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
,
52 class YoutubeBaseInfoExtractor(InfoExtractor
):
53 """Provide base functions for Youtube extractors"""
54 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
55 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
56 _PASSWORD_CHALLENGE_URL
= 'https://accounts.google.com/signin/challenge/sl/password'
57 _NETRC_MACHINE
= 'youtube'
58 # If True it will raise an error if no login info is provided
59 _LOGIN_REQUIRED
= False
61 def _set_language(self
):
63 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
64 # YouTube sets the expire time to about two months
65 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
67 def _ids_to_results(self
, ids
):
69 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
74 Attempt to log in to YouTube.
75 True is returned if successful or skipped.
76 False is returned if login failed.
78 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
80 (username
, password
) = self
._get
_login
_info
()
81 # No authentication to be performed
83 if self
._LOGIN
_REQUIRED
:
84 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
87 login_page
= self
._download
_webpage
(
88 self
._LOGIN
_URL
, None,
89 note
='Downloading login page',
90 errnote
='unable to fetch login page', fatal
=False)
91 if login_page
is False:
94 login_form
= self
._hidden
_inputs
(login_page
)
97 'checkConnection': 'youtube',
102 login_results
= self
._download
_webpage
(
103 self
._PASSWORD
_CHALLENGE
_URL
, None,
104 note
='Logging in', errnote
='unable to log in', fatal
=False,
105 data
=urlencode_postdata(login_form
))
106 if login_results
is False:
109 error_msg
= self
._html
_search
_regex
(
110 r
'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
111 login_results
, 'error message', default
=None)
113 raise ExtractorError('Unable to login: %s' % error_msg
, expected
=True)
115 if re
.search(r
'id="errormsg_0_Passwd"', login_results
) is not None:
116 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected
=True)
119 # TODO add SMS and phone call support - these require making a request and then prompting the user
121 if re
.search(r
'(?i)<form[^>]+id="challenge"', login_results
) is not None:
122 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
125 self
._downloader
.report_warning(
126 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
127 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
130 tfa_code
= remove_start(tfa_code
, 'G-')
132 tfa_form_strs
= self
._form
_hidden
_inputs
('challenge', login_results
)
134 tfa_form_strs
.update({
139 tfa_data
= urlencode_postdata(tfa_form_strs
)
141 tfa_req
= sanitized_Request(self
._TWOFACTOR
_URL
, tfa_data
)
142 tfa_results
= self
._download
_webpage
(
144 note
='Submitting TFA code', errnote
='unable to submit tfa', fatal
=False)
146 if tfa_results
is False:
149 if re
.search(r
'(?i)<form[^>]+id="challenge"', tfa_results
) is not None:
150 self
._downloader
.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
152 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', tfa_results
) is not None:
153 self
._downloader
.report_warning('unable to log in - did the page structure change?')
155 if re
.search(r
'smsauth-interstitial-reviewsettings', tfa_results
) is not None:
156 self
._downloader
.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
159 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', login_results
) is not None:
160 self
._downloader
.report_warning('unable to log in: bad username or password')
164 def _real_initialize(self
):
165 if self
._downloader
is None:
168 if not self
._login
():
172 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
173 # Extract entries from page with "Load more" button
174 def _entries(self
, page
, playlist_id
):
175 more_widget_html
= content_html
= page
176 for page_num
in itertools
.count(1):
177 for entry
in self
._process
_page
(content_html
):
180 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
184 more
= self
._download
_json
(
185 'https://youtube.com/%s' % mobj
.group('more'), playlist_id
,
186 'Downloading page #%s' % page_num
,
187 transform_source
=uppercase_escape
)
188 content_html
= more
['content_html']
189 if not content_html
.strip():
190 # Some webpages show a "Load more" button but they don't
193 more_widget_html
= more
['load_more_widget_html']
196 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
197 def _process_page(self
, content
):
198 for video_id
, video_title
in self
.extract_videos_from_page(content
):
199 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
201 def extract_videos_from_page(self
, page
):
204 for mobj
in re
.finditer(self
._VIDEO
_RE
, page
):
205 # The link with index 0 is not the first video of the playlist (not sure if still actual)
206 if 'index' in mobj
.groupdict() and mobj
.group('id') == '0':
208 video_id
= mobj
.group('id')
209 video_title
= unescapeHTML(mobj
.group('title'))
211 video_title
= video_title
.strip()
213 idx
= ids_in_page
.index(video_id
)
214 if video_title
and not titles_in_page
[idx
]:
215 titles_in_page
[idx
] = video_title
217 ids_in_page
.append(video_id
)
218 titles_in_page
.append(video_title
)
219 return zip(ids_in_page
, titles_in_page
)
222 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
223 def _process_page(self
, content
):
224 for playlist_id
in orderedSet(re
.findall(
225 r
'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
227 yield self
.url_result(
228 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
230 def _real_extract(self
, url
):
231 playlist_id
= self
._match
_id
(url
)
232 webpage
= self
._download
_webpage
(url
, playlist_id
)
233 title
= self
._og
_search
_title
(webpage
, fatal
=False)
234 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
237 class YoutubeIE(YoutubeBaseInfoExtractor
):
238 IE_DESC
= 'YouTube.com'
239 _VALID_URL
= r
"""(?x)^
241 (?:https?://|//) # http(s):// or protocol-independent URL
242 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
243 (?:www\.)?deturl\.com/www\.youtube\.com/|
244 (?:www\.)?pwnyoutube\.com/|
245 (?:www\.)?yourepeat\.com/|
246 tube\.majestyc\.net/|
247 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
248 (?:.*?\#/)? # handle anchor (#/) redirect urls
249 (?: # the various things that can precede the ID:
250 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
251 |(?: # or the v= param in all its forms
252 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
253 (?:\?|\#!?) # the params delimiter ? or # or #!
254 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
259 youtu\.be| # just youtu.be/xxxx
260 vid\.plus| # or vid.plus/xxxx
261 zwearz\.com/watch| # or zwearz.com/watch/xxxx
263 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
265 )? # all until now is optional -> you can pass the naked ID
266 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
267 (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
268 (?(1).+)? # if we found the ID, everything can follow
270 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
272 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
273 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
274 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
275 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
276 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
277 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
278 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
279 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
280 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
281 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
282 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
283 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
284 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
285 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
286 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
287 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
288 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
289 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
293 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
294 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
295 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
296 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
297 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
298 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
299 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
301 # Apple HTTP Live Streaming
302 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
303 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
304 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
305 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
306 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
307 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
308 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
309 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
312 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
313 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
314 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
315 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
316 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
317 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
318 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
319 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
320 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40}
,
321 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40}
,
322 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}
,
325 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}
,
326 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}
,
327 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}
,
328 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'}
,
329 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'}
,
332 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
333 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
334 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
335 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
336 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
337 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}
,
338 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40}
,
339 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
340 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
341 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
342 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
343 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
344 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
345 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
346 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
347 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
348 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
349 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
350 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
351 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
352 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40}
,
353 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40}
,
356 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}
,
357 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}
,
359 # Dash webm audio with opus inside
360 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}
,
361 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}
,
362 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}
,
365 '_rtmp': {'protocol': 'rtmp'}
,
367 _SUBTITLE_FORMATS
= ('ttml', 'vtt')
372 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
376 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
377 'uploader': 'Philipp Hagemeister',
378 'uploader_id': 'phihag',
379 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag',
380 'upload_date': '20121002',
381 'license': 'Standard YouTube License',
382 '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 .',
383 'categories': ['Science & Technology'],
384 'tags': ['youtube-dl'],
386 'dislike_count': int,
392 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
393 'note': 'Test generic use_cipher_signature video (#897)',
397 'upload_date': '20120506',
398 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
399 'alt_title': 'I Love It (feat. Charli XCX)',
400 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
401 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
402 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
