]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[youtube] Relax html5 player regexes (closes #18465, closes #18466)
[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/|
cd5a74a2 354 (?:www\.)?invidio\.us/|
e69ae5b9 355 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
c5e8d7af
PH
356 (?:.*?\#/)? # handle anchor (#/) redirect urls
357 (?: # the various things that can precede the ID:
ac7553d0 358 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 359 |(?: # or the v= param in all its forms
f7000f3a 360 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 361 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 362 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
363 v=
364 )
f4b05232 365 ))
cbaed4bb
S
366 |(?:
367 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
368 vid\.plus| # or vid.plus/xxxx
369 zwearz\.com/watch| # or zwearz.com/watch/xxxx
cbaed4bb 370 )/
edb53e2d 371 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 372 )
c5e8d7af 373 )? # all until now is optional -> you can pass the naked ID
8963d9c2 374 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
d0ba5587
S
375 (?!.*?\blist=
376 (?:
377 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
378 WL # WL are handled by the watch later IE
379 )
380 )
c5e8d7af 381 (?(1).+)? # if we found the ID, everything can follow
d0ba5587 382 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
c5e8d7af 383 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
2c62dc26 384 _formats = {
c2d3cb4c 385 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
386 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
387 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
388 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
389 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
390 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
391 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
392 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 393 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 394 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
395 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
396 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
397 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
398 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
399 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 400 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 401 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
402 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 403
404
405 # 3D videos
c2d3cb4c 406 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
407 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
408 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
409 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 410 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
411 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
412 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 413
96fb5605 414 # Apple HTTP Live Streaming
11f12195 415 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 416 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
417 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
418 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
419 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
420 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 421 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
422 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
423
424 # DASH mp4 video
d23028a8
S
425 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
426 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
427 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
428 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
429 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
430 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
431 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
432 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
433 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
434 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
435 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
436 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 437
f6f1fc92 438 # Dash mp4 audio
d23028a8
S
439 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
440 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
441 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
442 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
443 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
444 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
445 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
446
447 # Dash webm
d23028a8
S
448 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
449 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
450 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
451 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
452 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
453 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
454 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
455 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
456 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
457 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
458 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
459 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
460 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
461 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
462 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 463 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
464 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
465 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
466 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
467 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
468 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
469 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
470
471 # Dash webm audio
d23028a8
S
472 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
473 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 474
0857baad 475 # Dash webm audio with opus inside
d23028a8
S
476 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
477 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
478 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 479
ce6b9a2d
PH
480 # RTMP (unnamed)
481 '_rtmp': {'protocol': 'rtmp'},
c5e8d7af 482 }
23d17e4b 483 _SUBTITLE_FORMATS = ('ttml', 'vtt')
836a086c 484
fd5c4aab
S
485 _GEO_BYPASS = False
486
78caa52a 487 IE_NAME = 'youtube'
2eb88d95
PH
488 _TESTS = [
489 {
2d3d2997 490 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
491 'info_dict': {
492 'id': 'BaW_jenozKc',
493 'ext': 'mp4',
494 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
495 'uploader': 'Philipp Hagemeister',
496 'uploader_id': 'phihag',
ec85ded8 497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
dd4c4492
S
498 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
499 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 500 'upload_date': '20121002',
7caf9830 501 'license': 'Standard YouTube License',
4bc3a23e
PH
502 '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 .',
503 'categories': ['Science & Technology'],
000b6b5a 504 'tags': ['youtube-dl'],
556dbe7f 505 'duration': 10,
dbdaaa23 506 'view_count': int,
3e7c1224
PH
507 'like_count': int,
508 'dislike_count': int,
7c80519c 509 'start_time': 1,
297a564b 510 'end_time': 9,
2eb88d95 511 }
0e853ca4 512 },
0e853ca4 513 {
2d3d2997 514 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
4bc3a23e
PH
515 'note': 'Test generic use_cipher_signature video (#897)',
516 'info_dict': {
517 'id': 'UxxajLWwzqY',
518 'ext': 'mp4',
519 'upload_date': '20120506',
520 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
0cb58b02 521 'alt_title': 'I Love It (feat. Charli XCX)',
7caf9830 522 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
000b6b5a
S
523 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
524 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
525 'iconic ep', 'iconic', 'love', 'it'],
556dbe7f 526 'duration': 180,
4bc3a23e
PH
527 'uploader': 'Icona Pop',
528 'uploader_id': 'IconaPop',
ec85ded8 529 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
7caf9830 530 'license': 'Standard YouTube License',
0cb58b02 531 'creator': 'Icona Pop',
936784b2
S
532 'track': 'I Love It (feat. Charli XCX)',
533 'artist': 'Icona Pop',
2eb88d95 534 }
c108eb73
JMF
535 },
536 {
4bc3a23e
PH
537 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
538 'note': 'Test VEVO video with age protection (#956)',
539 'info_dict': {
540 'id': '07FYdnEawAQ',
541 'ext': 'mp4',
542 'upload_date': '20130703',
543 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
0cb58b02 544 'alt_title': 'Tunnel Vision',
4bc3a23e 545 'description': 'md5:64249768eec3bc4276236606ea996373',
556dbe7f 546 'duration': 419,
4bc3a23e
PH
547 'uploader': 'justintimberlakeVEVO',
548 'uploader_id': 'justintimberlakeVEVO',
ec85ded8 549 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
7caf9830 550 'license': 'Standard YouTube License',
0cb58b02 551 'creator': 'Justin Timberlake',
7e72694b 552 'track': 'Tunnel Vision',
936784b2 553 'artist': 'Justin Timberlake',
34952f09 554 'age_limit': 18,
c108eb73
JMF
555 }
556 },
fccd3771 557 {
4bc3a23e
PH
558 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
559 'note': 'Embed-only video (#1746)',
560 'info_dict': {
561 'id': 'yZIXLfi8CZQ',
562 'ext': 'mp4',
563 'upload_date': '20120608',
564 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
565 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
566 'uploader': 'SET India',
94bfcd23 567 'uploader_id': 'setindia',
ec85ded8 568 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
7caf9830 569 'license': 'Standard YouTube License',
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 583 'upload_date': '20121002',
7caf9830 584 'license': 'Standard YouTube License',
11b56058
PM
585 '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 .',
586 'categories': ['Science & Technology'],
587 'tags': ['youtube-dl'],
556dbe7f 588 'duration': 10,
dbdaaa23 589 'view_count': int,
11b56058
PM
590 'like_count': int,
591 'dislike_count': int,
34a7de29
S
592 },
593 'params': {
594 'skip_download': True,
595 },
11b56058 596 },
dd27fd17 597 {
2d3d2997 598 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
599 'note': '256k DASH audio (format 141) via DASH manifest',
600 'info_dict': {
601 'id': 'a9LDPn-MO4I',
602 'ext': 'm4a',
603 'upload_date': '20121002',
604 'uploader_id': '8KVIDEO',
ec85ded8 605 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
606 'description': '',
607 'uploader': '8KVIDEO',
7caf9830 608 'license': 'Standard YouTube License',
4bc3a23e 609 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 610 },
4bc3a23e
PH
611 'params': {
612 'youtube_include_dash_manifest': True,
613 'format': '141',
4919603f 614 },
de3c7fe0 615 'skip': 'format 141 not served anymore',
dd27fd17 616 },
3489b7d2
JMF
617 # DASH manifest with encrypted signature
618 {
78caa52a
PH
619 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
620 'info_dict': {
621 'id': 'IB3lcPjvWLA',
622 'ext': 'm4a',
b766eb27 623 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
eb6793ba 624 'description': 'md5:1900ed86ee514927b9e00fbead6969a5',
556dbe7f 625 'duration': 244,
78caa52a
PH
626 'uploader': 'AfrojackVEVO',
627 'uploader_id': 'AfrojackVEVO',
628 'upload_date': '20131011',
7caf9830 629 'license': 'Standard YouTube License',
3489b7d2 630 },
4bc3a23e 631 'params': {
78caa52a 632 'youtube_include_dash_manifest': True,
de3c7fe0 633 'format': '141/bestaudio[ext=m4a]',
3489b7d2
JMF
634 },
635 },
aaeb86f6
S
636 # JS player signature function name containing $
637 {
638 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
639 'info_dict': {
640 'id': 'nfWlot6h_JM',
641 'ext': 'm4a',
642 'title': 'Taylor Swift - Shake It Off',
0cb58b02 643 'alt_title': 'Shake It Off',
f57b7835 644 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
556dbe7f 645 'duration': 242,
aaeb86f6
S
646 'uploader': 'TaylorSwiftVEVO',
647 'uploader_id': 'TaylorSwiftVEVO',
648 'upload_date': '20140818',
7caf9830 649 'license': 'Standard YouTube License',
0cb58b02 650 'creator': 'Taylor Swift',
aaeb86f6
S
651 },
652 'params': {
653 'youtube_include_dash_manifest': True,
de3c7fe0 654 'format': '141/bestaudio[ext=m4a]',
aaeb86f6
S
655 },
656 },
aa79ac0c
PH
657 # Controversy video
658 {
659 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
660 'info_dict': {
661 'id': 'T4XJQO3qol8',
662 'ext': 'mp4',
556dbe7f 663 'duration': 219,
aa79ac0c 664 'upload_date': '20100909',
eb6793ba 665 'uploader': 'TJ Kirk',
aa79ac0c 666 'uploader_id': 'TheAmazingAtheist',
ec85ded8 667 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
7caf9830 668 'license': 'Standard YouTube License',
aa79ac0c
PH
669 'title': 'Burning Everyone\'s Koran',
670 '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',
671 }
c522adb1
JMF
672 },
673 # Normal age-gate video (No vevo, embed allowed)
674 {
2d3d2997 675 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
676 'info_dict': {
677 'id': 'HtVdAasjOgU',
678 'ext': 'mp4',
679 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 680 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 681 'duration': 142,
