3 from __future__
import unicode_literals
14 from .common
import InfoExtractor
, SearchInfoExtractor
15 from ..jsinterp
import JSInterpreter
16 from ..swfinterp
import SWFInterpreter
17 from ..compat
import (
20 compat_urllib_parse_unquote
,
21 compat_urllib_parse_unquote_plus
,
22 compat_urllib_parse_urlencode
,
23 compat_urllib_parse_urlparse
,
32 get_element_by_attribute
,
53 class YoutubeBaseInfoExtractor(InfoExtractor
):
54 """Provide base functions for Youtube extractors"""
55 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
56 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
57 _PASSWORD_CHALLENGE_URL
= 'https://accounts.google.com/signin/challenge/sl/password'
58 _NETRC_MACHINE
= 'youtube'
59 # If True it will raise an error if no login info is provided
60 _LOGIN_REQUIRED
= False
62 _PLAYLIST_ID_RE
= r
'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}'
64 def _set_language(self
):
66 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
67 # YouTube sets the expire time to about two months
68 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
70 def _ids_to_results(self
, ids
):
72 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
77 Attempt to log in to YouTube.
78 True is returned if successful or skipped.
79 False is returned if login failed.
81 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
83 (username
, password
) = self
._get
_login
_info
()
84 # No authentication to be performed
86 if self
._LOGIN
_REQUIRED
:
87 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
90 login_page
= self
._download
_webpage
(
91 self
._LOGIN
_URL
, None,
92 note
='Downloading login page',
93 errnote
='unable to fetch login page', fatal
=False)
94 if login_page
is False:
97 login_form
= self
._hidden
_inputs
(login_page
)
100 'checkConnection': 'youtube',
105 login_results
= self
._download
_webpage
(
106 self
._PASSWORD
_CHALLENGE
_URL
, None,
107 note
='Logging in', errnote
='unable to log in', fatal
=False,
108 data
=urlencode_postdata(login_form
))
109 if login_results
is False:
112 error_msg
= self
._html
_search
_regex
(
113 r
'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
114 login_results
, 'error message', default
=None)
116 raise ExtractorError('Unable to login: %s' % error_msg
, expected
=True)
118 if re
.search(r
'id="errormsg_0_Passwd"', login_results
) is not None:
119 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected
=True)
122 # TODO add SMS and phone call support - these require making a request and then prompting the user
124 if re
.search(r
'(?i)<form[^>]+id="challenge"', login_results
) is not None:
125 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
128 self
._downloader
.report_warning(
129 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
130 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
133 tfa_code
= remove_start(tfa_code
, 'G-')
135 tfa_form_strs
= self
._form
_hidden
_inputs
('challenge', login_results
)
137 tfa_form_strs
.update({
142 tfa_data
= urlencode_postdata(tfa_form_strs
)
144 tfa_req
= sanitized_Request(self
._TWOFACTOR
_URL
, tfa_data
)
145 tfa_results
= self
._download
_webpage
(
147 note
='Submitting TFA code', errnote
='unable to submit tfa', fatal
=False)
149 if tfa_results
is False:
152 if re
.search(r
'(?i)<form[^>]+id="challenge"', tfa_results
) is not None:
153 self
._downloader
.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
155 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', tfa_results
) is not None:
156 self
._downloader
.report_warning('unable to log in - did the page structure change?')
158 if re
.search(r
'smsauth-interstitial-reviewsettings', tfa_results
) is not None:
159 self
._downloader
.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
162 if re
.search(r
'(?i)<form[^>]+id="gaia_loginform"', login_results
) is not None:
163 self
._downloader
.report_warning('unable to log in: bad username or password')
167 def _real_initialize(self
):
168 if self
._downloader
is None:
171 if not self
._login
():
175 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
176 # Extract entries from page with "Load more" button
177 def _entries(self
, page
, playlist_id
):
178 more_widget_html
= content_html
= page
179 for page_num
in itertools
.count(1):
180 for entry
in self
._process
_page
(content_html
):
183 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
187 more
= self
._download
_json
(
188 'https://youtube.com/%s' % mobj
.group('more'), playlist_id
,
189 'Downloading page #%s' % page_num
,
190 transform_source
=uppercase_escape
)
191 content_html
= more
['content_html']
192 if not content_html
.strip():
193 # Some webpages show a "Load more" button but they don't
196 more_widget_html
= more
['load_more_widget_html']
199 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
200 def _process_page(self
, content
):
201 for video_id
, video_title
in self
.extract_videos_from_page(content
):
202 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
204 def extract_videos_from_page(self
, page
):
207 for mobj
in re
.finditer(self
._VIDEO
_RE
, page
):
208 # The link with index 0 is not the first video of the playlist (not sure if still actual)
209 if 'index' in mobj
.groupdict() and mobj
.group('id') == '0':
211 video_id
= mobj
.group('id')
212 video_title
= unescapeHTML(mobj
.group('title'))
214 video_title
= video_title
.strip()
216 idx
= ids_in_page
.index(video_id
)
217 if video_title
and not titles_in_page
[idx
]:
218 titles_in_page
[idx
] = video_title
220 ids_in_page
.append(video_id
)
221 titles_in_page
.append(video_title
)
222 return zip(ids_in_page
, titles_in_page
)
225 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
226 def _process_page(self
, content
):
227 for playlist_id
in orderedSet(re
.findall(
228 r
'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
230 yield self
.url_result(
231 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
233 def _real_extract(self
, url
):
234 playlist_id
= self
._match
_id
(url
)
235 webpage
= self
._download
_webpage
(url
, playlist_id
)
236 title
= self
._og
_search
_title
(webpage
, fatal
=False)
237 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
240 class YoutubeIE(YoutubeBaseInfoExtractor
):
241 IE_DESC
= 'YouTube.com'
242 _VALID_URL
= r
"""(?x)^
244 (?:https?://|//) # http(s):// or protocol-independent URL
245 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
246 (?:www\.)?deturl\.com/www\.youtube\.com/|
247 (?:www\.)?pwnyoutube\.com/|
248 (?:www\.)?yourepeat\.com/|
249 tube\.majestyc\.net/|
250 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
251 (?:.*?\#/)? # handle anchor (#/) redirect urls
252 (?: # the various things that can precede the ID:
253 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
254 |(?: # or the v= param in all its forms
255 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
256 (?:\?|\#!?) # the params delimiter ? or # or #!
