]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[wrzuta] Remove extractor (closes #20684) (#20801)
[yt-dlp.git] / youtube_dl / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
5
0ca96d48 6import itertools
c5e8d7af 7import json
c4417ddb 8import os.path
d77ab8e2 9import random
c5e8d7af 10import re
42939b61 11import time
e0df6211 12import traceback
c5e8d7af 13
b05654f0 14from .common import InfoExtractor, SearchInfoExtractor
2b25cb5d 15from ..jsinterp import JSInterpreter
54256267 16from ..swfinterp import SWFInterpreter
4bb4a188 17from ..compat import (
edf3e38e 18 compat_chr,
8d81f3e3 19 compat_kwargs,
c5e8d7af 20 compat_parse_qs,
7fd002c0
S
21 compat_urllib_parse_unquote,
22 compat_urllib_parse_unquote_plus,
15707c7e 23 compat_urllib_parse_urlencode,
7c80519c 24 compat_urllib_parse_urlparse,
7c61bd36 25 compat_urlparse,
c5e8d7af 26 compat_str,
4bb4a188
PH
27)
28from ..utils import (
c5e8d7af 29 clean_html,
9b9c5355 30 error_to_compat_str,
c5e8d7af 31 ExtractorError,
2d30521a 32 float_or_none,
4bb4a188
PH
33 get_element_by_attribute,
34 get_element_by_id,
dd27fd17 35 int_or_none,
94278f72 36 mimetype2ext,
4bb4a188 37 orderedSet,
6310acf5 38 parse_codecs,
7c80519c 39 parse_duration,
54fc90aa 40 qualities,
0cb58b02 41 remove_quotes,
3995d37d 42 remove_start,
cf7e015f 43 smuggle_url,
dbdaaa23 44 str_or_none,
c93d53f5 45 str_to_int,
556dbe7f 46 try_get,
c5e8d7af
PH
47 unescapeHTML,
48 unified_strdate,
cf7e015f 49 unsmuggle_url,
81c2f20b 50 uppercase_escape,
21c340b8 51 url_or_none,
6e6bc8da 52 urlencode_postdata,
c5e8d7af
PH
53)
54
5f6a1245 55
de7f3446 56class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b
JMF
57 """Provide base functions for Youtube extractors"""
58 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
9303ce3e 59 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
e00eb564
S
60
61 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
3995d37d
S
62 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
63 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
e00eb564 64
b2e8bc1b
JMF
65 _NETRC_MACHINE = 'youtube'
66 # If True it will raise an error if no login info is provided
67 _LOGIN_REQUIRED = False
68
409b9324 69 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
d0ba5587 70
b2e8bc1b 71 def _set_language(self):
810fb84d
PH
72 self._set_cookie(
73 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
42939b61 74 # YouTube sets the expire time to about two months
810fb84d 75 expire_time=time.time() + 2 * 30 * 24 * 3600)
b2e8bc1b 76
25f14e9f
S
77 def _ids_to_results(self, ids):
78 return [
79 self.url_result(vid_id, 'Youtube', video_id=vid_id)
80 for vid_id in ids]
81
b2e8bc1b 82 def _login(self):
83317f69 83 """
84 Attempt to log in to YouTube.
85 True is returned if successful or skipped.
86 False is returned if login failed.
87
88 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
89 """
68217024 90 username, password = self._get_login_info()
b2e8bc1b
JMF
91 # No authentication to be performed
92 if username is None:
70d35d16 93 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
69ea8ca4 94 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
83317f69 95 return True
b2e8bc1b 96
7cc3570e
PH
97 login_page = self._download_webpage(
98 self._LOGIN_URL, None,
69ea8ca4
PH
99 note='Downloading login page',
100 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
101 if login_page is False:
102 return
b2e8bc1b 103
1212e997 104 login_form = self._hidden_inputs(login_page)
c5e8d7af 105
e00eb564
S
106 def req(url, f_req, note, errnote):
107 data = login_form.copy()
108 data.update({
109 'pstMsg': 1,
110 'checkConnection': 'youtube',
111 'checkedDomains': 'youtube',
112 'hl': 'en',
113 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
3995d37d 114 'f.req': json.dumps(f_req),
e00eb564
S
115 'flowName': 'GlifWebSignIn',
116 'flowEntry': 'ServiceLogin',
041bc3ad 117 })
e00eb564
S
118 return self._download_json(
119 url, None, note=note, errnote=errnote,
120 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
121 fatal=False,
122 data=urlencode_postdata(data), headers={
123 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
124 'Google-Accounts-XSRF': 1,
125 })
126
3995d37d
S
127 def warn(message):
128 self._downloader.report_warning(message)
129
130 lookup_req = [
131 username,
132 None, [], None, 'US', None, None, 2, False, True,
133 [
134 None, None,
135 [2, 1, None, 1,
136 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
137 None, [], 4],
138 1, [None, None, []], None, None, None, True
139 ],
140 username,
141 ]
142
e00eb564 143 lookup_results = req(
3995d37d 144 self._LOOKUP_URL, lookup_req,
e00eb564
S
145 'Looking up account info', 'Unable to look up account info')
146
147 if lookup_results is False:
148 return False
041bc3ad 149
3995d37d
S
150 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
151 if not user_hash:
152 warn('Unable to extract user hash')
153 return False
154
155 challenge_req = [
156 user_hash,
157 None, 1, None, [1, None, None, None, [password, None, True]],
158 [
159 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
160 1, [None, None, []], None, None, None, True
161 ]]
83317f69 162
3995d37d
S
163 challenge_results = req(
164 self._CHALLENGE_URL, challenge_req,
165 'Logging in', 'Unable to log in')
83317f69 166
3995d37d 167 if challenge_results is False:
e00eb564 168 return
83317f69 169
3995d37d
S
170 login_res = try_get(challenge_results, lambda x: x[0][5], list)
171 if login_res:
172 login_msg = try_get(login_res, lambda x: x[5], compat_str)
173 warn(
174 'Unable to login: %s' % 'Invalid password'
175 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
176 return False
177
178 res = try_get(challenge_results, lambda x: x[0][-1], list)
179 if not res:
180 warn('Unable to extract result entry')
181 return False
182
9a6628aa
S
183 login_challenge = try_get(res, lambda x: x[0][0], list)
184 if login_challenge:
185 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
186 if challenge_str == 'TWO_STEP_VERIFICATION':
3995d37d
S
187 # SEND_SUCCESS - TFA code has been successfully sent to phone
188 # QUOTA_EXCEEDED - reached the limit of TFA codes
9a6628aa 189 status = try_get(login_challenge, lambda x: x[5], compat_str)
3995d37d
S
190 if status == 'QUOTA_EXCEEDED':
191 warn('Exceeded the limit of TFA codes, try later')
192 return False
193
194 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
195 if not tl:
196 warn('Unable to extract TL')
197 return False
198
199 tfa_code = self._get_tfa_info('2-step verification code')
200
201 if not tfa_code:
202 warn(
203 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
204 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
205 return False
206
207 tfa_code = remove_start(tfa_code, 'G-')
208
209 tfa_req = [
210 user_hash, None, 2, None,
211 [
212 9, None, None, None, None, None, None, None,
213 [None, tfa_code, True, 2]
214 ]]
215
216 tfa_results = req(
217 self._TFA_URL.format(tl), tfa_req,
218 'Submitting TFA code', 'Unable to submit TFA code')
219
220 if tfa_results is False:
221 return False
222
223 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
224 if tfa_res:
225 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
226 warn(
227 'Unable to finish TFA: %s' % 'Invalid TFA code'
228 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
229 return False
230
231 check_cookie_url = try_get(
232 tfa_results, lambda x: x[0][-1][2], compat_str)
9a6628aa
S
233 else:
234 CHALLENGES = {
235 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
236 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
237 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
238 }
239 challenge = CHALLENGES.get(
240 challenge_str,
241 '%s returned error %s.' % (self.IE_NAME, challenge_str))
242 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
243 return False
3995d37d
S
244 else:
245 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
246
247 if not check_cookie_url:
248 warn('Unable to extract CheckCookie URL')
249 return False
e00eb564
S
250
251 check_cookie_results = self._download_webpage(
3995d37d
S
252 check_cookie_url, None, 'Checking cookie', fatal=False)
253
254 if check_cookie_results is False:
255 return False
e00eb564 256
3995d37d
S
257 if 'https://myaccount.google.com/' not in check_cookie_results:
258 warn('Unable to log in')
b2e8bc1b 259 return False
e00eb564 260
b2e8bc1b
JMF
261 return True
262
30226342 263 def _download_webpage_handle(self, *args, **kwargs):
c1148516
S
264 query = kwargs.get('query', {}).copy()
265 query['disable_polymer'] = 'true'
266 kwargs['query'] = query
30226342 267 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
8d81f3e3
S
268 *args, **compat_kwargs(kwargs))
269
b2e8bc1b
JMF
270 def _real_initialize(self):
271 if self._downloader is None:
272 return
42939b61 273 self._set_language()
b2e8bc1b
JMF
274 if not self._login():
275 return
c5e8d7af 276
8377574c 277
8e7aad20 278class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
061a75ed 279 # Extract entries from page with "Load more" button
648e6a1f
S
280 def _entries(self, page, playlist_id):
281 more_widget_html = content_html = page
282 for page_num in itertools.count(1):
061a75ed
S
283 for entry in self._process_page(content_html):
284 yield entry
648e6a1f
S
285
286 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
287 if not mobj:
288 break
289
290 more = self._download_json(
291 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
292 'Downloading page #%s' % page_num,
293 transform_source=uppercase_escape)
294 content_html = more['content_html']
295 if not content_html.strip():
296 # Some webpages show a "Load more" button but they don't
297 # have more videos
298 break
299 more_widget_html = more['load_more_widget_html']
300
061a75ed
S
301
302class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
303 def _process_page(self, content):
304 for video_id, video_title in self.extract_videos_from_page(content):
305 yield self.url_result(video_id, 'Youtube', video_id, video_title)
306
648e6a1f
S
307 def extract_videos_from_page(self, page):
308 ids_in_page = []
309 titles_in_page = []
310 for mobj in re.finditer(self._VIDEO_RE, page):
311 # The link with index 0 is not the first video of the playlist (not sure if still actual)
312 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
313 continue
314 video_id = mobj.group('id')
315 video_title = unescapeHTML(mobj.group('title'))
316 if video_title:
317 video_title = video_title.strip()
318 try:
319 idx = ids_in_page.index(video_id)
320 if video_title and not titles_in_page[idx]:
321 titles_in_page[idx] = video_title
322 except ValueError:
323 ids_in_page.append(video_id)
324 titles_in_page.append(video_title)
325 return zip(ids_in_page, titles_in_page)
326
327
061a75ed
S
328class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
329 def _process_page(self, content):
6dee688e
S
330 for playlist_id in orderedSet(re.findall(
331 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
332 content)):
061a75ed
S
333 yield self.url_result(
334 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
335
0c148415
S
336 def _real_extract(self, url):
337 playlist_id = self._match_id(url)
338 webpage = self._download_webpage(url, playlist_id)
0c148415 339 title = self._og_search_title(webpage, fatal=False)
061a75ed 340 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
0c148415
S
341
342
360e1ca5 343class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 344 IE_DESC = 'YouTube.com'
cb7dfeea 345 _VALID_URL = r"""(?x)^
c5e8d7af 346 (
edb53e2d 347 (?:https?://|//) # http(s):// or protocol-independent URL
cb7dfeea 348 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
484aaeb2 349 (?:www\.)?deturl\.com/www\.youtube\.com/|
e70dc1d1 350 (?:www\.)?pwnyoutube\.com/|
8b561bfc 351 (?:www\.)?hooktube\.com/|
f7000f3a 352 (?:www\.)?yourepeat\.com/|
e69ae5b9 353 tube\.majestyc\.net/|
77d95677 354 (?:(?:www|dev)\.)?invidio\.us/|
355 (?:www\.)?invidiou\.sh/|
8ae113ca 356 (?:www\.)?invidious\.snopyta\.org/|
357 (?:www\.)?invidious\.kabi\.tk/|
358 (?:www\.)?vid\.wxzm\.sx/|
e69ae5b9 359 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
c5e8d7af
PH
360 (?:.*?\#/)? # handle anchor (#/) redirect urls
361 (?: # the various things that can precede the ID:
ac7553d0 362 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 363 |(?: # or the v= param in all its forms
f7000f3a 364 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 365 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 366 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
367 v=
368 )
f4b05232 369 ))
cbaed4bb
S
370 |(?:
371 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
372 vid\.plus| # or vid.plus/xxxx
373 zwearz\.com/watch| # or zwearz.com/watch/xxxx
cbaed4bb 374 )/
edb53e2d 375 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 376 )
c5e8d7af 377 )? # all until now is optional -> you can pass the naked ID
8963d9c2 378 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
d0ba5587
S
379 (?!.*?\blist=
380 (?:
381 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
382 WL # WL are handled by the watch later IE
383 )
384 )
c5e8d7af 385 (?(1).+)? # if we found the ID, everything can follow
d0ba5587 386 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
c5e8d7af 387 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
2c62dc26 388 _formats = {
c2d3cb4c 389 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
390 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
391 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
392 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
393 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
394 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
395 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
396 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 397 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 398 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
399 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
400 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
401 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
402 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
403 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 404 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 405 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
406 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 407
408
409 # 3D videos
c2d3cb4c 410 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
411 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
412 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
413 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 414 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
415 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
416 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 417
96fb5605 418 # Apple HTTP Live Streaming
11f12195 419 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 420 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
421 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
422 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
423 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
424 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 425 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
426 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
427
428 # DASH mp4 video
d23028a8
S
429 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
430 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
431 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
432 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
433 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 434 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
435 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
436 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
