]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[test/helper] Add support for maxcount and count collection len test checkers
[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 },
825cd268
RA
1080 {
1081 # DRM protected
1082 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1083 'only_matching': True,
1084 }
2eb88d95
PH
1085 ]
1086
e0df6211
PH
1087 def __init__(self, *args, **kwargs):
1088 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 1089 self._player_cache = {}
e0df6211 1090
c5e8d7af
PH
1091 def report_video_info_webpage_download(self, video_id):
1092 """Report attempt to download video info webpage."""
69ea8ca4 1093 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 1094
c5e8d7af
PH
1095 def report_information_extraction(self, video_id):
1096 """Report attempt to extract video information."""
69ea8ca4 1097 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
1098
1099 def report_unavailable_format(self, video_id, format):
1100 """Report extracted video URL."""
69ea8ca4 1101 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
1102
1103 def report_rtmp_download(self):
1104 """Indicate the download will use the RTMP protocol."""
69ea8ca4 1105 self.to_screen('RTMP download detected')
c5e8d7af 1106
60064c53
PH
1107 def _signature_cache_id(self, example_sig):
1108 """ Return a string representation of a signature """
78caa52a 1109 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
1110
1111 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 1112 id_m = re.match(
63529e93 1113 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
cf010131 1114 player_url)
c081b35c
PH
1115 if not id_m:
1116 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
1117 player_type = id_m.group('ext')
1118 player_id = id_m.group('id')
1119
c4417ddb 1120 # Read from filesystem cache
60064c53
PH
1121 func_id = '%s_%s_%s' % (
1122 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 1123 assert os.path.basename(func_id) == func_id
a0e07d31 1124
69ea8ca4 1125 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 1126 if cache_spec is not None:
78caa52a 1127 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 1128
6d1a55a5
PH
1129 download_note = (
1130 'Downloading player %s' % player_url
1131 if self._downloader.params.get('verbose') else
1132 'Downloading %s player %s' % (player_type, player_id)
1133 )
e0df6211
PH
1134 if player_type == 'js':
1135 code = self._download_webpage(
1136 player_url, video_id,
6d1a55a5 1137 note=download_note,
69ea8ca4 1138 errnote='Download of %s failed' % player_url)
83799698 1139 res = self._parse_sig_js(code)
c4417ddb 1140 elif player_type == 'swf':
e0df6211
PH
1141 urlh = self._request_webpage(
1142 player_url, video_id,
6d1a55a5 1143 note=download_note,
69ea8ca4 1144 errnote='Download of %s failed' % player_url)
e0df6211 1145 code = urlh.read()
83799698 1146 res = self._parse_sig_swf(code)
e0df6211
PH
1147 else:
1148 assert False, 'Invalid player type %r' % player_type
1149
785521bf
PH
1150 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1151 cache_res = res(test_string)
1152 cache_spec = [ord(c) for c in cache_res]
83799698 1153
69ea8ca4 1154 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
1155 return res
1156
60064c53 1157 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1158 def gen_sig_code(idxs):
1159 def _genslice(start, end, step):
78caa52a 1160 starts = '' if start == 0 else str(start)
8bcc8756 1161 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1162 steps = '' if step == 1 else (':%d' % step)
78caa52a 1163 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1164
1165 step = None
7af808a5
PH
1166 # Quelch pyflakes warnings - start will be set when step is set
1167 start = '(Never used)'
edf3e38e
PH
1168 for i, prev in zip(idxs[1:], idxs[:-1]):
1169 if step is not None:
1170 if i - prev == step:
1171 continue
1172 yield _genslice(start, prev, step)
1173 step = None
1174 continue
1175 if i - prev in [-1, 1]:
1176 step = i - prev
1177 start = prev
1178 continue
1179 else:
78caa52a 1180 yield 's[%d]' % prev
edf3e38e 1181 if step is None:
78caa52a 1182 yield 's[%d]' % i
edf3e38e
PH
1183 else:
1184 yield _genslice(start, i, step)
1185
78caa52a 1186 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1187 cache_res = func(test_string)
edf3e38e 1188 cache_spec = [ord(c) for c in cache_res]
78caa52a 1189 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1190 signature_id_tuple = '(%s)' % (
1191 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1192 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1193 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1194 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1195
e0df6211
PH
1196 def _parse_sig_js(self, jscode):
1197 funcname = self._search_regex(
3c90cc8b 1198 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35
S
1199 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1200 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2511eee2
S
1201 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1202 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 1203 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1204
1205 jsi = JSInterpreter(jscode)
1206 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1207 return lambda s: initial_function([s])
1208
1209 def _parse_sig_swf(self, file_contents):
54256267 1210 swfi = SWFInterpreter(file_contents)
78caa52a 1211 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 1212 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 1213 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
1214 return lambda s: initial_function([s])
1215
83799698 1216 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 1217 """Turn the encrypted s field into a working signature"""
6b37f0be 1218
c8bf86d5 1219 if player_url is None:
69ea8ca4 1220 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1221
69ea8ca4 1222 if player_url.startswith('//'):
78caa52a 1223 player_url = 'https:' + player_url
3c90cc8b
S
1224 elif not re.match(r'https?://', player_url):
1225 player_url = compat_urlparse.urljoin(
1226 'https://www.youtube.com', player_url)
c8bf86d5 1227 try:
62af3a0e 1228 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1229 if player_id not in self._player_cache:
1230 func = self._extract_signature_function(
60064c53 1231 video_id, player_url, s
c8bf86d5
PH
1232 )
1233 self._player_cache[player_id] = func
1234 func = self._player_cache[player_id]
1235 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1236 self._print_sig_code(func, s)
c8bf86d5
PH
1237 return func(s)
1238 except Exception as e:
1239 tb = traceback.format_exc()
1240 raise ExtractorError(
78caa52a 1241 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1242
360e1ca5 1243 def _get_subtitles(self, video_id, webpage):
de7f3446 1244 try:
60e47a26 1245 subs_doc = self._download_xml(
38c2e5b8 1246 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1247 video_id, note=False)
1248 except ExtractorError as err:
9b9c5355 1249 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1250 return {}
de7f3446
JMF
1251
1252 sub_lang_list = {}
60e47a26
JMF
1253 for track in subs_doc.findall('track'):
1254 lang = track.attrib['lang_code']
7e660ac1
LD
1255 if lang in sub_lang_list:
1256 continue
360e1ca5 1257 sub_formats = []
23d17e4b 1258 for ext in self._SUBTITLE_FORMATS:
15707c7e 1259 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1260 'lang': lang,
1261 'v': video_id,
1262 'fmt': ext,
1263 'name': track.attrib['name'].encode('utf-8'),
1264 })
1265 sub_formats.append({
1266 'url': 'https://www.youtube.com/api/timedtext?' + params,
1267 'ext': ext,
1268 })
1269 sub_lang_list[lang] = sub_formats
de7f3446 1270 if not sub_lang_list:
69ea8ca4 1271 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1272 return {}
1273 return sub_lang_list
1274
a72778d3
S
1275 def _get_ytplayer_config(self, video_id, webpage):
1276 patterns = (
526b3b07
S
1277 # User data may contain arbitrary character sequences that may affect
1278 # JSON extraction with regex, e.g. when '};' is contained the second
1279 # regex won't capture the whole JSON. Yet working around by trying more
1280 # concrete regex first keeping in mind proper quoted string handling
1281 # to be implemented in future that will replace this workaround (see
1282 # https://github.com/rg3/youtube-dl/issues/7468,
1283 # https://github.com/rg3/youtube-dl/pull/7599)
a72778d3
S
1284 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1285 r';ytplayer\.config\s*=\s*({.+?});',
1286 )
1287 config = self._search_regex(
1288 patterns, webpage, 'ytplayer.config', default=None)
1289 if config:
1290 return self._parse_json(
1291 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1292
360e1ca5 1293 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1294 """We need the webpage for getting the captions url, pass it as an
1295 argument to speed up the process."""