403 'iconic ep', 'iconic', 'love', 'it'],
404 'uploader': 'Icona Pop',
405 'uploader_id': 'IconaPop',
406 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IconaPop',
407 'license': 'Standard YouTube License',
408 'creator': 'Icona Pop',
412 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
413 'note': 'Test VEVO video with age protection (#956)',
417 'upload_date': '20130703',
418 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
419 'alt_title': 'Tunnel Vision',
420 'description': 'md5:64249768eec3bc4276236606ea996373',
421 'uploader': 'justintimberlakeVEVO',
422 'uploader_id': 'justintimberlakeVEVO',
423 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
424 'license': 'Standard YouTube License',
425 'creator': 'Justin Timberlake',
430 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
431 'note': 'Embed-only video (#1746)',
435 'upload_date': '20120608',
436 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
437 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
438 'uploader': 'SET India',
439 'uploader_id': 'setindia',
440 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/setindia',
441 'license': 'Standard YouTube License',
446 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
447 'note': 'Use the first video ID in the URL',
451 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
452 'uploader': 'Philipp Hagemeister',
453 'uploader_id': 'phihag',
454 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag',
455 'upload_date': '20121002',
456 'license': 'Standard YouTube License',
457 '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 .',
458 'categories': ['Science & Technology'],
459 'tags': ['youtube-dl'],
461 'dislike_count': int,
464 'skip_download': True,
468 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
469 'note': '256k DASH audio (format 141) via DASH manifest',
473 'upload_date': '20121002',
474 'uploader_id': '8KVIDEO',
475 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
477 'uploader': '8KVIDEO',
478 'license': 'Standard YouTube License',
479 'title': 'UHDTV TEST 8K VIDEO.mp4'
482 'youtube_include_dash_manifest': True,
485 'skip': 'format 141 not served anymore',
487 # DASH manifest with encrypted signature
489 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
493 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
494 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
495 'uploader': 'AfrojackVEVO',
496 'uploader_id': 'AfrojackVEVO',
497 'upload_date': '20131011',
498 'license': 'Standard YouTube License',
501 'youtube_include_dash_manifest': True,
502 'format': '141/bestaudio[ext=m4a]',
505 # JS player signature function name containing $
507 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
511 'title': 'Taylor Swift - Shake It Off',
512 'alt_title': 'Shake It Off',
513 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
514 'uploader': 'TaylorSwiftVEVO',
515 'uploader_id': 'TaylorSwiftVEVO',
516 'upload_date': '20140818',
517 'license': 'Standard YouTube License',
518 'creator': 'Taylor Swift',
521 'youtube_include_dash_manifest': True,
522 'format': '141/bestaudio[ext=m4a]',
527 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
531 'upload_date': '20100909',
532 'uploader': 'The Amazing Atheist',
533 'uploader_id': 'TheAmazingAtheist',
534 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
535 'license': 'Standard YouTube License',
536 'title': 'Burning Everyone\'s Koran',
537 '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',
540 # Normal age-gate video (No vevo, embed allowed)
542 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
546 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
547 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
548 'uploader': 'The Witcher',
549 'uploader_id': 'WitcherGame',
550 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
551 'upload_date': '20140605',
552 'license': 'Standard YouTube License',
556 # Age-gate video with encrypted signature
558 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
562 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
563 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
564 'uploader': 'LloydVEVO',
565 'uploader_id': 'LloydVEVO',
566 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
567 'upload_date': '20110629',
568 'license': 'Standard YouTube License',
572 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
574 'url': '__2ABJjxzNo',
578 'upload_date': '20100430',
579 'uploader_id': 'deadmau5',
580 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/deadmau5',
581 'creator': 'deadmau5',
582 'description': 'md5:12c56784b8032162bb936a5f76d55360',
583 'uploader': 'deadmau5',
584 'license': 'Standard YouTube License',
585 'title': 'Deadmau5 - Some Chords (HD)',
586 'alt_title': 'Some Chords',
588 'expected_warnings': [
589 'DASH manifest missing',
592 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
594 'url': 'lqQg6PlCWgI',
598 'upload_date': '20150827',
599 'uploader_id': 'olympic',
600 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/olympic',
601 'license': 'Standard YouTube License',
602 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
603 'uploader': 'Olympic',
604 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
607 'skip_download': 'requires avconv',
612 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
616 'stretched_ratio': 16 / 9.,
617 'upload_date': '20110310',
618 'uploader_id': 'AllenMeow',
619 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
620 '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',
622 'license': 'Standard YouTube License',
623 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
626 # url_encoded_fmt_stream_map is empty string
628 'url': 'qEJwOuvDf7I',
632 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
634 'upload_date': '20150404',
635 'uploader_id': 'spbelect',
636 'uploader': 'Наблюдатели Петербурга',
639 'skip_download': 'requires avconv',
641 'skip': 'This live event has ended.',
643 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
645 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
649 'title': 'md5:7b81415841e02ecd4313668cde88737a',
650 'description': 'md5:116377fd2963b81ec4ce64b542173306',
651 'upload_date': '20150625',
652 'uploader_id': 'dorappi2000',
653 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
654 'uploader': 'dorappi2000',
655 'license': 'Standard YouTube License',
656 'formats': 'mincount:32',
659 # DASH manifest with segment_list
661 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
662 'md5': '8ce563a1d667b599d21064e982ab9e31',
666 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
667 'uploader': 'Airtek',
668 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
669 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
670 'license': 'Standard YouTube License',
671 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
674 'youtube_include_dash_manifest': True,
675 'format': '135', # bestvideo
677 'skip': 'This live event has ended.',
680 # Multifeed videos (multiple cameras), URL is for Main Camera
681 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
684 'title': 'teamPGP: Rocket League Noob Stream',
685 'description': 'md5:dc7872fb300e143831327f1bae3af010',
691 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
692 'description': 'md5:dc7872fb300e143831327f1bae3af010',
693 'upload_date': '20150721',
694 'uploader': 'Beer Games Beer',
695 'uploader_id': 'beergamesbeer',
696 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
697 'license': 'Standard YouTube License',
703 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
704 'description': 'md5:dc7872fb300e143831327f1bae3af010',
705 'upload_date': '20150721',
706 'uploader': 'Beer Games Beer',
707 'uploader_id': 'beergamesbeer',
708 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
709 'license': 'Standard YouTube License',
715 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
716 'description': 'md5:dc7872fb300e143831327f1bae3af010',
717 'upload_date': '20150721',
718 'uploader': 'Beer Games Beer',
719 'uploader_id': 'beergamesbeer',
720 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
721 'license': 'Standard YouTube License',
727 'title': 'teamPGP: Rocket League Noob Stream (zim)',
728 'description': 'md5:dc7872fb300e143831327f1bae3af010',
729 'upload_date': '20150721',
730 'uploader': 'Beer Games Beer',
731 'uploader_id': 'beergamesbeer',
732 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
733 'license': 'Standard YouTube License',
737 'skip_download': True,
741 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
742 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
745 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
748 'skip': 'Not multifeed anymore',
751 'url': 'https://vid.plus/FlRa-iH7PGw',
752 'only_matching': True,
755 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
756 'only_matching': True,
759 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
760 # Also tests cut-off URL expansion in video description (see
761 # https://github.com/rg3/youtube-dl/issues/1892,
762 # https://github.com/rg3/youtube-dl/issues/8164)
763 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
767 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
768 'alt_title': 'Dark Walk',
769 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
770 'upload_date': '20151119',
771 'uploader_id': 'IronSoulElf',
772 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
773 'uploader': 'IronSoulElf',
774 'license': 'Standard YouTube License',
775 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
778 'skip_download': True,
782 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
783 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
784 'only_matching': True,
787 # Video with yt:stretch=17:0
788 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
792 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
793 'description': 'md5:ee18a25c350637c8faff806845bddee9',
794 'upload_date': '20151107',
795 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
796 'uploader': 'CH GAMER DROID',
799 'skip_download': True,
801 'skip': 'This video does not exist.',
804 # Video licensed under Creative Commons
805 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
809 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
810 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
811 'upload_date': '20150127',
812 'uploader_id': 'BerkmanCenter',
813 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
814 'uploader': 'BerkmanCenter',
815 'license': 'Creative Commons Attribution license (reuse allowed)',
818 'skip_download': True,
822 # Channel-like uploader_url
823 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
827 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
828 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
829 'upload_date': '20151119',
830 'uploader': 'Bernie 2016',
831 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
832 'uploader_url': 're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
833 'license': 'Creative Commons Attribution license (reuse allowed)',
836 'skip_download': True,
840 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
841 'only_matching': True,
844 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
845 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
846 'only_matching': True,
849 # Rental video preview
850 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
854 'title': 'Piku - Trailer',
855 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
856 'upload_date': '20150811',
857 'uploader': 'FlixMatrix',
858 'uploader_id': 'FlixMatrixKaravan',
859 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
860 'license': 'Standard YouTube License',
863 'skip_download': True,
868 def __init__(self
, *args
, **kwargs
):
869 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
870 self
._player
_cache
= {}
872 def report_video_info_webpage_download(self
, video_id
):
873 """Report attempt to download video info webpage."""
874 self
.to_screen('%s: Downloading video info webpage' % video_id
)
876 def report_information_extraction(self
, video_id
):
877 """Report attempt to extract video information."""
878 self
.to_screen('%s: Extracting video information' % video_id
)
880 def report_unavailable_format(self
, video_id
, format
):
881 """Report extracted video URL."""
882 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
884 def report_rtmp_download(self
):
885 """Indicate the download will use the RTMP protocol."""