437 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
438 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
439 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
440 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 441
f6f1fc92 442 # Dash mp4 audio
d23028a8
S
443 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
444 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
445 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
446 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
447 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
448 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
449 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
450
451 # Dash webm
d23028a8
S
452 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
453 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
454 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
455 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
456 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
457 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
458 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
459 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
460 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
461 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
462 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
463 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
464 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
465 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
466 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 467 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
468 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
469 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
470 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
471 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
472 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
473 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
474
475 # Dash webm audio
d23028a8
S
476 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
477 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 478
0857baad 479 # Dash webm audio with opus inside
d23028a8
S
480 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
481 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
482 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 483
ce6b9a2d
PH
484 # RTMP (unnamed)
485 '_rtmp': {'protocol': 'rtmp'},
c5e8d7af 486 }
19041a38 487 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 488
fd5c4aab
S
489 _GEO_BYPASS = False
490
78caa52a 491 IE_NAME = 'youtube'
2eb88d95
PH
492 _TESTS = [
493 {
2d3d2997 494 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
495 'info_dict': {
496 'id': 'BaW_jenozKc',
497 'ext': 'mp4',
498 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
499 'uploader': 'Philipp Hagemeister',
500 'uploader_id': 'phihag',
ec85ded8 501 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
dd4c4492
S
502 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
503 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e
PH
504 'upload_date': '20121002',
505 '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 .',
506 'categories': ['Science & Technology'],
000b6b5a 507 'tags': ['youtube-dl'],
556dbe7f 508 'duration': 10,
dbdaaa23 509 'view_count': int,
3e7c1224
PH
510 'like_count': int,
511 'dislike_count': int,
7c80519c 512 'start_time': 1,
297a564b 513 'end_time': 9,
2eb88d95 514 }
0e853ca4 515 },
0e853ca4 516 {
2d3d2997 517 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
4bc3a23e
PH
518 'note': 'Test generic use_cipher_signature video (#897)',
519 'info_dict': {
520 'id': 'UxxajLWwzqY',
521 'ext': 'mp4',
522 'upload_date': '20120506',
523 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
0cb58b02 524 'alt_title': 'I Love It (feat. Charli XCX)',
7caf9830 525 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
000b6b5a
S
526 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
527 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
528 'iconic ep', 'iconic', 'love', 'it'],
556dbe7f 529 'duration': 180,
4bc3a23e
PH
530 'uploader': 'Icona Pop',
531 'uploader_id': 'IconaPop',
ec85ded8 532 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
0cb58b02 533 'creator': 'Icona Pop',
936784b2
S
534 'track': 'I Love It (feat. Charli XCX)',
535 'artist': 'Icona Pop',
2eb88d95 536 }
c108eb73
JMF
537 },
538 {
4bc3a23e
PH
539 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
540 'note': 'Test VEVO video with age protection (#956)',
541 'info_dict': {
542 'id': '07FYdnEawAQ',
543 'ext': 'mp4',
544 'upload_date': '20130703',
4fe54c12 545 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
0cb58b02 546 'alt_title': 'Tunnel Vision',
4fe54c12 547 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
556dbe7f 548 'duration': 419,
4bc3a23e
PH
549 'uploader': 'justintimberlakeVEVO',
550 'uploader_id': 'justintimberlakeVEVO',
ec85ded8 551 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
0cb58b02 552 'creator': 'Justin Timberlake',
7e72694b 553 'track': 'Tunnel Vision',
936784b2 554 'artist': 'Justin Timberlake',
34952f09 555 'age_limit': 18,
c108eb73
JMF
556 }
557 },
fccd3771 558 {
4bc3a23e
PH
559 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
560 'note': 'Embed-only video (#1746)',
561 'info_dict': {
562 'id': 'yZIXLfi8CZQ',
563 'ext': 'mp4',
564 'upload_date': '20120608',
565 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
566 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
567 'uploader': 'SET India',
94bfcd23 568 'uploader_id': 'setindia',
ec85ded8 569 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 570 'age_limit': 18,
fccd3771
PH
571 }
572 },
11b56058 573 {
2d3d2997 574 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
11b56058
PM
575 'note': 'Use the first video ID in the URL',
576 'info_dict': {
577 'id': 'BaW_jenozKc',
578 'ext': 'mp4',
579 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
580 'uploader': 'Philipp Hagemeister',
581 'uploader_id': 'phihag',
ec85ded8 582 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058
PM
583 'upload_date': '20121002',
584 '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 .',
585 'categories': ['Science & Technology'],
586 'tags': ['youtube-dl'],
556dbe7f 587 'duration': 10,
dbdaaa23 588 'view_count': int,
11b56058
PM
589 'like_count': int,
590 'dislike_count': int,
34a7de29
S
591 },
592 'params': {
593 'skip_download': True,
594 },
11b56058 595 },
dd27fd17 596 {
2d3d2997 597 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
598 'note': '256k DASH audio (format 141) via DASH manifest',
599 'info_dict': {
600 'id': 'a9LDPn-MO4I',
601 'ext': 'm4a',
602 'upload_date': '20121002',
603 'uploader_id': '8KVIDEO',
ec85ded8 604 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
605 'description': '',
606 'uploader': '8KVIDEO',
607 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 608 },
4bc3a23e
PH
609 'params': {
610 'youtube_include_dash_manifest': True,
611 'format': '141',
4919603f 612 },
de3c7fe0 613 'skip': 'format 141 not served anymore',
dd27fd17 614 },
3489b7d2
JMF
615 # DASH manifest with encrypted signature
616 {
78caa52a
PH
617 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
618 'info_dict': {
619 'id': 'IB3lcPjvWLA',
620 'ext': 'm4a',
4fe54c12
S
621 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
622 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
556dbe7f 623 'duration': 244,
78caa52a
PH
624 'uploader': 'AfrojackVEVO',
625 'uploader_id': 'AfrojackVEVO',
626 'upload_date': '20131011',
3489b7d2 627 },
4bc3a23e 628 'params': {
78caa52a 629 'youtube_include_dash_manifest': True,
de3c7fe0 630 'format': '141/bestaudio[ext=m4a]',
3489b7d2
JMF
631 },
632 },
aaeb86f6
S
633 # JS player signature function name containing $
634 {
635 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
636 'info_dict': {
637 'id': 'nfWlot6h_JM',
638 'ext': 'm4a',
639 'title': 'Taylor Swift - Shake It Off',
4fe54c12 640 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
556dbe7f 641 'duration': 242,
aaeb86f6
S
642 'uploader': 'TaylorSwiftVEVO',
643 'uploader_id': 'TaylorSwiftVEVO',
644 'upload_date': '20140818',
0cb58b02 645 'creator': 'Taylor Swift',
aaeb86f6
S
646 },
647 'params': {
648 'youtube_include_dash_manifest': True,
de3c7fe0 649 'format': '141/bestaudio[ext=m4a]',
aaeb86f6
S
650 },
651 },
aa79ac0c
PH
652 # Controversy video
653 {
654 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
655 'info_dict': {
656 'id': 'T4XJQO3qol8',
657 'ext': 'mp4',
556dbe7f 658 'duration': 219,
aa79ac0c 659 'upload_date': '20100909',
4fe54c12 660 'uploader': 'Amazing Atheist',
aa79ac0c 661 'uploader_id': 'TheAmazingAtheist',
ec85ded8 662 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
aa79ac0c
PH
663 'title': 'Burning Everyone\'s Koran',
664 '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',
665 }
c522adb1
JMF
666 },
667 # Normal age-gate video (No vevo, embed allowed)
668 {
2d3d2997 669 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
670 'info_dict': {
671 'id': 'HtVdAasjOgU',
672 'ext': 'mp4',
673 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 674 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 675 'duration': 142,
c522adb1
JMF
676 'uploader': 'The Witcher',
677 'uploader_id': 'WitcherGame',
ec85ded8 678 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 679 'upload_date': '20140605',
34952f09 680 'age_limit': 18,
c522adb1
JMF
681 },
682 },
fccae2b9
S
683 # Age-gate video with encrypted signature
684 {
2d3d2997 685 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
fccae2b9
S
686 'info_dict': {
687 'id': '6kLq3WMV1nU',
4fe54c12 688 'ext': 'mp4',
fccae2b9
S
689 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
690 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
eb6793ba 691 'duration': 246,
fccae2b9
S
692 'uploader': 'LloydVEVO',
693 'uploader_id': 'LloydVEVO',
ec85ded8 694 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
fccae2b9 695 'upload_date': '20110629',
34952f09 696 'age_limit': 18,
fccae2b9
S
697 },
698 },
067aa17e 699 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
7d02dcfa 700 # YouTube Red ad is not captured for creator
774e208f
PH
701 {
702 'url': '__2ABJjxzNo',
703 'info_dict': {
704 'id': '__2ABJjxzNo',
705 'ext': 'mp4',
556dbe7f 706 'duration': 266,
774e208f
PH
707 'upload_date': '20100430',
708 'uploader_id': 'deadmau5',
ec85ded8 709 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
0cb58b02 710 'creator': 'deadmau5',
774e208f
PH
711 'description': 'md5:12c56784b8032162bb936a5f76d55360',
712 'uploader': 'deadmau5',
713 'title': 'Deadmau5 - Some Chords (HD)',
0cb58b02 714 'alt_title': 'Some Chords',
774e208f
PH
715 },
716 'expected_warnings': [
717 'DASH manifest missing',
718 ]
e52a40ab 719 },
067aa17e 720 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
721 {
722 'url': 'lqQg6PlCWgI',
723 'info_dict': {
724 'id': 'lqQg6PlCWgI',
725 'ext': 'mp4',
556dbe7f 726 'duration': 6085,
90227264 727 'upload_date': '20150827',
cbe2bd91 728 'uploader_id': 'olympic',
ec85ded8 729 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 730 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
be49068d 731 'uploader': 'Olympic',
cbe2bd91
PH
732 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
733 },
734 'params': {
735 'skip_download': 'requires avconv',
e52a40ab 736 }
cbe2bd91 737 },
6271f1ca
PH
738 # Non-square pixels
739 {
740 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
741 'info_dict': {
742 'id': '_b-2C3KPAM0',
743 'ext': 'mp4',
744 'stretched_ratio': 16 / 9.,
556dbe7f 745 'duration': 85,
6271f1ca
PH
746 'upload_date': '20110310',
747 'uploader_id': 'AllenMeow',
ec85ded8 748 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 749 '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',
eb6793ba 750 'uploader': '孫ᄋᄅ',
6271f1ca
PH
751 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
752 },
06b491eb
S
753 },
754 # url_encoded_fmt_stream_map is empty string
755 {
756 'url': 'qEJwOuvDf7I',
757 'info_dict': {
758 'id': 'qEJwOuvDf7I',
f57b7835 759 'ext': 'webm',
06b491eb
S
760 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
761 'description': '',
762 'upload_date': '20150404',
763 'uploader_id': 'spbelect',
764 'uploader': 'Наблюдатели Петербурга',
765 },
766 'params': {
767 'skip_download': 'requires avconv',
e323cf3f
S
768 },
769 'skip': 'This live event has ended.',
06b491eb 770 },
067aa17e 771 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
772 {
773 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
774 'info_dict': {
775 'id': 'FIl7x6_3R5Y',
eb6793ba 776 'ext': 'webm',
da77d856
S
777 'title': 'md5:7b81415841e02ecd4313668cde88737a',
778 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 779 'duration': 220,
da77d856
S
780 'upload_date': '20150625',
781 'uploader_id': 'dorappi2000',
ec85ded8 782 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 783 'uploader': 'dorappi2000',
eb6793ba 784 'formats': 'mincount:31',
da77d856 785 },
eb6793ba 786 'skip': 'not actual anymore',
2ee8f5d8 787 },
8a1a26ce
YCH
788 # DASH manifest with segment_list
789 {
790 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
791 'md5': '8ce563a1d667b599d21064e982ab9e31',
792 'info_dict': {
793 'id': 'CsmdDsKjzN8',
794 'ext': 'mp4',
17ee98e1 795 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
796 'uploader': 'Airtek',
797 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
798 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
799 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
800 },
801 'params': {
802 'youtube_include_dash_manifest': True,
803 'format': '135', # bestvideo
be49068d
S
804 },
805 'skip': 'This live event has ended.',
2ee8f5d8 806 },
cf7e015f
S
807 {
808 # Multifeed videos (multiple cameras), URL is for Main Camera
809 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
810 'info_dict': {
811 'id': 'jqWvoWXjCVs',
812 'title': 'teamPGP: Rocket League Noob Stream',
813 'description': 'md5:dc7872fb300e143831327f1bae3af010',
814 },
815 'playlist': [{
816 'info_dict': {
817 'id': 'jqWvoWXjCVs',
818 'ext': 'mp4',
819 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
820 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 821 'duration': 7335,
cf7e015f
S
822 'upload_date': '20150721',
823 'uploader': 'Beer Games Beer',
824 'uploader_id': 'beergamesbeer',
ec85ded8 825 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 826 'license': 'Standard YouTube License',
cf7e015f
S
827 },
828 }, {
829 'info_dict': {
830 'id': '6h8e8xoXJzg',
831 'ext': 'mp4',
832 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
833 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 834 'duration': 7337,
cf7e015f
S
835 'upload_date': '20150721',
836 'uploader': 'Beer Games Beer',
837 'uploader_id': 'beergamesbeer',
ec85ded8 838 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 839 'license': 'Standard YouTube License',
cf7e015f
S
840 },
841 }, {
842 'info_dict': {
843 'id': 'PUOgX5z9xZw',
844 'ext': 'mp4',
845 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
846 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 847 'duration': 7337,
cf7e015f
S
848 'upload_date': '20150721',
849 'uploader': 'Beer Games Beer',
850 'uploader_id': 'beergamesbeer',
ec85ded8 851 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 852 'license': 'Standard YouTube License',
cf7e015f
S
853 },
854 }, {
855 'info_dict': {
856 'id': 'teuwxikvS5k',
857 'ext': 'mp4',
858 'title': 'teamPGP: Rocket League Noob Stream (zim)',
859 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 860 'duration': 7334,
cf7e015f
S
861 'upload_date': '20150721',
862 'uploader': 'Beer Games Beer',
863 'uploader_id': 'beergamesbeer',
ec85ded8 864 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 865 'license': 'Standard YouTube License',
cf7e015f