69ea8ca4 1296 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1297 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1298 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1299 if not player_config:
de7f3446
JMF
1300 self._downloader.report_warning(err_msg)
1301 return {}
de7f3446 1302 try:
0792d563 1303 args = player_config['args']
b78b292f
S
1304 caption_url = args.get('ttsurl')
1305 if caption_url:
1306 timestamp = args['timestamp']
1307 # We get the available subtitles
15707c7e 1308 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1309 'type': 'list',
1310 'tlangs': 1,
1311 'asrs': 1,
1312 })
1313 list_url = caption_url + '&' + list_params
1314 caption_list = self._download_xml(list_url, video_id)
1315 original_lang_node = caption_list.find('track')
1316 if original_lang_node is None:
1317 self._downloader.report_warning('Video doesn\'t have automatic captions')
1318 return {}
1319 original_lang = original_lang_node.attrib['lang_code']
1320 caption_kind = original_lang_node.attrib.get('kind', '')
1321
1322 sub_lang_list = {}
1323 for lang_node in caption_list.findall('target'):
1324 sub_lang = lang_node.attrib['lang_code']
1325 sub_formats = []
1326 for ext in self._SUBTITLE_FORMATS:
15707c7e 1327 params = compat_urllib_parse_urlencode({
b78b292f
S
1328 'lang': original_lang,
1329 'tlang': sub_lang,
1330 'fmt': ext,
1331 'ts': timestamp,
1332 'kind': caption_kind,
1333 })
1334 sub_formats.append({
1335 'url': caption_url + '&' + params,
1336 'ext': ext,
1337 })
1338 sub_lang_list[sub_lang] = sub_formats
1339 return sub_lang_list
1340
ddbb4c5c
S
1341 def make_captions(sub_url, sub_langs):
1342 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1343 caption_qs = compat_parse_qs(parsed_sub_url.query)
1344 captions = {}
1345 for sub_lang in sub_langs:
1346 sub_formats = []
1347 for ext in self._SUBTITLE_FORMATS:
1348 caption_qs.update({
1349 'tlang': [sub_lang],
1350 'fmt': [ext],
1351 })
1352 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1353 query=compat_urllib_parse_urlencode(caption_qs, True)))
1354 sub_formats.append({
1355 'url': sub_url,
1356 'ext': ext,
1357 })
1358 captions[sub_lang] = sub_formats
1359 return captions
1360
1361 # New captions format as of 22.06.2017
1362 player_response = args.get('player_response')
1363 if player_response and isinstance(player_response, compat_str):
1364 player_response = self._parse_json(
1365 player_response, video_id, fatal=False)
1366 if player_response:
1367 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1368 base_url = renderer['captionTracks'][0]['baseUrl']
1369 sub_lang_list = []
1370 for lang in renderer['translationLanguages']:
1371 lang_code = lang.get('languageCode')
1372 if lang_code:
1373 sub_lang_list.append(lang_code)
1374 return make_captions(base_url, sub_lang_list)
1375
b78b292f
S
1376 # Some videos don't provide ttsurl but rather caption_tracks and
1377 # caption_translation_languages (e.g. 20LmZk1hakA)
ddbb4c5c 1378 # Does not used anymore as of 22.06.2017
b78b292f
S
1379 caption_tracks = args['caption_tracks']
1380 caption_translation_languages = args['caption_translation_languages']
1381 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
ddbb4c5c 1382 sub_lang_list = []
b78b292f
S
1383 for lang in caption_translation_languages.split(','):
1384 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1385 sub_lang = lang_qs.get('lc', [None])[0]
ddbb4c5c
S
1386 if sub_lang:
1387 sub_lang_list.append(sub_lang)
1388 return make_captions(caption_url, sub_lang_list)
de7f3446
JMF
1389 # An extractor error can be raise by the download process if there are
1390 # no automatic captions but there are subtitles
ddbb4c5c 1391 except (KeyError, IndexError, ExtractorError):
de7f3446
JMF
1392 self._downloader.report_warning(err_msg)
1393 return {}
1394
21c340b8
S
1395 def _mark_watched(self, video_id, video_info, player_response):
1396 playback_url = url_or_none(try_get(
1397 player_response,
1398 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1399 video_info, lambda x: x['videostats_playback_base_url'][0]))
d77ab8e2
S
1400 if not playback_url:
1401 return
1402 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1403 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1404
1405 # cpn generation algorithm is reverse engineered from base.js.
1406 # In fact it works even with dummy cpn.
1407 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1408 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1409
1410 qs.update({
1411 'ver': ['2'],
1412 'cpn': [cpn],
1413 })
1414 playback_url = compat_urlparse.urlunparse(
15707c7e 1415 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1416
1417 self._download_webpage(
1418 playback_url, video_id, 'Marking watched',
1419 'Unable to mark watched', fatal=False)
1420
66c9fa36
S
1421 @staticmethod
1422 def _extract_urls(webpage):
1423 # Embedded YouTube player
1424 entries = [
1425 unescapeHTML(mobj.group('url'))
1426 for mobj in re.finditer(r'''(?x)
1427 (?:
1428 <iframe[^>]+?src=|
1429 data-video-url=|
1430 <embed[^>]+?src=|
1431 embedSWF\(?:\s*|
1432 <object[^>]+data=|
1433 new\s+SWFObject\(
1434 )
1435 (["\'])
1436 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 1437 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
1438 \1''', webpage)]
1439
1440 # lazyYT YouTube embed
1441 entries.extend(list(map(
1442 unescapeHTML,
1443 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1444
1445 # Wordpress "YouTube Video Importer" plugin
1446 matches = re.findall(r'''(?x)<div[^>]+
1447 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1448 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1449 entries.extend(m[-1] for m in matches)
1450
1451 return entries
1452
1453 @staticmethod
1454 def _extract_url(webpage):
1455 urls = YoutubeIE._extract_urls(webpage)
1456 return urls[0] if urls else None
1457
97665381
PH
1458 @classmethod
1459 def extract_id(cls, url):
1460 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1461 if mobj is None:
69ea8ca4 1462 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1463 video_id = mobj.group(2)
1464 return video_id
1465
1fb07d10
JG
1466 def _extract_annotations(self, video_id):
1467 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1468 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1469
9cafc3fd
S
1470 @staticmethod
1471 def _extract_chapters(description, duration):
1472 if not description:
1473 return None
1474 chapter_lines = re.findall(
1475 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1476 description)
1477 if not chapter_lines:
1478 return None
1479 chapters = []
1480 for next_num, (chapter_line, time_point) in enumerate(
1481 chapter_lines, start=1):
1482 start_time = parse_duration(time_point)
1483 if start_time is None:
1484 continue
39d4c1be
S
1485 if start_time > duration:
1486 break
9cafc3fd
S
1487 end_time = (duration if next_num == len(chapter_lines)
1488 else parse_duration(chapter_lines[next_num][1]))
1489 if end_time is None:
1490 continue
39d4c1be
S
1491 if end_time > duration:
1492 end_time = duration
1493 if start_time > end_time:
1494 break
9cafc3fd
S
1495 chapter_title = re.sub(
1496 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1497 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1498 chapters.append({
1499 'start_time': start_time,
1500 'end_time': end_time,
1501 'title': chapter_title,
1502 })
1503 return chapters
1504
c5e8d7af 1505 def _real_extract(self, url):
cf7e015f
S
1506 url, smuggled_data = unsmuggle_url(url, {})
1507
7e8c0af0 1508 proto = (
78caa52a
PH
1509 'http' if self._downloader.params.get('prefer_insecure', False)
1510 else 'https')
7e8c0af0 1511
7c80519c 1512 start_time = None
297a564b 1513 end_time = None
7c80519c
JMF
1514 parsed_url = compat_urllib_parse_urlparse(url)
1515 for component in [parsed_url.fragment, parsed_url.query]:
1516 query = compat_parse_qs(component)
297a564b 1517 if start_time is None and 't' in query:
7c80519c 1518 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1519 if start_time is None and 'start' in query:
1520 start_time = parse_duration(query['start'][0])
297a564b
JMF
1521 if end_time is None and 'end' in query:
1522 end_time = parse_duration(query['end'][0])
7c80519c 1523
c5e8d7af
PH
1524 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1525 mobj = re.search(self._NEXT_URL_RE, url)
1526 if mobj:
7fd002c0 1527 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1528 video_id = self.extract_id(url)
c5e8d7af
PH
1529
1530 # Get video webpage
aa79ac0c 1531 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1532 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1533
1534 # Attempt to extract SWF player URL
e0df6211 1535 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1536 if mobj is not None:
1537 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1538 else:
1539 player_url = None
1540
d8d24a92
S
1541 dash_mpds = []
1542
1543 def add_dash_mpd(video_info):
1544 dash_mpd = video_info.get('dashmpd')
1545 if dash_mpd and dash_mpd[0] not in dash_mpds:
1546 dash_mpds.append(dash_mpd[0])
1547
561b456e
S
1548 def add_dash_mpd_pr(pl_response):
1549 dash_mpd = url_or_none(try_get(
1550 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1551 compat_str))
1552 if dash_mpd and dash_mpd not in dash_mpds:
1553 dash_mpds.append(dash_mpd)
1554
c7121fa7
S
1555 is_live = None
1556 view_count = None
1557
1558 def extract_view_count(v_info):
1559 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1560
dbdaaa23
S
1561 player_response = {}
1562
c5e8d7af 1563 # Get video info
6449cd80 1564 embed_webpage = None
c108eb73 1565 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1566 age_gate = True
1567 # We simulate the access to the video from www.youtube.com/v/{video_id}
1568 # this can be viewed without login into Youtube
beb95e77
CL
1569 url = proto + '://www.youtube.com/embed/%s' % video_id
1570 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1571 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1572 'video_id': video_id,
1573 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1574 'sts': self._search_regex(
beb95e77 1575 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1576 })
7e8c0af0 1577 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1578 video_info_webpage = self._download_webpage(
1579 video_info_url, video_id,
20436c30 1580 note='Refetching age-gated info webpage',
94bd3613 1581 errnote='unable to download video info webpage')
c5e8d7af 1582 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1583 add_dash_mpd(video_info)
c108eb73
JMF
1584 else:
1585 age_gate = False
bc93bdb5 1586 video_info = None
dc4e4f90 1587 sts = None
d8d24a92 1588 # Try looking directly into the video webpage
a72778d3
S
1589 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1590 if ytplayer_config:
4e62ebe2 1591 args = ytplayer_config['args']
4c76aa06 1592 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
d8d24a92
S
1593 # Convert to the same format returned by compat_parse_qs
1594 video_info = dict((k, [v]) for k, v in args.items())
1595 add_dash_mpd(video_info)
6496ccb4
S
1596 # Rental video is not rented but preview is available (e.g.
1597 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1598 # https://github.com/rg3/youtube-dl/issues/10532)
1599 if not video_info and args.get('ypc_vid'):
1600 return self.url_result(
1601 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
2fe1ff85
JMF
1602 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1603 is_live = True
dc4e4f90 1604 sts = ytplayer_config.get('sts')
dbdaaa23
S
1605 if not player_response:
1606 pl_response = str_or_none(args.get('player_response'))
1607 if pl_response:
1608 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1609 if isinstance(pl_response, dict):
1610 player_response = pl_response
0a3cf9ad 1611 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
561b456e 1612 add_dash_mpd_pr(player_response)
0a3cf9ad
S
1613 # We also try looking in get_video_info since it may contain different dashmpd
1614 # URL that points to a DASH manifest with possibly different itag set (some itags
1615 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1616 # manifest pointed by get_video_info's dashmpd).
1617 # The general idea is to take a union of itags of both DASH manifests (for example
1618 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
4e62ebe2 1619 self.report_video_info_webpage_download(video_id)
dc4e4f90
S
1620 for el in ('info', 'embedded', 'detailpage', 'vevo', ''):
1621 query = {
1622 'video_id': video_id,
1623 'ps': 'default',
1624 'eurl': '',
1625 'gl': 'US',
1626 'hl': 'en',
1627 }
1628 if el:
1629 query['el'] = el
1630 if sts:
1631 query['sts'] = sts
810fb84d 1632 video_info_webpage = self._download_webpage(
dc4e4f90 1633 '%s://www.youtube.com/get_video_info' % proto,
4e62ebe2 1634 video_id, note=False,
dc4e4f90
S
1635 errnote='unable to download video info webpage',
1636 fatal=False, query=query)
1637 if not video_info_webpage:
1638 continue
0a3cf9ad 1639 get_video_info = compat_parse_qs(video_info_webpage)
dbdaaa23
S
1640 if not player_response:
1641 pl_response = get_video_info.get('player_response', [None])[0]
1642 if isinstance(pl_response, dict):
1643 player_response = pl_response
561b456e 1644 add_dash_mpd_pr(player_response)
fd545fc6 1645 add_dash_mpd(get_video_info)
c7121fa7
S
1646 if view_count is None:
1647 view_count = extract_view_count(get_video_info)
0a3cf9ad
S
1648 if not video_info:
1649 video_info = get_video_info
1650 if 'token' in get_video_info:
89ea063e
S
1651 # Different get_video_info requests may report different results, e.g.
1652 # some may report video unavailability, but some may serve it without
1653 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1654 # the original webpage as well as el=info and el=embedded get_video_info
1655 # requests report video unavailability due to geo restriction while
1656 # el=detailpage succeeds and returns valid data). This is probably
1657 # due to YouTube measures against IP ranges of hosting providers.
1658 # Working around by preferring the first succeeded video_info containing
1659 # the token if no such video_info yet was found.