257 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
262 youtu\.be| # just youtu.be/xxxx
263 vid\.plus| # or vid.plus/xxxx
264 zwearz\.com/watch| # or zwearz.com/watch/xxxx
266 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
268 )? # all until now is optional -> you can pass the naked ID
269 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
272 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
273 WL # WL are handled by the watch later IE
276 (?(1).+)? # if we found the ID, everything can follow
277 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
278 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
280 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
281 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
282 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
283 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
284 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
285 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
286 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
287 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
288 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
289 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
290 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
291 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
292 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
293 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
294 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
295 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
296 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
297 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
301 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
302 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
303 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
304 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
305 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
306 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
307 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
309 # Apple HTTP Live Streaming
310 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
311 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
312 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
313 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
314 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
315 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
316 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
317 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
320 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
321 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
322 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
323 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
324 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
325 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
326 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
327 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
328 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
329 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
330 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
331 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
334 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
335 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
336 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
337 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
338 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
339 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
340 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
343 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
344 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
345 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
346 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
347 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
348 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
349 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
350 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
351 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
352 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
353 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
354 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
355 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
356 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
357 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
358 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
359 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
360 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
361 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
362 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
363 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
364 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
367 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
368 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
370 # Dash webm audio with opus inside
371 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
372 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
373 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
376 '_rtmp': {'protocol': 'rtmp'}
,
378 _SUBTITLE_FORMATS
= ('ttml', 'vtt')
385 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
389 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
390 'uploader': 'Philipp Hagemeister',
391 'uploader_id': 'phihag',
392 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
393 'upload_date': '20121002',
394 'license': 'Standard YouTube License',
395 'description': 'test chars: "\'/\\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 .',
396 'categories': ['Science & Technology'],
397 'tags': ['youtube-dl'],
400 'dislike_count': int,
406 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
407 'note': 'Test generic use_cipher_signature video (#897)',
411 'upload_date': '20120506',
412 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
413 'alt_title': 'I Love It (feat. Charli XCX)',
414 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
415 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
416 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
417 'iconic ep', 'iconic', 'love', 'it'],
419 'uploader': 'Icona Pop',
420 'uploader_id': 'IconaPop',
421 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IconaPop',
422 'license': 'Standard YouTube License',
423 'creator': 'Icona Pop',
427 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
428 'note': 'Test VEVO video with age protection (#956)',
432 'upload_date': '20130703',
433 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
434 'alt_title': 'Tunnel Vision',
435 'description': 'md5:64249768eec3bc4276236606ea996373',
437 'uploader': 'justintimberlakeVEVO',
438 'uploader_id': 'justintimberlakeVEVO',
439 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
440 'license': 'Standard YouTube License',
441 'creator': 'Justin Timberlake',
446 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
447 'note': 'Embed-only video (#1746)',
451 'upload_date': '20120608',
452 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
453 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
454 'uploader': 'SET India',
455 'uploader_id': 'setindia',
456 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
457 'license': 'Standard YouTube License',
462 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
463 'note': 'Use the first video ID in the URL',
467 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
468 'uploader': 'Philipp Hagemeister',
469 'uploader_id': 'phihag',
470 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
471 'upload_date': '20121002',
472 'license': 'Standard YouTube License',
473 'description': 'test chars: "\'/\\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 .',
474 'categories': ['Science & Technology'],
475 'tags': ['youtube-dl'],
478 'dislike_count': int,
481 'skip_download': True,
485 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
486 'note': '256k DASH audio (format 141) via DASH manifest',
490 'upload_date': '20121002',
491 'uploader_id': '8KVIDEO',
492 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
494 'uploader': '8KVIDEO',
495 'license': 'Standard YouTube License',
496 'title': 'UHDTV TEST 8K VIDEO.mp4'
499 'youtube_include_dash_manifest': True,
502 'skip': 'format 141 not served anymore',
504 # DASH manifest with encrypted signature
506 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
510 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
511 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
513 'uploader': 'AfrojackVEVO',
514 'uploader_id': 'AfrojackVEVO',
515 'upload_date': '20131011',
516 'license': 'Standard YouTube License',
519 'youtube_include_dash_manifest': True,
520 'format': '141/bestaudio[ext=m4a]',
523 # JS player signature function name containing $
525 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
529 'title': 'Taylor Swift - Shake It Off',
530 'alt_title': 'Shake It Off',
531 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
533 'uploader': 'TaylorSwiftVEVO',
534 'uploader_id': 'TaylorSwiftVEVO',
535 'upload_date': '20140818',
536 'license': 'Standard YouTube License',
537 'creator': 'Taylor Swift',
540 'youtube_include_dash_manifest': True,
541 'format': '141/bestaudio[ext=m4a]',
546 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
551 'upload_date': '20100909',
552 'uploader': 'The Amazing Atheist',
553 'uploader_id': 'TheAmazingAtheist',
554 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
555 'license': 'Standard YouTube License',
556 'title': 'Burning Everyone\'s Koran',
557 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
560 # Normal age-gate video (No vevo, embed allowed)
562 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
566 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
567 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
569 'uploader': 'The Witcher',
570 'uploader_id': 'WitcherGame',
571 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
572 'upload_date': '20140605',
573 'license': 'Standard YouTube License',
577 # Age-gate video with encrypted signature
579 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
583 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
584 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
586 'uploader': 'LloydVEVO',
587 'uploader_id': 'LloydVEVO',
588 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
589 'upload_date': '20110629',
590 'license': 'Standard YouTube License',
594 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
596 'url': '__2ABJjxzNo',
601 'upload_date': '20100430',
602 'uploader_id': 'deadmau5',
603 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
604 'creator': 'deadmau5',
605 'description': 'md5:12c56784b8032162bb936a5f76d55360',
606 'uploader': 'deadmau5',
607 'license': 'Standard YouTube License',
608 'title': 'Deadmau5 - Some Chords (HD)',
609 'alt_title': 'Some Chords',
611 'expected_warnings': [
612 'DASH manifest missing',
615 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
617 'url': 'lqQg6PlCWgI',
622 'upload_date': '20150827',
623 'uploader_id': 'olympic',
624 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
625 'license': 'Standard YouTube License',
626 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
627 'uploader': 'Olympic',
628 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
631 'skip_download': 'requires avconv',
636 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
640 'stretched_ratio': 16 / 9.,
642 'upload_date': '20110310',
643 'uploader_id': 'AllenMeow',
644 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
645 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
647 'license': 'Standard YouTube License',
648 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
651 # url_encoded_fmt_stream_map is empty string
653 'url': 'qEJwOuvDf7I',
657 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
659 'upload_date': '20150404',
660 'uploader_id': 'spbelect',
661 'uploader': 'Наблюдатели Петербурга',
664 'skip_download': 'requires avconv',
666 'skip': 'This live event has ended.',
668 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
670 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
674 'title': 'md5:7b81415841e02ecd4313668cde88737a',
675 'description': 'md5:116377fd2963b81ec4ce64b542173306',
677 'upload_date': '20150625',
678 'uploader_id': 'dorappi2000',
679 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
680 'uploader': 'dorappi2000',
681 'license': 'Standard YouTube License',
682 'formats': 'mincount:32',
685 # DASH manifest with segment_list
687 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
688 'md5': '8ce563a1d667b599d21064e982ab9e31',
692 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
693 'uploader': 'Airtek',
694 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
695 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
696 'license': 'Standard YouTube License',
697 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
700 'youtube_include_dash_manifest': True,
701 'format': '135', # bestvideo
703 'skip': 'This live event has ended.',
706 # Multifeed videos (multiple cameras), URL is for Main Camera
707 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
710 'title': 'teamPGP: Rocket League Noob Stream',
711 'description': 'md5:dc7872fb300e143831327f1bae3af010',
717 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
718 'description': 'md5:dc7872fb300e143831327f1bae3af010',
720 'upload_date': '20150721',
721 'uploader': 'Beer Games Beer',
722 'uploader_id': 'beergamesbeer',
723 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
724 'license': 'Standard YouTube License',
730 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
731 'description': 'md5:dc7872fb300e143831327f1bae3af010',
733 'upload_date': '20150721',
734 'uploader': 'Beer Games Beer',
735 'uploader_id': 'beergamesbeer',
736 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
737 'license': 'Standard YouTube License',
743 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
744 'description': 'md5:dc7872fb300e143831327f1bae3af010',
746 'upload_date': '20150721',
747 'uploader': 'Beer Games Beer',
748 'uploader_id': 'beergamesbeer',
749 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
750 'license': 'Standard YouTube License',
756 'title': 'teamPGP: Rocket League Noob Stream (zim)',
757 'description': 'md5:dc7872fb300e143831327f1bae3af010',
759 'upload_date': '20150721',
760 'uploader': 'Beer Games Beer',
761 'uploader_id': 'beergamesbeer',
762 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
763 'license': 'Standard YouTube License',
767 'skip_download': True,
771 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
772 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
775 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
778 'skip': 'Not multifeed anymore',
781 'url': 'https://vid.plus/FlRa-iH7PGw',
782 'only_matching': True,
785 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
786 'only_matching': True,
789 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
790 # Also tests cut-off URL expansion in video description (see
791 # https://github.com/rg3/youtube-dl/issues/1892,
792 # https://github.com/rg3/youtube-dl/issues/8164)
793 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
797 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
798 'alt_title': 'Dark Walk',
799 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
801 'upload_date': '20151119',
802 'uploader_id': 'IronSoulElf',
803 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
804 'uploader': 'IronSoulElf',
805 'license': 'Standard YouTube License',
806 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
809 'skip_download': True,
813 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
814 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
815 'only_matching': True,
818 # Video with yt:stretch=17:0
819 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
823 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
824 'description': 'md5:ee18a25c350637c8faff806845bddee9',
825 'upload_date': '20151107',
826 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
827 'uploader': 'CH GAMER DROID',
830 'skip_download': True,
832 'skip': 'This video does not exist.',
835 # Video licensed under Creative Commons
836 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
840 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
841 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
843 'upload_date': '20150127',
844 'uploader_id': 'BerkmanCenter',
845 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
846 'uploader': 'The Berkman Klein Center for Internet & Society',
847 'license': 'Creative Commons Attribution license (reuse allowed)',
850 'skip_download': True,
854 # Channel-like uploader_url
855 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
859 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
860 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
862 'upload_date': '20151119',
863 'uploader': 'Bernie 2016',
864 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
865 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
866 'license': 'Creative Commons Attribution license (reuse allowed)',
869 'skip_download': True,
873 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
874 'only_matching': True,
877 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
878 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
879 'only_matching': True,
882 # Rental video preview
883 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
887 'title': 'Piku - Trailer',
888 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
889 'upload_date': '20150811',
890 'uploader': 'FlixMatrix',
891 'uploader_id': 'FlixMatrixKaravan',
892 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
893 'license': 'Standard YouTube License',
896 'skip_download': True,
900 # YouTube Red video with episode data
901 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
905 'title': 'Isolation - Mind Field (Ep 1)',
906 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
908 'upload_date': '20170118',
909 'uploader': 'Vsauce',
910 'uploader_id': 'Vsauce',
911 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
912 'license': 'Standard YouTube License',
913 'series': 'Mind Field',
918 'skip_download': True,
920 'expected_warnings': [
921 'Skipping DASH manifest',
926 'url': '1t24XAntNCY',
927 'only_matching': True,
930 # geo restricted to JP
931 'url': 'sJL6WA-aGkQ',
932 'only_matching': True,
935 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
936 'only_matching': True,
940 def __init__(self
, *args
, **kwargs
):
941 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
942 self
._player
_cache
= {}
944 def report_video_info_webpage_download(self
, video_id
):
945 """Report attempt to download video info webpage."""