S
866 },
867 }],
868 'params': {
869 'skip_download': True,
870 },
4fe54c12 871 'skip': 'This video is not available.',
cbaed4bb 872 },
f9f49d87 873 {
067aa17e 874 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
875 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
876 'info_dict': {
877 'id': 'gVfLd0zydlo',
878 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
879 },
880 'playlist_count': 2,
be49068d 881 'skip': 'Not multifeed anymore',
f9f49d87 882 },
cbaed4bb 883 {
2d3d2997 884 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 885 'only_matching': True,
0e49d9a6 886 },
6d4fc66b 887 {
2d3d2997 888 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
889 'only_matching': True,
890 },
0e49d9a6 891 {
067aa17e 892 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 893 # Also tests cut-off URL expansion in video description (see
067aa17e
S
894 # https://github.com/ytdl-org/youtube-dl/issues/1892,
895 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
896 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
897 'info_dict': {
898 'id': 'lsguqyKfVQg',
899 'ext': 'mp4',
900 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
eb6793ba 901 'alt_title': 'Dark Walk - Position Music',
0e49d9a6 902 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 903 'duration': 133,
0e49d9a6
LL
904 'upload_date': '20151119',
905 'uploader_id': 'IronSoulElf',
ec85ded8 906 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 907 'uploader': 'IronSoulElf',
eb6793ba
S
908 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
909 'track': 'Dark Walk - Position Music',
910 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
0e49d9a6
LL
911 },
912 'params': {
913 'skip_download': True,
914 },
915 },
61f92af1 916 {
067aa17e 917 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
918 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
919 'only_matching': True,
920 },
313dfc45
LL
921 {
922 # Video with yt:stretch=17:0
923 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
924 'info_dict': {
925 'id': 'Q39EVAstoRM',
926 'ext': 'mp4',
927 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
928 'description': 'md5:ee18a25c350637c8faff806845bddee9',
929 'upload_date': '20151107',
930 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
931 'uploader': 'CH GAMER DROID',
932 },
933 'params': {
934 'skip_download': True,
935 },
be49068d 936 'skip': 'This video does not exist.',
313dfc45 937 },
7caf9830
S
938 {
939 # Video licensed under Creative Commons
940 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
941 'info_dict': {
942 'id': 'M4gD1WSo5mA',
943 'ext': 'mp4',
944 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
945 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 946 'duration': 721,
7caf9830
S
947 'upload_date': '20150127',
948 'uploader_id': 'BerkmanCenter',
ec85ded8 949 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 950 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
951 'license': 'Creative Commons Attribution license (reuse allowed)',
952 },
953 'params': {
954 'skip_download': True,
955 },
956 },
fd050249
S
957 {
958 # Channel-like uploader_url
959 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
960 'info_dict': {
961 'id': 'eQcmzGIKrzg',
962 'ext': 'mp4',
963 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
964 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
556dbe7f 965 'duration': 4060,
fd050249 966 'upload_date': '20151119',
eb6793ba 967 'uploader': 'Bernie Sanders',
fd050249 968 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 969 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
970 'license': 'Creative Commons Attribution license (reuse allowed)',
971 },
972 'params': {
973 'skip_download': True,
974 },
975 },
040ac686
S
976 {
977 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
978 'only_matching': True,
7f29cf54
S
979 },
980 {
067aa17e 981 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
982 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
983 'only_matching': True,
6496ccb4
S
984 },
985 {
986 # Rental video preview
987 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
988 'info_dict': {
989 'id': 'uGpuVWrhIzE',
990 'ext': 'mp4',
991 'title': 'Piku - Trailer',
992 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
993 'upload_date': '20150811',
994 'uploader': 'FlixMatrix',
995 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 996 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
997 'license': 'Standard YouTube License',
998 },
999 'params': {
1000 'skip_download': True,
1001 },
eb6793ba 1002 'skip': 'This video is not available.',
022a5d66 1003 },
12afdc2a
S
1004 {
1005 # YouTube Red video with episode data
1006 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1007 'info_dict': {
1008 'id': 'iqKdEhx-dD4',
1009 'ext': 'mp4',
1010 'title': 'Isolation - Mind Field (Ep 1)',
4fe54c12 1011 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
556dbe7f 1012 'duration': 2085,
12afdc2a
S
1013 'upload_date': '20170118',
1014 'uploader': 'Vsauce',
1015 'uploader_id': 'Vsauce',
1016 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1017 'series': 'Mind Field',
1018 'season_number': 1,
1019 'episode_number': 1,
1020 },
1021 'params': {
1022 'skip_download': True,
1023 },
1024 'expected_warnings': [
1025 'Skipping DASH manifest',
1026 ],
1027 },
c7121fa7
S
1028 {
1029 # The following content has been identified by the YouTube community
1030 # as inappropriate or offensive to some audiences.
1031 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1032 'info_dict': {
1033 'id': '6SJNVb0GnPI',
1034 'ext': 'mp4',
1035 'title': 'Race Differences in Intelligence',
1036 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1037 'duration': 965,
1038 'upload_date': '20140124',
1039 'uploader': 'New Century Foundation',
1040 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1041 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1042 },
1043 'params': {
1044 'skip_download': True,
1045 },
1046 },
022a5d66
S
1047 {
1048 # itag 212
1049 'url': '1t24XAntNCY',
1050 'only_matching': True,
fd5c4aab
S
1051 },
1052 {
1053 # geo restricted to JP
1054 'url': 'sJL6WA-aGkQ',
1055 'only_matching': True,
1056 },
d0ba5587
S
1057 {
1058 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1059 'only_matching': True,
1060 },
cd5a74a2
S
1061 {
1062 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1063 'only_matching': True,
1064 },
825cd268
RA
1065 {
1066 # DRM protected
1067 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1068 'only_matching': True,
4fe54c12
S
1069 },
1070 {
1071 # Video with unsupported adaptive stream type formats
1072 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1073 'info_dict': {
1074 'id': 'Z4Vy8R84T1U',
1075 'ext': 'mp4',
1076 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1077 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1078 'duration': 433,
1079 'upload_date': '20130923',
1080 'uploader': 'Amelia Putri Harwita',
1081 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1082 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1083 'formats': 'maxcount:10',
1084 },
1085 'params': {
1086 'skip_download': True,
1087 'youtube_include_dash_manifest': False,
1088 },
825cd268 1089 }
2eb88d95
PH
1090 ]
1091
e0df6211
PH
1092 def __init__(self, *args, **kwargs):
1093 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 1094 self._player_cache = {}
e0df6211 1095
c5e8d7af
PH
1096 def report_video_info_webpage_download(self, video_id):
1097 """Report attempt to download video info webpage."""
69ea8ca4 1098 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 1099
c5e8d7af
PH
1100 def report_information_extraction(self, video_id):
1101 """Report attempt to extract video information."""
69ea8ca4 1102 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
1103
1104 def report_unavailable_format(self, video_id, format):
1105 """Report extracted video URL."""
69ea8ca4 1106 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
1107
1108 def report_rtmp_download(self):
1109 """Indicate the download will use the RTMP protocol."""
69ea8ca4 1110 self.to_screen('RTMP download detected')
c5e8d7af 1111
60064c53
PH
1112 def _signature_cache_id(self, example_sig):
1113 """ Return a string representation of a signature """
78caa52a 1114 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
1115
1116 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 1117 id_m = re.match(
63529e93 1118 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
cf010131 1119 player_url)
c081b35c
PH
1120 if not id_m:
1121 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
1122 player_type = id_m.group('ext')
1123 player_id = id_m.group('id')
1124
c4417ddb 1125 # Read from filesystem cache
60064c53
PH
1126 func_id = '%s_%s_%s' % (
1127 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 1128 assert os.path.basename(func_id) == func_id
a0e07d31 1129
69ea8ca4 1130 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 1131 if cache_spec is not None:
78caa52a 1132 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 1133
6d1a55a5
PH
1134 download_note = (
1135 'Downloading player %s' % player_url
1136 if self._downloader.params.get('verbose') else
1137 'Downloading %s player %s' % (player_type, player_id)
1138 )
e0df6211
PH
1139 if player_type == 'js':
1140 code = self._download_webpage(
1141 player_url, video_id,
6d1a55a5 1142 note=download_note,
69ea8ca4 1143 errnote='Download of %s failed' % player_url)
83799698 1144 res = self._parse_sig_js(code)
c4417ddb 1145 elif player_type == 'swf':
e0df6211
PH
1146 urlh = self._request_webpage(
1147 player_url, video_id,
6d1a55a5 1148 note=download_note,
69ea8ca4 1149 errnote='Download of %s failed' % player_url)
e0df6211 1150 code = urlh.read()
83799698 1151 res = self._parse_sig_swf(code)
e0df6211
PH
1152 else:
1153 assert False, 'Invalid player type %r' % player_type
1154
785521bf
PH
1155 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1156 cache_res = res(test_string)
1157 cache_spec = [ord(c) for c in cache_res]
83799698 1158
69ea8ca4 1159 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
1160 return res
1161
60064c53 1162 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1163 def gen_sig_code(idxs):
1164 def _genslice(start, end, step):
78caa52a 1165 starts = '' if start == 0 else str(start)
8bcc8756 1166 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1167 steps = '' if step == 1 else (':%d' % step)
78caa52a 1168 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1169
1170 step = None
7af808a5
PH
1171 # Quelch pyflakes warnings - start will be set when step is set
1172 start = '(Never used)'
edf3e38e
PH
1173 for i, prev in zip(idxs[1:], idxs[:-1]):
1174 if step is not None:
1175 if i - prev == step:
1176 continue
1177 yield _genslice(start, prev, step)
1178 step = None
1179 continue
1180 if i - prev in [-1, 1]:
1181 step = i - prev
1182 start = prev
1183 continue
1184 else:
78caa52a 1185 yield 's[%d]' % prev
edf3e38e 1186 if step is None:
78caa52a 1187 yield 's[%d]' % i
edf3e38e
PH
1188 else:
1189 yield _genslice(start, i, step)
1190
78caa52a 1191 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1192 cache_res = func(test_string)
edf3e38e 1193 cache_spec = [ord(c) for c in cache_res]
78caa52a 1194 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1195 signature_id_tuple = '(%s)' % (
1196 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1197 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1198 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1199 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1200
e0df6211
PH
1201 def _parse_sig_js(self, jscode):
1202 funcname = self._search_regex(
3c90cc8b 1203 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 1204 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
fa4ac365
S
1205 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
1206 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2511eee2 1207 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 1208 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1209
1210 jsi = JSInterpreter(jscode)
1211 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1212 return lambda s: initial_function([s])
1213
1214 def _parse_sig_swf(self, file_contents):
54256267 1215 swfi = SWFInterpreter(file_contents)
78caa52a 1216 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 1217 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 1218 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
1219 return lambda s: initial_function([s])
1220
83799698 1221 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 1222 """Turn the encrypted s field into a working signature"""
6b37f0be 1223
c8bf86d5 1224 if player_url is None:
69ea8ca4 1225 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1226
69ea8ca4 1227 if player_url.startswith('//'):
78caa52a 1228 player_url = 'https:' + player_url
3c90cc8b
S
1229 elif not re.match(r'https?://', player_url):
1230 player_url = compat_urlparse.urljoin(
1231 'https://www.youtube.com', player_url)
c8bf86d5 1232 try:
62af3a0e 1233 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1234 if player_id not in self._player_cache:
1235 func = self._extract_signature_function(
60064c53 1236 video_id, player_url, s
c8bf86d5
PH
1237 )
1238 self._player_cache[player_id] = func
1239 func = self._player_cache[player_id]
1240 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1241 self._print_sig_code(func, s)
c8bf86d5
PH
1242 return func(s)
1243 except Exception as e:
1244 tb = traceback.format_exc()
1245 raise ExtractorError(
78caa52a 1246 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1247
360e1ca5 1248 def _get_subtitles(self, video_id, webpage):
de7f3446 1249 try:
60e47a26 1250 subs_doc = self._download_xml(
38c2e5b8 1251 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1252 video_id, note=False)
1253 except ExtractorError as err:
9b9c5355 1254 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1255 return {}
de7f3446
JMF
1256
1257 sub_lang_list = {}
60e47a26
JMF
1258 for track in subs_doc.findall('track'):
1259 lang = track.attrib['lang_code']
7e660ac1
LD
1260 if lang in sub_lang_list:
1261 continue
360e1ca5 1262 sub_formats = []
23d17e4b 1263 for ext in self._SUBTITLE_FORMATS:
15707c7e 1264 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1265 'lang': lang,
1266 'v': video_id,
1267 'fmt': ext,
1268 'name': track.attrib['name'].encode('utf-8'),
1269 })
1270 sub_formats.append({
1271 'url': 'https://www.youtube.com/api/timedtext?' + params,
1272 'ext': ext,
1273 })
1274 sub_lang_list[lang] = sub_formats
de7f3446 1275 if not sub_lang_list:
69ea8ca4 1276 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1277 return {}
1278 return sub_lang_list
1279
a72778d3
S
1280 def _get_ytplayer_config(self, video_id, webpage):
1281 patterns = (
526b3b07
S
1282 # User data may contain arbitrary character sequences that may affect
1283 # JSON extraction with regex, e.g. when '};' is contained the second
1284 # regex won't capture the whole JSON. Yet working around by trying more
1285 # concrete regex first keeping in mind proper quoted string handling
1286 # to be implemented in future that will replace this workaround (see
067aa17e
S
1287 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1288 # https://github.com/ytdl-org/youtube-dl/pull/7599)
a72778d3
S
1289 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1290 r';ytplayer\.config\s*=\s*({.+?});',
1291 )
1292 config = self._search_regex(
1293 patterns, webpage, 'ytplayer.config', default=None)
1294 if config:
1295 return self._parse_json(
1296 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1297
360e1ca5 1298 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1299 """We need the webpage for getting the captions url, pass it as an
1300 argument to speed up the process."""