44b2264f
S
1660 if 'token' not in video_info:
1661 video_info = get_video_info
4e62ebe2 1662 break
bbb7c3f7
YCH
1663
1664 def extract_unavailable_message():
1665 return self._html_search_regex(
1666 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1667 video_webpage, 'unavailable message', default=None)
1668
c5e8d7af
PH
1669 if 'token' not in video_info:
1670 if 'reason' in video_info:
af214c3a 1671 if 'The uploader has not made this video available in your country.' in video_info['reason']:
fd5c4aab
S
1672 regions_allowed = self._html_search_meta(
1673 'regionsAllowed', video_webpage, default=None)
1674 countries = regions_allowed.split(',') if regions_allowed else None
1675 self.raise_geo_restricted(
1676 msg=video_info['reason'][0], countries=countries)
bbb7c3f7
YCH
1677 reason = video_info['reason'][0]
1678 if 'Invalid parameters' in reason:
1679 unavailable_message = extract_unavailable_message()
1680 if unavailable_message:
1681 reason = unavailable_message
d11271dd 1682 raise ExtractorError(
bbb7c3f7 1683 'YouTube said: %s' % reason,
d11271dd 1684 expected=True, video_id=video_id)
c5e8d7af 1685 else:
d11271dd 1686 raise ExtractorError(
78caa52a 1687 '"token" parameter not in video info for unknown reason',
d11271dd 1688 video_id=video_id)
c5e8d7af 1689
825cd268
RA
1690 if video_info.get('license_info'):
1691 raise ExtractorError('This video is DRM protected.', expected=True)
1692
dbdaaa23
S
1693 video_details = try_get(
1694 player_response, lambda x: x['videoDetails'], dict) or {}
1695
cf7e015f
S
1696 # title
1697 if 'title' in video_info:
1698 video_title = video_info['title'][0]
dbdaaa23
S
1699 elif 'title' in player_response:
1700 video_title = video_details['title']
cf7e015f
S
1701 else:
1702 self._downloader.report_warning('Unable to extract video title')
1703 video_title = '_'
1704
1705 # description
9cafc3fd 1706 description_original = video_description = get_element_by_id("eow-description", video_webpage)
cf7e015f 1707 if video_description:
fa4bc6e7
RA
1708
1709 def replace_url(m):
1710 redir_url = compat_urlparse.urljoin(url, m.group(1))
1711 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1712 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1713 qs = compat_parse_qs(parsed_redir_url.query)
1714 q = qs.get('q')
1715 if q and q[0]:
1716 return q[0]
1717 return redir_url
1718
9cafc3fd 1719 description_original = video_description = re.sub(r'''(?x)
cf7e015f 1720 <a\s+
25cb7a0e 1721 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1722 (?:title|href)="([^"]+)"\s+
25cb7a0e 1723 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1724 class="[^"]*"[^>]*>
23f13e97 1725 [^<]+\.{3}\s*
cf7e015f 1726 </a>
fa4bc6e7 1727 ''', replace_url, video_description)
cf7e015f
S
1728 video_description = clean_html(video_description)
1729 else:
1730 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1731 if fd_mobj:
1732 video_description = unescapeHTML(fd_mobj.group(1))
1733 else:
1734 video_description = ''
1735
8fe10494 1736 if not smuggled_data.get('force_singlefeed', False):
5e1eddb9 1737 if not self._downloader.params.get('noplaylist'):
8fe10494
S
1738 multifeed_metadata_list = try_get(
1739 player_response,
1740 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1741 compat_str) or try_get(
1742 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1743 if multifeed_metadata_list:
1744 entries = []
1745 feed_ids = []
1746 for feed in multifeed_metadata_list.split(','):
1747 # Unquote should take place before split on comma (,) since textual
1748 # fields may contain comma as well (see
1749 # https://github.com/rg3/youtube-dl/issues/8536)
1750 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1751 entries.append({
1752 '_type': 'url_transparent',
1753 'ie_key': 'Youtube',
1754 'url': smuggle_url(
1755 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1756 {'force_singlefeed': True}),
1757 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1758 })
1759 feed_ids.append(feed_data['id'][0])
1760 self.to_screen(
1761 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1762 % (', '.join(feed_ids), video_id))
1763 return self.playlist_result(entries, video_id, video_title, video_description)
1764 else:
1765 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1766
c7121fa7 1767 if view_count is None:
1c9c8de2 1768 view_count = extract_view_count(video_info)
dbdaaa23
S
1769 if view_count is None and video_details:
1770 view_count = int_or_none(video_details.get('viewCount'))
1d699755 1771
c5e8d7af
PH
1772 # Check for "rental" videos
1773 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
c9612c04 1774 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
c5e8d7af 1775
c63ca0ee
S
1776 def _extract_filesize(media_url):
1777 return int_or_none(self._search_regex(
1778 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1779
c5e8d7af
PH
1780 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1781 self.report_rtmp_download()
dd27fd17
PH
1782 formats = [{
1783 'format_id': '_rtmp',
1784 'protocol': 'rtmp',
1785 'url': video_info['conn'][0],
1786 'player_url': player_url,
1787 }]
391dd6f0 1788 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 1789 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1790 if 'rtmpe%3Dyes' in encoded_url_map:
a7055eb9 1791 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1792 formats_spec = {}
82156fdb 1793 fmt_list = video_info.get('fmt_list', [''])[0]
1794 if fmt_list:
1795 for fmt in fmt_list.split(','):
1796 spec = fmt.split('/')
3318832e 1797 if len(spec) > 1:
1798 width_height = spec[1].split('x')
1799 if len(width_height) == 2:
1800 formats_spec[spec[0]] = {
1801 'resolution': spec[1],
1802 'width': int_or_none(width_height[0]),
1803 'height': int_or_none(width_height[1]),
1804 }
54fc90aa 1805 q = qualities(['small', 'medium', 'hd720'])
140a13f5
RA
1806 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1807 if streaming_formats:
1808 for fmt in streaming_formats:
1809 itag = str_or_none(fmt.get('itag'))
1810 if not itag:
1811 continue
1812 quality = fmt.get('quality')
1813 quality_label = fmt.get('qualityLabel') or quality
1814 formats_spec[itag] = {
1815 'asr': int_or_none(fmt.get('audioSampleRate')),
1816 'filesize': int_or_none(fmt.get('contentLength')),
1817 'format_note': quality_label,
1818 'fps': int_or_none(fmt.get('fps')),
1819 'height': int_or_none(fmt.get('height')),
1820 'quality': q(quality),
1821 # bitrate for itag 43 is always 2147483647
1822 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1823 'width': int_or_none(fmt.get('width')),
1824 }
c9afb51c 1825 formats = []
00fe14fc 1826 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1827 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1828 if 'itag' not in url_data or 'url' not in url_data:
1829 continue
2f483bc1
S
1830 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1831 # Unsupported FORMAT_STREAM_TYPE_OTF
1832 if stream_type == 3:
1833 continue
201e9eaa
PH
1834 format_id = url_data['itag'][0]
1835 url = url_data['url'][0]
1836
a49eccdf 1837 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
6449cd80 1838 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
beb95e77 1839 jsplayer_url_json = self._search_regex(
6449cd80
PH
1840 ASSETS_RE,
1841 embed_webpage if age_gate else video_webpage,
1842 'JS player URL (1)', default=None)
1843 if not jsplayer_url_json and not age_gate:
1844 # We need the embed website after all
1845 if embed_webpage is None:
1846 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1847 embed_webpage = self._download_webpage(
1848 embed_url, video_id, 'Downloading embed webpage')
1849 jsplayer_url_json = self._search_regex(
1850 ASSETS_RE, embed_webpage, 'JS player URL')
1851
beb95e77 1852 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1853 if player_url is None:
1854 player_url_json = self._search_regex(
1855 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1856 video_webpage, 'age gate player URL')
201e9eaa
PH
1857 player_url = json.loads(player_url_json)
1858
a49eccdf
YCH
1859 if 'sig' in url_data:
1860 url += '&signature=' + url_data['sig'][0]
1861 elif 's' in url_data:
1862 encrypted_sig = url_data['s'][0]
1863
201e9eaa 1864 if self._downloader.params.get('verbose'):
cf010131 1865 if player_url is None:
201e9eaa
PH
1866 player_version = 'unknown'
1867 player_desc = 'unknown'
1868 else:
1869 if player_url.endswith('swf'):
1870 player_version = self._search_regex(
1871 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1872 'flash player', fatal=False)
201e9eaa 1873 player_desc = 'flash player %s' % player_version
cf010131 1874 else:
201e9eaa 1875 player_version = self._search_regex(
b62985a9 1876 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
63529e93 1877 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
201e9eaa
PH
1878 player_url,
1879 'html5 player', fatal=False)
78caa52a 1880 player_desc = 'html5 player %s' % player_version
201e9eaa 1881
60064c53 1882 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1883 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1884 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1885
1886 signature = self._decrypt_signature(
1887 encrypted_sig, video_id, player_url, age_gate)
1888 url += '&signature=' + signature
1889 if 'ratebypass' not in url:
1890 url += '&ratebypass=yes'
c9afb51c 1891
94278f72
YCH