946 self
.to_screen('%s: Downloading video info webpage' % video_id
)
948 def report_information_extraction(self
, video_id
):
949 """Report attempt to extract video information."""
950 self
.to_screen('%s: Extracting video information' % video_id
)
952 def report_unavailable_format(self
, video_id
, format
):
953 """Report extracted video URL."""
954 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
956 def report_rtmp_download(self
):
957 """Indicate the download will use the RTMP protocol."""
958 self
.to_screen('RTMP download detected')
960 def _signature_cache_id(self
, example_sig
):
961 """ Return a string representation of a signature """
962 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
964 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
966 r
'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
969 raise ExtractorError('Cannot identify player %r' % player_url
)
970 player_type
= id_m
.group('ext')
971 player_id
= id_m
.group('id')
973 # Read from filesystem cache
974 func_id
= '%s_%s_%s' % (
975 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
976 assert os
.path
.basename(func_id
) == func_id
978 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
979 if cache_spec
is not None:
980 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
983 'Downloading player %s' % player_url
984 if self
._downloader
.params
.get('verbose') else
985 'Downloading %s player %s' % (player_type
, player_id
)
987 if player_type
== 'js':
988 code
= self
._download
_webpage
(
989 player_url
, video_id
,
991 errnote
='Download of %s failed' % player_url
)
992 res
= self
._parse
_sig
_js
(code
)
993 elif player_type
== 'swf':
994 urlh
= self
._request
_webpage
(
995 player_url
, video_id
,
997 errnote
='Download of %s failed' % player_url
)
999 res
= self
._parse
_sig
_swf
(code
)
1001 assert False, 'Invalid player type %r' % player_type
1003 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1004 cache_res
= res(test_string
)
1005 cache_spec
= [ord(c
) for c
in cache_res
]
1007 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1010 def _print_sig_code(self
, func
, example_sig
):
1011 def gen_sig_code(idxs
):
1012 def _genslice(start
, end
, step
):
1013 starts
= '' if start
== 0 else str(start
)
1014 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1015 steps
= '' if step
== 1 else (':%d' % step
)
1016 return 's[%s%s%s]' % (starts
, ends
, steps
)
1019 # Quelch pyflakes warnings - start will be set when step is set
1020 start
= '(Never used)'
1021 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1022 if step
is not None:
1023 if i
- prev
== step
:
1025 yield _genslice(start
, prev
, step
)
1028 if i
- prev
in [-1, 1]:
1033 yield 's[%d]' % prev
1037 yield _genslice(start
, i
, step
)
1039 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1040 cache_res
= func(test_string
)
1041 cache_spec
= [ord(c
) for c
in cache_res
]
1042 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1043 signature_id_tuple
= '(%s)' % (
1044 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1045 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1046 ' return %s\n') % (signature_id_tuple
, expr_code
)
1047 self
.to_screen('Extracted signature function:\n' + code
)
1049 def _parse_sig_js(self
, jscode
):
1050 funcname
= self
._search
_regex
(
1051 (r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1052 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1053 jscode, 'Initial JS player signature function name
', group='sig
')
1055 jsi = JSInterpreter(jscode)
1056 initial_function = jsi.extract_function(funcname)
1057 return lambda s: initial_function([s])
1059 def _parse_sig_swf(self, file_contents):
1060 swfi = SWFInterpreter(file_contents)
1061 TARGET_CLASSNAME = 'SignatureDecipher
'
1062 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1063 initial_function = swfi.extract_function(searched_class, 'decipher
')
1064 return lambda s: initial_function([s])
1066 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1067 """Turn the encrypted s field into a working signature"""
1069 if player_url is None:
1070 raise ExtractorError('Cannot decrypt signature without player_url
')
1072 if player_url.startswith('//'):
1073 player_url = 'https
:' + player_url
1074 elif not re.match(r'https?
://', player_url):
1075 player_url = compat_urlparse.urljoin(
1076 'https
://www
.youtube
.com
', player_url)
1078 player_id = (player_url, self._signature_cache_id(s))
1079 if player_id not in self._player_cache:
1080 func = self._extract_signature_function(
1081 video_id, player_url, s
1083 self._player_cache[player_id] = func
1084 func = self._player_cache[player_id]
1085 if self._downloader.params.get('youtube_print_sig_code
'):
1086 self._print_sig_code(func, s)
1088 except Exception as e:
1089 tb = traceback.format_exc()
1090 raise ExtractorError(
1091 'Signature extraction failed
: ' + tb, cause=e)
1093 def _get_subtitles(self, video_id, webpage):
1095 subs_doc = self._download_xml(
1096 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1097 video_id, note=False)
1098 except ExtractorError as err:
1099 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1103 for track in subs_doc.findall('track
'):
1104 lang = track.attrib['lang_code
']
1105 if lang in sub_lang_list:
1108 for ext in self._SUBTITLE_FORMATS:
1109 params = compat_urllib_parse_urlencode({
1113 'name
': track.attrib['name
'].encode('utf
-8'),
1115 sub_formats.append({
1116 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1119 sub_lang_list[lang] = sub_formats
1120 if not sub_lang_list:
1121 self._downloader.report_warning('video doesn
\'t have subtitles
')
1123 return sub_lang_list
1125 def _get_ytplayer_config(self, video_id, webpage):
1127 # User data may contain arbitrary character sequences that may affect
1128 # JSON extraction with regex, e.g. when '};' is contained the second
1129 # regex won't capture the whole JSON
. Yet working around by trying more
1130 # concrete regex first keeping in mind proper quoted string handling
1131 # to be implemented in future that will replace this workaround (see
1132 # https://github.com/rg3/youtube-dl/issues/7468,
1133 # https://github.com/rg3/youtube-dl/pull/7599)
1134 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1135 r
';ytplayer\.config\s*=\s*({.+?});',
1137 config
= self
._search
_regex
(
1138 patterns
, webpage
, 'ytplayer.config', default
=None)
1140 return self
._parse
_json
(
1141 uppercase_escape(config
), video_id
, fatal
=False)
1143 def _get_automatic_captions(self
, video_id
, webpage
):
1144 """We need the webpage for getting the captions url, pass it as an
1145 argument to speed up the process."""
1146 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1147 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1148 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1149 if not player_config
:
1150 self
._downloader
.report_warning(err_msg
)
1153 args
= player_config
['args']
1154 caption_url
= args
.get('ttsurl')
1156 timestamp
= args
['timestamp']
1157 # We get the available subtitles
1158 list_params
= compat_urllib_parse_urlencode({
1163 list_url
= caption_url
+ '&' + list_params
1164 caption_list
= self
._download
_xml
(list_url
, video_id
)
1165 original_lang_node
= caption_list
.find('track')
1166 if original_lang_node
is None:
1167 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1169 original_lang
= original_lang_node
.attrib
['lang_code']
1170 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1173 for lang_node
in caption_list
.findall('target'):
1174 sub_lang
= lang_node
.attrib
['lang_code']
1176 for ext
in self
._SUBTITLE
_FORMATS
:
1177 params
= compat_urllib_parse_urlencode({
1178 'lang': original_lang
,
1182 'kind': caption_kind
,
1184 sub_formats
.append({
1185 'url': caption_url
+ '&' + params
,
1188 sub_lang_list
[sub_lang
] = sub_formats
1189 return sub_lang_list
1191 # Some videos don't provide ttsurl but rather caption_tracks and
1192 # caption_translation_languages (e.g. 20LmZk1hakA)
1193 caption_tracks
= args
['caption_tracks']
1194 caption_translation_languages
= args
['caption_translation_languages']
1195 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1196 parsed_caption_url
= compat_urllib_parse_urlparse(caption_url
)
1197 caption_qs
= compat_parse_qs(parsed_caption_url
.query
)
1200 for lang
in caption_translation_languages
.split(','):
1201 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1202 sub_lang
= lang_qs
.get('lc', [None])[0]
1206 for ext
in self
._SUBTITLE
_FORMATS
:
1208 'tlang': [sub_lang
],
1211 sub_url
= compat_urlparse
.urlunparse(parsed_caption_url
._replace
(
1212 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1213 sub_formats
.append({
1217 sub_lang_list
[sub_lang
] = sub_formats
1218 return sub_lang_list
1219 # An extractor error can be raise by the download process if there are
1220 # no automatic captions but there are subtitles
1221 except (KeyError, ExtractorError
):
1222 self
._downloader
.report_warning(err_msg
)
1225 def _mark_watched(self
, video_id
, video_info
):
1226 playback_url
= video_info
.get('videostats_playback_base_url', [None])[0]
1227 if not playback_url
:
1229 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1230 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1232 # cpn generation algorithm is reverse engineered from base.js.
1233 # In fact it works even with dummy cpn.