886 self
.to_screen('RTMP download detected')
888 def _signature_cache_id(self
, example_sig
):
889 """ Return a string representation of a signature """
890 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
892 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
894 r
'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
897 raise ExtractorError('Cannot identify player %r' % player_url
)
898 player_type
= id_m
.group('ext')
899 player_id
= id_m
.group('id')
901 # Read from filesystem cache
902 func_id
= '%s_%s_%s' % (
903 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
904 assert os
.path
.basename(func_id
) == func_id
906 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
907 if cache_spec
is not None:
908 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
911 'Downloading player %s' % player_url
912 if self
._downloader
.params
.get('verbose') else
913 'Downloading %s player %s' % (player_type
, player_id
)
915 if player_type
== 'js':
916 code
= self
._download
_webpage
(
917 player_url
, video_id
,
919 errnote
='Download of %s failed' % player_url
)
920 res
= self
._parse
_sig
_js
(code
)
921 elif player_type
== 'swf':
922 urlh
= self
._request
_webpage
(
923 player_url
, video_id
,
925 errnote
='Download of %s failed' % player_url
)
927 res
= self
._parse
_sig
_swf
(code
)
929 assert False, 'Invalid player type %r' % player_type
931 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
932 cache_res
= res(test_string
)
933 cache_spec
= [ord(c
) for c
in cache_res
]
935 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
938 def _print_sig_code(self
, func
, example_sig
):
939 def gen_sig_code(idxs
):
940 def _genslice(start
, end
, step
):
941 starts
= '' if start
== 0 else str(start
)
942 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
943 steps
= '' if step
== 1 else (':%d' % step
)
944 return 's[%s%s%s]' % (starts
, ends
, steps
)
947 # Quelch pyflakes warnings - start will be set when step is set
948 start
= '(Never used)'
949 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
953 yield _genslice(start
, prev
, step
)
956 if i
- prev
in [-1, 1]:
965 yield _genslice(start
, i
, step
)
967 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
968 cache_res
= func(test_string
)
969 cache_spec
= [ord(c
) for c
in cache_res
]
970 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
971 signature_id_tuple
= '(%s)' % (
972 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
973 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
974 ' return %s\n') % (signature_id_tuple
, expr_code
)
975 self
.to_screen('Extracted signature function:\n' + code
)
977 def _parse_sig_js(self
, jscode
):
978 funcname
= self
._search
_regex
(
979 r
'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode
,
980 'Initial JS player signature function name')
982 jsi
= JSInterpreter(jscode
)
983 initial_function
= jsi
.extract_function(funcname
)
984 return lambda s
: initial_function([s
])
986 def _parse_sig_swf(self
, file_contents
):
987 swfi
= SWFInterpreter(file_contents
)
988 TARGET_CLASSNAME
= 'SignatureDecipher'
989 searched_class
= swfi
.extract_class(TARGET_CLASSNAME
)
990 initial_function
= swfi
.extract_function(searched_class
, 'decipher')
991 return lambda s
: initial_function([s
])
993 def _decrypt_signature(self
, s
, video_id
, player_url
, age_gate
=False):
994 """Turn the encrypted s field into a working signature"""
996 if player_url
is None:
997 raise ExtractorError('Cannot decrypt signature without player_url')
999 if player_url
.startswith('//'):
1000 player_url
= 'https:' + player_url
1002 player_id
= (player_url
, self
._signature
_cache
_id
(s
))
1003 if player_id
not in self
._player
_cache
:
1004 func
= self
._extract
_signature
_function
(
1005 video_id
, player_url
, s
1007 self
._player
_cache
[player_id
] = func
1008 func
= self
._player
_cache
[player_id
]
1009 if self
._downloader
.params
.get('youtube_print_sig_code'):
1010 self
._print
_sig
_code
(func
, s
)
1012 except Exception as e
:
1013 tb
= traceback
.format_exc()
1014 raise ExtractorError(
1015 'Signature extraction failed: ' + tb
, cause
=e
)
1017 def _get_subtitles(self
, video_id
, webpage
):
1019 subs_doc
= self
._download
_xml
(
1020 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id
,
1021 video_id
, note
=False)
1022 except ExtractorError
as err
:
1023 self
._downloader
.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err
))
1027 for track
in subs_doc
.findall('track'):
1028 lang
= track
.attrib
['lang_code']
1029 if lang
in sub_lang_list
:
1032 for ext
in self
._SUBTITLE
_FORMATS
:
1033 params
= compat_urllib_parse_urlencode({
1037 'name': track
.attrib
['name'].encode('utf-8'),
1039 sub_formats
.append({
1040 'url': 'https://www.youtube.com/api/timedtext?' + params
,
1043 sub_lang_list
[lang
] = sub_formats
1044 if not sub_lang_list
:
1045 self
._downloader
.report_warning('video doesn\'t have subtitles')
1047 return sub_lang_list
1049 def _get_ytplayer_config(self
, video_id
, webpage
):
1051 # User data may contain arbitrary character sequences that may affect
1052 # JSON extraction with regex, e.g. when '};' is contained the second
1053 # regex won't capture the whole JSON. Yet working around by trying more
1054 # concrete regex first keeping in mind proper quoted string handling
1055 # to be implemented in future that will replace this workaround (see
1056 # https://github.com/rg3/youtube-dl/issues/7468,
1057 # https://github.com/rg3/youtube-dl/pull/7599)
1058 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1059 r
';ytplayer\.config\s*=\s*({.+?});',
1061 config
= self
._search
_regex
(
1062 patterns
, webpage
, 'ytplayer.config', default
=None)
1064 return self
._parse
_json
(
1065 uppercase_escape(config
), video_id
, fatal
=False)
1067 def _get_automatic_captions(self
, video_id
, webpage
):
1068 """We need the webpage for getting the captions url, pass it as an
1069 argument to speed up the process."""
1070 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1071 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1072 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1073 if not player_config
:
1074 self
._downloader
.report_warning(err_msg
)
1077 args
= player_config
['args']
1078 caption_url
= args
.get('ttsurl')
1080 timestamp
= args
['timestamp']
1081 # We get the available subtitles
1082 list_params
= compat_urllib_parse_urlencode({
1087 list_url
= caption_url
+ '&' + list_params
1088 caption_list
= self
._download
_xml
(list_url
, video_id
)
1089 original_lang_node
= caption_list
.find('track')
1090 if original_lang_node
is None:
1091 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1093 original_lang
= original_lang_node
.attrib
['lang_code']
1094 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1097 for lang_node
in caption_list
.findall('target'):
1098 sub_lang
= lang_node
.attrib
['lang_code']
1100 for ext
in self
._SUBTITLE
_FORMATS
:
1101 params
= compat_urllib_parse_urlencode({
1102 'lang': original_lang
,
1106 'kind': caption_kind
,
1108 sub_formats
.append({
1109 'url': caption_url
+ '&' + params
,
1112 sub_lang_list
[sub_lang
] = sub_formats
1113 return sub_lang_list
1115 # Some videos don't provide ttsurl but rather caption_tracks and
1116 # caption_translation_languages (e.g. 20LmZk1hakA)
1117 caption_tracks
= args
['caption_tracks']
1118 caption_translation_languages
= args
['caption_translation_languages']
1119 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1120 parsed_caption_url
= compat_urllib_parse_urlparse(caption_url
)
1121 caption_qs
= compat_parse_qs(parsed_caption_url
.query
)
1124 for lang
in caption_translation_languages
.split(','):
1125 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1126 sub_lang
= lang_qs
.get('lc', [None])[0]
1130 for ext
in self
._SUBTITLE
_FORMATS
:
1132 'tlang': [sub_lang
],
1135 sub_url
= compat_urlparse
.urlunparse(parsed_caption_url
._replace
(
1136 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1137 sub_formats
.append({
1141 sub_lang_list
[sub_lang
] = sub_formats
1142 return sub_lang_list
1143 # An extractor error can be raise by the download process if there are
1144 # no automatic captions but there are subtitles
1145 except (KeyError, ExtractorError
):
1146 self
._downloader
.report_warning(err_msg
)
1149 def _mark_watched(self
, video_id
, video_info
):
1150 playback_url
= video_info
.get('videostats_playback_base_url', [None])[0]
1151 if not playback_url
:
1153 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1154 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1156 # cpn generation algorithm is reverse engineered from base.js.
1157 # In fact it works even with dummy cpn.
1158 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1159 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1165 playback_url
= compat_urlparse
.urlunparse(
1166 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1168 self
._download
_webpage
(
1169 playback_url
, video_id
, 'Marking watched',
1170 'Unable to mark watched', fatal
=False)
1173 def extract_id(cls
, url
):
1174 mobj
= re
.match(cls
._VALID
_URL
, url
, re
.VERBOSE
)
1176 raise ExtractorError('Invalid URL: %s' % url
)
1177 video_id
= mobj
.group(2)
1180 def _extract_from_m3u8(self
, manifest_url
, video_id
):
1183 def _get_urls(_manifest
):
1184 lines
= _manifest
.split('\n')
1185 urls
= filter(lambda l
: l
and not l
.startswith('#'),
1188 manifest
= self
._download
_webpage
(manifest_url
, video_id
, 'Downloading formats manifest')
1189 formats_urls
= _get_urls(manifest
)
1190 for format_url
in formats_urls
:
1191 itag
= self
._search
_regex
(r
'itag/(\d+?)/', format_url
, 'itag')
1192 url_map
[itag
] = format_url
1195 def _extract_annotations(self
, video_id
):
1196 url
= 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1197 return self
._download
_webpage
(url
, video_id
, note
='Searching for annotations.', errnote
='Unable to download video annotations.')