1892 dct = {
1893 'format_id': format_id,
1894 'url': url,
1895 'player_url': player_url,
1896 }
1897 if format_id in self._formats:
1898 dct.update(self._formats[format_id])
3318832e 1899 if format_id in formats_spec:
1900 dct.update(formats_spec[format_id])
94278f72 1901
aabc2be6
S
1902 # Some itags are not included in DASH manifest thus corresponding formats will
1903 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1904 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1905 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1906 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72 1907
c63ca0ee
S
1908 filesize = int_or_none(url_data.get(
1909 'clen', [None])[0]) or _extract_filesize(url)
1910
140a13f5 1911 quality = url_data.get('quality', [None])[0]
54fc90aa 1912
94278f72 1913 more_fields = {
c63ca0ee 1914 'filesize': filesize,
aabc2be6 1915 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1916 'width': width,
1917 'height': height,
1918 'fps': int_or_none(url_data.get('fps', [None])[0]),
140a13f5 1919 'format_note': url_data.get('quality_label', [None])[0] or quality,
54fc90aa 1920 'quality': q(quality),
c9afb51c 1921 }
94278f72
YCH
1922 for key, value in more_fields.items():
1923 if value:
1924 dct[key] = value
aabc2be6
S
1925 type_ = url_data.get('type', [None])[0]
1926 if type_:
1927 type_split = type_.split(';')
1928 kind_ext = type_split[0].split('/')
1929 if len(kind_ext) == 2:
94278f72
YCH
1930 kind, _ = kind_ext
1931 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1932 if kind in ('audio', 'video'):
1933 codecs = None
1934 for mobj in re.finditer(
1935 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1936 if mobj.group('key') == 'codecs':
1937 codecs = mobj.group('val')
1938 break
1939 if codecs:
6310acf5 1940 dct.update(parse_codecs(codecs))
e4a60912
S
1941 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
1942 dct['downloader_options'] = {
1943 # Youtube throttles chunks >~10M
1944 'http_chunk_size': 10485760,
1945 }
aabc2be6 1946 formats.append(dct)
c5e8d7af 1947 else:
c3e54389
S
1948 manifest_url = (
1949 url_or_none(try_get(
1950 player_response,
1951 lambda x: x['streamingData']['hlsManifestUrl'],
1952 compat_str)) or
1953 url_or_none(try_get(
1954 video_info, lambda x: x['hlsvp'][0], compat_str)))
1955 if manifest_url:
1956 formats = []
1957 m3u8_formats = self._extract_m3u8_formats(
1958 manifest_url, video_id, 'mp4', fatal=False)
1959 for a_format in m3u8_formats:
1960 itag = self._search_regex(
1961 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1962 if itag:
1963 a_format['format_id'] = itag
1964 if itag in self._formats:
1965 dct = self._formats[itag].copy()
1966 dct.update(a_format)
1967 a_format = dct
1968 a_format['player_url'] = player_url
1969 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1970 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1971 formats.append(a_format)
1972 else:
1973 error_message = clean_html(video_info.get('reason', [None])[0])
1974 if not error_message:
1975 error_message = extract_unavailable_message()
1976 if error_message:
1977 raise ExtractorError(error_message, expected=True)
1978 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1979
7e72694b 1980 # uploader
dbdaaa23
S
1981 video_uploader = try_get(
1982 video_info, lambda x: x['author'][0],
1983 compat_str) or str_or_none(video_details.get('author'))
7e72694b
S
1984 if video_uploader:
1985 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
1986 else:
1987 self._downloader.report_warning('unable to extract uploader name')
1988
1989 # uploader_id
1990 video_uploader_id = None
1991 video_uploader_url = None
1992 mobj = re.search(
1993 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1994 video_webpage)
1995 if mobj is not None:
1996 video_uploader_id = mobj.group('uploader_id')
1997 video_uploader_url = mobj.group('uploader_url')
1998 else:
1999 self._downloader.report_warning('unable to extract uploader nickname')
2000
dd4c4492
S
2001 channel_id = self._html_search_meta(
2002 'channelId', video_webpage, 'channel id')
2003 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2004
7e72694b
S
2005 # thumbnail image
2006 # We try first to get a high quality image:
2007 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2008 video_webpage, re.DOTALL)
2009 if m_thumb is not None:
2010 video_thumbnail = m_thumb.group(1)
2011 elif 'thumbnail_url' not in video_info:
2012 self._downloader.report_warning('unable to extract video thumbnail')
2013 video_thumbnail = None
2014 else: # don't panic if we can't find it
2015 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2016
2017 # upload date
2018 upload_date = self._html_search_meta(
2019 'datePublished', video_webpage, 'upload date', default=None)
2020 if not upload_date:
2021 upload_date = self._search_regex(
2022 [r'(?s)id="eow-date.*?>(.*?)</span>',
2023 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2024 video_webpage, 'upload date', default=None)
2025 upload_date = unified_strdate(upload_date)
2026
2027 video_license = self._html_search_regex(
2028 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2029 video_webpage, 'license', default=None)
2030
2031 m_music = re.search(
2032 r'''(?x)
2033 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2034 <ul[^>]*>\s*
2035 <li>(?P<title>.+?)
2036 by (?P<creator>.+?)
2037 (?:
2038 \(.+?\)|
2039 <a[^>]*
2040 (?:
2041 \bhref=["\']/red[^>]*>| # drop possible
2042 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2043 )
2044 .*?
2045 )?</li
2046 ''',
2047 video_webpage)
2048 if m_music:
2049 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2050 video_creator = clean_html(m_music.group('creator'))
2051 else:
2052 video_alt_title = video_creator = None
2053
2054 def extract_meta(field):
2055 return self._html_search_regex(
2056 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2057 video_webpage, field, default=None)
2058
2059 track = extract_meta('Song')
2060 artist = extract_meta('Artist')
2061
2062 m_episode = re.search(
2063 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2064 video_webpage)
2065 if m_episode:
c2dd2dc0 2066 series = unescapeHTML(m_episode.group('series'))
7e72694b
S
2067 season_number = int(m_episode.group('season'))
2068 episode_number = int(m_episode.group('episode'))
2069 else:
2070 series = season_number = episode_number = None
2071
2072 m_cat_container = self._search_regex(
2073 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2074 video_webpage, 'categories', default=None)
2075 if m_cat_container:
2076 category = self._html_search_regex(
2077 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2078 default=None)
2079 video_categories = None if category is None else [category]
2080 else:
2081 video_categories = None
2082
2083 video_tags = [
2084 unescapeHTML(m.group('content'))
2085 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2086
2087 def _extract_count(count_name):
2088 return str_to_int(self._search_regex(
2089 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2090 % re.escape(count_name),
2091 video_webpage, count_name, default=None))
2092
2093 like_count = _extract_count('like')
2094 dislike_count = _extract_count('dislike')
2095
dbdaaa23
S
2096 if view_count is None:
2097 view_count = str_to_int(self._search_regex(
2098 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2099 'view count', default=None))
2100
7e72694b
S
2101 # subtitles
2102 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2103 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2104
2105 video_duration = try_get(
2106 video_info, lambda x: int_or_none(x['length_seconds'][0]))
dbdaaa23
S
2107 if not video_duration:
2108 video_duration = int_or_none(video_details.get('lengthSeconds'))
7e72694b
S
2109 if not video_duration:
2110 video_duration = parse_duration(self._html_search_meta(
2111 'duration', video_webpage, 'video duration'))
2112
2113 # annotations
2114 video_annotations = None
2115 if self._downloader.params.get('writeannotations', False):
2116 video_annotations = self._extract_annotations(video_id)
2117
2118 chapters = self._extract_chapters(description_original, video_duration)
2119
dd27fd17 2120 # Look for the DASH manifest
203fb43f 2121 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 2122 dash_mpd_fatal = True
8ff648e4 2123 for mpd_url in dash_mpds:
d8d24a92 2124 dash_formats = {}
774e208f 2125 try:
05d0d131
YCH
2126 def decrypt_sig(mobj):
2127 s = mobj.group(1)
2128 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2129 return '/signature/%s' % dec_s
2130
8ff648e4 2131 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 2132
8ff648e4 2133 for df in self._extract_mpd_formats(
2134 mpd_url, video_id, fatal=dash_mpd_fatal,
2135 formats_dict=self._formats):
c63ca0ee
S
2136 if not df.get('filesize'):
2137 df['filesize'] = _extract_filesize(df['url'])
d8d24a92
S
2138 # Do not overwrite DASH format found in some previous DASH manifest
2139 if df['format_id'] not in dash_formats:
2140 dash_formats[df['format_id']] = df
77c6fb5b
S
2141 # Additional DASH manifests may end up in HTTP Error 403 therefore
2142 # allow them to fail without bug report message if we already have
2143 # some DASH manifest succeeded. This is temporary workaround to reduce
2144 # burst of bug reports until we figure out the reason and whether it
2145 # can be fixed at all.