1234 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1235 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1241 playback_url
= compat_urlparse
.urlunparse(
1242 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1244 self
._download
_webpage
(
1245 playback_url
, video_id
, 'Marking watched',
1246 'Unable to mark watched', fatal
=False)
1249 def extract_id(cls
, url
):
1250 mobj
= re
.match(cls
._VALID
_URL
, url
, re
.VERBOSE
)
1252 raise ExtractorError('Invalid URL: %s' % url
)
1253 video_id
= mobj
.group(2)
1256 def _extract_annotations(self
, video_id
):
1257 url
= 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1258 return self
._download
_webpage
(url
, video_id
, note
='Searching for annotations.', errnote
='Unable to download video annotations.')
1260 def _real_extract(self
, url
):
1261 url
, smuggled_data
= unsmuggle_url(url
, {})
1264 'http' if self
._downloader
.params
.get('prefer_insecure', False)
1269 parsed_url
= compat_urllib_parse_urlparse(url
)
1270 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
1271 query
= compat_parse_qs(component
)
1272 if start_time
is None and 't' in query
:
1273 start_time
= parse_duration(query
['t'][0])
1274 if start_time
is None and 'start' in query
:
1275 start_time
= parse_duration(query
['start'][0])
1276 if end_time
is None and 'end' in query
:
1277 end_time
= parse_duration(query
['end'][0])
1279 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1280 mobj
= re
.search(self
._NEXT
_URL
_RE
, url
)
1282 url
= proto
+ '://www.youtube.com/' + compat_urllib_parse_unquote(mobj
.group(1)).lstrip('/')
1283 video_id
= self
.extract_id(url
)
1286 url
= proto
+ '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1287 video_webpage
= self
._download
_webpage
(url
, video_id
)
1289 # Attempt to extract SWF player URL
1290 mobj
= re
.search(r
'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage
)
1291 if mobj
is not None:
1292 player_url
= re
.sub(r
'\\(.)', r
'\1', mobj
.group(1))
1298 def add_dash_mpd(video_info
):
1299 dash_mpd
= video_info
.get('dashmpd')
1300 if dash_mpd
and dash_mpd
[0] not in dash_mpds
:
1301 dash_mpds
.append(dash_mpd
[0])
1304 embed_webpage
= None
1306 if re
.search(r
'player-age-gate-content">', video_webpage
) is not None:
1308 # We simulate the access to the video from www.youtube.com/v/{video_id}
1309 # this can be viewed without login into Youtube
1310 url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1311 embed_webpage
= self
._download
_webpage
(url
, video_id
, 'Downloading embed webpage')
1312 data
= compat_urllib_parse_urlencode({
1313 'video_id': video_id
,
1314 'eurl': 'https://youtube.googleapis.com/v/' + video_id
,
1315 'sts': self
._search
_regex
(
1316 r
'"sts"\s*:\s*(\d+)', embed_webpage
, 'sts', default
=''),
1318 video_info_url
= proto
+ '://www.youtube.com/get_video_info?' + data
1319 video_info_webpage
= self
._download
_webpage
(
1320 video_info_url
, video_id
,
1321 note
='Refetching age-gated info webpage',
1322 errnote
='unable to download video info webpage')
1323 video_info
= compat_parse_qs(video_info_webpage
)
1324 add_dash_mpd(video_info
)
1328 # Try looking directly into the video webpage
1329 ytplayer_config
= self
._get
_ytplayer
_config
(video_id
, video_webpage
)
1331 args
= ytplayer_config
['args']
1332 if args
.get('url_encoded_fmt_stream_map'):
1333 # Convert to the same format returned by compat_parse_qs
1334 video_info
= dict((k
, [v
]) for k
, v
in args
.items())
1335 add_dash_mpd(video_info
)
1336 # Rental video is not rented but preview is available (e.g.
1337 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1338 # https://github.com/rg3/youtube-dl/issues/10532)
1339 if not video_info
and args
.get('ypc_vid'):
1340 return self
.url_result(
1341 args
['ypc_vid'], YoutubeIE
.ie_key(), video_id
=args
['ypc_vid'])
1342 if args
.get('livestream') == '1' or args
.get('live_playback') == 1:
1344 if not video_info
or self
._downloader
.params
.get('youtube_include_dash_manifest', True):
1345 # We also try looking in get_video_info since it may contain different dashmpd
1346 # URL that points to a DASH manifest with possibly different itag set (some itags
1347 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1348 # manifest pointed by get_video_info's dashmpd).
1349 # The general idea is to take a union of itags of both DASH manifests (for example
1350 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1351 self
.report_video_info_webpage_download(video_id
)
1352 for el_type
in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1354 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1355 % (proto
, video_id
, el_type
))
1356 video_info_webpage
= self
._download
_webpage
(
1358 video_id
, note
=False,
1359 errnote
='unable to download video info webpage')
1360 get_video_info
= compat_parse_qs(video_info_webpage
)
1361 if get_video_info
.get('use_cipher_signature') != ['True']:
1362 add_dash_mpd(get_video_info
)
1364 video_info
= get_video_info
1365 if 'token' in get_video_info
:
1366 # Different get_video_info requests may report different results, e.g.
1367 # some may report video unavailability, but some may serve it without
1368 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1369 # the original webpage as well as el=info and el=embedded get_video_info
1370 # requests report video unavailability due to geo restriction while
1371 # el=detailpage succeeds and returns valid data). This is probably
1372 # due to YouTube measures against IP ranges of hosting providers.
1373 # Working around by preferring the first succeeded video_info containing
1374 # the token if no such video_info yet was found.
1375 if 'token' not in video_info
:
1376 video_info
= get_video_info
1378 if 'token' not in video_info
:
1379 if 'reason' in video_info
:
1380 if 'The uploader has not made this video available in your country.' in video_info
['reason']:
1381 regions_allowed
= self
._html
_search
_meta
(
1382 'regionsAllowed', video_webpage
, default
=None)
1383 countries
= regions_allowed
.split(',') if regions_allowed
else None
1384 self
.raise_geo_restricted(
1385 msg
=video_info
['reason'][0], countries
=countries
)
1386 raise ExtractorError(
1387 'YouTube said: %s' % video_info
['reason'][0],
1388 expected
=True, video_id
=video_id
)
1390 raise ExtractorError(
1391 '"token" parameter not in video info for unknown reason',
1395 if 'title' in video_info
:
1396 video_title
= video_info
['title'][0]
1398 self
._downloader
.report_warning('Unable to extract video title')
1402 video_description
= get_element_by_id("eow-description", video_webpage
)
1403 if video_description
:
1404 video_description
= re
.sub(r
'''(?x)
1406 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1407 (?:title|href)="([^"]+)"\s+
1408 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1412 ''', r
'\1', video_description
)
1413 video_description
= clean_html(video_description
)
1415 fd_mobj
= re
.search(r
'<meta name="description" content="([^"]+)"', video_webpage
)
1417 video_description
= unescapeHTML(fd_mobj
.group(1))
1419 video_description
= ''
1421 if 'multifeed_metadata_list' in video_info
and not smuggled_data
.get('force_singlefeed', False):
1422 if not self
._downloader
.params
.get('noplaylist'):
1425 multifeed_metadata_list
= video_info
['multifeed_metadata_list'][0]
1426 for feed
in multifeed_metadata_list
.split(','):
1427 # Unquote should take place before split on comma (,) since textual
1428 # fields may contain comma as well (see
1429 # https://github.com/rg3/youtube-dl/issues/8536)
1430 feed_data
= compat_parse_qs(compat_urllib_parse_unquote_plus(feed
))
1432 '_type': 'url_transparent',
1433 'ie_key': 'Youtube',
1435 '%s://www.youtube.com/watch?v=%s' % (proto
, feed_data
['id'][0]),
1436 {'force_singlefeed': True}
),
1437 'title': '%s (%s)' % (video_title
, feed_data
['title'][0]),
1439 feed_ids
.append(feed_data
['id'][0])
1441 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1442 % (', '.join(feed_ids
), video_id
))
1443 return self
.playlist_result(entries
, video_id
, video_title
, video_description
)
1444 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
1446 if 'view_count' in video_info
:
1447 view_count
= int(video_info
['view_count'][0])
1451 # Check for "rental" videos
1452 if 'ypc_video_rental_bar_text' in video_info
and 'author' not in video_info
:
1453 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected
=True)
1455 # Start extracting information
1456 self
.report_information_extraction(video_id
)
1459 if 'author' not in video_info
:
1460 raise ExtractorError('Unable to extract uploader name')
1461 video_uploader
= compat_urllib_parse_unquote_plus(video_info