c522adb1
JMF
682 'uploader': 'The Witcher',
683 'uploader_id': 'WitcherGame',
ec85ded8 684 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 685 'upload_date': '20140605',
7caf9830 686 'license': 'Standard YouTube License',
34952f09 687 'age_limit': 18,
c522adb1
JMF
688 },
689 },
fccae2b9
S
690 # Age-gate video with encrypted signature
691 {
2d3d2997 692 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
fccae2b9
S
693 'info_dict': {
694 'id': '6kLq3WMV1nU',
eb6793ba 695 'ext': 'webm',
fccae2b9
S
696 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
697 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
eb6793ba 698 'duration': 246,
fccae2b9
S
699 'uploader': 'LloydVEVO',
700 'uploader_id': 'LloydVEVO',
ec85ded8 701 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
fccae2b9 702 'upload_date': '20110629',
7caf9830 703 'license': 'Standard YouTube License',
34952f09 704 'age_limit': 18,
fccae2b9
S
705 },
706 },
774e208f 707 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
7d02dcfa 708 # YouTube Red ad is not captured for creator
774e208f
PH
709 {
710 'url': '__2ABJjxzNo',
711 'info_dict': {
712 'id': '__2ABJjxzNo',
713 'ext': 'mp4',
556dbe7f 714 'duration': 266,
774e208f
PH
715 'upload_date': '20100430',
716 'uploader_id': 'deadmau5',
ec85ded8 717 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
0cb58b02 718 'creator': 'deadmau5',
774e208f
PH
719 'description': 'md5:12c56784b8032162bb936a5f76d55360',
720 'uploader': 'deadmau5',
7caf9830 721 'license': 'Standard YouTube License',
774e208f 722 'title': 'Deadmau5 - Some Chords (HD)',
0cb58b02 723 'alt_title': 'Some Chords',
774e208f
PH
724 },
725 'expected_warnings': [
726 'DASH manifest missing',
727 ]
e52a40ab
PH
728 },
729 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
730 {
731 'url': 'lqQg6PlCWgI',
732 'info_dict': {
733 'id': 'lqQg6PlCWgI',
734 'ext': 'mp4',
556dbe7f 735 'duration': 6085,
90227264 736 'upload_date': '20150827',
cbe2bd91 737 'uploader_id': 'olympic',
ec85ded8 738 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
7caf9830 739 'license': 'Standard YouTube License',
cbe2bd91 740 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
be49068d 741 'uploader': 'Olympic',
cbe2bd91
PH
742 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
743 },
744 'params': {
745 'skip_download': 'requires avconv',
e52a40ab 746 }
cbe2bd91 747 },
6271f1ca
PH
748 # Non-square pixels
749 {
750 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
751 'info_dict': {
752 'id': '_b-2C3KPAM0',
753 'ext': 'mp4',
754 'stretched_ratio': 16 / 9.,
556dbe7f 755 'duration': 85,
6271f1ca
PH
756 'upload_date': '20110310',
757 'uploader_id': 'AllenMeow',
ec85ded8 758 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 759 '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 760 'uploader': '孫ᄋᄅ',
7caf9830 761 'license': 'Standard YouTube License',
6271f1ca
PH
762 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
763 },
06b491eb
S
764 },
765 # url_encoded_fmt_stream_map is empty string
766 {
767 'url': 'qEJwOuvDf7I',
768 'info_dict': {
769 'id': 'qEJwOuvDf7I',
f57b7835 770 'ext': 'webm',
06b491eb
S
771 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
772 'description': '',
773 'upload_date': '20150404',
774 'uploader_id': 'spbelect',
775 'uploader': 'Наблюдатели Петербурга',
776 },
777 'params': {
778 'skip_download': 'requires avconv',
e323cf3f
S
779 },
780 'skip': 'This live event has ended.',
06b491eb 781 },
da77d856
S
782 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
783 {
784 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
785 'info_dict': {
786 'id': 'FIl7x6_3R5Y',
eb6793ba 787 'ext': 'webm',
da77d856
S
788 'title': 'md5:7b81415841e02ecd4313668cde88737a',
789 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 790 'duration': 220,
da77d856
S
791 'upload_date': '20150625',
792 'uploader_id': 'dorappi2000',
ec85ded8 793 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 794 'uploader': 'dorappi2000',
7caf9830 795 'license': 'Standard YouTube License',
eb6793ba 796 'formats': 'mincount:31',
da77d856 797 },
eb6793ba 798 'skip': 'not actual anymore',
2ee8f5d8 799 },
8a1a26ce
YCH
800 # DASH manifest with segment_list
801 {
802 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
803 'md5': '8ce563a1d667b599d21064e982ab9e31',
804 'info_dict': {
805 'id': 'CsmdDsKjzN8',
806 'ext': 'mp4',
17ee98e1 807 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
808 'uploader': 'Airtek',
809 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
810 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
7caf9830 811 'license': 'Standard YouTube License',
8a1a26ce
YCH
812 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
813 },
814 'params': {
815 'youtube_include_dash_manifest': True,
816 'format': '135', # bestvideo
be49068d
S
817 },
818 'skip': 'This live event has ended.',
2ee8f5d8 819 },
cf7e015f
S
820 {
821 # Multifeed videos (multiple cameras), URL is for Main Camera
822 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
823 'info_dict': {
824 'id': 'jqWvoWXjCVs',
825 'title': 'teamPGP: Rocket League Noob Stream',
826 'description': 'md5:dc7872fb300e143831327f1bae3af010',
827 },
828 'playlist': [{
829 'info_dict': {
830 'id': 'jqWvoWXjCVs',
831 'ext': 'mp4',
832 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
833 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 834 'duration': 7335,
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': '6h8e8xoXJzg',
844 'ext': 'mp4',
845 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
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': 'PUOgX5z9xZw',
857 'ext': 'mp4',
858 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
859 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 860 'duration': 7337,
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 'info_dict': {
869 'id': 'teuwxikvS5k',
870 'ext': 'mp4',
871 'title': 'teamPGP: Rocket League Noob Stream (zim)',
872 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 873 'duration': 7334,
cf7e015f
S
874 'upload_date': '20150721',
875 'uploader': 'Beer Games Beer',
876 'uploader_id': 'beergamesbeer',
ec85ded8 877 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 878 'license': 'Standard YouTube License',
cf7e015f
S
879 },
880 }],
881 'params': {
882 'skip_download': True,
883 },
cbaed4bb 884 },
f9f49d87
S
885 {
886 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
887 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
888 'info_dict': {
889 'id': 'gVfLd0zydlo',
890 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
891 },
892 'playlist_count': 2,
be49068d 893 'skip': 'Not multifeed anymore',
f9f49d87 894 },
cbaed4bb 895 {
2d3d2997 896 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 897 'only_matching': True,
0e49d9a6 898 },
6d4fc66b 899 {
2d3d2997 900 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
901 'only_matching': True,
902 },
0e49d9a6 903 {
61f92af1 904 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
a8776b10
S
905 # Also tests cut-off URL expansion in video description (see
906 # https://github.com/rg3/youtube-dl/issues/1892,
907 # https://github.com/rg3/youtube-dl/issues/8164)
0e49d9a6
LL
908 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
909 'info_dict': {
910 'id': 'lsguqyKfVQg',
911 'ext': 'mp4',
912 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
eb6793ba 913 'alt_title': 'Dark Walk - Position Music',
0e49d9a6 914 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 915 'duration': 133,
0e49d9a6
LL
916 'upload_date': '20151119',
917 'uploader_id': 'IronSoulElf',
ec85ded8 918 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 919 'uploader': 'IronSoulElf',
7caf9830 920 'license': 'Standard YouTube License',
eb6793ba
S
921 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
922 'track': 'Dark Walk - Position Music',
923 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
0e49d9a6
LL
924 },
925 'params': {
926 'skip_download': True,
927 },
928 },
61f92af1
S
929 {
930 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
931 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
932 'only_matching': True,
933 },
313dfc45
LL
934 {
935 # Video with yt:stretch=17:0
936 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
937 'info_dict': {
938 'id': 'Q39EVAstoRM',
939 'ext': 'mp4',
940 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
941 'description': 'md5:ee18a25c350637c8faff806845bddee9',
942 'upload_date': '20151107',
943 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
944 'uploader': 'CH GAMER DROID',
945 },
946 'params': {
947 'skip_download': True,
948 },
be49068d 949 'skip': 'This video does not exist.',
313dfc45 950 },
7caf9830
S
951 {
952 # Video licensed under Creative Commons
953 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
954 'info_dict': {
955 'id': 'M4gD1WSo5mA',
956 'ext': 'mp4',
957 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
958 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 959 'duration': 721,
7caf9830
S
960 'upload_date': '20150127',
961 'uploader_id': 'BerkmanCenter',
ec85ded8 962 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 963 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
964 'license': 'Creative Commons Attribution license (reuse allowed)',
965 },
966 'params': {
967 'skip_download': True,
968 },
969 },
fd050249
S
970 {
971 # Channel-like uploader_url
972 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
973 'info_dict': {
974 'id': 'eQcmzGIKrzg',
975 'ext': 'mp4',
976 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
977 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
556dbe7f 978 'duration': 4060,
fd050249 979 'upload_date': '20151119',
eb6793ba 980 'uploader': 'Bernie Sanders',
fd050249 981 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 982 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
983 'license': 'Creative Commons Attribution license (reuse allowed)',
984 },
985 'params': {
986 'skip_download': True,
987 },
988 },
040ac686
S
989 {
990 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
991 'only_matching': True,
7f29cf54
S
992 },
993 {
994 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
995 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
996 'only_matching': True,
6496ccb4
S
997 },
998 {
999 # Rental video preview
1000 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1001 'info_dict': {
1002 'id': 'uGpuVWrhIzE',
1003 'ext': 'mp4',
1004 'title': 'Piku - Trailer',
1005 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1006 'upload_date': '20150811',
1007 'uploader': 'FlixMatrix',
1008 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1009 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1010 'license': 'Standard YouTube License',
1011 },
1012 'params': {
1013 'skip_download': True,
1014 },
eb6793ba 1015 'skip': 'This video is not available.',
022a5d66 1016 },
12afdc2a
S
1017 {
1018 # YouTube Red video with episode data
1019 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1020 'info_dict': {
1021 'id': 'iqKdEhx-dD4',
1022 'ext': 'mp4',
1023 'title': 'Isolation - Mind Field (Ep 1)',
eb6793ba 1024 'description': 'md5:25b78d2f64ae81719f5c96319889b736',
556dbe7f 1025 'duration': 2085,
12afdc2a
S
1026 'upload_date': '20170118',
1027 'uploader': 'Vsauce',
1028 'uploader_id': 'Vsauce',
1029 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1030 'license': 'Standard YouTube License',
1031 'series': 'Mind Field',
1032 'season_number': 1,
1033 'episode_number': 1,
1034 },
1035 'params': {
1036 'skip_download': True,
1037 },
1038 'expected_warnings': [
1039 'Skipping DASH manifest',
1040 ],
1041 },
c7121fa7
S
1042 {
1043 # The following content has been identified by the YouTube community
1044 # as inappropriate or offensive to some audiences.
1045 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1046 'info_dict': {
1047 'id': '6SJNVb0GnPI',
1048 'ext': 'mp4',
1049 'title': 'Race Differences in Intelligence',
1050 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1051 'duration': 965,
1052 'upload_date': '20140124',
1053 'uploader': 'New Century Foundation',
1054 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1055 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1056 'license': 'Standard YouTube License',
c7121fa7
S
1057 },
1058 'params': {
1059 'skip_download': True,
1060 },
1061 },
022a5d66
S
1062 {
1063 # itag 212
1064 'url': '1t24XAntNCY',
1065 'only_matching': True,
fd5c4aab
S
1066 },
1067 {
1068 # geo restricted to JP
1069 'url': 'sJL6WA-aGkQ',
1070 'only_matching': True,
1071 },
d0ba5587
S
1072 {
1073 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1074 'only_matching': True,
1075 },
cd5a74a2
S
1076 {
1077 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1078 'only_matching': True,
1079 },
2eb88d95
PH
1080 ]
1081
e0df6211
PH
1082 def __init__(self, *args, **kwargs):
1083 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 1084 self._player_cache = {}
e0df6211 1085
c5e8d7af
PH
1086 def report_video_info_webpage_download(self, video_id):
1087 """Report attempt to download video info webpage."""
69ea8ca4 1088 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 1089
c5e8d7af
PH
1090 def report_information_extraction(self, video_id):
1091 """Report attempt to extract video information."""
