
2019 url_results
= self
._ids
_to
_results
(ids
)
2021 search_title
= lambda class_name
: get_element_by_attribute('class', class_name
, webpage
)
2023 search_title('playlist-title') or
2024 search_title('title long-title') or
2025 search_title('title'))
2026 title
= clean_html(title_span
)
2028 return self
.playlist_result(url_results
, playlist_id
, title
)
2030 def _extract_playlist(self
, playlist_id
):
2031 url
= self
._TEMPLATE
_URL
% playlist_id
2032 page
= self
._download
_webpage
(url
, playlist_id
)
2034 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2035 for match
in re
.findall(r
'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page
):
2036 match
= match
.strip()
2037 # Check if the playlist exists or is private
2038 mobj
= re
.match(r
'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match
)
2040 reason
= mobj
.group('reason')
2041 message
= 'This playlist %s' % reason
2042 if 'private' in reason
:
2043 message
+= ', use --username or --netrc to access it'
2045 raise ExtractorError(message
, expected
=True)
2046 elif re
.match(r
'[^<]*Invalid parameters[^<]*', match
):
2047 raise ExtractorError(
2048 'Invalid parameters. Maybe URL is incorrect.',
2050 elif re
.match(r
'[^<]*Choose your language[^<]*', match
):
2053 self
.report_warning('Youtube gives an alert message: ' + match
)
2055 playlist_title
= self
._html
_search
_regex
(
2056 r
'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2057 page
, 'title', default
=None)
2061 if not playlist_title
:
2063 # Some playlist URLs don't actually serve a playlist (e.g.
2064 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2065 next(self
._entries
(page
, playlist_id
))
2066 except StopIteration:
2069 return has_videos
, self
.playlist_result(
2070 self
._entries
(page
, playlist_id
), playlist_id
, playlist_title
)
2072 def _check_download_just_video(self
, url
, playlist_id
):
2073 # Check if it's a video-specific URL
2074 query_dict
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
2075 video_id
= query_dict
.get('v', [None])[0] or self
._search
_regex
(
2076 r
'(?:^|//)youtu\.be/([0-9A-Za-z_-]{11})', url
,
2077 'video id', default
=None)
2079 if self
._downloader
.params
.get('noplaylist'):
2080 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
2081 return video_id
, self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2083 self
.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id
, video_id
))
2084 return video_id
, None
2087 def _real_extract(self
, url
):
2088 # Extract playlist id
2089 mobj
= re
.match(self
._VALID
_URL
, url
)
2091 raise ExtractorError('Invalid URL: %s' % url
)
2092 playlist_id
= mobj
.group(1) or mobj
.group(2)
2094 video_id
, video
= self
._check
_download
_just
_video
(url
, playlist_id
)
2098 if playlist_id
.startswith(('RD', 'UL', 'PU')):
2099 # Mixes require a custom extraction process
2100 return self
._extract
_mix
(playlist_id
)
2102 has_videos
, playlist
= self
._extract
_playlist
(playlist_id
)
2103 if has_videos
or not video_id
:
2106 # Some playlist URLs don't actually serve a playlist (see
2107 # https://github.com/rg3/youtube-dl/issues/10537).
2108 # Fallback to plain video extraction if there is a video id
2109 # along with playlist id.
2110 return self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2113 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor
):
2114 IE_DESC
= 'YouTube.com channels'
2115 _VALID_URL
= r
'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2116 _TEMPLATE_URL
= 'https://www.youtube.com/channel/%s/videos'
2117 _VIDEO_RE
= r
'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2118 IE_NAME
= 'youtube:channel'
2120 'note': 'paginated channel',
2121 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2122 'playlist_mincount': 91,
2124 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2125 'title': 'Uploads from lex will',
2128 'note': 'Age restricted channel',
2129 # from https://www.youtube.com/user/DeusExOfficial