['author'][0])
1464 video_uploader_id
= None
1465 video_uploader_url
= None
1467 r
'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1469 if mobj
is not None:
1470 video_uploader_id
= mobj
.group('uploader_id')
1471 video_uploader_url
= mobj
.group('uploader_url')
1473 self
._downloader
.report_warning('unable to extract uploader nickname')
1476 # We try first to get a high quality image:
1477 m_thumb
= re
.search(r
'<span itemprop="thumbnail".*?href="(.*?)">',
1478 video_webpage
, re
.DOTALL
)
1479 if m_thumb
is not None:
1480 video_thumbnail
= m_thumb
.group(1)
1481 elif 'thumbnail_url' not in video_info
:
1482 self
._downloader
.report_warning('unable to extract video thumbnail')
1483 video_thumbnail
= None
1484 else: # don't panic if we can't find it
1485 video_thumbnail
= compat_urllib_parse_unquote_plus(video_info
['thumbnail_url'][0])
1488 upload_date
= self
._html
_search
_meta
(
1489 'datePublished', video_webpage
, 'upload date', default
=None)
1491 upload_date
= self
._search
_regex
(
1492 [r
'(?s)id="eow-date.*?>(.*?)</span>',
1493 r
'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1494 video_webpage
, 'upload date', default
=None)
1496 upload_date
= ' '.join(re
.sub(r
'[/,-]', r
' ', mobj
.group(1)).split())
1497 upload_date
= unified_strdate(upload_date
)
1499 video_license
= self
._html
_search
_regex
(
1500 r
'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1501 video_webpage
, 'license', default
=None)
1503 m_music
= re
.search(
1504 r
'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1507 video_alt_title
= remove_quotes(unescapeHTML(m_music
.group('title')))
1508 video_creator
= clean_html(m_music
.group('creator'))
1510 video_alt_title
= video_creator
= None
1512 m_episode
= re
.search(
1513 r
'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1516 series
= m_episode
.group('series')
1517 season_number
= int(m_episode
.group('season'))
1518 episode_number
= int(m_episode
.group('episode'))
1520 series
= season_number
= episode_number
= None
1522 m_cat_container
= self
._search
_regex
(
1523 r
'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1524 video_webpage
, 'categories', default
=None)
1526 category
= self
._html
_search
_regex
(
1527 r
'(?s)<a[^<]+>(.*?)</a>', m_cat_container
, 'category',
1529 video_categories
= None if category
is None else [category
]
1531 video_categories
= None
1534 unescapeHTML(m
.group('content'))
1535 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), video_webpage
)]
1537 def _extract_count(count_name
):
1538 return str_to_int(self
._search
_regex
(
1539 r
'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1540 % re
.escape(count_name
),
1541 video_webpage
, count_name
, default
=None))
1543 like_count
= _extract_count('like')
1544 dislike_count
= _extract_count('dislike')
1547 video_subtitles
= self
.extract_subtitles(video_id
, video_webpage
)
1548 automatic_captions
= self
.extract_automatic_captions(video_id
, video_webpage
)
1550 video_duration
= try_get(
1551 video_info
, lambda x
: int_or_none(x
['length_seconds'][0]))
1552 if not video_duration
:
1553 video_duration
= parse_duration(self
._html
_search
_meta
(
1554 'duration', video_webpage
, 'video duration'))
1557 video_annotations
= None
1558 if self
._downloader
.params
.get('writeannotations', False):
1559 video_annotations
= self
._extract
_annotations
(video_id
)
1561 if 'conn' in video_info
and video_info
['conn'][0].startswith('rtmp'):
1562 self
.report_rtmp_download()
1564 'format_id': '_rtmp',
1566 'url': video_info
['conn'][0],
1567 'player_url': player_url
,
1569 elif len(video_info
.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info
.get('adaptive_fmts', [''])[0]) >= 1:
1570 encoded_url_map
= video_info
.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info
.get('adaptive_fmts', [''])[0]
1571 if 'rtmpe%3Dyes' in encoded_url_map
:
1572 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected
=True)
1574 fmt_list
= video_info
.get('fmt_list', [''])[0]
1576 for fmt
in fmt_list
.split(','):
1577 spec
= fmt
.split('/')
1579 width_height
= spec
[1].split('x')
1580 if len(width_height
) == 2:
1581 formats_spec
[spec
[0]] = {
1582 'resolution': spec
[1],
1583 'width': int_or_none(width_height
[0]),
1584 'height': int_or_none(width_height
[1]),
1587 for url_data_str
in encoded_url_map
.split(','):
1588 url_data
= compat_parse_qs(url_data_str
)
1589 if 'itag' not in url_data
or 'url' not in url_data
:
1591 format_id
= url_data
['itag'][0]
1592 url
= url_data
['url'][0]
1594 if 'sig' in url_data
:
1595 url
+= '&signature=' + url_data
['sig'][0]
1596 elif 's' in url_data
:
1597 encrypted_sig
= url_data
['s'][0]
1598 ASSETS_RE
= r
'"assets":.+?"js":\s*("[^"]+")'
1600 jsplayer_url_json
= self
._search
_regex
(
1602 embed_webpage
if age_gate
else video_webpage
,
1603 'JS player URL (1)', default
=None)
1604 if not jsplayer_url_json
and not age_gate
:
1605 # We need the embed website after all
1606 if embed_webpage
is None:
1607 embed_url
= proto
+ '://www.youtube.com/embed/%s' % video_id
1608 embed_webpage
= self
._download
_webpage
(
1609 embed_url
, video_id
, 'Downloading embed webpage')
1610 jsplayer_url_json
= self
._search
_regex
(
1611 ASSETS_RE
, embed_webpage
, 'JS player URL')
1613 player_url
= json
.loads(jsplayer_url_json
)
1614 if player_url
is None:
1615 player_url_json
= self
._search
_regex
(
1616 r
'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1617 video_webpage
, 'age gate player URL')
1618 player_url
= json
.loads(player_url_json
)
1620 if self
._downloader
.params
.get('verbose'):
1621 if player_url
is None:
1622 player_version
= 'unknown'
1623 player_desc
= 'unknown'
1625 if player_url
.endswith('swf'):
1626 player_version
= self
._search
_regex
(
1627 r
'-(.+?)(?:/watch_as3)?\.swf$', player_url
,
1628 'flash player', fatal
=False)
1629 player_desc
= 'flash player %s' % player_version
1631 player_version
= self
._search
_regex
(
1632 [r
'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1633 r
'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
1635 'html5 player', fatal
=False)
1636 player_desc
= 'html5 player %s' % player_version
1638 parts_sizes
= self
._signature
_cache
_id
(encrypted_sig
)
1639 self
.to_screen('{%s} signature length %s, %s' %
1640 (format_id
, parts_sizes
, player_desc
))
1642 signature
= self
._decrypt
_signature
(
1643 encrypted_sig
, video_id
, player_url
, age_gate
)
1644 url
+= '&signature=' + signature
1645 if 'ratebypass' not in url
:
1646 url
+= '&ratebypass=yes'
1649 'format_id': format_id
,
1651 'player_url': player_url
,
1653 if format_id
in self
._formats
:
1654 dct
.update(self
._formats
[format_id
])
1655 if format_id
in formats_spec
:
1656 dct
.update(formats_spec
[format_id
])
1658 # Some itags are not included in DASH manifest thus corresponding formats will
1659 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1660 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1661 mobj
= re
.search(r
'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data
.get('size', [''])[0])
1662 width
, height
= (int(mobj
.group('width')), int(mobj
.group('height'))) if mobj
else (None, None)
1665 'filesize': int_or_none(url_data
.get('clen', [None])[0]),
1666 'tbr': float_or_none(url_data
.get('bitrate', [None])[0], 1000),
1669 'fps': int_or_none(url_data
.get('fps', [None])[0]),
1670 'format_note': url_data
.get('quality_label', [None])[0] or url_data
.get('quality', [None])[0],
1672 for key
, value
in more_fields
.items():
1675 type_
= url_data
.get('type', [None])[0]
1677 type_split
= type_
.split(';')
1678 kind_ext
= type_split
[0].split('/')
1679 if len(kind_ext
) == 2:
1681 dct
['ext'] = mimetype2ext(type_split
[0])
1682 if kind
in ('audio', 'video'):
1684 for mobj
in re
.finditer(
1685 r
'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
1686 if mobj.group('key
') == 'codecs
':
1687 codecs = mobj.group('val
')
1690 dct.update(parse_codecs(codecs))
1692 elif video_info.get('hlsvp
'):
1693 manifest_url = video_info['hlsvp
'][0]
1695 m3u8_formats = self._extract_m3u8_formats(
1696 manifest_url, video_id, 'mp4
', fatal=False)
1697 for a_format in m3u8_formats:
1698 itag = self._search_regex(
1699 r'/itag
/(\d
+)/', a_format['url
'], 'itag
', default=None)
1701 a_format['format_id
'] = itag
1702 if itag in self._formats:
1703 dct = self._formats[itag].copy()
1704 dct.update(a_format)
1706 a_format['player_url
'] = player_url
1707 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1708 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
1709 formats.append(a_format)
1711 unavailable_message = self._html_search_regex(
1712 r'(?s
)<h1
[^
>]+id="unavailable-message"[^
>]*>(.+?