69ea8ca4 1092 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
1093
1094 def report_unavailable_format(self, video_id, format):
1095 """Report extracted video URL."""
69ea8ca4 1096 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
1097
1098 def report_rtmp_download(self):
1099 """Indicate the download will use the RTMP protocol."""
69ea8ca4 1100 self.to_screen('RTMP download detected')
c5e8d7af 1101
60064c53
PH
1102 def _signature_cache_id(self, example_sig):
1103 """ Return a string representation of a signature """
78caa52a 1104 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
1105
1106 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 1107 id_m = re.match(
63529e93 1108 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
cf010131 1109 player_url)
c081b35c
PH
1110 if not id_m:
1111 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
1112 player_type = id_m.group('ext')
1113 player_id = id_m.group('id')
1114
c4417ddb 1115 # Read from filesystem cache
60064c53
PH
1116 func_id = '%s_%s_%s' % (
1117 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 1118 assert os.path.basename(func_id) == func_id
a0e07d31 1119
69ea8ca4 1120 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 1121 if cache_spec is not None:
78caa52a 1122 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 1123
6d1a55a5
PH
1124 download_note = (
1125 'Downloading player %s' % player_url
1126 if self._downloader.params.get('verbose') else
1127 'Downloading %s player %s' % (player_type, player_id)
1128 )
e0df6211
PH
1129 if player_type == 'js':
1130 code = self._download_webpage(
1131 player_url, video_id,
6d1a55a5 1132 note=download_note,
69ea8ca4 1133 errnote='Download of %s failed' % player_url)
83799698 1134 res = self._parse_sig_js(code)
c4417ddb 1135 elif player_type == 'swf':
e0df6211
PH
1136 urlh = self._request_webpage(
1137 player_url, video_id,
6d1a55a5 1138 note=download_note,
69ea8ca4 1139 errnote='Download of %s failed' % player_url)
e0df6211 1140 code = urlh.read()
83799698 1141 res = self._parse_sig_swf(code)
e0df6211
PH
1142 else:
1143 assert False, 'Invalid player type %r' % player_type
1144
785521bf
PH
1145 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1146 cache_res = res(test_string)
1147 cache_spec = [ord(c) for c in cache_res]
83799698 1148
69ea8ca4 1149 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
1150 return res
1151
60064c53 1152 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1153 def gen_sig_code(idxs):
1154 def _genslice(start, end, step):
78caa52a 1155 starts = '' if start == 0 else str(start)
8bcc8756 1156 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1157 steps = '' if step == 1 else (':%d' % step)
78caa52a 1158 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1159
1160 step = None
7af808a5
PH
1161 # Quelch pyflakes warnings - start will be set when step is set
1162 start = '(Never used)'
edf3e38e
PH
1163 for i, prev in zip(idxs[1:], idxs[:-1]):
1164 if step is not None:
1165 if i - prev == step:
1166 continue
1167 yield _genslice(start, prev, step)
1168 step = None
1169 continue
1170 if i - prev in [-1, 1]:
1171 step = i - prev
1172 start = prev
1173 continue
1174 else:
78caa52a 1175 yield 's[%d]' % prev
edf3e38e 1176 if step is None:
78caa52a 1177 yield 's[%d]' % i
edf3e38e
PH
1178 else:
1179 yield _genslice(start, i, step)
1180
78caa52a 1181 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1182 cache_res = func(test_string)
edf3e38e 1183 cache_spec = [ord(c) for c in cache_res]
78caa52a 1184 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1185 signature_id_tuple = '(%s)' % (
1186 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1187 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1188 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1189 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1190
e0df6211
PH
1191 def _parse_sig_js(self, jscode):
1192 funcname = self._search_regex(
3c90cc8b 1193 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35
S
1194 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1195 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2511eee2
S
1196 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1197 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 1198 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1199
1200 jsi = JSInterpreter(jscode)
1201 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1202 return lambda s: initial_function([s])
1203
1204 def _parse_sig_swf(self, file_contents):
54256267 1205 swfi = SWFInterpreter(file_contents)
78caa52a 1206 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 1207 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 1208 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
1209 return lambda s: initial_function([s])
1210
83799698 1211 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 1212 """Turn the encrypted s field into a working signature"""
6b37f0be 1213
c8bf86d5 1214 if player_url is None:
69ea8ca4 1215 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1216
69ea8ca4 1217 if player_url.startswith('//'):
78caa52a 1218 player_url = 'https:' + player_url
3c90cc8b
S
1219 elif not re.match(r'https?://', player_url):
1220 player_url = compat_urlparse.urljoin(
1221 'https://www.youtube.com', player_url)
c8bf86d5 1222 try:
62af3a0e 1223 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1224 if player_id not in self._player_cache:
1225 func = self._extract_signature_function(
60064c53 1226 video_id, player_url, s
c8bf86d5
PH
1227 )
1228 self._player_cache[player_id] = func
1229 func = self._player_cache[player_id]
1230 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1231 self._print_sig_code(func, s)
c8bf86d5
PH
1232 return func(s)
1233 except Exception as e:
1234 tb = traceback.format_exc()
1235 raise ExtractorError(
78caa52a 1236 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1237
360e1ca5 1238 def _get_subtitles(self, video_id, webpage):
de7f3446 1239 try:
60e47a26 1240 subs_doc = self._download_xml(
38c2e5b8 1241 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1242 video_id, note=False)
1243 except ExtractorError as err:
9b9c5355 1244 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1245 return {}
de7f3446
JMF
1246
1247 sub_lang_list = {}
60e47a26
JMF
1248 for track in subs_doc.findall('track'):
1249 lang = track.attrib['lang_code']
7e660ac1
LD
1250 if lang in sub_lang_list:
1251 continue
360e1ca5 1252 sub_formats = []
23d17e4b 1253 for ext in self._SUBTITLE_FORMATS:
15707c7e 1254 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1255 'lang': lang,
1256 'v': video_id,
1257 'fmt': ext,
1258 'name': track.attrib['name'].encode('utf-8'),
1259 })
1260 sub_formats.append({
1261 'url': 'https://www.youtube.com/api/timedtext?' + params,
1262 'ext': ext,
1263 })
1264 sub_lang_list[lang] = sub_formats
de7f3446 1265 if not sub_lang_list:
69ea8ca4 1266 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1267 return {}
1268 return sub_lang_list
1269
a72778d3
S
1270 def _get_ytplayer_config(self, video_id, webpage):
1271 patterns = (
526b3b07
S
1272 # User data may contain arbitrary character sequences that may affect
1273 # JSON extraction with regex, e.g. when '};' is contained the second
1274 # regex won't capture the whole JSON. Yet working around by trying more
1275 # concrete regex first keeping in mind proper quoted string handling
1276 # to be implemented in future that will replace this workaround (see
1277 # https://github.com/rg3/youtube-dl/issues/7468,
1278 # https://github.com/rg3/youtube-dl/pull/7599)
a72778d3
S
1279 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1280 r';ytplayer\.config\s*=\s*({.+?});',
1281 )
1282 config = self._search_regex(
1283 patterns, webpage, 'ytplayer.config', default=None)
1284 if config:
1285 return self._parse_json(
1286 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1287
360e1ca5 1288 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1289 """We need the webpage for getting the captions url, pass it as an
1290 argument to speed up the process."""
69ea8ca4 1291 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1292 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1293 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1294 if not player_config:
de7f3446
JMF
1295 self._downloader.report_warning(err_msg)
1296 return {}
de7f3446 1297 try:
0792d563 1298 args = player_config['args']
b78b292f
S
1299 caption_url = args.get('ttsurl')
1300 if caption_url:
1301 timestamp = args['timestamp']
1302 # We get the available subtitles
15707c7e 1303 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1304 'type': 'list',
1305 'tlangs': 1,
1306 'asrs': 1,
1307 })
1308 list_url = caption_url + '&' + list_params
1309 caption_list = self._download_xml(list_url, video_id)
1310 original_lang_node = caption_list.find('track')
1311 if original_lang_node is None:
1312 self._downloader.report_warning('Video doesn\'t have automatic captions')
1313 return {}
1314 original_lang = original_lang_node.attrib['lang_code']
1315 caption_kind = original_lang_node.attrib.get('kind', '')
1316
1317 sub_lang_list = {}
1318 for lang_node in caption_list.findall('target'):
1319 sub_lang = lang_node.attrib['lang_code']
1320 sub_formats = []
1321 for ext in self._SUBTITLE_FORMATS:
15707c7e 1322 params = compat_urllib_parse_urlencode({
b78b292f
S
1323 'lang': original_lang,
1324 'tlang': sub_lang,
1325 'fmt': ext,
1326 'ts': timestamp,
1327 'kind': caption_kind,
1328 })
1329 sub_formats.append({
1330 'url': caption_url + '&' + params,
1331 'ext': ext,
1332 })
1333 sub_lang_list[sub_lang] = sub_formats
1334 return sub_lang_list
1335
ddbb4c5c
S
1336 def make_captions(sub_url, sub_langs):
1337 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1338 caption_qs = compat_parse_qs(parsed_sub_url.query)
1339 captions = {}
1340 for sub_lang in sub_langs:
1341 sub_formats = []
1342 for ext in self._SUBTITLE_FORMATS:
1343 caption_qs.update({
1344 'tlang': [sub_lang],
1345 'fmt': [ext],
1346 })
1347 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1348 query=compat_urllib_parse_urlencode(caption_qs, True)))
1349 sub_formats.append({
1350 'url': sub_url,
1351 'ext': ext,
1352 })
1353 captions[sub_lang] = sub_formats
1354 return captions
1355
1356 # New captions format as of 22.06.2017
1357 player_response = args.get('player_response')
1358 if player_response and isinstance(player_response, compat_str):
1359 player_response = self._parse_json(
1360 player_response, video_id, fatal=False)
1361 if player_response:
1362 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1363 base_url = renderer['captionTracks'][0]['baseUrl']
1364 sub_lang_list = []
1365 for lang in renderer['translationLanguages']:
1366 lang_code = lang.get('languageCode')
1367 if lang_code:
1368 sub_lang_list.append(lang_code)
1369 return make_captions(base_url, sub_lang_list)
1370
b78b292f
S
1371 # Some videos don't provide ttsurl but rather caption_tracks and
1372 # caption_translation_languages (e.g. 20LmZk1hakA)
ddbb4c5c 1373 # Does not used anymore as of 22.06.2017
b78b292f
S
1374 caption_tracks = args['caption_tracks']
1375 caption_translation_languages = args['caption_translation_languages']
1376 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
ddbb4c5c 1377 sub_lang_list = []
b78b292f
S
1378 for lang in caption_translation_languages.split(','):
1379 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1380 sub_lang = lang_qs.get('lc', [None])[0]
ddbb4c5c
S
1381 if sub_lang:
1382 sub_lang_list.append(sub_lang)
1383 return make_captions(caption_url, sub_lang_list)
de7f3446
JMF
1384 # An extractor error can be raise by the download process if there are
1385 # no automatic captions but there are subtitles
ddbb4c5c 1386 except (KeyError, IndexError, ExtractorError):
de7f3446
JMF
1387 self._downloader.report_warning(err_msg)
1388 return {}
1389
21c340b8
S
1390 def _mark_watched(self, video_id, video_info, player_response):
1391 playback_url = url_or_none(try_get(
1392 player_response,
1393 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1394 video_info, lambda x: x['videostats_playback_base_url'][0]))
d77ab8e2
S
1395 if not playback_url:
1396 return
1397 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1398 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1399
1400 # cpn generation algorithm is reverse engineered from base.js.