1199 def _real_extract(self
, url
):
1200 url
, smuggled_data
= unsmuggle_url(url
, {})
1203 'http' if self
._downloader
.params
.get('prefer_insecure', False)
1208 parsed_url
= compat_urllib_parse_urlparse(url
)
1209 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
1210 query
= compat_parse_qs(component
)
1211 if start_time
is None and 't' in query
:
1212 start_time
= parse_duration(query
['t'][0])
1213 if start_time
is None and 'start' in query
:
1214 start_time
= parse_duration(query
['start'][0])
1215 if end_time
is None and 'end' in query
:
1216 end_time
= parse_duration(query
['end'][0])
1218 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1219 mobj
= re
.search(self
._NEXT
_URL
_RE
, url
)
1221 url
= proto
+ '://www.youtube.com/' + compat_urllib_parse_unquote(mobj
.group(1)).lstrip('/')
1222 video_id
= self
.extract_id(url
)
1225 url
= proto
+ '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1226 video_webpage
= self
._download
_webpage
(url
, video_id
)
1228 # Attempt to extract SWF player URL
1229 mobj
= re
.search(r
'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage
)
1230 if mobj
is not None:
1231 player_url
= re
.sub(r
'\\(.)', r
'\1', mobj
.group(1))
1237 def add_dash_mpd(video_info
):
1238 dash_mpd
= video_info
.get('dashmpd')
1239 if dash_mpd
and dash_mpd
[0] not in dash_mpds
:
1240 dash_mpds
.append(dash_mpd
[0])
1243 embed_webpage
= None
1245 if re
.search(r
'player-age-gate-content">', video_webpage
) is not None:
1247 # We simulate the access to the video from www.youtube.com/v/{video_id}
1248 # this can be viewed without login into Youtube
1249 url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1250 embed_webpage
= self
._download
_webpage
(url
, video_id
, 'Downloading embed webpage')
1251 data
= compat_urllib_parse_urlencode({
1252 'video_id': video_id
,
1253 'eurl': 'https://youtube.googleapis.com/v/' + video_id
,
1254 'sts': self
._search
_regex
(
1255 r
'"sts"\s*:\s*(\d+)', embed_webpage
, 'sts', default
=''),
1257 video_info_url
= proto
+ '://www.youtube.com/get_video_info?' + data
1258 video_info_webpage
= self
._download
_webpage
(
1259 video_info_url
, video_id
,
1260 note
='Refetching age-gated info webpage',
1261 errnote
='unable to download video info webpage')
1262 video_info
= compat_parse_qs(video_info_webpage
)
1263 add_dash_mpd(video_info
)
1267 # Try looking directly into the video webpage
1268 ytplayer_config
= self
._get
_ytplayer
_config
(video_id
, video_webpage
)
1270 args
= ytplayer_config
['args']
1271 if args
.get('url_encoded_fmt_stream_map'):
1272 # Convert to the same format returned by compat_parse_qs
1273 video_info
= dict((k
, [v
]) for k
, v
in args
.items())
1274 add_dash_mpd(video_info
)
1275 # Rental video is not rented but preview is available (e.g.
1276 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1277 # https://github.com/rg3/youtube-dl/issues/10532)
1278 if not video_info
and args
.get('ypc_vid'):
1279 return self
.url_result(
1280 args
['ypc_vid'], YoutubeIE
.ie_key(), video_id
=args
['ypc_vid'])
1281 if args
.get('livestream') == '1' or args
.get('live_playback') == 1:
1283 if not video_info
or self
._downloader
.params
.get('youtube_include_dash_manifest', True):
1284 # We also try looking in get_video_info since it may contain different dashmpd
1285 # URL that points to a DASH manifest with possibly different itag set (some itags
1286 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1287 # manifest pointed by get_video_info's dashmpd).
1288 # The general idea is to take a union of itags of both DASH manifests (for example
1289 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1290 self
.report_video_info_webpage_download(video_id
)
1291 for el_type
in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1293 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1294 % (proto
, video_id
, el_type
))
1295 video_info_webpage
= self
._download
_webpage
(
1297 video_id
, note
=False,
1298 errnote
='unable to download video info webpage')
1299 get_video_info
= compat_parse_qs(video_info_webpage
)
1300 if get_video_info
.get('use_cipher_signature') != ['True']:
1301 add_dash_mpd(get_video_info
)
1303 video_info
= get_video_info
1304 if 'token' in get_video_info
:
1305 # Different get_video_info requests may report different results, e.g.
1306 # some may report video unavailability, but some may serve it without
1307 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1308 # the original webpage as well as el=info and el=embedded get_video_info
1309 # requests report video unavailability due to geo restriction while
1310 # el=detailpage succeeds and returns valid data). This is probably
1311 # due to YouTube measures against IP ranges of hosting providers.
1312 # Working around by preferring the first succeeded video_info containing
1313 # the token if no such video_info yet was found.
1314 if 'token' not in video_info
:
1315 video_info
= get_video_info
1317 if 'token' not in video_info
:
1318 if 'reason' in video_info
:
1319 if 'The uploader has not made this video available in your country.' in video_info
['reason']:
1320 regions_allowed
= self
._html
_search
_meta
('regionsAllowed', video_webpage
, default
=None)
1322 raise ExtractorError('YouTube said: This video is available in %s only' % (
1323 ', '.join(map(ISO3166Utils
.short2full
, regions_allowed
.split(',')))),
1325 raise ExtractorError(
1326 'YouTube said: %s' % video_info
['reason'][0],
1327 expected
=True, video_id
=video_id
)
1329 raise ExtractorError(
1330 '"token" parameter not in video info for unknown reason',
1334 if 'title' in video_info
:
1335 video_title
= video_info
['title'][0]
1337 self
._downloader
.report_warning('Unable to extract video title')
1341 video_description
= get_element_by_id("eow-description", video_webpage
)
1342 if video_description
:
1343 video_description
= re
.sub(r
'''(?x)
1345 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1346 (?:title|href)="([^"]+)"\s+
1347 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1351 ''', r
'\1', video_description
)
1352 video_description
= clean_html(video_description
)
1354 fd_mobj
= re
.search(r
'<meta name="description" content="([^"]+)"', video_webpage
)
1356 video_description
= unescapeHTML(fd_mobj
.group(1))
1358 video_description
= ''
1360 if 'multifeed_metadata_list' in video_info
and not smuggled_data
.get('force_singlefeed', False):
1361 if not self
._downloader
.params
.get('noplaylist'):
1364 multifeed_metadata_list
= video_info
['multifeed_metadata_list'][0]
1365 for feed
in multifeed_metadata_list
.split(','):
1366 # Unquote should take place before split on comma (,) since textual
1367 # fields may contain comma as well (see
1368 # https://github.com/rg3/youtube-dl/issues/8536)
1369 feed_data
= compat_parse_qs(compat_urllib_parse_unquote_plus(feed
))
1371 '_type': 'url_transparent',
1372 'ie_key': 'Youtube',
1374 '%s://www.youtube.com/watch?v=%s' % (proto
, feed_data
['id'][0]),
1375 {'force_singlefeed': True}
),
1376 'title': '%s (%s)' % (video_title
, feed_data
['title'][0]),
1378 feed_ids
.append(feed_data
['id'][0])
1380 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1381 % (', '.join(feed_ids
), video_id
))
1382 return self
.playlist_result(entries
, video_id
, video_title
, video_description
)
1383 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
1385 if 'view_count' in video_info
:
1386 view_count
= int(video_info
['view_count'][0])
1390 # Check for "rental" videos
1391 if 'ypc_video_rental_bar_text' in video_info
and 'author' not in video_info
:
1392 raise ExtractorError('"rental" videos not supported')
1394 # Start extracting information
1395 self
.report_information_extraction(video_id
)
1398 if 'author' not in video_info
:
1399 raise ExtractorError('Unable to extract uploader name')
1400 video_uploader
= compat_urllib_parse_unquote_plus(video_info
['author'][0])
1403 video_uploader_id
= None
1404 video_uploader_url
= None
1406 r
'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1408 if mobj
is not None:
1409 video_uploader_id
= mobj
.group('uploader_id')
1410 video_uploader_url
= mobj
.group('uploader_url')
1412 self