2130 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2131 'playlist_mincount': 64,
2133 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2134 'title': 'Uploads from Deus Ex',
2139 def suitable(cls
, url
):
2140 return (False if YoutubePlaylistsIE
.suitable(url
) or YoutubeLiveIE
.suitable(url
)
2141 else super(YoutubeChannelIE
, cls
).suitable(url
))
2143 def _build_template_url(self
, url
, channel_id
):
2144 return self
._TEMPLATE
_URL
% channel_id
2146 def _real_extract(self
, url
):
2147 channel_id
= self
._match
_id
(url
)
2149 url
= self
._build
_template
_url
(url
, channel_id
)
2151 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2152 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2153 # otherwise fallback on channel by page extraction
2154 channel_page
= self
._download
_webpage
(
2155 url
+ '?view=57', channel_id
,
2156 'Downloading channel page', fatal
=False)
2157 if channel_page
is False:
2158 channel_playlist_id
= False
2160 channel_playlist_id
= self
._html
_search
_meta
(
2161 'channelId', channel_page
, 'channel id', default
=None)
2162 if not channel_playlist_id
:
2163 channel_url
= self
._html
_search
_meta
(
2164 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2165 channel_page
, 'channel url', default
=None)
2167 channel_playlist_id
= self
._search
_regex
(
2168 r
'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2169 channel_url
, 'channel id', default
=None)
2170 if channel_playlist_id
and channel_playlist_id
.startswith('UC'):
2171 playlist_id
= 'UU' + channel_playlist_id
[2:]
2172 return self
.url_result(
2173 compat_urlparse
.urljoin(url
, '/playlist?list=%s' % playlist_id
), 'YoutubePlaylist')
2175 channel_page
= self
._download
_webpage
(url
, channel_id
, 'Downloading page #1')
2176 autogenerated
= re
.search(r
'''(?x)
2178 channel-header-autogenerated-label|
2179 yt-channel-title-autogenerated
2180 )[^"]*"''', channel_page
) is not None
2183 # The videos are contained in a single page
2184 # the ajax pages can't be used, they are empty
2187 video_id
, 'Youtube', video_id
=video_id
,
2188 video_title
=video_title
)
2189 for video_id
, video_title
in self
.extract_videos_from_page(channel_page
)]
2190 return self
.playlist_result(entries
, channel_id
)
2193 next(self
._entries
(channel_page
, channel_id
))
2194 except StopIteration:
2195 alert_message
= self
._html
_search
_regex
(
2196 r
'(?s)<div[^>]+class=(["\']).*?
\byt
-alert
-message
\b.*?\
1[^
>]*>(?P
<alert
>[^
<]+)</div
>',
2197 channel_page, 'alert
', default=None, group='alert
')
2199 raise ExtractorError('Youtube said
: %s' % alert_message, expected=True)
2201 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2204 class YoutubeUserIE(YoutubeChannelIE):
2205 IE_DESC = 'YouTube
.com user
videos (URL
or "ytuser" keyword
)'
2206 _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_-]+)'
2207 _TEMPLATE_URL = 'https
://www
.youtube
.com
/%s/%s/videos
'
2208 IE_NAME = 'youtube
:user
'
2211 'url
': 'https
://www
.youtube
.com
/user
/TheLinuxFoundation
',
2212 'playlist_mincount
': 320,
2214 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ
',
2215 'title
': 'Uploads
from The Linux Foundation
',
2218 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2219 # but not https://www.youtube.com/user/12minuteathlete/videos
2220 'url
': 'https
://www
.youtube
.com
/c
/12minuteathlete
/videos
',
2221 'playlist_mincount
': 249,
2223 'id': 'UUVjM
-zV6_opMDx7WYxnjZiQ
',
2224 'title
': 'Uploads
from 12 Minute Athlete
',
2227 'url
': 'ytuser
:phihag
',
2228 'only_matching
': True,
2230 'url
': 'https
://www
.youtube
.com
/c
/gametrailers
',
2231 'only_matching
': True,
2233 'url
': 'https
://www
.youtube
.com
/gametrailers
',
2234 'only_matching
': True,
2236 # This channel is not available.
2237 'url
': 'https
://www
.youtube
.com
/user
/kananishinoSMEJ
/videos
',
2238 'only_matching
': True,
2242 def suitable(cls, url):
2243 # Don't
return True if the url can be extracted
with other youtube
2244 # extractor, the regex would is too permissive and it would match.