)</h1
>',
1713 video_webpage, 'unavailable message
', default=None)
1714 if unavailable_message:
1715 raise ExtractorError(unavailable_message, expected=True)
1716 raise ExtractorError('no conn
, hlsvp
or url_encoded_fmt_stream_map information found
in video info
')
1718 # Look for the DASH manifest
1719 if self._downloader.params.get('youtube_include_dash_manifest
', True):
1720 dash_mpd_fatal = True
1721 for mpd_url in dash_mpds:
1724 def decrypt_sig(mobj):
1726 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1727 return '/signature
/%s' % dec_s
1729 mpd_url = re.sub(r'/s
/([a
-fA
-F0
-9\
.]+)', decrypt_sig, mpd_url)
1731 for df in self._extract_mpd_formats(
1732 mpd_url, video_id, fatal=dash_mpd_fatal,
1733 formats_dict=self._formats):
1734 # Do not overwrite DASH format found in some previous DASH manifest
1735 if df['format_id
'] not in dash_formats:
1736 dash_formats[df['format_id
']] = df
1737 # Additional DASH manifests may end up in HTTP Error 403 therefore
1738 # allow them to fail without bug report message if we already have
1739 # some DASH manifest succeeded. This is temporary workaround to reduce
1740 # burst of bug reports until we figure out the reason and whether it
1741 # can be fixed at all.
1742 dash_mpd_fatal = False
1743 except (ExtractorError, KeyError) as e:
1744 self.report_warning(
1745 'Skipping DASH manifest
: %r' % e, video_id)
1747 # Remove the formats we found through non-DASH, they
1748 # contain less info and it can be wrong, because we use
1749 # fixed values (for example the resolution). See
1750 # https://github.com/rg3/youtube-dl/issues/5774 for an
1752 formats = [f for f in formats if f['format_id
'] not in dash_formats.keys()]
1753 formats.extend(dash_formats.values())
1755 # Check for malformed aspect ratio
1756 stretched_m = re.search(
1757 r'<meta\s
+property="og:video:tag".*?content
="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1760 w = float(stretched_m.group('w
'))
1761 h = float(stretched_m.group('h
'))
1762 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1763 # We will only process correct ratios.
1767 if f.get('vcodec
') != 'none
':
1768 f['stretched_ratio
'] = ratio
1770 self._sort_formats(formats)
1772 self.mark_watched(video_id, video_info)
1776 'uploader
': video_uploader,
1777 'uploader_id
': video_uploader_id,
1778 'uploader_url
': video_uploader_url,
1779 'upload_date
': upload_date,
1780 'license
': video_license,
1781 'creator
': video_creator,
1782 'title
': video_title,
1783 'alt_title
': video_alt_title,
1784 'thumbnail
': video_thumbnail,
1785 'description
': video_description,
1786 'categories
': video_categories,
1788 'subtitles
': video_subtitles,
1789 'automatic_captions
': automatic_captions,
1790 'duration
': video_duration,
1791 'age_limit
': 18 if age_gate else 0,
1792 'annotations
': video_annotations,
1793 'webpage_url
': proto + '://www
.youtube
.com
/watch?v
=%s' % video_id,
1794 'view_count
': view_count,
1795 'like_count
': like_count,
1796 'dislike_count
': dislike_count,
1797 'average_rating
': float_or_none(video_info.get('avg_rating
', [None])[0]),
1800 'start_time
': start_time,
1801 'end_time
': end_time,
1803 'season_number
': season_number,
1804 'episode_number
': episode_number,
1808 class YoutubeSharedVideoIE(InfoExtractor):
1809 _VALID_URL = r'(?
:https?
:)?
//(?
:www\
.)?youtube\
.com
/shared
\?.*\bci
=(?P
<id>[0-9A
-Za
-z_
-]{11}
)'
1810 IE_NAME = 'youtube
:shared
'
1813 'url
': 'https
://www
.youtube
.com
/shared?ci
=1nEzmT
-M4fU
',
1815 'id': 'uPDB5I9wfp8
',
1817 'title
': 'Pocoyo
: 90 minutos de episódios completos Português para crianç
as - PARTE
3',
1818 'description
': 'md5
:d9e4d9346a2dfff4c7dc4c8cec0f546d
',
1819 'upload_date
': '20160219',
1820 'uploader
': 'Pocoyo
- Portuguê
s (BR
)',
1821 'uploader_id
': 'PocoyoBrazil
',
1823 'add_ie
': ['Youtube
'],
1825 # There are already too many Youtube downloads
1826 'skip_download
': True,
1830 def _real_extract(self, url):
1831 video_id = self._match_id(url)
1833 webpage = self._download_webpage(url, video_id)
1835 real_video_id = self._html_search_meta(
1836 'videoId
', webpage, 'YouTube video
id', fatal=True)
1838 return self.url_result(real_video_id, YoutubeIE.ie_key())
1841 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1842 IE_DESC = 'YouTube
.com playlists
'
1843 _VALID_URL = r"""(?x)(?:
1849 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
1850 \? (?:.*?[&;])*? (?:p|a|list)=
1853 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1856 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
1857 # Top tracks, they can also include dots
1863 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
1864 _TEMPLATE_URL = 'https
://www
.youtube
.com
/playlist?
list=%s&disable_polymer
=true
'
1865 _VIDEO_RE = r'href
="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index
=(?P
<index
>\d
+)(?
:[^
>]+>(?P
<title
>[^
<]+))?
'
1866 IE_NAME = 'youtube
:playlist
'
1868 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1870 'title
': 'ytdl test PL
',
1871 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
',
1873 'playlist_count
': 3,
1875 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1877 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx
',
1878 'title
': 'YDL_Empty_List
',
1880 'playlist_count
': 0,
1881 'skip
': 'This playlist
is private
',
1883 'note
': 'Playlist
with deleted
videos (#651). As a bonus, the video #51 is also twice in this list.',
1884 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1886 'title': '29C3: Not my department',
1887 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1889 'playlist_count': 95,
1891 'note': 'issue #673',
1892 'url': 'PLBB231211A4F62143',
1894 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1895 'id': 'PLBB231211A4F62143',
1897 'playlist_mincount': 26,
1899 'note': 'Large playlist',
1900 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1902 'title': 'Uploads from Cauchemar',
1903 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1905 'playlist_mincount': 799,
1907 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1909 'title': 'YDL_safe_search',
1910 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1912 'playlist_count': 2,
1913 'skip': 'This playlist is private',
1916 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1917 'playlist_count': 4,
1920 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1923 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1924 'playlist_mincount': 485,
1926 'title': '2017 華語最新單曲 (2/24更新)',
1927 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1930 'note': 'Embedded SWF player',
1931 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1932 'playlist_count': 4,
1935 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1938 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1939 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1941 'title': 'Uploads from Interstellar Movie',
1942 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1944 'playlist_mincount': 21,
1946 # Playlist URL that does not actually serve a playlist
1947 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1949 'id': 'FqZTN594JQw',
1951 'title': "Smiley's People 01 detective, Adventure Series, Action",
1952 'uploader': 'STREEM',
1953 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1954 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1955 'upload_date': '20150526',
1956 'license': 'Standard YouTube License',
1957 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1958 'categories': ['People & Blogs'],
1961 'dislike_count': int,
1964 'skip_download': True,
1966 'add_ie': [YoutubeIE
.ie_key()],
1968 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1970 'id': 'yeWKywCrFtk',
1972 'title': 'Small Scale Baler and Braiding Rugs',
1973 'uploader': 'Backus-Page House Museum',
1974 'uploader_id': 'backuspagemuseum',
1975 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1976 'upload_date': '20161008',
1977 'license': 'Standard YouTube License',
1978 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1979 'categories': ['Nonprofits & Activism'],
1982 'dislike_count': int,
1986 'skip_download': True,
1989 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1990 'only_matching': True,
1992 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
1993 'only_matching': True,
1996 def _real_initialize(self
):
1999 def _extract_mix(self
, playlist_id
):
2000 # The mixes are generated from a single video
2001 # the id of the playlist is just 'RD' + video_id
2003 last_id
= playlist_id
[-11:]
2004 for n
in itertools
.count(1):
2005 url
= 'https://youtube.com/watch?v=%s&list=%s' % (last_id
, playlist_id
)
2006 webpage
= self
._download
_webpage
(
2007 url
, playlist_id
, 'Downloading page {0} of Youtube mix'.format(n
))
2008 new_ids
= orderedSet(re
.findall(
2009 r
'''(?xs)data-video-username=".*?".*?
2010 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re
.escape(playlist_id
),
2012 # Fetch new pages until all the videos are repeated, it seems that
2013 # there are always 51 unique videos.