._downloader
.report_warning('unable to extract uploader nickname')
1415 # We try first to get a high quality image:
1416 m_thumb
= re
.search(r
'<span itemprop="thumbnail".*?href="(.*?)">',
1417 video_webpage
, re
.DOTALL
)
1418 if m_thumb
is not None:
1419 video_thumbnail
= m_thumb
.group(1)
1420 elif 'thumbnail_url' not in video_info
:
1421 self
._downloader
.report_warning('unable to extract video thumbnail')
1422 video_thumbnail
= None
1423 else: # don't panic if we can't find it
1424 video_thumbnail
= compat_urllib_parse_unquote_plus(video_info
['thumbnail_url'][0])
1427 upload_date
= self
._html
_search
_meta
(
1428 'datePublished', video_webpage
, 'upload date', default
=None)
1430 upload_date
= self
._search
_regex
(
1431 [r
'(?s)id="eow-date.*?>(.*?)</span>',
1432 r
'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1433 video_webpage
, 'upload date', default
=None)
1435 upload_date
= ' '.join(re
.sub(r
'[/,-]', r
' ', mobj
.group(1)).split())
1436 upload_date
= unified_strdate(upload_date
)
1438 video_license
= self
._html
_search
_regex
(
1439 r
'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1440 video_webpage
, 'license', default
=None)
1442 m_music
= re
.search(
1443 r
'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1446 video_alt_title
= remove_quotes(unescapeHTML(m_music
.group('title')))
1447 video_creator
= clean_html(m_music
.group('creator'))
1449 video_alt_title
= video_creator
= None
1451 m_cat_container
= self
._search
_regex
(
1452 r
'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1453 video_webpage
, 'categories', default
=None)
1455 category
= self
._html
_search
_regex
(
1456 r
'(?s)<a[^<]+>(.*?)</a>', m_cat_container
, 'category',
1458 video_categories
= None if category
is None else [category
]
1460 video_categories
= None
1463 unescapeHTML(m
.group('content'))
1464 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), video_webpage
)]
1466 def _extract_count(count_name
):
1467 return str_to_int(self
._search
_regex
(
1468 r
'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1469 % re
.escape(count_name
),
1470 video_webpage
, count_name
, default
=None))
1472 like_count
= _extract_count('like')
1473 dislike_count
= _extract_count('dislike')
1476 video_subtitles
= self
.extract_subtitles(video_id
, video_webpage
)
1477 automatic_captions
= self
.extract_automatic_captions(video_id
, video_webpage
)
1479 if 'length_seconds' not in video_info
:
1480 self
._downloader
.report_warning('unable to extract video duration')
1481 video_duration
= None
1483 video_duration
= int(compat_urllib_parse_unquote_plus(video_info
['length_seconds'][0]))
1486 video_annotations
= None
1487 if self
._downloader
.params
.get('writeannotations', False):
1488 video_annotations
= self
._extract
_annotations
(video_id
)
1490 def _map_to_format_list(urlmap
):
1492 for itag
, video_real_url
in urlmap
.items():
1495 'url': video_real_url
,
1496 'player_url': player_url
,
1498 if itag
in self
._formats
:
1499 dct
.update(self
._formats
[itag
])
1503 if 'conn' in video_info
and video_info
['conn'][0].startswith('rtmp'):
1504 self
.report_rtmp_download()
1506 'format_id': '_rtmp',
1508 'url': video_info
['conn'][0],
1509 'player_url': player_url
,
1511 elif len(video_info
.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info
.get('adaptive_fmts', [''])[0]) >= 1:
1512 encoded_url_map
= video_info
.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info
.get('adaptive_fmts', [''])[0]
1513 if 'rtmpe%3Dyes' in encoded_url_map
:
1514 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected
=True)
1516 fmt_list
= video_info
.get('fmt_list', [''])[0]
1518 for fmt
in fmt_list
.split(','):
1519 spec
= fmt
.split('/')
1521 width_height
= spec
[1].split('x')
1522 if len(width_height
) == 2:
1523 formats_spec
[spec
[0]] = {
1524 'resolution': spec
[1],
1525 'width': int_or_none(width_height
[0]),
1526 'height': int_or_none(width_height
[1]),
1529 for url_data_str
in encoded_url_map
.split(','):
1530 url_data
= compat_parse_qs(url_data_str
)
1531 if 'itag' not in url_data
or 'url' not in url_data
:
1533 format_id
= url_data
['itag'][0]
1534 url
= url_data
['url'][0]
1536 if 'sig' in url_data
:
1537 url
+= '&signature=' + url_data
['sig'][0]
1538 elif 's' in url_data
:
1539 encrypted_sig
= url_data
['s'][0]
1540 ASSETS_RE
= r
'"assets":.+?"js":\s*("[^"]+")'
1542 jsplayer_url_json
= self
._search
_regex
(
1544 embed_webpage
if age_gate
else video_webpage
,
1545 'JS player URL (1)', default
=None)
1546 if not jsplayer_url_json
and not age_gate
:
1547 # We need the embed website after all
1548 if embed_webpage
is None:
1549 embed_url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1550 embed_webpage
= self
._download
_webpage
(
1551 embed_url
, video_id
, 'Downloading embed webpage')
1552 jsplayer_url_json
= self
._search
_regex
(
1553 ASSETS_RE
, embed_webpage
, 'JS player URL')
1555 player_url
= json
.loads(jsplayer_url_json
)
1556 if player_url
is None:
1557 player_url_json
= self
._search
_regex
(
1558 r
'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1559 video_webpage
, 'age gate player URL')
1560 player_url
= json
.loads(player_url_json
)
1562 if self
._downloader
.params
.get('verbose'):
1563 if player_url
is None:
1564 player_version
= 'unknown'
1565 player_desc
= 'unknown'
1567 if player_url
.endswith('swf'):
1568 player_version
= self
._search
_regex
(
1569 r
'-(.+?)(?:/watch_as3)?\.swf$', player_url
,
1570 'flash player', fatal
=False)
1571 player_desc
= 'flash player %s' % player_version
1573 player_version
= self
._search
_regex
(
1574 [r
'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r
'(?:www|player)-([^/]+)/base\.js'],
1576 'html5 player', fatal
=False)
1577 player_desc
= 'html5 player %s' % player_version
1579 parts_sizes
= self
._signature
_cache
_id
(encrypted_sig
)
1580 self
.to_screen('{%s} signature length %s, %s' %
1581 (format_id
, parts_sizes
, player_desc
))
1583 signature
= self
._decrypt
_signature
(
1584 encrypted_sig
, video_id
, player_url
, age_gate
)
1585 url
+= '&signature=' + signature
1586 if 'ratebypass' not in url
:
1587 url
+= '&ratebypass=yes'
1590 'format_id': format_id
,
1592 'player_url': player_url
,
1594 if format_id
in self
._formats
:
1595 dct
.update(self
._formats
[format_id
])
1596 if format_id
in formats_spec
:
1597 dct
.update(formats_spec
[format_id
])
1599 # Some itags are not included in DASH manifest thus corresponding formats will
1600 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1601 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1602 mobj
= re
.search(r
'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data
.get('size', [''])[0])
1603 width
, height
= (int(mobj
.group('width')), int(mobj
.group('height'))) if mobj
else (None, None)
1606 'filesize': int_or_none(url_data
.get('clen', [None])[0]),
1607 'tbr': float_or_none(url_data
.get('bitrate', [None])[0], 1000),
1610 'fps': int_or_none(url_data
.get('fps', [None])[0]),
1611 'format_note': url_data
.get('quality_label', [None])[0] or url_data
.get('quality', [None])[0],
1613 for key
, value
in more_fields
.items():
1616 type_
= url_data
.get('type', [None])[0]
1618 type_split
= type_
.split(';')
1619 kind_ext
= type_split
[0].split('/')
1620 if len(kind_ext
) == 2:
1622 dct
['ext'] = mimetype2ext(type_split
[0])
1623 if kind
in ('audio', 'video'):
1625 for mobj
in re
.finditer(
1626 r
'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
1627 if mobj.group('key
') == 'codecs
':
1628 codecs = mobj.group('val
')
1631 codecs = codecs.split(',')
1632 if len(codecs) == 2:
1633 acodec, vcodec = codecs[1], codecs[0]
1635 acodec, vcodec = (codecs[0], 'none
') if kind == 'audio
' else ('none
', codecs[0])
1641 elif video_info.get('hlsvp
'):
1642 manifest_url = video_info['hlsvp
'][0]
1643 url_map = self._extract_from_m3u8(manifest_url, video_id)
1644 formats = _map_to_format_list(url_map)
1645 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1646 for a_format in formats:
1647 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
1649 unavailable_message = self._html_search_regex(
1650 r'(?s
)<h1
[^
>]+id="unavailable-message"[^
>]*>(.+?