1401 # In fact it works even with dummy cpn.
1402 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1403 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1404
1405 qs.update({
1406 'ver': ['2'],
1407 'cpn': [cpn],
1408 })
1409 playback_url = compat_urlparse.urlunparse(
15707c7e 1410 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1411
1412 self._download_webpage(
1413 playback_url, video_id, 'Marking watched',
1414 'Unable to mark watched', fatal=False)
1415
66c9fa36
S
1416 @staticmethod
1417 def _extract_urls(webpage):
1418 # Embedded YouTube player
1419 entries = [
1420 unescapeHTML(mobj.group('url'))
1421 for mobj in re.finditer(r'''(?x)
1422 (?:
1423 <iframe[^>]+?src=|
1424 data-video-url=|
1425 <embed[^>]+?src=|
1426 embedSWF\(?:\s*|
1427 <object[^>]+data=|
1428 new\s+SWFObject\(
1429 )
1430 (["\'])
1431 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 1432 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
1433 \1''', webpage)]
1434
1435 # lazyYT YouTube embed
1436 entries.extend(list(map(
1437 unescapeHTML,
1438 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1439
1440 # Wordpress "YouTube Video Importer" plugin
1441 matches = re.findall(r'''(?x)<div[^>]+
1442 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1443 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1444 entries.extend(m[-1] for m in matches)
1445
1446 return entries
1447
1448 @staticmethod
1449 def _extract_url(webpage):
1450 urls = YoutubeIE._extract_urls(webpage)
1451 return urls[0] if urls else None
1452
97665381
PH
1453 @classmethod
1454 def extract_id(cls, url):
1455 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1456 if mobj is None:
69ea8ca4 1457 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1458 video_id = mobj.group(2)
1459 return video_id
1460
1fb07d10
JG
1461 def _extract_annotations(self, video_id):
1462 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1463 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1464
9cafc3fd
S
1465 @staticmethod
1466 def _extract_chapters(description, duration):
1467 if not description:
1468 return None
1469 chapter_lines = re.findall(
1470 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1471 description)
1472 if not chapter_lines:
1473 return None
1474 chapters = []
1475 for next_num, (chapter_line, time_point) in enumerate(
1476 chapter_lines, start=1):
1477 start_time = parse_duration(time_point)
1478 if start_time is None:
1479 continue
39d4c1be
S
1480 if start_time > duration:
1481 break
9cafc3fd
S
1482 end_time = (duration if next_num == len(chapter_lines)
1483 else parse_duration(chapter_lines[next_num][1]))
1484 if end_time is None:
1485 continue
39d4c1be
S
1486 if end_time > duration:
1487 end_time = duration
1488 if start_time > end_time:
1489 break
9cafc3fd
S
1490 chapter_title = re.sub(
1491 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1492 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1493 chapters.append({
1494 'start_time': start_time,
1495 'end_time': end_time,
1496 'title': chapter_title,
1497 })
1498 return chapters
1499
c5e8d7af 1500 def _real_extract(self, url):
cf7e015f
S
1501 url, smuggled_data = unsmuggle_url(url, {})
1502
7e8c0af0 1503 proto = (
78caa52a
PH
1504 'http' if self._downloader.params.get('prefer_insecure', False)
1505 else 'https')
7e8c0af0 1506
7c80519c 1507 start_time = None
297a564b 1508 end_time = None
7c80519c
JMF
1509 parsed_url = compat_urllib_parse_urlparse(url)
1510 for component in [parsed_url.fragment, parsed_url.query]:
1511 query = compat_parse_qs(component)
297a564b 1512 if start_time is None and 't' in query:
7c80519c 1513 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1514 if start_time is None and 'start' in query:
1515 start_time = parse_duration(query['start'][0])
297a564b
JMF
1516 if end_time is None and 'end' in query:
1517 end_time = parse_duration(query['end'][0])
7c80519c 1518
c5e8d7af
PH
1519 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1520 mobj = re.search(self._NEXT_URL_RE, url)
1521 if mobj:
7fd002c0 1522 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1523 video_id = self.extract_id(url)
c5e8d7af
PH
1524
1525 # Get video webpage
aa79ac0c 1526 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1527 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1528
1529 # Attempt to extract SWF player URL
e0df6211 1530 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1531 if mobj is not None:
1532 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1533 else:
1534 player_url = None
1535
d8d24a92
S
1536 dash_mpds = []
1537
1538 def add_dash_mpd(video_info):
1539 dash_mpd = video_info.get('dashmpd')
1540 if dash_mpd and dash_mpd[0] not in dash_mpds:
1541 dash_mpds.append(dash_mpd[0])
1542
c7121fa7
S
1543 is_live = None
1544 view_count = None
1545
1546 def extract_view_count(v_info):
1547 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1548
dbdaaa23
S
1549 player_response = {}
1550
c5e8d7af 1551 # Get video info
6449cd80 1552 embed_webpage = None
c108eb73 1553 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1554 age_gate = True
1555 # We simulate the access to the video from www.youtube.com/v/{video_id}
1556 # this can be viewed without login into Youtube
beb95e77
CL
1557 url = proto + '://www.youtube.com/embed/%s' % video_id
1558 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1559 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1560 'video_id': video_id,
1561 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1562 'sts': self._search_regex(
beb95e77 1563 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1564 })
7e8c0af0 1565 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1566 video_info_webpage = self._download_webpage(
1567 video_info_url, video_id,
20436c30 1568 note='Refetching age-gated info webpage',
94bd3613 1569 errnote='unable to download video info webpage')
c5e8d7af 1570 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1571 add_dash_mpd(video_info)
c108eb73
JMF
1572 else:
1573 age_gate = False
bc93bdb5 1574 video_info = None
dc4e4f90 1575 sts = None
d8d24a92 1576 # Try looking directly into the video webpage
a72778d3
S
1577 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1578 if ytplayer_config:
4e62ebe2 1579 args = ytplayer_config['args']
4c76aa06 1580 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
d8d24a92
S
1581 # Convert to the same format returned by compat_parse_qs
1582 video_info = dict((k, [v]) for k, v in args.items())
1583 add_dash_mpd(video_info)
6496ccb4
S
1584 # Rental video is not rented but preview is available (e.g.
1585 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1586 # https://github.com/rg3/youtube-dl/issues/10532)
1587 if not video_info and args.get('ypc_vid'):
1588 return self.url_result(
1589 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
2fe1ff85
JMF
1590 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1591 is_live = True
dc4e4f90 1592 sts = ytplayer_config.get('sts')
dbdaaa23
S
1593 if not player_response:
1594 pl_response = str_or_none(args.get('player_response'))
1595 if pl_response:
1596 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1597 if isinstance(pl_response, dict):
1598 player_response = pl_response
0a3cf9ad
S
1599 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1600 # We also try looking in get_video_info since it may contain different dashmpd
1601 # URL that points to a DASH manifest with possibly different itag set (some itags
1602 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1603 # manifest pointed by get_video_info's dashmpd).
1604 # The general idea is to take a union of itags of both DASH manifests (for example
1605 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
4e62ebe2 1606 self.report_video_info_webpage_download(video_id)
dc4e4f90
S
1607 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1608 query = {
1609 'video_id': video_id,
1610 'ps': 'default',
1611 'eurl': '',
1612 'gl': 'US',
1613 'hl': 'en',
1614 }
1615 if el:
1616 query['el'] = el
1617 if sts:
1618 query['sts'] = sts
810fb84d 1619 video_info_webpage = self._download_webpage(
dc4e4f90 1620 '%s://www.youtube.com/get_video_info' % proto,
4e62ebe2 1621 video_id, note=False,
dc4e4f90
S
1622 errnote='unable to download video info webpage',
1623 fatal=False, query=query)
1624 if not video_info_webpage:
1625 continue
0a3cf9ad 1626 get_video_info = compat_parse_qs(video_info_webpage)
dbdaaa23
S
1627 if not player_response:
1628 pl_response = get_video_info.get('player_response', [None])[0]
1629 if isinstance(pl_response, dict):
1630 player_response = pl_response
fd545fc6 1631 add_dash_mpd(get_video_info)
c7121fa7
S
1632 if view_count is None:
1633 view_count = extract_view_count(get_video_info)
0a3cf9ad
S
1634 if not video_info:
1635 video_info = get_video_info
1636 if 'token' in get_video_info:
89ea063e
S
1637 # Different get_video_info requests may report different results, e.g.
1638 # some may report video unavailability, but some may serve it without
1639 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1640 # the original webpage as well as el=info and el=embedded get_video_info
1641 # requests report video unavailability due to geo restriction while
1642 # el=detailpage succeeds and returns valid data). This is probably
1643 # due to YouTube measures against IP ranges of hosting providers.
1644 # Working around by preferring the first succeeded video_info containing
1645 # the token if no such video_info yet was found.