2014 new_ids
= [_id
for _id
in new_ids
if _id
not in ids
]
2020 url_results
= self
._ids
_to
_results
(ids
)
2022 search_title
= lambda class_name
: get_element_by_attribute('class', class_name
, webpage
)
2024 search_title('playlist-title') or
2025 search_title('title long-title') or
2026 search_title('title'))
2027 title
= clean_html(title_span
)
2029 return self
.playlist_result(url_results
, playlist_id
, title
)
2031 def _extract_playlist(self
, playlist_id
):
2032 url
= self
._TEMPLATE
_URL
% playlist_id
2033 page
= self
._download
_webpage
(url
, playlist_id
)
2035 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2036 for match
in re
.findall(r
'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page
):
2037 match
= match
.strip()
2038 # Check if the playlist exists or is private
2039 mobj
= re
.match(r
'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match
)
2041 reason
= mobj
.group('reason')
2042 message
= 'This playlist %s' % reason
2043 if 'private' in reason
:
2044 message
+= ', use --username or --netrc to access it'
2046 raise ExtractorError(message
, expected
=True)
2047 elif re
.match(r
'[^<]*Invalid parameters[^<]*', match
):
2048 raise ExtractorError(
2049 'Invalid parameters. Maybe URL is incorrect.',
2051 elif re
.match(r
'[^<]*Choose your language[^<]*', match
):
2054 self
.report_warning('Youtube gives an alert message: ' + match
)
2056 playlist_title
= self
._html
_search
_regex
(
2057 r
'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2058 page
, 'title', default
=None)
2062 if not playlist_title
:
2064 # Some playlist URLs don't actually serve a playlist (e.g.
2065 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2066 next(self
._entries
(page
, playlist_id
))
2067 except StopIteration:
2070 return has_videos
, self
.playlist_result(
2071 self
._entries
(page
, playlist_id
), playlist_id
, playlist_title
)
2073 def _check_download_just_video(self
, url
, playlist_id
):
2074 # Check if it's a video-specific URL
2075 query_dict
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
2076 video_id
= query_dict
.get('v', [None])[0] or self
._search
_regex
(
2077 r
'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url
,
2078 'video id', default
=None)
2080 if self
._downloader
.params
.get('noplaylist'):
2081 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
2082 return video_id
, self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2084 self
.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id
, video_id
))
2085 return video_id
, None
2088 def _real_extract(self
, url
):
2089 # Extract playlist id
2090 mobj
= re
.match(self
._VALID
_URL
, url
)
2092 raise ExtractorError('Invalid URL: %s' % url
)
2093 playlist_id
= mobj
.group(1) or mobj
.group(2)
2095 video_id
, video
= self
._check
_download
_just
_video
(url
, playlist_id
)
2099 if playlist_id
.startswith(('RD', 'UL', 'PU')):
2100 # Mixes require a custom extraction process
2101 return self
._extract
_mix
(playlist_id
)
2103 has_videos
, playlist
= self
._extract
_playlist
(playlist_id
)
2104 if has_videos
or not video_id
:
2107 # Some playlist URLs don't actually serve a playlist (see
2108 # https://github.com/rg3/youtube-dl/issues/10537).
2109 # Fallback to plain video extraction if there is a video id
2110 # along with playlist id.
2111 return self
.url_result(video_id
, 'Youtube', video_id
=video_id
)
2114 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor
):
2115 IE_DESC
= 'YouTube.com channels'
2116 _VALID_URL
= r
'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2117 _TEMPLATE_URL
= 'https://www.youtube.com/channel/%s/videos'
2118 _VIDEO_RE
= r
'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2119 IE_NAME
= 'youtube:channel'
2121 'note': 'paginated channel',
2122 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2123 'playlist_mincount': 91,
2125 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2126 'title': 'Uploads from lex will',
2129 'note': 'Age restricted channel',
2130 # from https://www.youtube.com/user/DeusExOfficial
2131 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2132 'playlist_mincount': 64,
2134 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2135 'title': 'Uploads from Deus Ex',
2140 def suitable(cls
, url
):
2141 return (False if YoutubePlaylistsIE
.suitable(url
) or YoutubeLiveIE
.suitable(url
)
2142 else super(YoutubeChannelIE
, cls
).suitable(url
))
2144 def _build_template_url(self
, url
, channel_id
):
2145 return self
._TEMPLATE
_URL
% channel_id
2147 def _real_extract(self
, url
):
2148 channel_id
= self
._match
_id
(url
)
2150 url
= self
._build
_template
_url
(url
, channel_id
)
2152 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2153 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2154 # otherwise fallback on channel by page extraction
2155 channel_page
= self
._download
_webpage
(
2156 url
+ '?view=57', channel_id
,
2157 'Downloading channel page', fatal
=False)
2158 if channel_page
is False:
2159 channel_playlist_id
= False
2161 channel_playlist_id
= self
._html
_search
_meta
(
2162 'channelId', channel_page
, 'channel id', default
=None)
2163 if not channel_playlist_id
:
2164 channel_url
= self
._html
_search
_meta
(
2165 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2166 channel_page
, 'channel url', default
=None)
2168 channel_playlist_id
= self
._search
_regex
(
2169 r
'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2170 channel_url
, 'channel id', default
=None)
2171 if channel_playlist_id
and channel_playlist_id
.startswith('UC'):
2172 playlist_id
= 'UU' + channel_playlist_id
[2:]
2173 return self
.url_result(
2174 compat_urlparse
.urljoin(url
, '/playlist?list=%s' % playlist_id
), 'YoutubePlaylist')
2176 channel_page
= self
._download
_webpage
(url
, channel_id
, 'Downloading page #1')
2177 autogenerated
= re
.search(r
'''(?x)
2179 channel-header-autogenerated-label|
2180 yt-channel-title-autogenerated
2181 )[^"]*"''', channel_page
) is not None
2184 # The videos are contained in a single page
2185 # the ajax pages can't be used, they are empty
2188 video_id
, 'Youtube', video_id
=video_id
,
2189 video_title
=video_title
)
2190 for video_id
, video_title
in self
.extract_videos_from_page(channel_page
)]
2191 return self
.playlist_result(entries
, channel_id
)
2194 next(self
._entries
(channel_page
, channel_id
))
2195 except StopIteration:
2196 alert_message
= self
._html
_search
_regex
(
2197 r
'(?s)<div[^>]+class=(["\']).*?
\byt
-alert
-message
\b.*?\
1[^
>]*>(?P
<alert
>[^
<]+)</div
>',
2198 channel_page, 'alert
', default=None, group='alert
')
2200 raise ExtractorError('Youtube said
: %s' % alert_message, expected=True)
2202 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2205 class YoutubeUserIE(YoutubeChannelIE):
2206 IE_DESC = 'YouTube
.com user
videos (URL
or "ytuser" keyword
)'
2207 _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_-]+)'
2208 _TEMPLATE_URL = 'https
://www
.youtube
.com
/%s/%s/videos
'
2209 IE_NAME = 'youtube
:user
'
2212 'url
': 'https
://www
.youtube
.com
/user
/TheLinuxFoundation
',
2213 'playlist_mincount
': 320,
2215 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ
',
2216 'title
': 'Uploads
from The Linux Foundation
',
2219 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2220 # but not https://www.youtube.com/user/12minuteathlete/videos
2221 'url
': 'https
://www
.youtube
.com
/c
/12minuteathlete
/videos
',
2222 'playlist_mincount
': 249,
2224 'id': 'UUVjM
-zV6_opMDx7WYxnjZiQ
',
2225 'title
': 'Uploads
from 12 Minute Athlete
',
2228 'url
': 'ytuser
:phihag
',
2229 'only_matching
': True,
2231 'url
': 'https
://www
.youtube
.com
/c
/gametrailers
',
2232 'only_matching
': True,
2234 'url
': 'https
://www
.youtube
.com
/gametrailers
',
2235 'only_matching
': True,
2237 # This channel is not available, geo restricted to JP
2238 'url
': 'https
://www
.youtube
.com
/user
/kananishinoSMEJ
/videos
',
2239 'only_matching
': True,
2243 def suitable(cls, url):
2244 # Don't
return True if the url can be extracted
with other youtube
2245 # extractor, the regex would is too permissive and it would match.