)</h1
>',
1651 video_webpage, 'unavailable message
', default=None)
1652 if unavailable_message:
1653 raise ExtractorError(unavailable_message, expected=True)
1654 raise ExtractorError('no conn
, hlsvp
or url_encoded_fmt_stream_map information found
in video info
')
1656 # Look for the DASH manifest
1657 if self._downloader.params.get('youtube_include_dash_manifest
', True):
1658 dash_mpd_fatal = True
1659 for mpd_url in dash_mpds:
1662 def decrypt_sig(mobj):
1664 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1665 return '/signature
/%s' % dec_s
1667 mpd_url = re.sub(r'/s
/([a
-fA
-F0
-9\
.]+)', decrypt_sig, mpd_url)
1669 for df in self._extract_mpd_formats(
1670 mpd_url, video_id, fatal=dash_mpd_fatal,
1671 formats_dict=self._formats):
1672 # Do not overwrite DASH format found in some previous DASH manifest
1673 if df['format_id
'] not in dash_formats:
1674 dash_formats[df['format_id
']] = df
1675 # Additional DASH manifests may end up in HTTP Error 403 therefore
1676 # allow them to fail without bug report message if we already have
1677 # some DASH manifest succeeded. This is temporary workaround to reduce
1678 # burst of bug reports until we figure out the reason and whether it
1679 # can be fixed at all.
1680 dash_mpd_fatal = False
1681 except (ExtractorError, KeyError) as e:
1682 self.report_warning(
1683 'Skipping DASH manifest
: %r' % e, video_id)
1685 # Remove the formats we found through non-DASH, they
1686 # contain less info and it can be wrong, because we use
1687 # fixed values (for example the resolution). See
1688 # https://github.com/rg3/youtube-dl/issues/5774 for an
1690 formats = [f for f in formats if f['format_id
'] not in dash_formats.keys()]
1691 formats.extend(dash_formats.values())
1693 # Check for malformed aspect ratio
1694 stretched_m = re.search(
1695 r'<meta\s
+property="og:video:tag".*?content
="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1698 w = float(stretched_m.group('w
'))
1699 h = float(stretched_m.group('h
'))
1700 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1701 # We will only process correct ratios.
1705 if f.get('vcodec
') != 'none
':
1706 f['stretched_ratio
'] = ratio
1708 self._sort_formats(formats)
1710 self.mark_watched(video_id, video_info)
1714 'uploader
': video_uploader,
1715 'uploader_id
': video_uploader_id,
1716 'uploader_url
': video_uploader_url,
1717 'upload_date
': upload_date,
1718 'license
': video_license,
1719 'creator
': video_creator,
1720 'title
': video_title,
1721 'alt_title
': video_alt_title,
1722 'thumbnail
': video_thumbnail,
1723 'description
': video_description,
1724 'categories
': video_categories,
1726 'subtitles
': video_subtitles,
1727 'automatic_captions
': automatic_captions,
1728 'duration
': video_duration,
1729 'age_limit
': 18 if age_gate else 0,
1730 'annotations
': video_annotations,
1731 'webpage_url
': proto + '://www
.youtube
.com
/watch?v
=%s' % video_id,
1732 'view_count
': view_count,
1733 'like_count
': like_count,
1734 'dislike_count
': dislike_count,
1735 'average_rating
': float_or_none(video_info.get('avg_rating
', [None])[0]),
1738 'start_time
': start_time,
1739 'end_time
': end_time,
1743 class YoutubeSharedVideoIE(InfoExtractor):
1744 _VALID_URL = r'(?
:https?
:)?
//(?
:www\
.)?youtube\
.com
/shared
\?.*\bci
=(?P
<id>[0-9A
-Za
-z_
-]{11}
)'
1745 IE_NAME = 'youtube
:shared
'
1748 'url
': 'https
://www
.youtube
.com
/shared?ci
=1nEzmT
-M4fU
',
1750 'id': 'uPDB5I9wfp8
',
1752 'title
': 'Pocoyo
: 90 minutos de episódios completos Português para crianç
as - PARTE
3',
1753 'description
': 'md5
:d9e4d9346a2dfff4c7dc4c8cec0f546d
',
1754 'upload_date
': '20160219',
1755 'uploader
': 'Pocoyo
- Portuguê
s (BR
)',
1756 'uploader_id
': 'PocoyoBrazil
',
1758 'add_ie
': ['Youtube
'],
1760 # There are already too many Youtube downloads
1761 'skip_download
': True,
1765 def _real_extract(self, url):
1766 video_id = self._match_id(url)
1768 webpage = self._download_webpage(url, video_id)
1770 real_video_id = self._html_search_meta(
1771 'videoId
', webpage, 'YouTube video
id', fatal=True)
1773 return self.url_result(real_video_id, YoutubeIE.ie_key())
1776 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1777 IE_DESC = 'YouTube
.com playlists
'
1778 _VALID_URL = r"""(?x)(?:
1784 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1785 \? (?:.*?[&;])*? (?:p|a|list)=
1788 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1791 (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
1792 # Top tracks, they can also include dots
1797 ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
1799 _TEMPLATE_URL = 'https
://www
.youtube
.com
/playlist?
list=%s'
1800 _VIDEO_RE = r'href
="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index
=(?P
<index
>\d
+)(?
:[^
>]+>(?P
<title
>[^
<]+))?
'
1801 IE_NAME = 'youtube
:playlist
'
1803 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1805 'title
': 'ytdl test PL
',
1806 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1808 'playlist_count
': 3,
1810 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1812 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1813 'title
': 'YDL_Empty_List
',
1815 'playlist_count
': 0,
1817 'note
': 'Playlist
with deleted
videos (#651). As a bonus, the video #51 is also twice in this list.',
1818 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1820 'title': '29C3: Not my department',
1821 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1823 'playlist_count': 95,
1825 'note': 'issue #673',
1826 'url': 'PLBB231211A4F62143',
1828 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1829 'id': 'PLBB231211A4F62143',
1831 'playlist_mincount': 26,
1833 'note': 'Large playlist',
1834 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1836 'title': 'Uploads from Cauchemar',
1837 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1839 'playlist_mincount': 799,
1841 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1843 'title': 'YDL_safe_search',
1844 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1846 'playlist_count': 2,
1849 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1850 'playlist_count': 4,
1853 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1856 'note': 'Embedded SWF player',
1857 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1858 'playlist_count': 4,
1861 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1864 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1865 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1867 'title': 'Uploads from Interstellar Movie',
1868 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1870 'playlist_mincount': 21,
1872 # Playlist URL that does not actually serve a playlist
1873 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1875 'id': 'FqZTN594JQw',
1877 'title': "Smiley's People 01 detective, Adventure Series, Action",
1878 'uploader': 'STREEM',
1879 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1880 'uploader_url': 're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1881 'upload_date': '20150526',
1882 'license': 'Standard YouTube License',
1883 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1884 'categories': ['People & Blogs'],
1887 'dislike_count': int,
1890 'skip_download': True,
1892 'add_ie': [YoutubeIE
.ie_key()],
1894 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1896 'id': 'yeWKywCrFtk',
1898 'title': 'Small Scale Baler and Braiding Rugs',
1899 'uploader': 'Backus-Page House Museum',
1900 'uploader_id': 'backuspagemuseum',
1901 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1902 'upload_date': '20161008',
1903 'license': 'Standard YouTube License',
1904 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1905 'categories': ['Nonprofits & Activism'],
1908 'dislike_count': int,
1912 'skip_download': True,
1915 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1916 'only_matching': True,
1919 def _real_initialize(self
):
1922 def _extract_mix(self
, playlist_id
):
1923 # The mixes are generated from a single video
1924 # the id of the playlist is just 'RD' + video_id
1926 last_id
= playlist_id
[-11:]
1927 for n
in itertools
.count(1):
1928 url
= 'https://youtube.com/watch?v=%s&list=%s' % (last_id
, playlist_id
)
1929 webpage
= self
._download
_webpage
(
1930 url
, playlist_id
, 'Downloading page {0} of Youtube mix'.format(n
))
1931 new_ids
= orderedSet(re
.findall(
1932 r
'''(?xs)data-video-username=".*?".*?
1933 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re
.escape(playlist_id
),
1935 # Fetch new pages until all the videos are repeated, it seems that
1936 # there are always 51 unique videos.