2146 dash_mpd_fatal = False
774e208f
PH
2147 except (ExtractorError, KeyError) as e:
2148 self.report_warning(
2149 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 2150 if dash_formats:
04b3b3df
JMF
2151 # Remove the formats we found through non-DASH, they
2152 # contain less info and it can be wrong, because we use
2153 # fixed values (for example the resolution). See
2154 # https://github.com/rg3/youtube-dl/issues/5774 for an
2155 # example.
d80265cc 2156 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 2157 formats.extend(dash_formats.values())
d80044c2 2158
6271f1ca
PH
2159 # Check for malformed aspect ratio
2160 stretched_m = re.search(
2161 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2162 video_webpage)
2163 if stretched_m:
313dfc45
LL
2164 w = float(stretched_m.group('w'))
2165 h = float(stretched_m.group('h'))
5faf9fed
S
2166 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2167 # We will only process correct ratios.
313dfc45 2168 if w > 0 and h > 0:
41f24c32 2169 ratio = w / h
313dfc45
LL
2170 for f in formats:
2171 if f.get('vcodec') != 'none':
2172 f['stretched_ratio'] = ratio
6271f1ca 2173
4bcc7bd1 2174 self._sort_formats(formats)
4ea3be0a 2175
21c340b8 2176 self.mark_watched(video_id, video_info, player_response)
d77ab8e2 2177
4ea3be0a 2178 return {
8bcc8756
JW
2179 'id': video_id,
2180 'uploader': video_uploader,
2181 'uploader_id': video_uploader_id,
fd050249 2182 'uploader_url': video_uploader_url,
dd4c4492
S
2183 'channel_id': channel_id,
2184 'channel_url': channel_url,
8bcc8756 2185 'upload_date': upload_date,
7caf9830 2186 'license': video_license,
936784b2 2187 'creator': video_creator or artist,
8bcc8756 2188 'title': video_title,
936784b2 2189 'alt_title': video_alt_title or track,
8bcc8756
JW
2190 'thumbnail': video_thumbnail,
2191 'description': video_description,
2192 'categories': video_categories,
000b6b5a 2193 'tags': video_tags,
8bcc8756 2194 'subtitles': video_subtitles,
360e1ca5 2195 'automatic_captions': automatic_captions,
8bcc8756
JW
2196 'duration': video_duration,
2197 'age_limit': 18 if age_gate else 0,
2198 'annotations': video_annotations,
9cafc3fd 2199 'chapters': chapters,
7e8c0af0 2200 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 2201 'view_count': view_count,
4ea3be0a 2202 'like_count': like_count,
2203 'dislike_count': dislike_count,
2d30521a 2204 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 2205 'formats': formats,
2fe1ff85 2206 'is_live': is_live,
7c80519c 2207 'start_time': start_time,
297a564b 2208 'end_time': end_time,
12afdc2a
S
2209 'series': series,
2210 'season_number': season_number,
2211 'episode_number': episode_number,
936784b2
S
2212 'track': track,
2213 'artist': artist,
4ea3be0a 2214 }
c5e8d7af 2215
5f6a1245 2216
8e7aad20 2217class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2218 IE_DESC = 'YouTube.com playlists'
d67cc9fa 2219 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
2220 (?:https?://)?
2221 (?:\w+\.)?
c5e8d7af 2222 (?:
c0345b82
S
2223 (?:
2224 youtube\.com|
2225 invidio\.us
2226 )
2227 /
feaa5ad7 2228 (?:
87dadd45 2229 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
feaa5ad7
S
2230 \? (?:.*?[&;])*? (?:p|a|list)=
2231 | p/
2232 )|
2233 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
c5e8d7af 2234 )
d67cc9fa 2235 (
409b9324 2236 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
5f6a1245 2237 # Top tracks, they can also include dots
d67cc9fa
JMF
2238 |(?:MC)[\w\.]*
2239 )
c5e8d7af
PH
2240 .*
2241 |
d0ba5587
S
2242 (%(playlist_id)s)
2243 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
8d81f3e3 2244 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
648e6a1f 2245 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 2246 IE_NAME = 'youtube:playlist'
81127aa5
PH
2247 _TESTS = [{
2248 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2249 'info_dict': {
2250 'title': 'ytdl test PL',
a1cf99d0 2251 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
2252 },
2253 'playlist_count': 3,
9291475f
PH
2254 }, {
2255 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2256 'info_dict': {
acf757f4 2257 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
2258 'title': 'YDL_Empty_List',
2259 },
2260 'playlist_count': 0,
4201ba13 2261 'skip': 'This playlist is private',
9291475f
PH
2262 }, {
2263 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2264 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2265 'info_dict': {
2266 'title': '29C3: Not my department',
acf757f4 2267 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
2268 },
2269 'playlist_count': 95,
2270 }, {
2271 'note': 'issue #673',
2272 'url': 'PLBB231211A4F62143',
2273 'info_dict': {
f46a8702 2274 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 2275 'id': 'PLBB231211A4F62143',
9291475f
PH
2276 },
2277 'playlist_mincount': 26,
2278 }, {
2279 'note': 'Large playlist',
2280 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2281 'info_dict': {
2282 'title': 'Uploads from Cauchemar',
acf757f4 2283 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
2284 },
2285 'playlist_mincount': 799,
2286 }, {
2287 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2288 'info_dict': {
2289 'title': 'YDL_safe_search',
acf757f4 2290 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
2291 },
2292 'playlist_count': 2,
4201ba13 2293 'skip': 'This playlist is private',
ac7553d0
PH
2294 }, {
2295 'note': 'embedded',
2d3d2997 2296 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0
PH
2297 'playlist_count': 4,
2298 'info_dict': {
2299 'title': 'JODA15',
acf757f4 2300 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 2301 }
87dadd45
S
2302 }, {
2303 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2304 'playlist_mincount': 485,
2305 'info_dict': {
2306 'title': '2017 華語最新單曲 (2/24更新)',
2307 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2308 }
6b08cdf6
PH
2309 }, {
2310 'note': 'Embedded SWF player',
2d3d2997 2311 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
6b08cdf6
PH
2312 'playlist_count': 4,
2313 'info_dict': {
2314 'title': 'JODA7',
acf757f4 2315 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 2316 }
4b7df0d3
JMF
2317 }, {
2318 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2319 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2320 'info_dict': {
acf757f4
PH
2321 'title': 'Uploads from Interstellar Movie',
2322 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 2323 },
481cc733 2324 'playlist_mincount': 21,
dacb3a86
S
2325 }, {
2326 # Playlist URL that does not actually serve a playlist
2327 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2328 'info_dict': {
2329 'id': 'FqZTN594JQw',
2330 'ext': 'webm',
2331 'title': "Smiley's People 01 detective, Adventure Series, Action",
2332 'uploader': 'STREEM',