2246 other_yt_ies
= iter(klass
for (name
, klass
) in globals().items() if name
.startswith('Youtube') and name
.endswith('IE') and klass
is not cls
)
2247 if any(ie
.suitable(url
) for ie
in other_yt_ies
):
2250 return super(YoutubeUserIE
, cls
).suitable(url
)
2252 def _build_template_url(self
, url
, channel_id
):
2253 mobj
= re
.match(self
._VALID
_URL
, url
)
2254 return self
._TEMPLATE
_URL
% (mobj
.group('user') or 'user', mobj
.group('id'))
2257 class YoutubeLiveIE(YoutubeBaseInfoExtractor
):
2258 IE_DESC
= 'YouTube.com live streams'
2259 _VALID_URL
= r
'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2260 IE_NAME
= 'youtube:live'
2263 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2265 'id': 'a48o2S1cPoo',
2267 'title': 'The Young Turks - Live Main Show',
2268 'uploader': 'The Young Turks',
2269 'uploader_id': 'TheYoungTurks',
2270 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2271 'upload_date': '20150715',
2272 'license': 'Standard YouTube License',
2273 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2274 'categories': ['News & Politics'],
2275 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2277 'dislike_count': int,
2280 'skip_download': True,
2283 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2284 'only_matching': True,
2286 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2287 'only_matching': True,
2289 'url': 'https://www.youtube.com/TheYoungTurks/live',
2290 'only_matching': True,
2293 def _real_extract(self
, url
):
2294 mobj
= re
.match(self
._VALID
_URL
, url
)
2295 channel_id
= mobj
.group('id')
2296 base_url
= mobj
.group('base_url')
2297 webpage
= self
._download
_webpage
(url
, channel_id
, fatal
=False)
2299 page_type
= self
._og
_search
_property
(
2300 'type', webpage
, 'page type', default
=None)
2301 video_id
= self
._html
_search
_meta
(
2302 'videoId', webpage
, 'video id', default
=None)
2303 if page_type
== 'video' and video_id
and re
.match(r
'^[0-9A-Za-z_-]{11}$', video_id
):
2304 return self
.url_result(video_id
, YoutubeIE
.ie_key())
2305 return self
.url_result(base_url
)
2308 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor
):
2309 IE_DESC
= 'YouTube.com user/channel playlists'
2310 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2311 IE_NAME
= 'youtube:playlists'
2314 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2315 'playlist_mincount': 4,
2317 'id': 'ThirstForScience',
2318 'title': 'Thirst for Science',
2321 # with "Load more" button
2322 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2323 'playlist_mincount': 70,
2326 'title': 'Игорь Клейнер',
2329 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2330 'playlist_mincount': 17,
2332 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2333 'title': 'Chem Player',
2338 class YoutubeSearchIE(SearchInfoExtractor
, YoutubePlaylistIE
):
2339 IE_DESC
= 'YouTube.com searches'
2340 # there doesn't appear to be a real limit, for example if you search for
2341 # 'python' you get more than 8.000.000 results
2342 _MAX_RESULTS
= float('inf')
2343 IE_NAME
= 'youtube:search'
2344 _SEARCH_KEY
= 'ytsearch'
2345 _EXTRA_QUERY_ARGS
= {}
2348 def _get_n_results(self
, query
, n
):
2349 """Get a specified number of results for a query"""
2355 'search_query': query
.encode('utf-8'),
2357 url_query
.update(self
._EXTRA
_QUERY
_ARGS
)
2358 result_url
= 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query
)
2360 for pagenum
in itertools
.count(1):
2361 data
= self
._download
_json
(
2362 result_url
, video_id
='query "%s"' % query
,
2363 note
='Downloading page %s' % pagenum
,
2364 errnote
='Unable to download API page',
2365 query
={'spf': 'navigate'}
)
2366 html_content
= data
[1]['body']['content']
2368 if 'class="search-message' in html_content
:
2369 raise ExtractorError(
2370 '[youtube] No video results', expected
=True)
2372 new_videos
= self
._ids
_to
_results
(orderedSet(re
.findall(
2373 r
'href="/watch\?v=(.{11})', html_content
)))
2374 videos
+= new_videos
2375 if not new_videos
or len(videos
) > limit
:
2377 next_link
= self
._html
_search
_regex
(
2378 r
'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2379 html_content
, 'next link', default
=None)
2380 if next_link
is None:
2382 result_url
= compat_urlparse
.urljoin('https://www.youtube.com/', next_link
)
2386 return self
.playlist_result(videos
, query
)
2389 class YoutubeSearchDateIE(YoutubeSearchIE
):
2390 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
2391 _SEARCH_KEY
= 'ytsearchdate'
2392 IE_DESC
= 'YouTube.com searches, newest videos first'
2393 _EXTRA_QUERY_ARGS
= {'search_sort': 'video_date_uploaded'}
2396 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor
):
2397 IE_DESC
= 'YouTube.com search URLs'
2398 IE_NAME
= 'youtube:search_url'
2399 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2400 _VIDEO_RE
= r
'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2402 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2403 'playlist_mincount': 5,
2405 'title': 'youtube-dl test video',
2408 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2409 'only_matching': True,
2412 def _real_extract(self
, url
):
2413 mobj
= re
.match(self
._VALID
_URL
, url
)
2414 query
= compat_urllib_parse_unquote_plus(mobj
.group('query'))
2415 webpage
= self
._download
_webpage
(url
, query
)
2416 return self
.playlist_result(self
._process
_page
(webpage
), playlist_title
=query
)
2419 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor
):
2420 IE_DESC
= 'YouTube.com (multi-season) shows'
2421 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2422 IE_NAME
= 'youtube:show'
2424 'url': 'https://www.youtube.com/show/airdisasters',
2425 'playlist_mincount': 5,
2427 'id': 'airdisasters',
2428 'title': 'Air Disasters',
2432 def _real_extract(self
, url
):
2433 playlist_id
= self
._match
_id
(url
)
2434 return super(YoutubeShowIE
, self
)._real
_extract
(
2435 'https://www.youtube.com/show/%s/playlists' % playlist_id
)
2438 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor
):
2440 Base class for feed extractors
2441 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2443 _LOGIN_REQUIRED
= True
2447 return 'youtube:%s' % self
._FEED
_NAME
2449 def _real_initialize(self
):
2452 def _real_extract(self
, url
):
2453 page
= self
._download
_webpage
(
2454 'https://www.youtube.com/feed/%s' % self
._FEED
_NAME
, self
._PLAYLIST
_TITLE
)
2456 # The extraction process is the same as for playlists, but the regex
2457 # for the video ids doesn't contain an index
2459 more_widget_html
= content_html
= page
2460 for page_num
in itertools
.count(1):
2461 matches
= re
.findall(r
'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html
)
2463 # 'recommended' feed has infinite 'load more' and each new portion spins
2464 # the same videos in (sometimes) slightly different order, so we'll check
2465 # for unicity and break when portion has no new videos
2466 new_ids
= filter(lambda video_id
: video_id
not in ids
, orderedSet(matches
))
2472 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
2476 more
= self
._download
_json
(
2477 'https://youtube.com/%s' % mobj
.group('more'), self
._PLAYLIST
_TITLE
,
2478 'Downloading page #%s' % page_num
,
2479 transform_source
=uppercase_escape
)
2480 content_html
= more
['content_html']
2481 more_widget_html
= more
['load_more_widget_html']
2483 return self
.playlist_result(
2484 self
._ids
_to
_results
(ids
), playlist_title
=self
._PLAYLIST
_TITLE
)
2487 class YoutubeWatchLaterIE(YoutubePlaylistIE
):
2488 IE_NAME
= 'youtube:watchlater'
2489 IE_DESC
= 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2490 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2493 'url': 'https://www.youtube.com/playlist?list=WL',
2494 'only_matching': True,
2496 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2497 'only_matching': True,
2500 def _real_extract(self
, url
):
2501 _
, video
= self
._check
_download
_just
_video
(url
, 'WL')
2504 _
, playlist
= self
._extract
_playlist
('WL')
2508 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
2509 IE_NAME
= 'youtube:favorites'
2510 IE_DESC
= 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2511 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2512 _LOGIN_REQUIRED
= True
2514 def _real_extract(self
, url
):
2515 webpage
= self
._download
_webpage
('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2516 playlist_id
= self
._search
_regex
(r
'list=(.+?)["&]', webpage
, 'favourites playlist id')
2517 return self
.url_result(playlist_id
, 'YoutubePlaylist')
2520 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
2521 IE_DESC
= 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2522 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2523 _FEED_NAME
= 'recommended'
2524 _PLAYLIST_TITLE
= 'Youtube Recommended videos'
2527 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
2528 IE_DESC
= 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2529 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2530 _FEED_NAME
= 'subscriptions'
2531 _PLAYLIST_TITLE
= 'Youtube Subscriptions'
2534 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
2535 IE_DESC
= 'Youtube watch history, ":ythistory" for short (requires authentication)'
2536 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2537 _FEED_NAME
= 'history'
2538 _PLAYLIST_TITLE
= 'Youtube History'
2541 class YoutubeTruncatedURLIE(InfoExtractor
):
2542 IE_NAME
= 'youtube:truncated_url'
2543 IE_DESC
= False # Do not list
2544 _VALID_URL
= r
'''(?x)
2546 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2549 annotation_id=annotation_[^&]+|
2555 attribution_link\?a=[^&]+
2561 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2562 'only_matching': True,
2564 'url': 'https://www.youtube.com/watch?',
2565 'only_matching': True,
2567 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2568 'only_matching': True,
2570 'url': 'https://www.youtube.com/watch?feature=foo',
2571 'only_matching': True,
2573 'url': 'https://www.youtube.com/watch?hl=en-GB',
2574 'only_matching': True,
2576 'url': 'https://www.youtube.com/watch?t=2372',
2577 'only_matching': True,
2580 def _real_extract(self
, url
):
2581 raise ExtractorError(
2582 'Did you forget to quote the URL? Remember that & is a meta '
2583 'character in most shells, so you want to put the URL in quotes, '
2585 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2586 ' or simply youtube-dl BaW_jenozKc .',
2590 class YoutubeTruncatedIDIE(InfoExtractor
):
2591 IE_NAME
= 'youtube:truncated_id'
2592 IE_DESC
= False # Do not list
2593 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2596 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2597 'only_matching': True,
2600 def _real_extract(self
, url
):
2601 video_id
= self
._match
_id
(url
)
2602 raise ExtractorError(
2603 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id
, url
),