1937 new_ids
= [_id
for _id
in new_ids
if _id
not in ids
]
1943 url_results
= self
._ids
_to
_results
(ids
)
1945 search_title
= lambda class_name
: get_element_by_attribute('class', class_name
, webpage
)
1947 search_title('playlist-title') or
1948 search_title('title long-title') or
1949 search_title('title'))
1950 title
= clean_html(title_span
)
1952 return self
.playlist_result(url_results
, playlist_id
, title
)
1954 def _extract_playlist(self
, playlist_id
):
1955 url
= self
._TEMPLATE
_URL
% playlist_id
1956 page
= self
._download
_webpage
(url
, playlist_id
)
1958 for match
in re
.findall(r
'<div class="yt-alert-message">([^<]+)</div>', page
):
1959 match
= match
.strip()
1960 # Check if the playlist exists or is private
1961 if re
.match(r
'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match
):
1962 raise ExtractorError(
1963 'The playlist doesn\'t exist or is private, use --username or '
1964 '--netrc to access it.',
1966 elif re
.match(r
'[^<]*Invalid parameters[^<]*', match
):
1967 raise ExtractorError(
1968 'Invalid parameters. Maybe URL is incorrect.',
1970 elif re
.match(r
'[^<]*Choose your language[^<]*', match
):
1973 self
.report_warning('Youtube gives an alert message: ' + match
)
1975 playlist_title
= self
._html
_search
_regex
(
1976 r
'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
1977 page
, 'title', default
=None)
1981 if not playlist_title
:
1983 # Some playlist URLs don't actually serve a playlist (e.g.
1984 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
1985 next(self
._entries
(page
, playlist_id
))
1986 except StopIteration:
1989 return has_videos
, self
.playlist_result(
1990 self
._entries
(page
, playlist_id
), playlist_id
, playlist_title
)
1992 def _check_download_just_video(self
, url
, playlist_id
):
1993 # Check if it's a video-specific URL
1994 query_dict
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
1995 video_id
= query_dict
.get('v', [None])[0] or self
._search
_regex
(
1996 r
'(?:^|//)youtu\.be/([0-9A-Za-z_-]{11})', url
,
1997 'video id', default
=None)
1999 if self
._downloader
.params
.get('noplaylist'):
2000 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
2001 return video_id
, self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2003 self
.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id
, video_id
))
2004 return video_id
, None
2007 def _real_extract(self
, url
):
2008 # Extract playlist id
2009 mobj
= re
.match(self
._VALID
_URL
, url
)
2011 raise ExtractorError('Invalid URL: %s' % url
)
2012 playlist_id
= mobj
.group(1) or mobj
.group(2)
2014 video_id
, video
= self
._check
_download
_just
_video
(url
, playlist_id
)
2018 if playlist_id
.startswith(('RD', 'UL', 'PU')):
2019 # Mixes require a custom extraction process
2020 return self
._extract
_mix
(playlist_id
)
2022 has_videos
, playlist
= self
._extract
_playlist
(playlist_id
)
2023 if has_videos
or not video_id
:
2026 # Some playlist URLs don't actually serve a playlist (see
2027 # https://github.com/rg3/youtube-dl/issues/10537).
2028 # Fallback to plain video extraction if there is a video id
2029 # along with playlist id.
2030 return self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2033 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor
):
2034 IE_DESC
= 'YouTube.com channels'
2035 _VALID_URL
= r
'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2036 _TEMPLATE_URL
= 'https://www.youtube.com/channel/%s/videos'
2037 _VIDEO_RE
= r
'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2038 IE_NAME
= 'youtube:channel'
2040 'note': 'paginated channel',
2041 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2042 'playlist_mincount': 91,
2044 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2045 'title': 'Uploads from lex will',
2048 'note': 'Age restricted channel',
2049 # from https://www.youtube.com/user/DeusExOfficial
2050 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2051 'playlist_mincount': 64,
2053 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2054 'title': 'Uploads from Deus Ex',
2059 def suitable(cls
, url
):
2060 return (False if YoutubePlaylistsIE
.suitable(url
) or YoutubeLiveIE
.suitable(url
)
2061 else super(YoutubeChannelIE
, cls
).suitable(url
))
2063 def _build_template_url(self
, url
, channel_id
):
2064 return self
._TEMPLATE
_URL
% channel_id
2066 def _real_extract(self
, url
):
2067 channel_id
= self
._match
_id
(url
)
2069 url
= self
._build
_template
_url
(url
, channel_id
)
2071 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2072 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2073 # otherwise fallback on channel by page extraction
2074 channel_page
= self
._download
_webpage
(
2075 url
+ '?view=57', channel_id
,
2076 'Downloading channel page', fatal
=False)
2077 if channel_page
is False:
2078 channel_playlist_id
= False
2080 channel_playlist_id
= self
._html
_search
_meta
(
2081 'channelId', channel_page
, 'channel id', default
=None)
2082 if not channel_playlist_id
:
2083 channel_url
= self
._html
_search
_meta
(
2084 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2085 channel_page
, 'channel url', default
=None)
2087 channel_playlist_id
= self
._search
_regex
(
2088 r
'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2089 channel_url
, 'channel id', default
=None)
2090 if channel_playlist_id
and channel_playlist_id
.startswith('UC'):
2091 playlist_id
= 'UU' + channel_playlist_id
[2:]
2092 return self
.url_result(
2093 compat_urlparse
.urljoin(url
, '/playlist?list=%s' % playlist_id
), 'YoutubePlaylist')
2095 channel_page
= self
._download
_webpage
(url
, channel_id
, 'Downloading page #1')
2096 autogenerated
= re
.search(r
'''(?x)
2098 channel-header-autogenerated-label|
2099 yt-channel-title-autogenerated
2100 )[^"]*"''', channel_page
) is not None
2103 # The videos are contained in a single page
2104 # the ajax pages can't be used, they are empty
2107 video_id
, 'Youtube', video_id
=video_id
,
2108 video_title
=video_title
)
2109 for video_id
, video_title
in self
.extract_videos_from_page(channel_page
)]
2110 return self
.playlist_result(entries
, channel_id
)
2113 next(self
._entries
(channel_page
, channel_id
))
2114 except StopIteration:
2115 alert_message
= self
._html
_search
_regex
(
2116 r
'(?s)<div[^>]+class=(["\']).*?
\byt
-alert
-message
\b.*?\
1[^
>]*>(?P
<alert
>[^
<]+)</div
>',
2117 channel_page, 'alert
', default=None, group='alert
')
2119 raise ExtractorError('Youtube said
: %s' % alert_message, expected=True)
2121 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2124 class YoutubeUserIE(YoutubeChannelIE):
2125 IE_DESC = 'YouTube
.com user
videos (URL
or "ytuser" keyword
)'
2126 _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_-]+)'
2127 _TEMPLATE_URL = 'https
://www
.youtube
.com
/%s/%s/videos
'
2128 IE_NAME = 'youtube
:user
'
2131 'url
': 'https
://www
.youtube
.com
/user
/TheLinuxFoundation
',
2132 'playlist_mincount
': 320,
2134 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ
',
2135 'title
': 'Uploads
from The Linux Foundation
',
2138 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2139 # but not https://www.youtube.com/user/12minuteathlete/videos
2140 'url
': 'https
://www
.youtube
.com
/c
/12minuteathlete
/videos
',
2141 'playlist_mincount
': 249,
2143 'id': 'UUVjM
-zV6_opMDx7WYxnjZiQ
',
2144 'title
': 'Uploads
from 12 Minute Athlete
',
2147 'url
': 'ytuser
:phihag
',
2148 'only_matching
': True,
2150 'url
': 'https
://www
.youtube
.com
/c
/gametrailers
',
2151 'only_matching
': True,
2153 'url
': 'https
://www
.youtube
.com
/gametrailers
',
2154 'only_matching
': True,
2156 # This channel is not available.
2157 'url
': 'https
://www
.youtube
.com
/user
/kananishinoSMEJ
/videos
',
2158 'only_matching
': True,
2162 def suitable(cls, url):
2163 # Don't
return True if the url can be extracted
with other youtube
2164 # extractor, the regex would is too permissive and it would match.