44b2264f
S
1646 if 'token' not in video_info:
1647 video_info = get_video_info
4e62ebe2 1648 break
bbb7c3f7
YCH
1649
1650 def extract_unavailable_message():
1651 return self._html_search_regex(
1652 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1653 video_webpage, 'unavailable message', default=None)
1654
c5e8d7af
PH
1655 if 'token' not in video_info:
1656 if 'reason' in video_info:
af214c3a 1657 if 'The uploader has not made this video available in your country.' in video_info['reason']:
fd5c4aab
S
1658 regions_allowed = self._html_search_meta(
1659 'regionsAllowed', video_webpage, default=None)
1660 countries = regions_allowed.split(',') if regions_allowed else None
1661 self.raise_geo_restricted(
1662 msg=video_info['reason'][0], countries=countries)
bbb7c3f7
YCH
1663 reason = video_info['reason'][0]
1664 if 'Invalid parameters' in reason:
1665 unavailable_message = extract_unavailable_message()
1666 if unavailable_message:
1667 reason = unavailable_message
d11271dd 1668 raise ExtractorError(
bbb7c3f7 1669 'YouTube said: %s' % reason,
d11271dd 1670 expected=True, video_id=video_id)
c5e8d7af 1671 else:
d11271dd 1672 raise ExtractorError(
78caa52a 1673 '"token" parameter not in video info for unknown reason',
d11271dd 1674 video_id=video_id)
c5e8d7af 1675
dbdaaa23
S
1676 video_details = try_get(
1677 player_response, lambda x: x['videoDetails'], dict) or {}
1678
cf7e015f
S
1679 # title
1680 if 'title' in video_info:
1681 video_title = video_info['title'][0]
dbdaaa23
S
1682 elif 'title' in player_response:
1683 video_title = video_details['title']
cf7e015f
S
1684 else:
1685 self._downloader.report_warning('Unable to extract video title')
1686 video_title = '_'
1687
1688 # description
9cafc3fd 1689 description_original = video_description = get_element_by_id("eow-description", video_webpage)
cf7e015f 1690 if video_description:
fa4bc6e7
RA
1691
1692 def replace_url(m):
1693 redir_url = compat_urlparse.urljoin(url, m.group(1))
1694 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1695 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1696 qs = compat_parse_qs(parsed_redir_url.query)
1697 q = qs.get('q')
1698 if q and q[0]:
1699 return q[0]
1700 return redir_url
1701
9cafc3fd 1702 description_original = video_description = re.sub(r'''(?x)
cf7e015f 1703 <a\s+
25cb7a0e 1704 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1705 (?:title|href)="([^"]+)"\s+
25cb7a0e 1706 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1707 class="[^"]*"[^>]*>
23f13e97 1708 [^<]+\.{3}\s*
cf7e015f 1709 </a>
fa4bc6e7 1710 ''', replace_url, video_description)
cf7e015f
S
1711 video_description = clean_html(video_description)
1712 else:
1713 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1714 if fd_mobj:
1715 video_description = unescapeHTML(fd_mobj.group(1))
1716 else:
1717 video_description = ''
1718
8fe10494 1719 if not smuggled_data.get('force_singlefeed', False):
5e1eddb9 1720 if not self._downloader.params.get('noplaylist'):
8fe10494
S
1721 multifeed_metadata_list = try_get(
1722 player_response,
1723 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1724 compat_str) or try_get(
1725 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1726 if multifeed_metadata_list:
1727 entries = []
1728 feed_ids = []
1729 for feed in multifeed_metadata_list.split(','):
1730 # Unquote should take place before split on comma (,) since textual
1731 # fields may contain comma as well (see
1732 # https://github.com/rg3/youtube-dl/issues/8536)
1733 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1734 entries.append({
1735 '_type': 'url_transparent',
1736 'ie_key': 'Youtube',
1737 'url': smuggle_url(
1738 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1739 {'force_singlefeed': True}),
1740 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1741 })
1742 feed_ids.append(feed_data['id'][0])
1743 self.to_screen(
1744 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1745 % (', '.join(feed_ids), video_id))
1746 return self.playlist_result(entries, video_id, video_title, video_description)
1747 else:
1748 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1749
c7121fa7 1750 if view_count is None:
1c9c8de2 1751 view_count = extract_view_count(video_info)
dbdaaa23
S
1752 if view_count is None and video_details:
1753 view_count = int_or_none(video_details.get('viewCount'))
1d699755 1754
c5e8d7af
PH
1755 # Check for "rental" videos
1756 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
c9612c04 1757 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
c5e8d7af 1758
c63ca0ee
S
1759 def _extract_filesize(media_url):
1760 return int_or_none(self._search_regex(
1761 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1762
c5e8d7af
PH
1763 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1764 self.report_rtmp_download()
dd27fd17
PH
1765 formats = [{
1766 'format_id': '_rtmp',
1767 'protocol': 'rtmp',
1768 'url': video_info['conn'][0],
1769 'player_url': player_url,
1770 }]
391dd6f0 1771 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 1772 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1773 if 'rtmpe%3Dyes' in encoded_url_map:
a7055eb9 1774 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1775 formats_spec = {}
82156fdb 1776 fmt_list = video_info.get('fmt_list', [''])[0]
1777 if fmt_list:
1778 for fmt in fmt_list.split(','):
1779 spec = fmt.split('/')
3318832e 1780 if len(spec) > 1:
1781 width_height = spec[1].split('x')
1782 if len(width_height) == 2:
1783 formats_spec[spec[0]] = {
1784 'resolution': spec[1],
1785 'width': int_or_none(width_height[0]),
1786 'height': int_or_none(width_height[1]),
1787 }
54fc90aa 1788 q = qualities(['small', 'medium', 'hd720'])
c9afb51c 1789 formats = []
00fe14fc 1790 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1791 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1792 if 'itag' not in url_data or 'url' not in url_data:
1793 continue
1794 format_id = url_data['itag'][0]
1795 url = url_data['url'][0]
1796
a49eccdf 1797 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
6449cd80 1798 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
beb95e77 1799 jsplayer_url_json = self._search_regex(
6449cd80
PH
1800 ASSETS_RE,
1801 embed_webpage if age_gate else video_webpage,
1802 'JS player URL (1)', default=None)
1803 if not jsplayer_url_json and not age_gate:
1804 # We need the embed website after all
1805 if embed_webpage is None:
1806 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1807 embed_webpage = self._download_webpage(
1808 embed_url, video_id, 'Downloading embed webpage')
1809 jsplayer_url_json = self._search_regex(
1810 ASSETS_RE, embed_webpage, 'JS player URL')
1811
beb95e77 1812 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1813 if player_url is None:
1814 player_url_json = self._search_regex(
1815 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1816 video_webpage, 'age gate player URL')
201e9eaa
PH
1817 player_url = json.loads(player_url_json)
1818
a49eccdf
YCH
1819 if 'sig' in url_data:
1820 url += '&signature=' + url_data['sig'][0]
1821 elif 's' in url_data:
1822 encrypted_sig = url_data['s'][0]
1823
201e9eaa 1824 if self._downloader.params.get('verbose'):
cf010131 1825 if player_url is None:
201e9eaa
PH
1826 player_version = 'unknown'
1827 player_desc = 'unknown'
1828 else:
1829 if player_url.endswith('swf'):
1830 player_version = self._search_regex(
1831 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1832 'flash player', fatal=False)
201e9eaa 1833 player_desc = 'flash player %s' % player_version
cf010131 1834 else:
201e9eaa 1835 player_version = self._search_regex(
b62985a9 1836 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
63529e93 1837 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
201e9eaa
PH
1838 player_url,
1839 'html5 player', fatal=False)
78caa52a 1840 player_desc = 'html5 player %s' % player_version
201e9eaa 1841
60064c53 1842 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1843 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1844 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1845
1846 signature = self._decrypt_signature(
1847 encrypted_sig, video_id, player_url, age_gate)
1848 url += '&signature=' + signature
1849 if 'ratebypass' not in url:
1850 url += '&ratebypass=yes'
c9afb51c 1851
94278f72
YCH
1852 dct = {
1853 'format_id': format_id,
1854 'url': url,
1855 'player_url': player_url,
1856 }
1857 if format_id in self._formats:
1858 dct.update(self._formats[format_id])
3318832e 1859 if format_id in formats_spec:
1860 dct.update(formats_spec[format_id])
94278f72 1861
aabc2be6
S
1862 # Some itags are not included in DASH manifest thus corresponding formats will
1863 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1864 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1865 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1866 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72 1867
c63ca0ee
S
1868 filesize = int_or_none(url_data.get(
1869 'clen', [None])[0]) or _extract_filesize(url)
1870
54fc90aa
RA
1871 quality = url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0]
1872
94278f72 1873 more_fields = {
c63ca0ee 1874 'filesize': filesize,
aabc2be6 1875 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1876 'width': width,
1877 'height': height,
1878 'fps': int_or_none(url_data.get('fps', [None])[0]),
54fc90aa
RA
1879 'format_note': quality,
1880 'quality': q(quality),
c9afb51c 1881 }
94278f72
YCH
1882 for key, value in more_fields.items():
1883 if value:
1884 dct[key] = value
aabc2be6
S
1885 type_ = url_data.get('type', [None])[0]
1886 if type_:
1887 type_split = type_.split(';')
1888 kind_ext = type_split[0].split('/')
1889 if len(kind_ext) == 2:
94278f72
YCH
1890 kind, _ = kind_ext
1891 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1892 if kind in ('audio', 'video'):
1893 codecs = None
1894 for mobj in re.finditer(
1895 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1896 if mobj.group('key') == 'codecs':
1897 codecs = mobj.group('val')
1898 break
1899 if codecs:
6310acf5 1900 dct.update(parse_codecs(codecs))
e4a60912
S
1901 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
1902 dct['downloader_options'] = {
1903 # Youtube throttles chunks >~10M
1904 'http_chunk_size': 10485760,
1905 }
aabc2be6 1906 formats.append(dct)
1d043b93
JMF
1907 elif video_info.get('hlsvp'):
1908 manifest_url = video_info['hlsvp'][0]
89beedd3
RA
1909 formats = []
1910 m3u8_formats = self._extract_m3u8_formats(
1911 manifest_url, video_id, 'mp4', fatal=False)
1912 for a_format in m3u8_formats:
1913 itag = self._search_regex(
1914 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1915 if itag:
1916 a_format['format_id'] = itag
1917 if itag in self._formats:
1918 dct = self._formats[itag].copy()
1919 dct.update(a_format)
1920 a_format = dct
1921 a_format['player_url'] = player_url
1922 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
049d71d8 1923 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
89beedd3 1924 formats.append(a_format)
c5e8d7af 1925 else:
4c76aa06
RA
1926 error_message = clean_html(video_info.get('reason', [None])[0])
1927 if not error_message:
1928 error_message = extract_unavailable_message()
1929 if error_message:
1930 raise ExtractorError(error_message, expected=True)
69ea8ca4 1931 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1932
7e72694b 1933 # uploader
dbdaaa23
S
1934 video_uploader = try_get(
1935 video_info, lambda x: x['author'][0],
1936 compat_str) or str_or_none(video_details.get('author'))
7e72694b
S
1937 if video_uploader:
1938 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
1939 else:
1940 self._downloader.report_warning('unable to extract uploader name')
1941
1942 # uploader_id
1943 video_uploader_id = None
1944 video_uploader_url = None
1945 mobj = re.search(
1946 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1947 video_webpage)
1948 if mobj is not None:
1949 video_uploader_id = mobj.group('uploader_id')
1950 video_uploader_url = mobj.group('uploader_url')
1951 else:
1952 self._downloader.report_warning('unable to extract uploader nickname')
1953
dd4c4492
S
1954 channel_id = self._html_search_meta(
1955 'channelId', video_webpage, 'channel id')
1956 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
1957
7e72694b
S
1958 # thumbnail image
1959 # We try first to get a high quality image:
1960 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1961 video_webpage, re.DOTALL)
1962 if m_thumb is not None:
1963 video_thumbnail = m_thumb.group(1)
1964 elif 'thumbnail_url' not in video_info:
1965 self._downloader.report_warning('unable to extract video thumbnail')
1966 video_thumbnail = None
1967 else: # don't panic if we can't find it
1968 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1969
1970 # upload date
1971 upload_date = self._html_search_meta(
1972 'datePublished', video_webpage, 'upload date', default=None)
1973 if not upload_date:
1974 upload_date = self._search_regex(
1975 [r'(?s)id="eow-date.*?>(.*?)</span>',
1976 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
1977 video_webpage, 'upload date', default=None)
1978 upload_date = unified_strdate(upload_date)
1979
1980 video_license = self._html_search_regex(
1981 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1982 video_webpage, 'license', default=None)
1983
1984 m_music = re.search(
1985 r'''(?x)
1986 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
1987 <ul[^>]*>\s*
1988 <li>(?P<title>.+?)
1989 by (?P<creator>.+?)
1990 (?:
1991 \(.+?\)|
1992 <a[^>]*
1993 (?:
1994 \bhref=["\']/red[^>]*>| # drop possible
1995 >\s*Listen ad-free with YouTube Red # YouTube Red ad
1996 )
1997 .*?