2245 other_yt_ies
= iter(klass
for (name
, klass
) in globals().items() if name
.startswith('Youtube') and name
.endswith('IE') and klass
is not cls
)
2246 if any(ie
.suitable(url
) for ie
in other_yt_ies
):
2249 return super(YoutubeUserIE
, cls
).suitable(url
)
2251 def _build_template_url(self
, url
, channel_id
):
2252 mobj
= re
.match(self
._VALID
_URL
, url
)
2253 return self
._TEMPLATE
_URL
% (mobj
.group('user') or 'user', mobj
.group('id'))
2256 class YoutubeLiveIE(YoutubeBaseInfoExtractor
):
2257 IE_DESC
= 'YouTube.com live streams'
2258 _VALID_URL
= r
'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2259 IE_NAME
= 'youtube:live'
2262 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2264 'id': 'a48o2S1cPoo',
2266 'title': 'The Young Turks - Live Main Show',
2267 'uploader': 'The Young Turks',
2268 'uploader_id': 'TheYoungTurks',
2269 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2270 'upload_date': '20150715',
2271 'license': 'Standard YouTube License',
2272 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2273 'categories': ['News & Politics'],
2274 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2276 'dislike_count': int,
2279 'skip_download': True,
2282 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2283 'only_matching': True,
2285 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2286 'only_matching': True,
2288 'url': 'https://www.youtube.com/TheYoungTurks/live',
2289 'only_matching': True,
2292 def _real_extract(self
, url
):
2293 mobj
= re
.match(self
._VALID
_URL
, url
)
2294 channel_id
= mobj
.group('id')
2295 base_url
= mobj
.group('base_url')
2296 webpage
= self
._download
_webpage
(url
, channel_id
, fatal
=False)
2298 page_type
= self
._og
_search
_property
(
2299 'type', webpage
, 'page type', default
=None)
2300 video_id
= self
._html
_search
_meta
(
2301 'videoId', webpage
, 'video id', default
=None)
2302 if page_type
== 'video' and video_id
and re
.match(r
'^[0-9A-Za-z_-]{11}$', video_id
):
2303 return self
.url_result(video_id
, YoutubeIE
.ie_key())
2304 return self
.url_result(base_url
)
2307 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor
):
2308 IE_DESC
= 'YouTube.com user/channel playlists'
2309 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2310 IE_NAME
= 'youtube:playlists'
2313 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2314 'playlist_mincount': 4,
2316 'id': 'ThirstForScience',
2317 'title': 'Thirst for Science',
2320 # with "Load more" button
2321 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2322 'playlist_mincount': 70,
2325 'title': 'ŠŠ³Š¾ŃŃ ŠŠ»ŠµŠ¹Š½ŠµŃ',
2328 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2329 'playlist_mincount': 17,
2331 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2332 'title': 'Chem Player',
2337 class YoutubeSearchIE(SearchInfoExtractor
, YoutubePlaylistIE
):
2338 IE_DESC
= 'YouTube.com searches'
2339 # there doesn't appear to be a real limit, for example if you search for
2340 # 'python' you get more than 8.000.000 results
2341 _MAX_RESULTS
= float('inf')
2342 IE_NAME
= 'youtube:search'
2343 _SEARCH_KEY
= 'ytsearch'
2344 _EXTRA_QUERY_ARGS
= {}
2347 def _get_n_results(self
, query
, n
):
2348 """Get a specified number of results for a query"""
2354 'search_query': query
.encode('utf-8'),
2356 url_query
.update(self
._EXTRA
_QUERY
_ARGS
)
2357 result_url
= 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query
)
2359 for pagenum
in itertools
.count(1):
2360 data
= self
._download
_json
(
2361 result_url
, video_id
='query "%s"' % query
,
2362 note
='Downloading page %s' % pagenum
,
2363 errnote
='Unable to download API page',
2364 query
={'spf': 'navigate'})
2365 html_content
= data
[1]['body']['content']
2367 if 'class="search-message' in html_content
:
2368 raise ExtractorError(
2369 '[youtube] No video results', expected
=True)
2371 new_videos
= self
._ids
_to
_results
(orderedSet(re
.findall(
2372 r
'href="/watch\?v=(.{11})', html_content
)))
2373 videos
+= new_videos
2374 if not new_videos
or len(videos
) > limit
:
2376 next_link
= self
._html
_search
_regex
(
2377 r
'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2378 html_content
, 'next link', default
=None)
2379 if next_link
is None:
2381 result_url
= compat_urlparse
.urljoin('https://www.youtube.com/', next_link
)
2385 return self
.playlist_result(videos
, query
)
2388 class YoutubeSearchDateIE(YoutubeSearchIE
):
2389 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
2390 _SEARCH_KEY
= 'ytsearchdate'
2391 IE_DESC
= 'YouTube.com searches, newest videos first'
2392 _EXTRA_QUERY_ARGS
= {'search_sort': 'video_date_uploaded'}
2395 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor
):
2396 IE_DESC
= 'YouTube.com search URLs'
2397 IE_NAME
= 'youtube:search_url'
2398 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2399 _VIDEO_RE
= r
'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2401 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2402 'playlist_mincount': 5,
2404 'title': 'youtube-dl test video',
2407 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2408 'only_matching': True,
2411 def _real_extract(self
, url
):
2412 mobj
= re
.match(self
._VALID
_URL
, url
)
2413 query
= compat_urllib_parse_unquote_plus(mobj
.group('query'))
2414 webpage
= self
._download
_webpage
(url
, query
)
2415 return self
.playlist_result(self
._process
_page
(webpage
), playlist_title
=query
)