2165 other_yt_ies
= iter(klass
for (name
, klass
) in globals().items() if name
.startswith('Youtube') and name
.endswith('IE') and klass
is not cls
)
2166 if any(ie
.suitable(url
) for ie
in other_yt_ies
):
2169 return super(YoutubeUserIE
, cls
).suitable(url
)
2171 def _build_template_url(self
, url
, channel_id
):
2172 mobj
= re
.match(self
._VALID
_URL
, url
)
2173 return self
._TEMPLATE
_URL
% (mobj
.group('user') or 'user', mobj
.group('id'))
2176 class YoutubeLiveIE(YoutubeBaseInfoExtractor
):
2177 IE_DESC
= 'YouTube.com live streams'
2178 _VALID_URL
= r
'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2179 IE_NAME
= 'youtube:live'
2182 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2184 'id': 'a48o2S1cPoo',
2186 'title': 'The Young Turks - Live Main Show',
2187 'uploader': 'The Young Turks',
2188 'uploader_id': 'TheYoungTurks',
2189 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2190 'upload_date': '20150715',
2191 'license': 'Standard YouTube License',
2192 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2193 'categories': ['News & Politics'],
2194 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2196 'dislike_count': int,
2199 'skip_download': True,
2202 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2203 'only_matching': True,
2205 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2206 'only_matching': True,
2208 'url': 'https://www.youtube.com/TheYoungTurks/live',
2209 'only_matching': True,
2212 def _real_extract(self
, url
):
2213 mobj
= re
.match(self
._VALID
_URL
, url
)
2214 channel_id
= mobj
.group('id')
2215 base_url
= mobj
.group('base_url')
2216 webpage
= self
._download
_webpage
(url
, channel_id
, fatal
=False)
2218 page_type
= self
._og
_search
_property
(
2219 'type', webpage
, 'page type', default
=None)
2220 video_id
= self
._html
_search
_meta
(
2221 'videoId', webpage
, 'video id', default
=None)
2222 if page_type
== 'video' and video_id
and re
.match(r
'^[0-9A-Za-z_-]{11}$', video_id
):
2223 return self
.url_result(video_id
, YoutubeIE
.ie_key())
2224 return self
.url_result(base_url
)
2227 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor
):
2228 IE_DESC
= 'YouTube.com user/channel playlists'
2229 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2230 IE_NAME
= 'youtube:playlists'
2233 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2234 'playlist_mincount': 4,
2236 'id': 'ThirstForScience',
2237 'title': 'Thirst for Science',
2240 # with "Load more" button
2241 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2242 'playlist_mincount': 70,
2245 'title': 'Игорь Клейнер',
2248 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2249 'playlist_mincount': 17,
2251 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2252 'title': 'Chem Player',
2257 class YoutubeSearchIE(SearchInfoExtractor
, YoutubePlaylistIE
):
2258 IE_DESC
= 'YouTube.com searches'
2259 # there doesn't appear to be a real limit, for example if you search for
2260 # 'python' you get more than 8.000.000 results
2261 _MAX_RESULTS
= float('inf')
2262 IE_NAME
= 'youtube:search'
2263 _SEARCH_KEY
= 'ytsearch'
2264 _EXTRA_QUERY_ARGS
= {}
2267 def _get_n_results(self
, query
, n
):
2268 """Get a specified number of results for a query"""
2273 for pagenum
in itertools
.count(1):
2275 'search_query': query
.encode('utf-8'),
2279 url_query
.update(self
._EXTRA
_QUERY
_ARGS
)
2280 result_url
= 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query
)
2281 data
= self
._download
_json
(
2282 result_url
, video_id
='query "%s"' % query
,
2283 note
='Downloading page %s' % pagenum
,
2284 errnote
='Unable to download API page')
2285 html_content
= data
[1]['body']['content']
2287 if 'class="search-message' in html_content
:
2288 raise ExtractorError(
2289 '[youtube] No video results', expected
=True)
2291 new_videos
= self
._ids
_to
_results
(orderedSet(re
.findall(
2292 r
'href="/watch\?v=(.{11})', html_content
)))
2293 videos
+= new_videos
2294 if not new_videos
or len(videos
) > limit
:
2299 return self
.playlist_result(videos
, query
)
2302 class YoutubeSearchDateIE(YoutubeSearchIE
):
2303 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
2304 _SEARCH_KEY
= 'ytsearchdate'
2305 IE_DESC
= 'YouTube.com searches, newest videos first'
2306 _EXTRA_QUERY_ARGS
= {'search_sort': 'video_date_uploaded'}
2309 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor
):
2310 IE_DESC
= 'YouTube.com search URLs'
2311 IE_NAME
= 'youtube:search_url'
2312 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2313 _VIDEO_RE
= r
'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2315 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2316 'playlist_mincount': 5,
2318 'title': 'youtube-dl test video',
2321 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2322 'only_matching': True,
2325 def _real_extract(self
, url
):
2326 mobj
= re
.match(self
._VALID
_URL
, url
)
2327 query
= compat_urllib_parse_unquote_plus(mobj
.group('query'))
2328 webpage
= self
._download
_webpage
(url
, query
)
2329 return self
.playlist_result(self
._process
_page
(webpage
), playlist_title
=query
)
2332 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor
):
2333 IE_DESC
= 'YouTube.com (multi-season) shows'
2334 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2335 IE_NAME
= 'youtube:show'
2337 'url': 'https://www.youtube.com/show/airdisasters',
2338 'playlist_mincount': 5,
2340 'id': 'airdisasters',
2341 'title': 'Air Disasters',
2345 def _real_extract(self
, url
):
2346 playlist_id
= self
._match
_id
(url
)
2347 return super(YoutubeShowIE
, self
)._real
_extract
(
2348 'https://www.youtube.com/show/%s/playlists' % playlist_id
)
2351 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor
):
2353 Base class for feed extractors
2354 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2356 _LOGIN_REQUIRED
= True
2360 return 'youtube:%s' % self
._FEED
_NAME
2362 def _real_initialize(self
):
2365 def _real_extract(self
, url
):
2366 page
= self
._download
_webpage
(
2367 'https://www.youtube.com/feed/%s' % self
._FEED
_NAME
, self
._PLAYLIST
_TITLE
)
2369 # The extraction process is the same as for playlists, but the regex
2370 # for the video ids doesn't contain an index
2372 more_widget_html
= content_html
= page
2373 for page_num
in itertools
.count(1):
2374 matches
= re
.findall(r
'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html
)
2376 # 'recommended' feed has infinite 'load more' and each new portion spins
2377 # the same videos in (sometimes) slightly different order, so we'll check
2378 # for unicity and break when portion has no new videos
2379 new_ids
= filter(lambda video_id
: video_id
not in ids
, orderedSet(matches
))
2385 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
2389 more
= self
._download
_json
(
2390 'https://youtube.com/%s' % mobj
.group('more'), self
._PLAYLIST
_TITLE
,
2391 'Downloading page #%s' % page_num
,
2392 transform_source
=uppercase_escape
)
2393 content_html
= more
['content_html']
2394 more_widget_html
= more
['load_more_widget_html']
2396 return self
.playlist_result(
2397 self
._ids
_to
_results
(ids
), playlist_title
=self
._PLAYLIST
_TITLE
)
2400 class YoutubeWatchLaterIE(YoutubePlaylistIE
):
2401 IE_NAME
= 'youtube:watchlater'
2402 IE_DESC
= 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2403 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2406 'url': 'https://www.youtube.com/playlist?list=WL',
2407 'only_matching': True,
2409 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2410 'only_matching': True,
2413 def _real_extract(self
, url
):
2414 _
, video
= self
._check
_download
_just
_video
(url
, 'WL')
2417 _
, playlist
= self
._extract
_playlist
('WL')
2421 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
2422 IE_NAME
= 'youtube:favorites'
2423 IE_DESC
= 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2424 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2425 _LOGIN_REQUIRED
= True
2427 def _real_extract(self
, url
):
2428 webpage
= self
._download
_webpage
('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2429 playlist_id
= self
._search
_regex
(r
'list=(.+?)["&]', webpage
, 'favourites playlist id')
2430 return self
.url_result(playlist_id
, 'YoutubePlaylist')
2433 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
2434 IE_DESC
= 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2435 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2436 _FEED_NAME
= 'recommended'
2437 _PLAYLIST_TITLE
= 'Youtube Recommended videos'
2440 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
2441 IE_DESC
= 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2442 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2443 _FEED_NAME
= 'subscriptions'
2444 _PLAYLIST_TITLE
= 'Youtube Subscriptions'
2447 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
2448 IE_DESC
= 'Youtube watch history, ":ythistory" for short (requires authentication)'
2449 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2450 _FEED_NAME
= 'history'
2451 _PLAYLIST_TITLE
= 'Youtube History'
2454 class YoutubeTruncatedURLIE(InfoExtractor
):
2455 IE_NAME
= 'youtube:truncated_url'
2456 IE_DESC
= False # Do not list
2457 _VALID_URL
= r
'''(?x)
2459 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2462 annotation_id=annotation_[^&]+|
2468 attribution_link\?a=[^&]+
2474 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2475 'only_matching': True,
2477 'url': 'https://www.youtube.com/watch?',
2478 'only_matching': True,
2480 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2481 'only_matching': True,
2483 'url': 'https://www.youtube.com/watch?feature=foo',
2484 'only_matching': True,
2486 'url': 'https://www.youtube.com/watch?hl=en-GB',
2487 'only_matching': True,
2489 'url': 'https://www.youtube.com/watch?t=2372',
2490 'only_matching': True,
2493 def _real_extract(self
, url
):
2494 raise ExtractorError(
2495 'Did you forget to quote the URL? Remember that & is a meta '
2496 'character in most shells, so you want to put the URL in quotes, '
2498 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2499 ' or simply youtube-dl BaW_jenozKc .',
2503 class YoutubeTruncatedIDIE(InfoExtractor
):
2504 IE_NAME
= 'youtube:truncated_id'
2505 IE_DESC
= False # Do not list
2506 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2509 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2510 'only_matching': True,
2513 def _real_extract(self
, url
):
2514 video_id
= self
._match
_id
(url
)
2515 raise ExtractorError(
2516 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id
, url
),