2333 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 2334 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
2335 'upload_date': '20150526',
2336 'license': 'Standard YouTube License',
2337 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2338 'categories': ['People & Blogs'],
2339 'tags': list,
dbdaaa23 2340 'view_count': int,
dacb3a86
S
2341 'like_count': int,
2342 'dislike_count': int,
2343 },
2344 'params': {
2345 'skip_download': True,
2346 },
2347 'add_ie': [YoutubeIE.ie_key()],
481cc733
S
2348 }, {
2349 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2350 'info_dict': {
2351 'id': 'yeWKywCrFtk',
2352 'ext': 'mp4',
2353 'title': 'Small Scale Baler and Braiding Rugs',
2354 'uploader': 'Backus-Page House Museum',
2355 'uploader_id': 'backuspagemuseum',
ec85ded8 2356 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
481cc733
S
2357 'upload_date': '20161008',
2358 'license': 'Standard YouTube License',
2359 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2360 'categories': ['Nonprofits & Activism'],
2361 'tags': list,
2362 'like_count': int,
2363 'dislike_count': int,
2364 },
2365 'params': {
2366 'noplaylist': True,
2367 'skip_download': True,
2368 },
feaa5ad7
S
2369 }, {
2370 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2371 'only_matching': True,
a6857510
S
2372 }, {
2373 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2374 'only_matching': True,
409b9324
S
2375 }, {
2376 # music album playlist
2377 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2378 'only_matching': True,
c0345b82
S
2379 }, {
2380 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2381 'only_matching': True,
81127aa5 2382 }]
c5e8d7af 2383
880e1c52
JMF
2384 def _real_initialize(self):
2385 self._login()
2386
652cdaa2 2387 def _extract_mix(self, playlist_id):
99209c29 2388 # The mixes are generated from a single video
652cdaa2 2389 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
2390 ids = []
2391 last_id = playlist_id[-11:]
2392 for n in itertools.count(1):
2393 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2394 webpage = self._download_webpage(
2395 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2396 new_ids = orderedSet(re.findall(
2397 r'''(?xs)data-video-username=".*?".*?
2398 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
2399 webpage))
2400 # Fetch new pages until all the videos are repeated, it seems that
2401 # there are always 51 unique videos.
2402 new_ids = [_id for _id in new_ids if _id not in ids]
2403 if not new_ids:
2404 break
2405 ids.extend(new_ids)
2406 last_id = ids[-1]
2407
2408 url_results = self._ids_to_results(ids)
2409
bc2f773b 2410 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
2411 title_span = (
2412 search_title('playlist-title') or
2413 search_title('title long-title') or
2414 search_title('title'))
76d1700b 2415 title = clean_html(title_span)
652cdaa2
JMF
2416
2417 return self.playlist_result(url_results, playlist_id, title)
2418
448830ce 2419 def _extract_playlist(self, playlist_id):
dbb94fb0
S
2420 url = self._TEMPLATE_URL % playlist_id
2421 page = self._download_webpage(url, playlist_id)
dbb94fb0 2422
8bc0800d
G
2423 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2424 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
39b62db1
YCH
2425 match = match.strip()
2426 # Check if the playlist exists or is private
4201ba13
S
2427 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2428 if mobj:
2429 reason = mobj.group('reason')
2430 message = 'This playlist %s' % reason
2431 if 'private' in reason:
2432 message += ', use --username or --netrc to access it'
2433 message += '.'
2434 raise ExtractorError(message, expected=True)
39b62db1
YCH
2435 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2436 raise ExtractorError(
2437 'Invalid parameters. Maybe URL is incorrect.',
2438 expected=True)
2439 elif re.match(r'[^<]*Choose your language[^<]*', match):
2440 continue
2441 else:
2442 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 2443
dbb94fb0 2444 playlist_title = self._html_search_regex(
63b4295d 2445 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
dacb3a86 2446 page, 'title', default=None)
c5e8d7af 2447
07aeced6
S
2448 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2449 uploader = self._search_regex(
2450 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2451 page, 'uploader', default=None)
2452 mobj = re.search(
2453 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2454 page)
2455 if mobj:
2456 uploader_id = mobj.group('uploader_id')
2457 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2458 else:
2459 uploader_id = uploader_url = None
2460
dacb3a86
S
2461 has_videos = True
2462
2463 if not playlist_title:
2464 try:
2465 # Some playlist URLs don't actually serve a playlist (e.g.
2466 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2467 next(self._entries(page, playlist_id))
2468 except StopIteration:
2469 has_videos = False
2470
07aeced6 2471 playlist = self.playlist_result(
dacb3a86 2472 self._entries(page, playlist_id), playlist_id, playlist_title)
07aeced6
S
2473 playlist.update({
2474 'uploader': uploader,
2475 'uploader_id': uploader_id,
2476 'uploader_url': uploader_url,
2477 })
2478
2479 return has_videos, playlist
c5e8d7af 2480
ebf1b291 2481 def _check_download_just_video(self, url, playlist_id):
448830ce
S
2482 # Check if it's a video-specific URL
2483 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
481cc733 2484 video_id = query_dict.get('v', [None])[0] or self._search_regex(
87dadd45 2485 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
481cc733
S
2486 'video id', default=None)
2487 if video_id:
448830ce
S
2488 if self._downloader.params.get('noplaylist'):
2489 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
dacb3a86 2490 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce
S
2491 else:
2492 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
dacb3a86
S
2493 return video_id, None
2494 return None, None
448830ce 2495
ebf1b291
S
2496 def _real_extract(self, url):
2497 # Extract playlist id
2498 mobj = re.match(self._VALID_URL, url)
2499 if mobj is None:
2500 raise ExtractorError('Invalid URL: %s' % url)
2501 playlist_id = mobj.group(1) or mobj.group(2)
2502
dacb3a86 2503 video_id, video = self._check_download_just_video(url, playlist_id)
ebf1b291
S
2504 if video:
2505 return video
2506
466a6145 2507 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
2508 # Mixes require a custom extraction process
2509 return self._extract_mix(playlist_id)
2510
dacb3a86
S
2511 has_videos, playlist = self._extract_playlist(playlist_id)
2512 if has_videos or not video_id:
2513 return playlist
2514
2515 # Some playlist URLs don't actually serve a playlist (see
2516 # https://github.com/rg3/youtube-dl/issues/10537).
2517 # Fallback to plain video extraction if there is a video id
2518 # along with playlist id.