1998 )?</li
1999 ''',
2000 video_webpage)
2001 if m_music:
2002 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2003 video_creator = clean_html(m_music.group('creator'))
2004 else:
2005 video_alt_title = video_creator = None
2006
2007 def extract_meta(field):
2008 return self._html_search_regex(
2009 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2010 video_webpage, field, default=None)
2011
2012 track = extract_meta('Song')
2013 artist = extract_meta('Artist')
2014
2015 m_episode = re.search(
2016 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2017 video_webpage)
2018 if m_episode:
2019 series = m_episode.group('series')
2020 season_number = int(m_episode.group('season'))
2021 episode_number = int(m_episode.group('episode'))
2022 else:
2023 series = season_number = episode_number = None
2024
2025 m_cat_container = self._search_regex(
2026 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2027 video_webpage, 'categories', default=None)
2028 if m_cat_container:
2029 category = self._html_search_regex(
2030 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2031 default=None)
2032 video_categories = None if category is None else [category]
2033 else:
2034 video_categories = None
2035
2036 video_tags = [
2037 unescapeHTML(m.group('content'))
2038 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2039
2040 def _extract_count(count_name):
2041 return str_to_int(self._search_regex(
2042 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2043 % re.escape(count_name),
2044 video_webpage, count_name, default=None))
2045
2046 like_count = _extract_count('like')
2047 dislike_count = _extract_count('dislike')
2048
dbdaaa23
S
2049 if view_count is None:
2050 view_count = str_to_int(self._search_regex(
2051 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2052 'view count', default=None))
2053
7e72694b
S
2054 # subtitles
2055 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2056 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2057
2058 video_duration = try_get(
2059 video_info, lambda x: int_or_none(x['length_seconds'][0]))
dbdaaa23
S
2060 if not video_duration:
2061 video_duration = int_or_none(video_details.get('lengthSeconds'))
7e72694b
S
2062 if not video_duration:
2063 video_duration = parse_duration(self._html_search_meta(
2064 'duration', video_webpage, 'video duration'))
2065
2066 # annotations
2067 video_annotations = None
2068 if self._downloader.params.get('writeannotations', False):
2069 video_annotations = self._extract_annotations(video_id)
2070
2071 chapters = self._extract_chapters(description_original, video_duration)
2072
dd27fd17 2073 # Look for the DASH manifest
203fb43f 2074 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 2075 dash_mpd_fatal = True
8ff648e4 2076 for mpd_url in dash_mpds:
d8d24a92 2077 dash_formats = {}
774e208f 2078 try:
05d0d131
YCH
2079 def decrypt_sig(mobj):
2080 s = mobj.group(1)
2081 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2082 return '/signature/%s' % dec_s
2083
8ff648e4 2084 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 2085
8ff648e4 2086 for df in self._extract_mpd_formats(
2087 mpd_url, video_id, fatal=dash_mpd_fatal,
2088 formats_dict=self._formats):
c63ca0ee
S
2089 if not df.get('filesize'):
2090 df['filesize'] = _extract_filesize(df['url'])
d8d24a92
S
2091 # Do not overwrite DASH format found in some previous DASH manifest
2092 if df['format_id'] not in dash_formats:
2093 dash_formats[df['format_id']] = df
77c6fb5b
S
2094 # Additional DASH manifests may end up in HTTP Error 403 therefore
2095 # allow them to fail without bug report message if we already have
2096 # some DASH manifest succeeded. This is temporary workaround to reduce
2097 # burst of bug reports until we figure out the reason and whether it
2098 # can be fixed at all.
2099 dash_mpd_fatal = False
774e208f
PH
2100 except (ExtractorError, KeyError) as e:
2101 self.report_warning(
2102 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 2103 if dash_formats:
04b3b3df
JMF
2104 # Remove the formats we found through non-DASH, they
2105 # contain less info and it can be wrong, because we use
2106 # fixed values (for example the resolution). See
2107 # https://github.com/rg3/youtube-dl/issues/5774 for an
2108 # example.
d80265cc 2109 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 2110 formats.extend(dash_formats.values())
d80044c2 2111
6271f1ca
PH
2112 # Check for malformed aspect ratio
2113 stretched_m = re.search(
2114 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2115 video_webpage)
2116 if stretched_m:
313dfc45
LL
2117 w = float(stretched_m.group('w'))
2118 h = float(stretched_m.group('h'))
5faf9fed
S
2119 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2120 # We will only process correct ratios.
313dfc45 2121 if w > 0 and h > 0:
41f24c32 2122 ratio = w / h
313dfc45
LL
2123 for f in formats:
2124 if f.get('vcodec') != 'none':
2125 f['stretched_ratio'] = ratio
6271f1ca 2126
4bcc7bd1 2127 self._sort_formats(formats)
4ea3be0a 2128
21c340b8 2129 self.mark_watched(video_id, video_info, player_response)
d77ab8e2 2130
4ea3be0a 2131 return {
8bcc8756
JW
2132 'id': video_id,
2133 'uploader': video_uploader,
2134 'uploader_id': video_uploader_id,
fd050249 2135 'uploader_url': video_uploader_url,
dd4c4492
S
2136 'channel_id': channel_id,
2137 'channel_url': channel_url,
8bcc8756 2138 'upload_date': upload_date,
7caf9830 2139 'license': video_license,
936784b2 2140 'creator': video_creator or artist,
8bcc8756 2141 'title': video_title,
936784b2 2142 'alt_title': video_alt_title or track,
8bcc8756
JW
2143 'thumbnail': video_thumbnail,
2144 'description': video_description,
2145 'categories': video_categories,
000b6b5a 2146 'tags': video_tags,
8bcc8756 2147 'subtitles': video_subtitles,
360e1ca5 2148 'automatic_captions': automatic_captions,
8bcc8756
JW
2149 'duration': video_duration,
2150 'age_limit': 18 if age_gate else 0,
2151 'annotations': video_annotations,
9cafc3fd 2152 'chapters': chapters,
7e8c0af0 2153 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 2154 'view_count': view_count,
4ea3be0a 2155 'like_count': like_count,
2156 'dislike_count': dislike_count,
2d30521a 2157 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 2158 'formats': formats,
2fe1ff85 2159 'is_live': is_live,
7c80519c 2160 'start_time': start_time,
297a564b 2161 'end_time': end_time,
12afdc2a
S
2162 'series': series,
2163 'season_number': season_number,
2164 'episode_number': episode_number,
936784b2
S
2165 'track': track,
2166 'artist': artist,
4ea3be0a 2167 }
c5e8d7af 2168
5f6a1245 2169
8e7aad20 2170class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2171 IE_DESC = 'YouTube.com playlists'
d67cc9fa 2172 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
2173 (?:https?://)?
2174 (?:\w+\.)?
c5e8d7af 2175 (?:
c0345b82
S
2176 (?:
2177 youtube\.com|
2178 invidio\.us
2179 )
2180 /
feaa5ad7 2181 (?:
87dadd45 2182 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
feaa5ad7
S
2183 \? (?:.*?[&;])*? (?:p|a|list)=
2184 | p/
2185 )|
2186 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
c5e8d7af 2187 )
d67cc9fa 2188 (
409b9324 2189 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
5f6a1245 2190 # Top tracks, they can also include dots
d67cc9fa
JMF
2191 |(?:MC)[\w\.]*
2192 )
c5e8d7af
PH
2193 .*
2194 |
d0ba5587
S
2195 (%(playlist_id)s)
2196 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
8d81f3e3 2197 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
648e6a1f 2198 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 2199 IE_NAME = 'youtube:playlist'
81127aa5
PH
2200 _TESTS = [{
2201 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2202 'info_dict': {
2203 'title': 'ytdl test PL',
a1cf99d0 2204 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
2205 },
2206 'playlist_count': 3,
9291475f
PH
2207 }, {
2208 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2209 'info_dict': {
acf757f4 2210 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
2211 'title': 'YDL_Empty_List',
2212 },
2213 'playlist_count': 0,
4201ba13 2214 'skip': 'This playlist is private',
9291475f
PH
2215 }, {
2216 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2217 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2218 'info_dict': {
2219 'title': '29C3: Not my department',
acf757f4 2220 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
2221 },
2222 'playlist_count': 95,
2223 }, {
2224 'note': 'issue #673',
2225 'url': 'PLBB231211A4F62143',
2226 'info_dict': {
f46a8702 2227 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 2228 'id': 'PLBB231211A4F62143',
9291475f
PH
2229 },
2230 'playlist_mincount': 26,
2231 }, {
2232 'note': 'Large playlist',
2233 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2234 'info_dict': {
2235 'title': 'Uploads from Cauchemar',
acf757f4 2236 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
2237 },
2238 'playlist_mincount': 799,
2239 }, {
2240 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2241 'info_dict': {
2242 'title': 'YDL_safe_search',
acf757f4 2243 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
2244 },
2245 'playlist_count': 2,
4201ba13 2246 'skip': 'This playlist is private',
ac7553d0
PH
2247 }, {
2248 'note': 'embedded',
2d3d2997 2249 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0
PH
2250 'playlist_count': 4,
2251 'info_dict': {
2252 'title': 'JODA15',
acf757f4 2253 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 2254 }
87dadd45
S
2255 }, {
2256 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2257 'playlist_mincount': 485,
2258 'info_dict': {
2259 'title': '2017 華語最新單曲 (2/24更新)',
2260 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2261 }
6b08cdf6
PH
2262 }, {
2263 'note': 'Embedded SWF player',
2d3d2997 2264 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
6b08cdf6
PH
2265 'playlist_count': 4,
2266 'info_dict': {
2267 'title': 'JODA7',
acf757f4 2268 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 2269 }
4b7df0d3
JMF
2270 }, {
2271 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2272 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2273 'info_dict': {
acf757f4
PH
2274 'title': 'Uploads from Interstellar Movie',
2275 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 2276 },
481cc733 2277 'playlist_mincount': 21,
dacb3a86
S
2278 }, {
2279 # Playlist URL that does not actually serve a playlist
2280 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2281 'info_dict': {
2282 'id': 'FqZTN594JQw',
2283 'ext': 'webm',
2284 'title': "Smiley's People 01 detective, Adventure Series, Action",
2285 'uploader': 'STREEM',
2286 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 2287 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
2288 'upload_date': '20150526',
2289 'license': 'Standard YouTube License',
2290 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2291 'categories': ['People & Blogs'],
2292 'tags': list,
dbdaaa23 2293 'view_count': int,
dacb3a86
S
2294 'like_count': int,
2295 'dislike_count': int,
2296 },
2297 'params': {
2298 'skip_download': True,
2299 },
2300 'add_ie': [YoutubeIE.ie_key()],
481cc733
S
2301 }, {
2302 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2303 'info_dict': {
2304 'id': 'yeWKywCrFtk',
2305 'ext': 'mp4',
2306 'title': 'Small Scale Baler and Braiding Rugs',
2307 'uploader': 'Backus-Page House Museum',
2308 'uploader_id': 'backuspagemuseum',
ec85ded8 2309 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
481cc733
S
2310 'upload_date': '20161008',
2311 'license': 'Standard YouTube License',
2312 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2313 'categories': ['Nonprofits & Activism'],
2314 'tags': list,
2315 'like_count': int,
2316 'dislike_count': int,
2317 },
2318 'params': {
2319 'noplaylist': True,
2320 'skip_download': True,
2321 },
feaa5ad7
S
2322 }, {
2323 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2324 'only_matching': True,
a6857510
S
2325 }, {
2326 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2327 'only_matching': True,
409b9324
S
2328 }, {
2329 # music album playlist
2330 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2331 'only_matching': True,
c0345b82
S
2332 }, {
2333 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2334 'only_matching': True,
81127aa5 2335 }]
c5e8d7af 2336
880e1c52
JMF
2337 def _real_initialize(self):
2338 self._login()
2339
652cdaa2 2340 def _extract_mix(self, playlist_id):
99209c29 2341 # The mixes are generated from a single video
652cdaa2 2342 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
2343 ids = []
2344 last_id = playlist_id[-11:]
2345 for n in itertools.count(1):
2346 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2347 webpage = self._download_webpage(
2348 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2349 new_ids = orderedSet(re.findall(
2350 r'''(?xs)data-video-username=".*?".*?