2418 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor
):
2419 IE_DESC
= 'YouTube.com (multi-season) shows'
2420 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2421 IE_NAME
= 'youtube:show'
2423 'url': 'https://www.youtube.com/show/airdisasters',
2424 'playlist_mincount': 5,
2426 'id': 'airdisasters',
2427 'title': 'Air Disasters',
2431 def _real_extract(self
, url
):
2432 playlist_id
= self
._match
_id
(url
)
2433 return super(YoutubeShowIE
, self
)._real
_extract
(
2434 'https://www.youtube.com/show/%s/playlists' % playlist_id
)
2437 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor
):
2439 Base class for feed extractors
2440 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2442 _LOGIN_REQUIRED
= True
2446 return 'youtube:%s' % self
._FEED
_NAME
2448 def _real_initialize(self
):
2451 def _real_extract(self
, url
):
2452 page
= self
._download
_webpage
(
2453 'https://www.youtube.com/feed/%s' % self
._FEED
_NAME
, self
._PLAYLIST
_TITLE
)
2455 # The extraction process is the same as for playlists, but the regex
2456 # for the video ids doesn't contain an index
2458 more_widget_html
= content_html
= page
2459 for page_num
in itertools
.count(1):
2460 matches
= re
.findall(r
'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html
)
2462 # 'recommended' feed has infinite 'load more' and each new portion spins
2463 # the same videos in (sometimes) slightly different order, so we'll check
2464 # for unicity and break when portion has no new videos
2465 new_ids
= filter(lambda video_id
: video_id
not in ids
, orderedSet(matches
))
2471 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
2475 more
= self
._download
_json
(
2476 'https://youtube.com/%s' % mobj
.group('more'), self
._PLAYLIST
_TITLE
,
2477 'Downloading page #%s' % page_num
,
2478 transform_source
=uppercase_escape
)
2479 content_html
= more
['content_html']
2480 more_widget_html
= more
['load_more_widget_html']
2482 return self
.playlist_result(
2483 self
._ids
_to
_results
(ids
), playlist_title
=self
._PLAYLIST
_TITLE
)
2486 class YoutubeWatchLaterIE(YoutubePlaylistIE
):
2487 IE_NAME
= 'youtube:watchlater'
2488 IE_DESC
= 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2489 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2492 'url': 'https://www.youtube.com/playlist?list=WL',
2493 'only_matching': True,
2495 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2496 'only_matching': True,
2499 def _real_extract(self
, url
):
2500 _
, video
= self
._check
_download
_just
_video
(url
, 'WL')
2503 _
, playlist
= self
._extract
_playlist
('WL')
2507 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
2508 IE_NAME
= 'youtube:favorites'
2509 IE_DESC
= 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2510 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2511 _LOGIN_REQUIRED
= True
2513 def _real_extract(self
, url
):
2514 webpage
= self
._download
_webpage
('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2515 playlist_id
= self
._search
_regex
(r
'list=(.+?)["&]', webpage
, 'favourites playlist id')
2516 return self
.url_result(playlist_id
, 'YoutubePlaylist')
2519 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
2520 IE_DESC
= 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2521 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2522 _FEED_NAME
= 'recommended'
2523 _PLAYLIST_TITLE
= 'Youtube Recommended videos'
2526 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
2527 IE_DESC
= 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2528 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2529 _FEED_NAME
= 'subscriptions'
2530 _PLAYLIST_TITLE
= 'Youtube Subscriptions'
2533 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
2534 IE_DESC
= 'Youtube watch history, ":ythistory" for short (requires authentication)'
2535 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2536 _FEED_NAME
= 'history'
2537 _PLAYLIST_TITLE
= 'Youtube History'
2540 class YoutubeTruncatedURLIE(InfoExtractor
):
2541 IE_NAME
= 'youtube:truncated_url'
2542 IE_DESC
= False # Do not list
2543 _VALID_URL
= r
'''(?x)
2545 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2548 annotation_id=annotation_[^&]+|
2554 attribution_link\?a=[^&]+
2560 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2561 'only_matching': True,
2563 'url': 'https://www.youtube.com/watch?',
2564 'only_matching': True,
2566 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2567 'only_matching': True,
2569 'url': 'https://www.youtube.com/watch?feature=foo',
2570 'only_matching': True,
2572 'url': 'https://www.youtube.com/watch?hl=en-GB',
2573 'only_matching': True,
2575 'url': 'https://www.youtube.com/watch?t=2372',
2576 'only_matching': True,
2579 def _real_extract(self
, url
):
2580 raise ExtractorError(
2581 'Did you forget to quote the URL? Remember that & is a meta '
2582 'character in most shells, so you want to put the URL in quotes, '
2584 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2585 ' or simply youtube-dl BaW_jenozKc .',
2589 class YoutubeTruncatedIDIE(InfoExtractor
):
2590 IE_NAME
= 'youtube:truncated_id'
2591 IE_DESC
= False # Do not list
2592 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2595 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2596 'only_matching': True,
2599 def _real_extract(self
, url
):
2600 video_id
= self
._match
_id
(url
)
2601 raise ExtractorError(
2602 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id
, url
),