69ea8ca4 1301 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1302 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1303 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1304 if not player_config:
de7f3446
JMF
1305 self._downloader.report_warning(err_msg)
1306 return {}
de7f3446 1307 try:
0792d563 1308 args = player_config['args']
b78b292f
S
1309 caption_url = args.get('ttsurl')
1310 if caption_url:
1311 timestamp = args['timestamp']
1312 # We get the available subtitles
15707c7e 1313 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1314 'type': 'list',
1315 'tlangs': 1,
1316 'asrs': 1,
1317 })
1318 list_url = caption_url + '&' + list_params
1319 caption_list = self._download_xml(list_url, video_id)
1320 original_lang_node = caption_list.find('track')
1321 if original_lang_node is None:
1322 self._downloader.report_warning('Video doesn\'t have automatic captions')
1323 return {}
1324 original_lang = original_lang_node.attrib['lang_code']
1325 caption_kind = original_lang_node.attrib.get('kind', '')
1326
1327 sub_lang_list = {}
1328 for lang_node in caption_list.findall('target'):
1329 sub_lang = lang_node.attrib['lang_code']
1330 sub_formats = []
1331 for ext in self._SUBTITLE_FORMATS:
15707c7e 1332 params = compat_urllib_parse_urlencode({
b78b292f
S
1333 'lang': original_lang,
1334 'tlang': sub_lang,
1335 'fmt': ext,
1336 'ts': timestamp,
1337 'kind': caption_kind,
1338 })
1339 sub_formats.append({
1340 'url': caption_url + '&' + params,
1341 'ext': ext,
1342 })
1343 sub_lang_list[sub_lang] = sub_formats
1344 return sub_lang_list
1345
ddbb4c5c
S
1346 def make_captions(sub_url, sub_langs):
1347 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1348 caption_qs = compat_parse_qs(parsed_sub_url.query)
1349 captions = {}
1350 for sub_lang in sub_langs:
1351 sub_formats = []
1352 for ext in self._SUBTITLE_FORMATS:
1353 caption_qs.update({
1354 'tlang': [sub_lang],
1355 'fmt': [ext],
1356 })
1357 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1358 query=compat_urllib_parse_urlencode(caption_qs, True)))
1359 sub_formats.append({
1360 'url': sub_url,
1361 'ext': ext,
1362 })
1363 captions[sub_lang] = sub_formats
1364 return captions
1365
1366 # New captions format as of 22.06.2017
1367 player_response = args.get('player_response')
1368 if player_response and isinstance(player_response, compat_str):
1369 player_response = self._parse_json(
1370 player_response, video_id, fatal=False)
1371 if player_response:
1372 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1373 base_url = renderer['captionTracks'][0]['baseUrl']
1374 sub_lang_list = []
1375 for lang in renderer['translationLanguages']:
1376 lang_code = lang.get('languageCode')
1377 if lang_code:
1378 sub_lang_list.append(lang_code)
1379 return make_captions(base_url, sub_lang_list)
1380
b78b292f
S
1381 # Some videos don't provide ttsurl but rather caption_tracks and
1382 # caption_translation_languages (e.g. 20LmZk1hakA)
ddbb4c5c 1383 # Does not used anymore as of 22.06.2017
b78b292f
S
1384 caption_tracks = args['caption_tracks']
1385 caption_translation_languages = args['caption_translation_languages']
1386 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
ddbb4c5c 1387 sub_lang_list = []
b78b292f
S
1388 for lang in caption_translation_languages.split(','):
1389 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1390 sub_lang = lang_qs.get('lc', [None])[0]
ddbb4c5c
S
1391 if sub_lang:
1392 sub_lang_list.append(sub_lang)
1393 return make_captions(caption_url, sub_lang_list)
de7f3446
JMF
1394 # An extractor error can be raise by the download process if there are
1395 # no automatic captions but there are subtitles
ddbb4c5c 1396 except (KeyError, IndexError, ExtractorError):
de7f3446
JMF
1397 self._downloader.report_warning(err_msg)
1398 return {}
1399
21c340b8
S
1400 def _mark_watched(self, video_id, video_info, player_response):
1401 playback_url = url_or_none(try_get(
1402 player_response,
1403 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1404 video_info, lambda x: x['videostats_playback_base_url'][0]))
d77ab8e2
S
1405 if not playback_url:
1406 return
1407 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1408 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1409
1410 # cpn generation algorithm is reverse engineered from base.js.
1411 # In fact it works even with dummy cpn.
1412 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1413 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1414
1415 qs.update({
1416 'ver': ['2'],
1417 'cpn': [cpn],
1418 })
1419 playback_url = compat_urlparse.urlunparse(
15707c7e 1420 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1421
1422 self._download_webpage(
1423 playback_url, video_id, 'Marking watched',
1424 'Unable to mark watched', fatal=False)
1425
66c9fa36
S
1426 @staticmethod
1427 def _extract_urls(webpage):
1428 # Embedded YouTube player
1429 entries = [
1430 unescapeHTML(mobj.group('url'))
1431 for mobj in re.finditer(r'''(?x)
1432 (?:
1433 <iframe[^>]+?src=|
1434 data-video-url=|
1435 <embed[^>]+?src=|
1436 embedSWF\(?:\s*|
1437 <object[^>]+data=|
1438 new\s+SWFObject\(
1439 )
1440 (["\'])
1441 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 1442 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
1443 \1''', webpage)]
1444
1445 # lazyYT YouTube embed
1446 entries.extend(list(map(
1447 unescapeHTML,
1448 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1449
1450 # Wordpress "YouTube Video Importer" plugin
1451 matches = re.findall(r'''(?x)<div[^>]+
1452 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1453 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1454 entries.extend(m[-1] for m in matches)
1455
1456 return entries
1457
1458 @staticmethod
1459 def _extract_url(webpage):
1460 urls = YoutubeIE._extract_urls(webpage)
1461 return urls[0] if urls else None
1462
97665381
PH
1463 @classmethod
1464 def extract_id(cls, url):
1465 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1466 if mobj is None:
69ea8ca4 1467 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1468 video_id = mobj.group(2)
1469 return video_id
1470
1fb07d10
JG
1471 def _extract_annotations(self, video_id):
1472 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1473 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1474
9cafc3fd
S
1475 @staticmethod
1476 def _extract_chapters(description, duration):
1477 if not description:
1478 return None
1479 chapter_lines = re.findall(
1480 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1481 description)
1482 if not chapter_lines:
1483 return None
1484 chapters = []
1485 for next_num, (chapter_line, time_point) in enumerate(
1486 chapter_lines, start=1):
1487 start_time = parse_duration(time_point)
1488 if start_time is None:
1489 continue
39d4c1be
S
1490 if start_time > duration:
1491 break
9cafc3fd
S
1492 end_time = (duration if next_num == len(chapter_lines)
1493 else parse_duration(chapter_lines[next_num][1]))
1494 if end_time is None:
1495 continue
39d4c1be
S
1496 if end_time > duration:
1497 end_time = duration
1498 if start_time > end_time:
1499 break
9cafc3fd
S
1500 chapter_title = re.sub(
1501 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1502 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1503 chapters.append({
1504 'start_time': start_time,
1505 'end_time': end_time,
1506 'title': chapter_title,
1507 })
1508 return chapters
1509
c5e8d7af 1510 def _real_extract(self, url):
cf7e015f
S
1511 url, smuggled_data = unsmuggle_url(url, {})
1512
7e8c0af0 1513 proto = (
78caa52a
PH
1514 'http' if self._downloader.params.get('prefer_insecure', False)
1515 else 'https')
7e8c0af0 1516
7c80519c 1517 start_time = None
297a564b 1518 end_time = None
7c80519c
JMF
1519 parsed_url = compat_urllib_parse_urlparse(url)
1520 for component in [parsed_url.fragment, parsed_url.query]:
1521 query = compat_parse_qs(component)
297a564b 1522 if start_time is None and 't' in query:
7c80519c 1523 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1524 if start_time is None and 'start' in query:
1525 start_time = parse_duration(query['start'][0])
297a564b
JMF
1526 if end_time is None and 'end' in query:
1527 end_time = parse_duration(query['end'][0])
7c80519c 1528
c5e8d7af
PH
1529 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1530 mobj = re.search(self._NEXT_URL_RE, url)
1531 if mobj:
7fd002c0 1532 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1533 video_id = self.extract_id(url)
c5e8d7af
PH
1534
1535 # Get video webpage
aa79ac0c 1536 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1537 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1538
1539 # Attempt to extract SWF player URL
e0df6211 1540 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1541 if mobj is not None:
1542 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1543 else:
1544 player_url = None
1545
d8d24a92
S
1546 dash_mpds = []
1547
1548 def add_dash_mpd(video_info):
1549 dash_mpd = video_info.get('dashmpd')
1550 if dash_mpd and dash_mpd[0] not in dash_mpds:
1551 dash_mpds.append(dash_mpd[0])
1552
561b456e
S
1553 def add_dash_mpd_pr(pl_response):
1554 dash_mpd = url_or_none(try_get(
1555 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1556 compat_str))
1557 if dash_mpd and dash_mpd not in dash_mpds:
1558 dash_mpds.append(dash_mpd)
1559
c7121fa7
S
1560 is_live = None
1561 view_count = None
1562
1563 def extract_view_count(v_info):
1564 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1565
dbdaaa23
S
1566 player_response = {}
1567
c5e8d7af 1568 # Get video info
6449cd80 1569 embed_webpage = None
c108eb73 1570 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1571 age_gate = True
1572 # We simulate the access to the video from www.youtube.com/v/{video_id}
1573 # this can be viewed without login into Youtube
beb95e77
CL
1574 url = proto + '://www.youtube.com/embed/%s' % video_id
1575 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1576 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1577 'video_id': video_id,
1578 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1579 'sts': self._search_regex(
beb95e77 1580 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1581 })
7e8c0af0 1582 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1583 video_info_webpage = self._download_webpage(
1584 video_info_url, video_id,
20436c30 1585 note='Refetching age-gated info webpage',
94bd3613 1586 errnote='unable to download video info webpage')
c5e8d7af 1587 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1588 add_dash_mpd(video_info)
c108eb73
JMF
1589 else:
1590 age_gate = False
bc93bdb5 1591 video_info = None
dc4e4f90 1592 sts = None
d8d24a92 1593 # Try looking directly into the video webpage
a72778d3
S
1594 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1595 if ytplayer_config:
4e62ebe2 1596 args = ytplayer_config['args']
4c76aa06 1597 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
d8d24a92
S
1598 # Convert to the same format returned by compat_parse_qs
1599 video_info = dict((k, [v]) for k, v in args.items())
1600 add_dash_mpd(video_info)
6496ccb4
S
1601 # Rental video is not rented but preview is available (e.g.