2351 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
2352 webpage))
2353 # Fetch new pages until all the videos are repeated, it seems that
2354 # there are always 51 unique videos.
2355 new_ids = [_id for _id in new_ids if _id not in ids]
2356 if not new_ids:
2357 break
2358 ids.extend(new_ids)
2359 last_id = ids[-1]
2360
2361 url_results = self._ids_to_results(ids)
2362
bc2f773b 2363 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
2364 title_span = (
2365 search_title('playlist-title') or
2366 search_title('title long-title') or
2367 search_title('title'))
76d1700b 2368 title = clean_html(title_span)
652cdaa2
JMF
2369
2370 return self.playlist_result(url_results, playlist_id, title)
2371
448830ce 2372 def _extract_playlist(self, playlist_id):
dbb94fb0
S
2373 url = self._TEMPLATE_URL % playlist_id
2374 page = self._download_webpage(url, playlist_id)
dbb94fb0 2375
8bc0800d
G
2376 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2377 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
39b62db1
YCH
2378 match = match.strip()
2379 # Check if the playlist exists or is private
4201ba13
S
2380 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2381 if mobj:
2382 reason = mobj.group('reason')
2383 message = 'This playlist %s' % reason
2384 if 'private' in reason:
2385 message += ', use --username or --netrc to access it'
2386 message += '.'
2387 raise ExtractorError(message, expected=True)
39b62db1
YCH
2388 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2389 raise ExtractorError(
2390 'Invalid parameters. Maybe URL is incorrect.',
2391 expected=True)
2392 elif re.match(r'[^<]*Choose your language[^<]*', match):
2393 continue
2394 else:
2395 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 2396
dbb94fb0 2397 playlist_title = self._html_search_regex(
63b4295d 2398 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
dacb3a86 2399 page, 'title', default=None)
c5e8d7af 2400
07aeced6
S
2401 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2402 uploader = self._search_regex(
2403 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2404 page, 'uploader', default=None)
2405 mobj = re.search(
2406 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2407 page)
2408 if mobj:
2409 uploader_id = mobj.group('uploader_id')
2410 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2411 else:
2412 uploader_id = uploader_url = None
2413
dacb3a86
S
2414 has_videos = True
2415
2416 if not playlist_title:
2417 try:
2418 # Some playlist URLs don't actually serve a playlist (e.g.
2419 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2420 next(self._entries(page, playlist_id))
2421 except StopIteration:
2422 has_videos = False
2423
07aeced6 2424 playlist = self.playlist_result(
dacb3a86 2425 self._entries(page, playlist_id), playlist_id, playlist_title)
07aeced6
S
2426 playlist.update({
2427 'uploader': uploader,
2428 'uploader_id': uploader_id,
2429 'uploader_url': uploader_url,
2430 })
2431
2432 return has_videos, playlist
c5e8d7af 2433
ebf1b291 2434 def _check_download_just_video(self, url, playlist_id):
448830ce
S
2435 # Check if it's a video-specific URL
2436 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
481cc733 2437 video_id = query_dict.get('v', [None])[0] or self._search_regex(
87dadd45 2438 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
481cc733
S
2439 'video id', default=None)
2440 if video_id:
448830ce
S
2441 if self._downloader.params.get('noplaylist'):
2442 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
dacb3a86 2443 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce
S
2444 else:
2445 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
dacb3a86
S
2446 return video_id, None
2447 return None, None
448830ce 2448
ebf1b291
S
2449 def _real_extract(self, url):
2450 # Extract playlist id
2451 mobj = re.match(self._VALID_URL, url)
2452 if mobj is None:
2453 raise ExtractorError('Invalid URL: %s' % url)
2454 playlist_id = mobj.group(1) or mobj.group(2)
2455
dacb3a86 2456 video_id, video = self._check_download_just_video(url, playlist_id)
ebf1b291
S
2457 if video:
2458 return video
2459
466a6145 2460 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
2461 # Mixes require a custom extraction process
2462 return self._extract_mix(playlist_id)
2463
dacb3a86
S
2464 has_videos, playlist = self._extract_playlist(playlist_id)
2465 if has_videos or not video_id:
2466 return playlist
2467
2468 # Some playlist URLs don't actually serve a playlist (see
2469 # https://github.com/rg3/youtube-dl/issues/10537).
2470 # Fallback to plain video extraction if there is a video id
2471 # along with playlist id.
2472 return self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce 2473
c5e8d7af 2474
648e6a1f 2475class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2476 IE_DESC = 'YouTube.com channels'
cd5a74a2 2477 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 2478 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 2479 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 2480 IE_NAME = 'youtube:channel'
cdc628a4
PH
2481 _TESTS = [{
2482 'note': 'paginated channel',
2483 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2484 'playlist_mincount': 91,
acf757f4 2485 'info_dict': {
9170ca5b
JMF
2486 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2487 'title': 'Uploads from lex will',
acf757f4 2488 }
5c43afd4
JMF
2489 }, {
2490 'note': 'Age restricted channel',
2491 # from https://www.youtube.com/user/DeusExOfficial
2492 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2493 'playlist_mincount': 64,
2494 'info_dict': {
2495 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2496 'title': 'Uploads from Deus Ex',
2497 },
cd5a74a2
S
2498 }, {
2499 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2500 'only_matching': True,
cdc628a4 2501 }]
c5e8d7af 2502
e462474e
S
2503 @classmethod
2504 def suitable(cls, url):
f07e276a
S
2505 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2506 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 2507
9558dcec
S
2508 def _build_template_url(self, url, channel_id):
2509 return self._TEMPLATE_URL % channel_id
2510
c5e8d7af 2511 def _real_extract(self, url):
9ff67727 2512 channel_id = self._match_id(url)
c5e8d7af 2513
9558dcec 2514 url = self._build_template_url(url, channel_id)
386bdfa6
S
2515
2516 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2517 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2518 # otherwise fallback on channel by page extraction
2519 channel_page = self._download_webpage(
2520 url + '?view=57', channel_id,
2521 'Downloading channel page', fatal=False)
2b3c2546
PH
2522 if channel_page is False:
2523 channel_playlist_id = False
2524 else:
2525 channel_playlist_id = self._html_search_meta(
2526 'channelId', channel_page, 'channel id', default=None)
2527 if not channel_playlist_id:
73c4ac2c
S
2528 channel_url = self._html_search_meta(
2529 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2530 channel_page, 'channel url', default=None)
2531 if channel_url:
2532 channel_playlist_id = self._search_regex(
2533 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2534 channel_url, 'channel id', default=None)
386bdfa6
S
2535 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2536 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2537 return self.url_result(
2538 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2539
60bf45c8 2540 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2541 autogenerated = re.search(r'''(?x)
2542 class="[^"]*?(?:
2543 channel-header-autogenerated-label|
2544 yt-channel-title-autogenerated
2545 )[^"]*"''', channel_page) is not None
c5e8d7af 2546
b9643eed
JMF
2547 if autogenerated:
2548 # The videos are contained in a single page
2549 # the ajax pages can't be used, they are empty
b82f815f 2550 entries = [
fb69240c
S
2551 self.url_result(
2552 video_id, 'Youtube', video_id=video_id,
2553 video_title=video_title)
8f02ad4f 2554 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2555 return self.playlist_result(entries, channel_id)
2556
73c4ac2c
S
2557 try:
2558 next(self._entries(channel_page, channel_id))
2559 except StopIteration:
2560 alert_message = self._html_search_regex(
2561 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2562 channel_page, 'alert', default=None, group='alert')
2563 if alert_message:
2564 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2565
648e6a1f 2566 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2567
2568
eb0f3e7e 2569class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2570 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
ea696249 2571 _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 2572 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
78caa52a 2573 IE_NAME = 'youtube:user'
c5e8d7af 2574
cdc628a4
PH
2575 _TESTS = [{
2576 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2577 'playlist_mincount': 320,
2578 'info_dict': {
73c4ac2c
S
2579 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2580 'title': 'Uploads from The Linux Foundation',
cdc628a4 2581 }
9558dcec
S
2582 }, {
2583 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2584 # but not https://www.youtube.com/user/12minuteathlete/videos
2585 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2586 'playlist_mincount': 249,
2587 'info_dict': {
2588 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2589 'title': 'Uploads from 12 Minute Athlete',
2590 }
cdc628a4
PH
2591 }, {
2592 'url': 'ytuser:phihag',
2593 'only_matching': True,
daa0df9e
YCH
2594 }, {
2595 'url': 'https://www.youtube.com/c/gametrailers',
2596 'only_matching': True,
9558dcec
S
2597 }, {
2598 'url': 'https://www.youtube.com/gametrailers',
2599 'only_matching': True,
73c4ac2c 2600 }, {
0e879f43 2601 # This channel is not available, geo restricted to JP
73c4ac2c
S
2602 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2603 'only_matching': True,
cdc628a4
PH
2604 }]
2605
e3ea4790 2606 @classmethod
f4b05232 2607 def suitable(cls, url):
e3ea4790
JMF
2608 # Don't return True if the url can be extracted with other youtube
2609 # extractor, the regex would is too permissive and it would match.