1602 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
067aa17e 1603 # https://github.com/ytdl-org/youtube-dl/issues/10532)
6496ccb4
S
1604 if not video_info and args.get('ypc_vid'):
1605 return self.url_result(
1606 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
2fe1ff85
JMF
1607 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1608 is_live = True
dc4e4f90 1609 sts = ytplayer_config.get('sts')
dbdaaa23
S
1610 if not player_response:
1611 pl_response = str_or_none(args.get('player_response'))
1612 if pl_response:
1613 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1614 if isinstance(pl_response, dict):
1615 player_response = pl_response
0a3cf9ad 1616 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
561b456e 1617 add_dash_mpd_pr(player_response)
0a3cf9ad
S
1618 # We also try looking in get_video_info since it may contain different dashmpd
1619 # URL that points to a DASH manifest with possibly different itag set (some itags
1620 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1621 # manifest pointed by get_video_info's dashmpd).
1622 # The general idea is to take a union of itags of both DASH manifests (for example
067aa17e 1623 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
4e62ebe2 1624 self.report_video_info_webpage_download(video_id)
dc4e4f90
S
1625 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1626 query = {
1627 'video_id': video_id,
1628 'ps': 'default',
1629 'eurl': '',
1630 'gl': 'US',
1631 'hl': 'en',
1632 }
1633 if el:
1634 query['el'] = el
1635 if sts:
1636 query['sts'] = sts
810fb84d 1637 video_info_webpage = self._download_webpage(
dc4e4f90 1638 '%s://www.youtube.com/get_video_info' % proto,
4e62ebe2 1639 video_id, note=False,
dc4e4f90
S
1640 errnote='unable to download video info webpage',
1641 fatal=False, query=query)
1642 if not video_info_webpage:
1643 continue
0a3cf9ad 1644 get_video_info = compat_parse_qs(video_info_webpage)
dbdaaa23
S
1645 if not player_response:
1646 pl_response = get_video_info.get('player_response', [None])[0]
1647 if isinstance(pl_response, dict):
1648 player_response = pl_response
561b456e 1649 add_dash_mpd_pr(player_response)
fd545fc6 1650 add_dash_mpd(get_video_info)
c7121fa7
S
1651 if view_count is None:
1652 view_count = extract_view_count(get_video_info)
0a3cf9ad
S
1653 if not video_info:
1654 video_info = get_video_info
56667d62
S
1655 get_token = get_video_info.get('token') or get_video_info.get('account_playback_token')
1656 if get_token:
89ea063e
S
1657 # Different get_video_info requests may report different results, e.g.
1658 # some may report video unavailability, but some may serve it without
067aa17e 1659 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
89ea063e
S
1660 # the original webpage as well as el=info and el=embedded get_video_info
1661 # requests report video unavailability due to geo restriction while
1662 # el=detailpage succeeds and returns valid data). This is probably
1663 # due to YouTube measures against IP ranges of hosting providers.
1664 # Working around by preferring the first succeeded video_info containing
1665 # the token if no such video_info yet was found.
56667d62
S
1666 token = video_info.get('token') or video_info.get('account_playback_token')
1667 if not token:
44b2264f 1668 video_info = get_video_info
4e62ebe2 1669 break
bbb7c3f7
YCH
1670
1671 def extract_unavailable_message():
1672 return self._html_search_regex(
1673 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1674 video_webpage, 'unavailable message', default=None)
1675
15be3eb5
RA
1676 if not video_info:
1677 unavailable_message = extract_unavailable_message()
1678 if not unavailable_message:
1679 unavailable_message = 'Unable to extract video data'
1680 raise ExtractorError(
1681 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1682
56667d62
S
1683 token = video_info.get('token') or video_info.get('account_playback_token')
1684 if not token:
c5e8d7af 1685 if 'reason' in video_info:
af214c3a 1686 if 'The uploader has not made this video available in your country.' in video_info['reason']:
fd5c4aab
S
1687 regions_allowed = self._html_search_meta(
1688 'regionsAllowed', video_webpage, default=None)
1689 countries = regions_allowed.split(',') if regions_allowed else None
1690 self.raise_geo_restricted(
1691 msg=video_info['reason'][0], countries=countries)
bbb7c3f7
YCH
1692 reason = video_info['reason'][0]
1693 if 'Invalid parameters' in reason:
1694 unavailable_message = extract_unavailable_message()
1695 if unavailable_message:
1696 reason = unavailable_message
d11271dd 1697 raise ExtractorError(
bbb7c3f7 1698 'YouTube said: %s' % reason,
d11271dd 1699 expected=True, video_id=video_id)
c5e8d7af 1700 else:
d11271dd 1701 raise ExtractorError(
78caa52a 1702 '"token" parameter not in video info for unknown reason',
d11271dd 1703 video_id=video_id)
c5e8d7af 1704
825cd268
RA
1705 if video_info.get('license_info'):
1706 raise ExtractorError('This video is DRM protected.', expected=True)
1707
dbdaaa23
S
1708 video_details = try_get(
1709 player_response, lambda x: x['videoDetails'], dict) or {}
1710
cf7e015f
S
1711 # title
1712 if 'title' in video_info:
1713 video_title = video_info['title'][0]
dbdaaa23
S
1714 elif 'title' in player_response:
1715 video_title = video_details['title']
cf7e015f
S
1716 else:
1717 self._downloader.report_warning('Unable to extract video title')
1718 video_title = '_'
1719
1720 # description
9cafc3fd 1721 description_original = video_description = get_element_by_id("eow-description", video_webpage)
cf7e015f 1722 if video_description:
fa4bc6e7
RA
1723
1724 def replace_url(m):
1725 redir_url = compat_urlparse.urljoin(url, m.group(1))
1726 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1727 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1728 qs = compat_parse_qs(parsed_redir_url.query)
1729 q = qs.get('q')
1730 if q and q[0]:
1731 return q[0]
1732 return redir_url
1733
9cafc3fd 1734 description_original = video_description = re.sub(r'''(?x)
cf7e015f 1735 <a\s+
25cb7a0e 1736 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1737 (?:title|href)="([^"]+)"\s+
25cb7a0e 1738 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1739 class="[^"]*"[^>]*>
23f13e97 1740 [^<]+\.{3}\s*
cf7e015f 1741 </a>
fa4bc6e7 1742 ''', replace_url, video_description)
cf7e015f
S
1743 video_description = clean_html(video_description)
1744 else:
1745 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1746 if fd_mobj:
1747 video_description = unescapeHTML(fd_mobj.group(1))
1748 else:
1749 video_description = ''
1750
8fe10494 1751 if not smuggled_data.get('force_singlefeed', False):
5e1eddb9 1752 if not self._downloader.params.get('noplaylist'):
8fe10494
S
1753 multifeed_metadata_list = try_get(
1754 player_response,
1755 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1756 compat_str) or try_get(
1757 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1758 if multifeed_metadata_list:
1759 entries = []
1760 feed_ids = []
1761 for feed in multifeed_metadata_list.split(','):
1762 # Unquote should take place before split on comma (,) since textual
1763 # fields may contain comma as well (see
067aa17e 1764 # https://github.com/ytdl-org/youtube-dl/issues/8536)
8fe10494
S
1765 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1766 entries.append({
1767 '_type': 'url_transparent',
1768 'ie_key': 'Youtube',
1769 'url': smuggle_url(
1770 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1771 {'force_singlefeed': True}),
1772 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1773 })
1774 feed_ids.append(feed_data['id'][0])
1775 self.to_screen(
1776 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1777 % (', '.join(feed_ids), video_id))
1778 return self.playlist_result(entries, video_id, video_title, video_description)
1779 else:
1780 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1781
c7121fa7 1782 if view_count is None:
1c9c8de2 1783 view_count = extract_view_count(video_info)
dbdaaa23
S
1784 if view_count is None and video_details:
1785 view_count = int_or_none(video_details.get('viewCount'))
1d699755 1786
c5e8d7af
PH
1787 # Check for "rental" videos
1788 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
067aa17e 1789 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
c5e8d7af 1790
c63ca0ee
S
1791 def _extract_filesize(media_url):
1792 return int_or_none(self._search_regex(
1793 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1794
c5e8d7af
PH
1795 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1796 self.report_rtmp_download()
dd27fd17
PH
1797 formats = [{
1798 'format_id': '_rtmp',
1799 'protocol': 'rtmp',
1800 'url': video_info['conn'][0],
1801 'player_url': player_url,
1802 }]
391dd6f0 1803 elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
5f6a1245 1804 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1805 if 'rtmpe%3Dyes' in encoded_url_map:
067aa17e 1806 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1807 formats_spec = {}
82156fdb 1808 fmt_list = video_info.get('fmt_list', [''])[0]
1809 if fmt_list:
1810 for fmt in fmt_list.split(','):
1811 spec = fmt.split('/')
3318832e 1812 if len(spec) > 1:
1813 width_height = spec[1].split('x')
1814 if len(width_height) == 2:
1815 formats_spec[spec[0]] = {
1816 'resolution': spec[1],
1817 'width': int_or_none(width_height[0]),
1818 'height': int_or_none(width_height[1]),
1819 }
54fc90aa 1820 q = qualities(['small', 'medium', 'hd720'])
140a13f5
RA
1821 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1822 if streaming_formats:
1823 for fmt in streaming_formats:
1824 itag = str_or_none(fmt.get('itag'))
1825 if not itag:
1826 continue
1827 quality = fmt.get('quality')
1828 quality_label = fmt.get('qualityLabel') or quality
1829 formats_spec[itag] = {
1830 'asr': int_or_none(fmt.get('audioSampleRate')),
1831 'filesize': int_or_none(fmt.get('contentLength')),
1832 'format_note': quality_label,
1833 'fps': int_or_none(fmt.get('fps')),
1834 'height': int_or_none(fmt.get('height')),
1835 'quality': q(quality),
1836 # bitrate for itag 43 is always 2147483647
1837 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1838 'width': int_or_none(fmt.get('width')),
1839 }
c9afb51c 1840 formats = []
00fe14fc 1841 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1842 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1843 if 'itag' not in url_data or 'url' not in url_data:
1844 continue
2f483bc1
S
1845 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1846 # Unsupported FORMAT_STREAM_TYPE_OTF
1847 if stream_type == 3:
1848 continue
201e9eaa
PH
1849 format_id = url_data['itag'][0]
1850 url = url_data['url'][0]
1851
a49eccdf 1852 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
6449cd80 1853 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
beb95e77 1854 jsplayer_url_json = self._search_regex(
6449cd80
PH
1855 ASSETS_RE,
1856 embed_webpage if age_gate else video_webpage,
1857 'JS player URL (1)', default=None)
1858 if not jsplayer_url_json and not age_gate:
1859 # We need the embed website after all
1860 if embed_webpage is None:
1861 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1862 embed_webpage = self._download_webpage(
1863 embed_url, video_id, 'Downloading embed webpage')
1864 jsplayer_url_json = self._search_regex(
1865 ASSETS_RE, embed_webpage, 'JS player URL')
1866
beb95e77 1867 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1868 if player_url is None:
1869 player_url_json = self._search_regex(
1870 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1871 video_webpage, 'age gate player URL')
201e9eaa
PH
1872 player_url = json.loads(player_url_json)
1873
a49eccdf
YCH
1874 if 'sig' in url_data:
1875 url += '&signature=' + url_data['sig'][0]
1876 elif 's' in url_data:
1877 encrypted_sig = url_data['s'][0]
1878
201e9eaa 1879 if self._downloader.params.get('verbose'):
cf010131 1880 if player_url is None:
201e9eaa
PH
1881 player_version = 'unknown'
1882 player_desc = 'unknown'
1883 else:
1884 if player_url.endswith('swf'):
1885 player_version = self._search_regex(
1886 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1887 'flash player', fatal=False)
201e9eaa 1888 player_desc = 'flash player %s' % player_version
cf010131 1889 else:
201e9eaa 1890 player_version = self._search_regex(
b62985a9 1891 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
63529e93 1892 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
201e9eaa
PH
1893 player_url,
1894 'html5 player', fatal=False)
78caa52a 1895 player_desc = 'html5 player %s' % player_version
201e9eaa 1896
60064c53 1897 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1898 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1899 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1900
1901 signature = self._decrypt_signature(
1902 encrypted_sig, video_id, player_url, age_gate)
1903 url += '&signature=' + signature
1904 if 'ratebypass' not in url:
1905 url += '&ratebypass=yes'
c9afb51c 1906
94278f72
YCH
1907 dct = {
1908 'format_id': format_id,
1909 'url': url,
1910 'player_url': player_url,
1911 }
1912 if format_id in self._formats:
1913 dct.update(self._formats[format_id])
3318832e 1914 if format_id in formats_spec:
1915 dct.update(formats_spec[format_id])
94278f72 1916
aabc2be6 1917 # Some itags are not included in DASH manifest thus corresponding formats will
067aa17e 1918 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
aabc2be6
S
1919 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1920 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1921 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72 1922
c63ca0ee
S
1923 filesize = int_or_none(url_data.get(
1924 'clen', [None])[0]) or _extract_filesize(url)
1925
140a13f5 1926 quality = url_data.get('quality', [None])[0]
54fc90aa 1927
94278f72 1928 more_fields = {
c63ca0ee 1929 'filesize': filesize,
aabc2be6 1930 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1931 'width': width,
1932 'height': height,
1933 'fps': int_or_none(url_data.get('fps', [None])[0]),
140a13f5 1934 'format_note': url_data.get('quality_label', [None])[0] or quality,
54fc90aa 1935 'quality': q(quality),
c9afb51c 1936 }
94278f72
YCH
1937 for key, value in more_fields.items():
1938 if value:
1939 dct[key] = value
aabc2be6
S
1940 type_ = url_data.get('type', [None])[0]
1941 if type_:
1942 type_split = type_.split(';')
1943 kind_ext = type_split[0].split('/')
1944 if len(kind_ext) == 2:
94278f72
YCH
1945 kind, _ = kind_ext
1946 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1947 if kind in ('audio', 'video'):
1948 codecs = None
1949 for mobj in re.finditer(
1950 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1951 if mobj.group('key') == 'codecs':
1952 codecs = mobj.group('val')
1953 break
1954 if codecs:
6310acf5 1955 dct.update(parse_codecs(codecs))
e4a60912
S
1956 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
1957 dct['downloader_options'] = {
1958 # Youtube throttles chunks >~10M
1959 'http_chunk_size': 10485760,
1960 }
aabc2be6 1961 formats.append(dct)
c5e8d7af 1962 else:
c3e54389
S
1963 manifest_url = (
1964 url_or_none(try_get(
1965 player_response,
1966 lambda x: x['streamingData']['hlsManifestUrl'],
1967 compat_str)) or
1968 url_or_none(try_get(
1969 video_info, lambda x: x['hlsvp'][0], compat_str)))
1970 if manifest_url:
1971 formats = []
1972 m3u8_formats = self._extract_m3u8_formats(
1973 manifest_url, video_id, 'mp4', fatal=False)
1974 for a_format in m3u8_formats:
1975 itag = self._search_regex(
1976 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1977 if itag:
1978 a_format['format_id'] = itag
1979 if itag in self._formats:
1980 dct = self._formats[itag].copy()
1981 dct.update(a_format)
1982 a_format = dct
1983 a_format['player_url'] = player_url
1984 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1985 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1986 formats.append(a_format)
1987 else:
1988 error_message = clean_html(video_info.get('reason', [None])[0])
1989 if not error_message:
1990 error_message = extract_unavailable_message()
1991 if error_message:
1992 raise ExtractorError(error_message, expected=True)
1993 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1994
7e72694b 1995 # uploader
dbdaaa23
S
1996 video_uploader = try_get(
1997 video_info, lambda x: x['author'][0],
1998 compat_str) or str_or_none(video_details.get('author'))
7e72694b
S
1999 if video_uploader:
2000 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2001 else:
2002 self._downloader.report_warning('unable to extract uploader name')
2003
2004 # uploader_id
2005 video_uploader_id = None
2006 video_uploader_url = None
2007 mobj = re.search(
2008 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2009 video_webpage)
2010 if mobj is not None:
2011 video_uploader_id = mobj.group('uploader_id')
2012 video_uploader_url = mobj.group('uploader_url')
2013 else:
2014 self._downloader.report_warning('unable to extract uploader nickname')
2015
dd4c4492
S
2016 channel_id = self._html_search_meta(
2017 'channelId', video_webpage, 'channel id')
2018 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2019
7e72694b
S
2020 # thumbnail image
2021 # We try first to get a high quality image:
2022 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2023 video_webpage, re.DOTALL)
2024 if m_thumb is not None:
2025 video_thumbnail = m_thumb.group(1)
2026 elif 'thumbnail_url' not in video_info:
2027 self._downloader.report_warning('unable to extract video thumbnail')
2028 video_thumbnail = None
2029 else: # don't panic if we can't find it
2030 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2031
2032 # upload date
2033 upload_date = self._html_search_meta(
2034 'datePublished', video_webpage, 'upload date', default=None)
2035 if not upload_date:
2036 upload_date = self._search_regex(
2037 [r'(?s)id="eow-date.*?>(.*?)</span>',
2038 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2039 video_webpage, 'upload date', default=None)
2040 upload_date = unified_strdate(upload_date)
2041
2042 video_license = self._html_search_regex(
2043 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2044 video_webpage, 'license', default=None)
2045
2046 m_music = re.search(
2047 r'''(?x)
2048 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2049 <ul[^>]*>\s*
2050 <li>(?P<title>.+?)
2051 by (?P<creator>.+?)
2052 (?:
2053 \(.+?\)|
2054 <a[^>]*
2055 (?:
2056 \bhref=["\']/red[^>]*>| # drop possible
2057 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2058 )
2059 .*?
2060 )?</li
2061 ''',
2062 video_webpage)
2063 if m_music:
2064 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2065 video_creator = clean_html(m_music.group('creator'))
2066 else:
2067 video_alt_title = video_creator = None
2068
2069 def extract_meta(field):
2070 return self._html_search_regex(
2071 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2072 video_webpage, field, default=None)
2073
2074 track = extract_meta('Song')
2075 artist = extract_meta('Artist')
2076
2077 m_episode = re.search(
2078 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2079 video_webpage)
2080 if m_episode:
c2dd2dc0 2081 series = unescapeHTML(m_episode.group('series'))
7e72694b
S
2082 season_number = int(m_episode.group('season'))
2083 episode_number = int(m_episode.group('episode'))
2084 else:
2085 series = season_number = episode_number = None
2086
2087 m_cat_container = self._search_regex(
2088 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2089 video_webpage, 'categories', default=None)
2090 if m_cat_container:
2091 category = self._html_search_regex(
2092 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2093 default=None)
2094 video_categories = None if category is None else [category]
2095 else:
2096 video_categories = None
2097
2098 video_tags = [
2099 unescapeHTML(m.group('content'))
2100 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2101
2102 def _extract_count(count_name):
2103 return str_to_int(self._search_regex(
2104 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2105 % re.escape(count_name),
2106 video_webpage, count_name, default=None))
2107
2108 like_count = _extract_count('like')
2109 dislike_count = _extract_count('dislike')
2110
dbdaaa23
S
2111 if view_count is None:
2112 view_count = str_to_int(self._search_regex(
2113 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2114 'view count', default=None))
2115
7e72694b
S
2116 # subtitles
2117 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2118 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2119
2120 video_duration = try_get(
2121 video_info, lambda x: int_or_none(x['length_seconds'][0]))
dbdaaa23
S
2122 if not video_duration:
2123 video_duration = int_or_none(video_details.get('lengthSeconds'))
7e72694b
S
2124 if not video_duration:
2125 video_duration = parse_duration(self._html_search_meta(
2126 'duration', video_webpage, 'video duration'))
2127
2128 # annotations
2129 video_annotations = None
2130 if self._downloader.params.get('writeannotations', False):
2131 video_annotations = self._extract_annotations(video_id)
2132
2133 chapters = self._extract_chapters(description_original, video_duration)
2134
dd27fd17 2135 # Look for the DASH manifest
203fb43f 2136 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 2137 dash_mpd_fatal = True
8ff648e4 2138 for mpd_url in dash_mpds:
d8d24a92 2139 dash_formats = {}
774e208f 2140 try:
05d0d131
YCH
2141 def decrypt_sig(mobj):
2142 s = mobj.group(1)
2143 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2144 return '/signature/%s' % dec_s
2145
8ff648e4 2146 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 2147
8ff648e4 2148 for df in self._extract_mpd_formats(
2149 mpd_url, video_id, fatal=dash_mpd_fatal,
2150 formats_dict=self._formats):
c63ca0ee
S
2151 if not df.get('filesize'):
2152 df['filesize'] = _extract_filesize(df['url'])
d8d24a92
S
2153 # Do not overwrite DASH format found in some previous DASH manifest
2154 if df['format_id'] not in dash_formats:
2155 dash_formats[df['format_id']] = df
77c6fb5b
S
2156 # Additional DASH manifests may end up in HTTP Error 403 therefore
2157 # allow them to fail without bug report message if we already have
2158 # some DASH manifest succeeded. This is temporary workaround to reduce
2159 # burst of bug reports until we figure out the reason and whether it
2160 # can be fixed at all.
2161 dash_mpd_fatal = False
774e208f
PH
2162 except (ExtractorError, KeyError) as e:
2163 self.report_warning(
2164 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 2165 if dash_formats:
04b3b3df
JMF
2166 # Remove the formats we found through non-DASH, they
2167 # contain less info and it can be wrong, because we use
2168 # fixed values (for example the resolution). See
067aa17e 2169 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
04b3b3df 2170 # example.
d80265cc 2171 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 2172 formats.extend(dash_formats.values())
d80044c2 2173
6271f1ca
PH
2174 # Check for malformed aspect ratio
2175 stretched_m = re.search(
2176 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2177 video_webpage)
2178 if stretched_m:
313dfc45
LL
2179 w = float(stretched_m.group('w'))
2180 h = float(stretched_m.group('h'))
5faf9fed
S
2181 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2182 # We will only process correct ratios.
313dfc45 2183 if w > 0 and h > 0:
41f24c32 2184 ratio = w / h
313dfc45
LL
2185 for f in formats:
2186 if f.get('vcodec') != 'none':
2187 f['stretched_ratio'] = ratio
6271f1ca 2188
4bcc7bd1 2189 self._sort_formats(formats)
4ea3be0a 2190
21c340b8 2191 self.mark_watched(video_id, video_info, player_response)
d77ab8e2 2192
4ea3be0a 2193 return {
8bcc8756
JW
2194 'id': video_id,
2195 'uploader': video_uploader,
2196 'uploader_id': video_uploader_id,
fd050249 2197 'uploader_url': video_uploader_url,
dd4c4492
S
2198 'channel_id': channel_id,
2199 'channel_url': channel_url,
8bcc8756 2200 'upload_date': upload_date,
7caf9830 2201 'license': video_license,
936784b2 2202 'creator': video_creator or artist,
8bcc8756 2203 'title': video_title,
936784b2 2204 'alt_title': video_alt_title or track,
8bcc8756
JW
2205 'thumbnail': video_thumbnail,
2206 'description': video_description,
2207 'categories': video_categories,
000b6b5a 2208 'tags': video_tags,
8bcc8756 2209 'subtitles': video_subtitles,
360e1ca5 2210 'automatic_captions': automatic_captions,
8bcc8756
JW
2211 'duration': video_duration,
2212 'age_limit': 18 if age_gate else 0,
2213 'annotations': video_annotations,
9cafc3fd 2214 'chapters': chapters,
7e8c0af0 2215 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 2216 'view_count': view_count,
4ea3be0a 2217 'like_count': like_count,
2218 'dislike_count': dislike_count,
2d30521a 2219 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 2220 'formats': formats,
2fe1ff85 2221 'is_live': is_live,
7c80519c 2222 'start_time': start_time,
297a564b 2223 'end_time': end_time,
12afdc2a
S
2224 'series': series,
2225 'season_number': season_number,
2226 'episode_number': episode_number,
936784b2
S
2227 'track': track,
2228 'artist': artist,
4ea3be0a 2229 }
c5e8d7af 2230
5f6a1245 2231
8e7aad20 2232class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2233 IE_DESC = 'YouTube.com playlists'
d67cc9fa 2234 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
2235 (?:https?://)?