f3a58d46 2610 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2611 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2612 return False
2613 else:
2614 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2615
9558dcec
S
2616 def _build_template_url(self, url, channel_id):
2617 mobj = re.match(self._VALID_URL, url)
2618 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2619
b05654f0 2620
f07e276a
S
2621class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2622 IE_DESC = 'YouTube.com live streams'
073d5bf5 2623 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
f07e276a
S
2624 IE_NAME = 'youtube:live'
2625
2626 _TESTS = [{
2d3d2997 2627 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
f07e276a
S
2628 'info_dict': {
2629 'id': 'a48o2S1cPoo',
2630 'ext': 'mp4',
2631 'title': 'The Young Turks - Live Main Show',
2632 'uploader': 'The Young Turks',
2633 'uploader_id': 'TheYoungTurks',
ec85ded8 2634 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
f07e276a
S
2635 'upload_date': '20150715',
2636 'license': 'Standard YouTube License',
2637 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2638 'categories': ['News & Politics'],
2639 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2640 'like_count': int,
2641 'dislike_count': int,
2642 },
2643 'params': {
2644 'skip_download': True,
2645 },
2646 }, {
2d3d2997 2647 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
f07e276a 2648 'only_matching': True,
c1b2a085
S
2649 }, {
2650 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2651 'only_matching': True,
073d5bf5
S
2652 }, {
2653 'url': 'https://www.youtube.com/TheYoungTurks/live',
2654 'only_matching': True,
f07e276a
S
2655 }]
2656
2657 def _real_extract(self, url):
2658 mobj = re.match(self._VALID_URL, url)
2659 channel_id = mobj.group('id')
2660 base_url = mobj.group('base_url')
2661 webpage = self._download_webpage(url, channel_id, fatal=False)
2662 if webpage:
2663 page_type = self._og_search_property(
e7f3529f 2664 'type', webpage, 'page type', default='')
f07e276a
S
2665 video_id = self._html_search_meta(
2666 'videoId', webpage, 'video id', default=None)
e7f3529f
S
2667 if page_type.startswith('video') and video_id and re.match(
2668 r'^[0-9A-Za-z_-]{11}$', video_id):
f07e276a
S
2669 return self.url_result(video_id, YoutubeIE.ie_key())
2670 return self.url_result(base_url)
2671
2672
e462474e
S
2673class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2674 IE_DESC = 'YouTube.com user/channel playlists'
2675 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2676 IE_NAME = 'youtube:playlists'
0c148415 2677
e568c223 2678 _TESTS = [{
2d3d2997 2679 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
0c148415
S
2680 'playlist_mincount': 4,
2681 'info_dict': {
2682 'id': 'ThirstForScience',
2683 'title': 'Thirst for Science',
2684 },
e568c223
S
2685 }, {
2686 # with "Load more" button
2d3d2997 2687 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
e568c223
S
2688 'playlist_mincount': 70,
2689 'info_dict': {
2690 'id': 'igorkle1',
2691 'title': 'Игорь Клейнер',
2692 },
e462474e
S
2693 }, {
2694 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2695 'playlist_mincount': 17,
2696 'info_dict': {
2697 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2698 'title': 'Chem Player',
2699 },
e568c223 2700 }]
0c148415
S
2701
2702
870f3bfc
S
2703class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2704 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2705
2706
2707class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
78caa52a 2708 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2709 # there doesn't appear to be a real limit, for example if you search for
2710 # 'python' you get more than 8.000.000 results
2711 _MAX_RESULTS = float('inf')
78caa52a 2712 IE_NAME = 'youtube:search'
b05654f0 2713 _SEARCH_KEY = 'ytsearch'
b4c08069 2714 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2715 _TESTS = []
b05654f0 2716
b05654f0
PH
2717 def _get_n_results(self, query, n):
2718 """Get a specified number of results for a query"""
2719
b4c08069 2720 videos = []
b05654f0
PH
2721 limit = n
2722
a22b2fd1
YCH
2723 url_query = {
2724 'search_query': query.encode('utf-8'),
2725 }
2726 url_query.update(self._EXTRA_QUERY_ARGS)
2727 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2728
b4c08069 2729 for pagenum in itertools.count(1):
b4c08069 2730 data = self._download_json(
69ea8ca4 2731 result_url, video_id='query "%s"' % query,
b4c08069 2732 note='Downloading page %s' % pagenum,
a22b2fd1
YCH
2733 errnote='Unable to download API page',
2734 query={'spf': 'navigate'})
b4c08069 2735 html_content = data[1]['body']['content']
7cc3570e 2736
b4c08069 2737 if 'class="search-message' in html_content:
07ad22b8 2738 raise ExtractorError(
78caa52a 2739 '[youtube] No video results', expected=True)
b05654f0 2740
870f3bfc 2741 new_videos = list(self._process_page(html_content))
b4c08069
JMF
2742 videos += new_videos
2743 if not new_videos or len(videos) > limit:
2744 break
a22b2fd1
YCH
2745 next_link = self._html_search_regex(
2746 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2747 html_content, 'next link', default=None)
2748 if next_link is None:
2749 break
2750 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
b05654f0 2751
b4c08069
JMF
2752 if len(videos) > n:
2753 videos = videos[:n]
b05654f0 2754 return self.playlist_result(videos, query)
75dff0ee 2755
c9ae7b95 2756
a3dd9248 2757class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2758 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2759 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2760 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2761 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2762
c9ae7b95 2763
870f3bfc 2764class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
78caa52a
PH
2765 IE_DESC = 'YouTube.com search URLs'
2766 IE_NAME = 'youtube:search_url'
d2c1f79f 2767 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
cdc628a4
PH
2768 _TESTS = [{
2769 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2770 'playlist_mincount': 5,
2771 'info_dict': {
2772 'title': 'youtube-dl test video',
2773 }
d2c1f79f
S
2774 }, {
2775 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2776 'only_matching': True,
cdc628a4 2777 }]
c9ae7b95
PH
2778
2779 def _real_extract(self, url):
2780 mobj = re.match(self._VALID_URL, url)
7fd002c0 2781 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2782 webpage = self._download_webpage(url, query)
175c2e9e 2783 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2784
2785
136dadde 2786class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2787 IE_DESC = 'YouTube.com (multi-season) shows'
92519402 2788 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2789 IE_NAME = 'youtube:show'
cdc628a4 2790 _TESTS = [{
4003bd82 2791 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2792 'playlist_mincount': 5,
cdc628a4
PH
2793 'info_dict': {
2794 'id': 'airdisasters',
2795 'title': 'Air Disasters',
2796 }
2797 }]
75dff0ee
JMF
2798
2799 def _real_extract(self, url):
136dadde
S
2800 playlist_id = self._match_id(url)
2801 return super(YoutubeShowIE, self)._real_extract(
2802 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2803
2804
b2e8bc1b 2805class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2806 """
25f14e9f 2807 Base class for feed extractors
d7ae0639
JMF
2808 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2809 """
b2e8bc1b 2810 _LOGIN_REQUIRED = True
d7ae0639
JMF
2811
2812 @property
2813 def IE_NAME(self):
78caa52a 2814 return 'youtube:%s' % self._FEED_NAME
04cc9617 2815
81f0259b 2816 def _real_initialize(self):
b2e8bc1b 2817 self._login()
81f0259b 2818
3853309f 2819 def _entries(self, page):
2bc43303
JMF
2820 # The extraction process is the same as for playlists, but the regex
2821 # for the video ids doesn't contain an index
2822 ids = []
2823 more_widget_html = content_html = page
2bc43303
JMF
2824 for page_num in itertools.count(1):
2825 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2826
2827 # 'recommended' feed has infinite 'load more' and each new portion spins
2828 # the same videos in (sometimes) slightly different order, so we'll check
2829 # for unicity and break when portion has no new videos
3853309f 2830 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
62c95fd5
S
2831 if not new_ids:
2832 break
2833
2bc43303
JMF
2834 ids.extend(new_ids)
2835
3853309f
S
2836 for entry in self._ids_to_results(new_ids):
2837 yield entry
2838
2bc43303
JMF
2839 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2840 if not mobj:
2841 break
2842
2843 more = self._download_json(
25f14e9f 2844 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2845 'Downloading page #%s' % page_num,
2846 transform_source=uppercase_escape)
2847 content_html = more['content_html']
2848 more_widget_html = more['load_more_widget_html']
2849
3853309f
S
2850 def _real_extract(self, url):
2851 page = self._download_webpage(
2852 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
2853 self._PLAYLIST_TITLE)
25f14e9f 2854 return self.playlist_result(
3853309f 2855 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
25f14e9f
S
2856
2857
2858class YoutubeWatchLaterIE(YoutubePlaylistIE):
2859 IE_NAME = 'youtube:watchlater'
2860 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
92519402 2861 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2862
bc7a9cd8
S
2863 _TESTS = [{
2864 'url': 'https://www.youtube.com/playlist?list=WL',
2865 'only_matching': True,
2866 }, {
2867 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2868 'only_matching': True,
2869 }]
25f14e9f
S
2870
2871 def _real_extract(self, url):
7e5dc339 2872 _, video = self._check_download_just_video(url, 'WL')
ebf1b291
S
2873 if video:
2874 return video
dacb3a86
S
2875 _, playlist = self._extract_playlist('WL')
2876 return playlist
f459d170 2877
5f6a1245 2878
c626a3d9 2879class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2880 IE_NAME = 'youtube:favorites'
f3a34072 2881 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
92519402 2882 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2883 _LOGIN_REQUIRED = True
2884
2885 def _real_extract(self, url):
2886 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2887 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2888 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2889
2890
25f14e9f
S
2891class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2892 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
92519402 2893 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
25f14e9f
S
2894 _FEED_NAME = 'recommended'
2895 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2896
1ed5b5c9 2897
25f14e9f
S
2898class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2899 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
92519402 2900 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
25f14e9f
S
2901 _FEED_NAME = 'subscriptions'
2902 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2903
1ed5b5c9 2904
25f14e9f
S
2905class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2906 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
92519402 2907 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
25f14e9f
S
2908 _FEED_NAME = 'history'
2909 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2910
2911
15870e90
PH
2912class YoutubeTruncatedURLIE(InfoExtractor):
2913 IE_NAME = 'youtube:truncated_url'
2914 IE_DESC = False # Do not list
975d35db 2915 _VALID_URL = r'''(?x)
b95aab84
PH
2916 (?:https?://)?
2917 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2918 (?:watch\?(?:
c4808c60 2919 feature=[a-z_]+|
b95aab84
PH
2920 annotation_id=annotation_[^&]+|
2921 x-yt-cl=[0-9]+|
c1708b89 2922 hl=[^&]*|
287be8c6 2923 t=[0-9]+
b95aab84
PH
2924 )?
2925 |
2926 attribution_link\?a=[^&]+
2927 )
2928 $
975d35db 2929 '''
15870e90 2930
c4808c60 2931 _TESTS = [{
2d3d2997 2932 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 2933 'only_matching': True,
dc2fc736 2934 }, {
2d3d2997 2935 'url': 'https://www.youtube.com/watch?',
dc2fc736 2936 'only_matching': True,
b95aab84
PH
2937 }, {
2938 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2939 'only_matching': True,
2940 }, {
2941 'url': 'https://www.youtube.com/watch?feature=foo',
2942 'only_matching': True,
c1708b89
PH
2943 }, {
2944 'url': 'https://www.youtube.com/watch?hl=en-GB',
2945 'only_matching': True,
287be8c6
PH
2946 }, {
2947 'url': 'https://www.youtube.com/watch?t=2372',
2948 'only_matching': True,
c4808c60
PH
2949 }]
2950
15870e90
PH
2951 def _real_extract(self, url):
2952 raise ExtractorError(
78caa52a
PH
2953 'Did you forget to quote the URL? Remember that & is a meta '
2954 'character in most shells, so you want to put the URL in quotes, '
2955 'like youtube-dl '
2d3d2997 2956 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
78caa52a 2957 ' or simply youtube-dl BaW_jenozKc .',
15870e90 2958 expected=True)
772fd5cc
PH
2959
2960
2961class YoutubeTruncatedIDIE(InfoExtractor):
2962 IE_NAME = 'youtube:truncated_id'
2963 IE_DESC = False # Do not list
b95aab84 2964 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
2965
2966 _TESTS = [{
2967 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2968 'only_matching': True,
2969 }]
2970
2971 def _real_extract(self, url):
2972 video_id = self._match_id(url)
2973 raise ExtractorError(
2974 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
2975 expected=True)