2236 (?:\w+\.)?
c5e8d7af 2237 (?:
c0345b82
S
2238 (?:
2239 youtube\.com|
2240 invidio\.us
2241 )
2242 /
feaa5ad7 2243 (?:
87dadd45 2244 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
feaa5ad7
S
2245 \? (?:.*?[&;])*? (?:p|a|list)=
2246 | p/
2247 )|
2248 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
c5e8d7af 2249 )
d67cc9fa 2250 (
409b9324 2251 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
5f6a1245 2252 # Top tracks, they can also include dots
d67cc9fa
JMF
2253 |(?:MC)[\w\.]*
2254 )
c5e8d7af
PH
2255 .*
2256 |
d0ba5587
S
2257 (%(playlist_id)s)
2258 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
8d81f3e3 2259 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
648e6a1f 2260 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 2261 IE_NAME = 'youtube:playlist'
81127aa5
PH
2262 _TESTS = [{
2263 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2264 'info_dict': {
2265 'title': 'ytdl test PL',
a1cf99d0 2266 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
2267 },
2268 'playlist_count': 3,
9291475f
PH
2269 }, {
2270 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2271 'info_dict': {
acf757f4 2272 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
2273 'title': 'YDL_Empty_List',
2274 },
2275 'playlist_count': 0,
4201ba13 2276 'skip': 'This playlist is private',
9291475f
PH
2277 }, {
2278 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2279 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2280 'info_dict': {
2281 'title': '29C3: Not my department',
acf757f4 2282 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
2283 },
2284 'playlist_count': 95,
2285 }, {
2286 'note': 'issue #673',
2287 'url': 'PLBB231211A4F62143',
2288 'info_dict': {
f46a8702 2289 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 2290 'id': 'PLBB231211A4F62143',
9291475f
PH
2291 },
2292 'playlist_mincount': 26,
2293 }, {
2294 'note': 'Large playlist',
2295 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2296 'info_dict': {
2297 'title': 'Uploads from Cauchemar',
acf757f4 2298 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
2299 },
2300 'playlist_mincount': 799,
2301 }, {
2302 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2303 'info_dict': {
2304 'title': 'YDL_safe_search',
acf757f4 2305 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
2306 },
2307 'playlist_count': 2,
4201ba13 2308 'skip': 'This playlist is private',
ac7553d0
PH
2309 }, {
2310 'note': 'embedded',
2d3d2997 2311 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0
PH
2312 'playlist_count': 4,
2313 'info_dict': {
2314 'title': 'JODA15',
acf757f4 2315 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 2316 }
87dadd45
S
2317 }, {
2318 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2319 'playlist_mincount': 485,
2320 'info_dict': {
2321 'title': '2017 華語最新單曲 (2/24更新)',
2322 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2323 }
6b08cdf6
PH
2324 }, {
2325 'note': 'Embedded SWF player',
2d3d2997 2326 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
6b08cdf6
PH
2327 'playlist_count': 4,
2328 'info_dict': {
2329 'title': 'JODA7',
acf757f4 2330 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 2331 }
4b7df0d3
JMF
2332 }, {
2333 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2334 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2335 'info_dict': {
acf757f4
PH
2336 'title': 'Uploads from Interstellar Movie',
2337 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 2338 },
481cc733 2339 'playlist_mincount': 21,
dacb3a86
S
2340 }, {
2341 # Playlist URL that does not actually serve a playlist
2342 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2343 'info_dict': {
2344 'id': 'FqZTN594JQw',
2345 'ext': 'webm',
2346 'title': "Smiley's People 01 detective, Adventure Series, Action",
2347 'uploader': 'STREEM',
2348 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 2349 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
2350 'upload_date': '20150526',
2351 'license': 'Standard YouTube License',
2352 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2353 'categories': ['People & Blogs'],
2354 'tags': list,
dbdaaa23 2355 'view_count': int,
dacb3a86
S
2356 'like_count': int,
2357 'dislike_count': int,
2358 },
2359 'params': {
2360 'skip_download': True,
2361 },
2362 'add_ie': [YoutubeIE.ie_key()],
481cc733
S
2363 }, {
2364 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2365 'info_dict': {
2366 'id': 'yeWKywCrFtk',
2367 'ext': 'mp4',
2368 'title': 'Small Scale Baler and Braiding Rugs',
2369 'uploader': 'Backus-Page House Museum',
2370 'uploader_id': 'backuspagemuseum',
ec85ded8 2371 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
481cc733
S
2372 'upload_date': '20161008',
2373 'license': 'Standard YouTube License',
2374 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2375 'categories': ['Nonprofits & Activism'],
2376 'tags': list,
2377 'like_count': int,
2378 'dislike_count': int,
2379 },
2380 'params': {
2381 'noplaylist': True,
2382 'skip_download': True,
2383 },
feaa5ad7
S
2384 }, {
2385 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2386 'only_matching': True,
a6857510
S
2387 }, {
2388 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2389 'only_matching': True,
409b9324
S
2390 }, {
2391 # music album playlist
2392 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2393 'only_matching': True,
c0345b82
S
2394 }, {
2395 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2396 'only_matching': True,
81127aa5 2397 }]
c5e8d7af 2398
880e1c52
JMF
2399 def _real_initialize(self):
2400 self._login()
2401
652cdaa2 2402 def _extract_mix(self, playlist_id):
99209c29 2403 # The mixes are generated from a single video
652cdaa2 2404 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
2405 ids = []
2406 last_id = playlist_id[-11:]
2407 for n in itertools.count(1):
2408 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2409 webpage = self._download_webpage(
2410 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2411 new_ids = orderedSet(re.findall(
2412 r'''(?xs)data-video-username=".*?".*?
2413 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
2414 webpage))
2415 # Fetch new pages until all the videos are repeated, it seems that
2416 # there are always 51 unique videos.
2417 new_ids = [_id for _id in new_ids if _id not in ids]
2418 if not new_ids:
2419 break
2420 ids.extend(new_ids)
2421 last_id = ids[-1]
2422
2423 url_results = self._ids_to_results(ids)
2424
bc2f773b 2425 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
2426 title_span = (
2427 search_title('playlist-title') or
2428 search_title('title long-title') or
2429 search_title('title'))
76d1700b 2430 title = clean_html(title_span)
652cdaa2
JMF
2431
2432 return self.playlist_result(url_results, playlist_id, title)
2433
448830ce 2434 def _extract_playlist(self, playlist_id):
dbb94fb0
S
2435 url = self._TEMPLATE_URL % playlist_id
2436 page = self._download_webpage(url, playlist_id)
dbb94fb0 2437
067aa17e 2438 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
8bc0800d 2439 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
39b62db1
YCH
2440 match = match.strip()
2441 # Check if the playlist exists or is private
4201ba13
S
2442 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2443 if mobj:
2444 reason = mobj.group('reason')
2445 message = 'This playlist %s' % reason
2446 if 'private' in reason:
2447 message += ', use --username or --netrc to access it'
2448 message += '.'
2449 raise ExtractorError(message, expected=True)
39b62db1
YCH
2450 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2451 raise ExtractorError(
2452 'Invalid parameters. Maybe URL is incorrect.',
2453 expected=True)
2454 elif re.match(r'[^<]*Choose your language[^<]*', match):
2455 continue
2456 else:
2457 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 2458
dbb94fb0 2459 playlist_title = self._html_search_regex(
63b4295d 2460 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
dacb3a86 2461 page, 'title', default=None)
c5e8d7af 2462
07aeced6
S
2463 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2464 uploader = self._search_regex(
2465 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2466 page, 'uploader', default=None)
2467 mobj = re.search(
2468 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2469 page)
2470 if mobj:
2471 uploader_id = mobj.group('uploader_id')
2472 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2473 else:
2474 uploader_id = uploader_url = None
2475
dacb3a86
S
2476 has_videos = True
2477
2478 if not playlist_title:
2479 try:
2480 # Some playlist URLs don't actually serve a playlist (e.g.
2481 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2482 next(self._entries(page, playlist_id))
2483 except StopIteration:
2484 has_videos = False
2485
07aeced6 2486 playlist = self.playlist_result(
dacb3a86 2487 self._entries(page, playlist_id), playlist_id, playlist_title)
07aeced6
S
2488 playlist.update({
2489 'uploader': uploader,
2490 'uploader_id': uploader_id,
2491 'uploader_url': uploader_url,
2492 })
2493
2494 return has_videos, playlist
c5e8d7af 2495
ebf1b291 2496 def _check_download_just_video(self, url, playlist_id):
448830ce
S
2497 # Check if it's a video-specific URL
2498 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
481cc733 2499 video_id = query_dict.get('v', [None])[0] or self._search_regex(
87dadd45 2500 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
481cc733
S
2501 'video id', default=None)
2502 if video_id:
448830ce
S
2503 if self._downloader.params.get('noplaylist'):
2504 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
dacb3a86 2505 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce
S
2506 else:
2507 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
dacb3a86
S
2508 return video_id, None
2509 return None, None
448830ce 2510
ebf1b291
S
2511 def _real_extract(self, url):
2512 # Extract playlist id
2513 mobj = re.match(self._VALID_URL, url)
2514 if mobj is None:
2515 raise ExtractorError('Invalid URL: %s' % url)
2516 playlist_id = mobj.group(1) or mobj.group(2)
2517
dacb3a86 2518 video_id, video = self._check_download_just_video(url, playlist_id)
ebf1b291
S
2519 if video:
2520 return video
2521
466a6145 2522 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
2523 # Mixes require a custom extraction process
2524 return self._extract_mix(playlist_id)
2525
dacb3a86
S
2526 has_videos, playlist = self._extract_playlist(playlist_id)
2527 if has_videos or not video_id:
2528 return playlist
2529
2530 # Some playlist URLs don't actually serve a playlist (see
067aa17e 2531 # https://github.com/ytdl-org/youtube-dl/issues/10537).
dacb3a86
S
2532 # Fallback to plain video extraction if there is a video id
2533 # along with playlist id.
2534 return self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce 2535
c5e8d7af 2536
648e6a1f 2537class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2538 IE_DESC = 'YouTube.com channels'
cd5a74a2 2539 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 2540 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 2541 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 2542 IE_NAME = 'youtube:channel'
cdc628a4
PH
2543 _TESTS = [{
2544 'note': 'paginated channel',
2545 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2546 'playlist_mincount': 91,
acf757f4 2547 'info_dict': {
9170ca5b
JMF
2548 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2549 'title': 'Uploads from lex will',
acf757f4 2550 }
5c43afd4
JMF
2551 }, {
2552 'note': 'Age restricted channel',
2553 # from https://www.youtube.com/user/DeusExOfficial
2554 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2555 'playlist_mincount': 64,
2556 'info_dict': {
2557 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2558 'title': 'Uploads from Deus Ex',
2559 },
cd5a74a2
S
2560 }, {
2561 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2562 'only_matching': True,
cdc628a4 2563 }]
c5e8d7af 2564
e462474e
S
2565 @classmethod
2566 def suitable(cls, url):
f07e276a
S
2567 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2568 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 2569
9558dcec
S
2570 def _build_template_url(self, url, channel_id):
2571 return self._TEMPLATE_URL % channel_id
2572
c5e8d7af 2573 def _real_extract(self, url):
9ff67727 2574 channel_id = self._match_id(url)
c5e8d7af 2575
9558dcec 2576 url = self._build_template_url(url, channel_id)
386bdfa6
S
2577
2578 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2579 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2580 # otherwise fallback on channel by page extraction
2581 channel_page = self._download_webpage(
2582 url + '?view=57', channel_id,
2583 'Downloading channel page', fatal=False)
2b3c2546
PH
2584 if channel_page is False:
2585 channel_playlist_id = False
2586 else:
2587 channel_playlist_id = self._html_search_meta(
2588 'channelId', channel_page, 'channel id', default=None)
2589 if not channel_playlist_id:
73c4ac2c
S
2590 channel_url = self._html_search_meta(
2591 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2592 channel_page, 'channel url', default=None)
2593 if channel_url:
2594 channel_playlist_id = self._search_regex(
2595 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2596 channel_url, 'channel id', default=None)
386bdfa6
S
2597 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2598 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2599 return self.url_result(
2600 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2601
60bf45c8 2602 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2603 autogenerated = re.search(r'''(?x)
2604 class="[^"]*?(?:
2605 channel-header-autogenerated-label|
2606 yt-channel-title-autogenerated
2607 )[^"]*"''', channel_page) is not None
c5e8d7af 2608
b9643eed
JMF
2609 if autogenerated:
2610 # The videos are contained in a single page
2611 # the ajax pages can't be used, they are empty
b82f815f 2612 entries = [
fb69240c
S
2613 self.url_result(
2614 video_id, 'Youtube', video_id=video_id,
2615 video_title=video_title)
8f02ad4f 2616 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2617 return self.playlist_result(entries, channel_id)
2618
73c4ac2c
S
2619 try:
2620 next(self._entries(channel_page, channel_id))
2621 except StopIteration:
2622 alert_message = self._html_search_regex(
2623 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2624 channel_page, 'alert', default=None, group='alert')
2625 if alert_message:
2626 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2627
648e6a1f 2628 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2629
2630
eb0f3e7e 2631class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2632 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
ea696249 2633 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
9558dcec 2634 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
78caa52a 2635 IE_NAME = 'youtube:user'
c5e8d7af 2636
cdc628a4
PH
2637 _TESTS = [{
2638 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2639 'playlist_mincount': 320,
2640 'info_dict': {
73c4ac2c
S
2641 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2642 'title': 'Uploads from The Linux Foundation',
cdc628a4 2643 }
9558dcec
S
2644 }, {
2645 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2646 # but not https://www.youtube.com/user/12minuteathlete/videos
2647 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2648 'playlist_mincount': 249,
2649 'info_dict': {
2650 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2651 'title': 'Uploads from 12 Minute Athlete',
2652 }
cdc628a4
PH
2653 }, {
2654 'url': 'ytuser:phihag',
2655 'only_matching': True,
daa0df9e
YCH
2656 }, {
2657 'url': 'https://www.youtube.com/c/gametrailers',
2658 'only_matching': True,
9558dcec
S
2659 }, {
2660 'url': 'https://www.youtube.com/gametrailers',
2661 'only_matching': True,
73c4ac2c 2662 }, {
0e879f43 2663 # This channel is not available, geo restricted to JP
73c4ac2c
S
2664 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2665 'only_matching': True,
cdc628a4
PH
2666 }]
2667
e3ea4790 2668 @classmethod
f4b05232 2669 def suitable(cls, url):
e3ea4790
JMF
2670 # Don't return True if the url can be extracted with other youtube
2671 # extractor, the regex would is too permissive and it would match.
f3a58d46 2672 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2673 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2674 return False
2675 else:
2676 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2677
9558dcec
S
2678 def _build_template_url(self, url, channel_id):
2679 mobj = re.match(self._VALID_URL, url)
2680 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2681
b05654f0 2682
f07e276a
S
2683class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2684 IE_DESC = 'YouTube.com live streams'
073d5bf5 2685 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
f07e276a
S
2686 IE_NAME = 'youtube:live'
2687
2688 _TESTS = [{
2d3d2997 2689 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
f07e276a
S
2690 'info_dict': {
2691 'id': 'a48o2S1cPoo',
2692 'ext': 'mp4',
2693 'title': 'The Young Turks - Live Main Show',
2694 'uploader': 'The Young Turks',
2695 'uploader_id': 'TheYoungTurks',
ec85ded8 2696 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
f07e276a
S
2697 'upload_date': '20150715',
2698 'license': 'Standard YouTube License',
2699 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2700 'categories': ['News & Politics'],
2701 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2702 'like_count': int,
2703 'dislike_count': int,
2704 },
2705 'params': {
2706 'skip_download': True,
2707 },
2708 }, {
2d3d2997 2709 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
f07e276a 2710 'only_matching': True,
c1b2a085
S
2711 }, {
2712 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2713 'only_matching': True,
073d5bf5
S
2714 }, {
2715 'url': 'https://www.youtube.com/TheYoungTurks/live',
2716 'only_matching': True,
f07e276a
S
2717 }]
2718
2719 def _real_extract(self, url):
2720 mobj = re.match(self._VALID_URL, url)
2721 channel_id = mobj.group('id')
2722 base_url = mobj.group('base_url')
2723 webpage = self._download_webpage(url, channel_id, fatal=False)
2724 if webpage:
2725 page_type = self._og_search_property(
e7f3529f 2726 'type', webpage, 'page type', default='')
f07e276a
S
2727 video_id = self._html_search_meta(
2728 'videoId', webpage, 'video id', default=None)
e7f3529f
S
2729 if page_type.startswith('video') and video_id and re.match(
2730 r'^[0-9A-Za-z_-]{11}$', video_id):
f07e276a
S
2731 return self.url_result(video_id, YoutubeIE.ie_key())
2732 return self.url_result(base_url)
2733
2734
e462474e
S
2735class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2736 IE_DESC = 'YouTube.com user/channel playlists'
2737 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2738 IE_NAME = 'youtube:playlists'
0c148415 2739
e568c223 2740 _TESTS = [{
2d3d2997 2741 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
0c148415
S
2742 'playlist_mincount': 4,
2743 'info_dict': {
2744 'id': 'ThirstForScience',
2745 'title': 'Thirst for Science',
2746 },
e568c223
S
2747 }, {
2748 # with "Load more" button
2d3d2997 2749 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
e568c223
S
2750 'playlist_mincount': 70,
2751 'info_dict': {
2752 'id': 'igorkle1',
2753 'title': 'Игорь Клейнер',
2754 },
e462474e
S
2755 }, {
2756 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2757 'playlist_mincount': 17,
2758 'info_dict': {
2759 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2760 'title': 'Chem Player',
2761 },
e568c223 2762 }]
0c148415
S
2763
2764
870f3bfc
S
2765class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2766 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2767
2768
2769class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
78caa52a 2770 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2771 # there doesn't appear to be a real limit, for example if you search for
2772 # 'python' you get more than 8.000.000 results
2773 _MAX_RESULTS = float('inf')
78caa52a 2774 IE_NAME = 'youtube:search'
b05654f0 2775 _SEARCH_KEY = 'ytsearch'
b4c08069 2776 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2777 _TESTS = []
b05654f0 2778
b05654f0
PH
2779 def _get_n_results(self, query, n):
2780 """Get a specified number of results for a query"""
2781
b4c08069 2782 videos = []
b05654f0
PH
2783 limit = n
2784
a22b2fd1
YCH
2785 url_query = {
2786 'search_query': query.encode('utf-8'),
2787 }
2788 url_query.update(self._EXTRA_QUERY_ARGS)
2789 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2790
b4c08069 2791 for pagenum in itertools.count(1):
b4c08069 2792 data = self._download_json(
69ea8ca4 2793 result_url, video_id='query "%s"' % query,
b4c08069 2794 note='Downloading page %s' % pagenum,
a22b2fd1
YCH
2795 errnote='Unable to download API page',
2796 query={'spf': 'navigate'})
b4c08069 2797 html_content = data[1]['body']['content']
7cc3570e 2798
b4c08069 2799 if 'class="search-message' in html_content:
07ad22b8 2800 raise ExtractorError(
78caa52a 2801 '[youtube] No video results', expected=True)
b05654f0 2802
870f3bfc 2803 new_videos = list(self._process_page(html_content))
b4c08069
JMF
2804 videos += new_videos
2805 if not new_videos or len(videos) > limit:
2806 break
a22b2fd1
YCH
2807 next_link = self._html_search_regex(
2808 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2809 html_content, 'next link', default=None)
2810 if next_link is None:
2811 break
2812 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
b05654f0 2813
b4c08069
JMF
2814 if len(videos) > n:
2815 videos = videos[:n]
b05654f0 2816 return self.playlist_result(videos, query)
75dff0ee 2817
c9ae7b95 2818
a3dd9248 2819class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2820 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2821 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2822 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2823 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2824
c9ae7b95 2825
870f3bfc 2826class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
78caa52a
PH
2827 IE_DESC = 'YouTube.com search URLs'
2828 IE_NAME = 'youtube:search_url'
d2c1f79f 2829 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
cdc628a4
PH
2830 _TESTS = [{
2831 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2832 'playlist_mincount': 5,
2833 'info_dict': {
2834 'title': 'youtube-dl test video',
2835 }
d2c1f79f
S
2836 }, {
2837 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2838 'only_matching': True,
cdc628a4 2839 }]
c9ae7b95
PH
2840
2841 def _real_extract(self, url):
2842 mobj = re.match(self._VALID_URL, url)
7fd002c0 2843 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2844 webpage = self._download_webpage(url, query)
175c2e9e 2845 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2846
2847
136dadde 2848class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2849 IE_DESC = 'YouTube.com (multi-season) shows'
92519402 2850 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2851 IE_NAME = 'youtube:show'
cdc628a4 2852 _TESTS = [{
4003bd82 2853 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2854 'playlist_mincount': 5,
cdc628a4
PH
2855 'info_dict': {
2856 'id': 'airdisasters',
2857 'title': 'Air Disasters',
2858 }
2859 }]
75dff0ee
JMF
2860
2861 def _real_extract(self, url):
136dadde
S
2862 playlist_id = self._match_id(url)
2863 return super(YoutubeShowIE, self)._real_extract(
2864 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2865
2866
b2e8bc1b 2867class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2868 """
25f14e9f 2869 Base class for feed extractors
d7ae0639
JMF
2870 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2871 """
b2e8bc1b 2872 _LOGIN_REQUIRED = True
d7ae0639
JMF
2873
2874 @property
2875 def IE_NAME(self):
78caa52a 2876 return 'youtube:%s' % self._FEED_NAME
04cc9617 2877
81f0259b 2878 def _real_initialize(self):
b2e8bc1b 2879 self._login()
81f0259b 2880
3853309f 2881 def _entries(self, page):
2bc43303
JMF
2882 # The extraction process is the same as for playlists, but the regex
2883 # for the video ids doesn't contain an index
2884 ids = []
2885 more_widget_html = content_html = page
2bc43303
JMF
2886 for page_num in itertools.count(1):
2887 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2888
2889 # 'recommended' feed has infinite 'load more' and each new portion spins
2890 # the same videos in (sometimes) slightly different order, so we'll check
2891 # for unicity and break when portion has no new videos
3853309f 2892 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
62c95fd5
S
2893 if not new_ids:
2894 break
2895
2bc43303
JMF
2896 ids.extend(new_ids)
2897
3853309f
S
2898 for entry in self._ids_to_results(new_ids):
2899 yield entry
2900
2bc43303
JMF
2901 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2902 if not mobj:
2903 break
2904
2905 more = self._download_json(
25f14e9f 2906 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2907 'Downloading page #%s' % page_num,
2908 transform_source=uppercase_escape)
2909 content_html = more['content_html']
2910 more_widget_html = more['load_more_widget_html']
2911
3853309f
S
2912 def _real_extract(self, url):
2913 page = self._download_webpage(
2914 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
2915 self._PLAYLIST_TITLE)
25f14e9f 2916 return self.playlist_result(
3853309f 2917 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
25f14e9f
S
2918
2919
2920class YoutubeWatchLaterIE(YoutubePlaylistIE):
2921 IE_NAME = 'youtube:watchlater'
2922 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
92519402 2923 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2924
bc7a9cd8
S
2925 _TESTS = [{
2926 'url': 'https://www.youtube.com/playlist?list=WL',
2927 'only_matching': True,
2928 }, {
2929 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2930 'only_matching': True,
2931 }]
25f14e9f
S
2932
2933 def _real_extract(self, url):
7e5dc339 2934 _, video = self._check_download_just_video(url, 'WL')
ebf1b291
S
2935 if video:
2936 return video
dacb3a86
S
2937 _, playlist = self._extract_playlist('WL')
2938 return playlist
f459d170 2939
5f6a1245 2940
c626a3d9 2941class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2942 IE_NAME = 'youtube:favorites'
f3a34072 2943 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
92519402 2944 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2945 _LOGIN_REQUIRED = True
2946
2947 def _real_extract(self, url):
2948 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2949 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2950 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2951
2952
25f14e9f
S
2953class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2954 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
92519402 2955 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
25f14e9f
S
2956 _FEED_NAME = 'recommended'
2957 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2958
1ed5b5c9 2959
25f14e9f
S
2960class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2961 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
92519402 2962 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
25f14e9f
S
2963 _FEED_NAME = 'subscriptions'
2964 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2965
1ed5b5c9 2966
25f14e9f
S
2967class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2968 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
92519402 2969 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
25f14e9f
S
2970 _FEED_NAME = 'history'
2971 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2972
2973
15870e90
PH
2974class YoutubeTruncatedURLIE(InfoExtractor):
2975 IE_NAME = 'youtube:truncated_url'
2976 IE_DESC = False # Do not list
975d35db 2977 _VALID_URL = r'''(?x)
b95aab84
PH
2978 (?:https?://)?
2979 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2980 (?:watch\?(?:
c4808c60 2981 feature=[a-z_]+|
b95aab84
PH
2982 annotation_id=annotation_[^&]+|
2983 x-yt-cl=[0-9]+|
c1708b89 2984 hl=[^&]*|
287be8c6 2985 t=[0-9]+
b95aab84
PH
2986 )?
2987 |
2988 attribution_link\?a=[^&]+
2989 )
2990 $
975d35db 2991 '''
15870e90 2992
c4808c60 2993 _TESTS = [{
2d3d2997 2994 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 2995 'only_matching': True,
dc2fc736 2996 }, {
2d3d2997 2997 'url': 'https://www.youtube.com/watch?',
dc2fc736 2998 'only_matching': True,
b95aab84
PH
2999 }, {
3000 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3001 'only_matching': True,
3002 }, {
3003 'url': 'https://www.youtube.com/watch?feature=foo',
3004 'only_matching': True,
c1708b89
PH
3005 }, {
3006 'url': 'https://www.youtube.com/watch?hl=en-GB',
3007 'only_matching': True,
287be8c6
PH
3008 }, {
3009 'url': 'https://www.youtube.com/watch?t=2372',
3010 'only_matching': True,
c4808c60
PH
3011 }]
3012
15870e90
PH
3013 def _real_extract(self, url):
3014 raise ExtractorError(
78caa52a
PH
3015 'Did you forget to quote the URL? Remember that & is a meta '
3016 'character in most shells, so you want to put the URL in quotes, '
3017 'like youtube-dl '
2d3d2997 3018 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
78caa52a 3019 ' or simply youtube-dl BaW_jenozKc .',
15870e90 3020 expected=True)
772fd5cc
PH
3021
3022
3023class YoutubeTruncatedIDIE(InfoExtractor):
3024 IE_NAME = 'youtube:truncated_id'
3025 IE_DESC = False # Do not list
b95aab84 3026 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
3027
3028 _TESTS = [{
3029 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3030 'only_matching': True,
3031 }]
3032
3033 def _real_extract(self, url):
3034 video_id = self._match_id(url)
3035 raise ExtractorError(
3036 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
3037 expected=True)