2519 return self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce 2520
c5e8d7af 2521
648e6a1f 2522class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2523 IE_DESC = 'YouTube.com channels'
cd5a74a2 2524 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 2525 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 2526 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 2527 IE_NAME = 'youtube:channel'
cdc628a4
PH
2528 _TESTS = [{
2529 'note': 'paginated channel',
2530 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2531 'playlist_mincount': 91,
acf757f4 2532 'info_dict': {
9170ca5b
JMF
2533 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2534 'title': 'Uploads from lex will',
acf757f4 2535 }
5c43afd4
JMF
2536 }, {
2537 'note': 'Age restricted channel',
2538 # from https://www.youtube.com/user/DeusExOfficial
2539 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2540 'playlist_mincount': 64,
2541 'info_dict': {
2542 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2543 'title': 'Uploads from Deus Ex',
2544 },
cd5a74a2
S
2545 }, {
2546 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2547 'only_matching': True,
cdc628a4 2548 }]
c5e8d7af 2549
e462474e
S
2550 @classmethod
2551 def suitable(cls, url):
f07e276a
S
2552 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2553 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 2554
9558dcec
S
2555 def _build_template_url(self, url, channel_id):
2556 return self._TEMPLATE_URL % channel_id
2557
c5e8d7af 2558 def _real_extract(self, url):
9ff67727 2559 channel_id = self._match_id(url)
c5e8d7af 2560
9558dcec 2561 url = self._build_template_url(url, channel_id)
386bdfa6
S
2562
2563 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2564 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2565 # otherwise fallback on channel by page extraction
2566 channel_page = self._download_webpage(
2567 url + '?view=57', channel_id,
2568 'Downloading channel page', fatal=False)
2b3c2546
PH
2569 if channel_page is False:
2570 channel_playlist_id = False
2571 else:
2572 channel_playlist_id = self._html_search_meta(
2573 'channelId', channel_page, 'channel id', default=None)
2574 if not channel_playlist_id:
73c4ac2c
S
2575 channel_url = self._html_search_meta(
2576 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2577 channel_page, 'channel url', default=None)
2578 if channel_url:
2579 channel_playlist_id = self._search_regex(
2580 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2581 channel_url, 'channel id', default=None)
386bdfa6
S
2582 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2583 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2584 return self.url_result(
2585 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2586
60bf45c8 2587 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2588 autogenerated = re.search(r'''(?x)
2589 class="[^"]*?(?:
2590 channel-header-autogenerated-label|
2591 yt-channel-title-autogenerated
2592 )[^"]*"''', channel_page) is not None
c5e8d7af 2593
b9643eed
JMF
2594 if autogenerated:
2595 # The videos are contained in a single page
2596 # the ajax pages can't be used, they are empty
b82f815f 2597 entries = [
fb69240c
S
2598 self.url_result(
2599 video_id, 'Youtube', video_id=video_id,
2600 video_title=video_title)
8f02ad4f 2601 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2602 return self.playlist_result(entries, channel_id)
2603
73c4ac2c
S
2604 try:
2605 next(self._entries(channel_page, channel_id))
2606 except StopIteration:
2607 alert_message = self._html_search_regex(
2608 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2609 channel_page, 'alert', default=None, group='alert')
2610 if alert_message:
2611 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2612
648e6a1f 2613 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2614
2615
eb0f3e7e 2616class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2617 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
ea696249 2618 _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 2619 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
78caa52a 2620 IE_NAME = 'youtube:user'
c5e8d7af 2621
cdc628a4
PH
2622 _TESTS = [{
2623 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2624 'playlist_mincount': 320,
2625 'info_dict': {
73c4ac2c
S
2626 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2627 'title': 'Uploads from The Linux Foundation',
cdc628a4 2628 }
9558dcec
S
2629 }, {
2630 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2631 # but not https://www.youtube.com/user/12minuteathlete/videos
2632 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2633 'playlist_mincount': 249,
2634 'info_dict': {
2635 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2636 'title': 'Uploads from 12 Minute Athlete',
2637 }
cdc628a4
PH
2638 }, {
2639 'url': 'ytuser:phihag',
2640 'only_matching': True,
daa0df9e
YCH
2641 }, {
2642 'url': 'https://www.youtube.com/c/gametrailers',
2643 'only_matching': True,
9558dcec
S
2644 }, {
2645 'url': 'https://www.youtube.com/gametrailers',
2646 'only_matching': True,
73c4ac2c 2647 }, {
0e879f43 2648 # This channel is not available, geo restricted to JP
73c4ac2c
S
2649 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2650 'only_matching': True,
cdc628a4
PH
2651 }]
2652
e3ea4790 2653 @classmethod
f4b05232 2654 def suitable(cls, url):
e3ea4790
JMF
2655 # Don't return True if the url can be extracted with other youtube
2656 # extractor, the regex would is too permissive and it would match.
f3a58d46 2657 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2658 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2659 return False
2660 else:
2661 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2662
9558dcec
S
2663 def _build_template_url(self, url, channel_id):
2664 mobj = re.match(self._VALID_URL, url)
2665 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2666
b05654f0 2667
f07e276a
S
2668class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2669 IE_DESC = 'YouTube.com live streams'
073d5bf5 2670 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
f07e276a
S
2671 IE_NAME = 'youtube:live'
2672
2673 _TESTS = [{
2d3d2997 2674 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
f07e276a
S
2675 'info_dict': {
2676 'id': 'a48o2S1cPoo',
2677 'ext': 'mp4',
2678 'title': 'The Young Turks - Live Main Show',
2679 'uploader': 'The Young Turks',
2680 'uploader_id': 'TheYoungTurks',
ec85ded8 2681 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
f07e276a
S
2682 'upload_date': '20150715',
2683 'license': 'Standard YouTube License',
2684 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2685 'categories': ['News & Politics'],
2686 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2687 'like_count': int,
2688 'dislike_count': int,
2689 },
2690 'params': {
2691 'skip_download': True,
2692 },
2693 }, {
2d3d2997 2694 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
f07e276a 2695 'only_matching': True,
c1b2a085
S
2696 }, {
2697 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2698 'only_matching': True,
073d5bf5
S
2699 }, {
2700 'url': 'https://www.youtube.com/TheYoungTurks/live',
2701 'only_matching': True,
f07e276a
S
2702 }]
2703
2704 def _real_extract(self, url):
2705 mobj = re.match(self._VALID_URL, url)
2706 channel_id = mobj.group('id')
2707 base_url = mobj.group('base_url')
2708 webpage = self._download_webpage(url, channel_id, fatal=False)
2709 if webpage:
2710 page_type = self._og_search_property(
e7f3529f 2711 'type', webpage, 'page type', default='')
f07e276a
S
2712 video_id = self._html_search_meta(
2713 'videoId', webpage, 'video id', default=None)
e7f3529f
S
2714 if page_type.startswith('video') and video_id and re.match(
2715 r'^[0-9A-Za-z_-]{11}$', video_id):
f07e276a
S
2716 return self.url_result(video_id, YoutubeIE.ie_key())
2717 return self.url_result(base_url)
2718
2719
e462474e
S
2720class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2721 IE_DESC = 'YouTube.com user/channel playlists'
2722 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2723 IE_NAME = 'youtube:playlists'
0c148415 2724
e568c223 2725 _TESTS = [{
2d3d2997 2726 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
0c148415
S
2727 'playlist_mincount': 4,
2728 'info_dict': {
2729 'id': 'ThirstForScience',
2730 'title': 'Thirst for Science',
2731 },
e568c223
S
2732 }, {
2733 # with "Load more" button
2d3d2997 2734 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
e568c223
S
2735 'playlist_mincount': 70,
2736 'info_dict': {
2737 'id': 'igorkle1',
2738 'title': 'Игорь Клейнер',
2739 },
e462474e
S
2740 }, {
2741 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2742 'playlist_mincount': 17,
2743 'info_dict': {
2744 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2745 'title': 'Chem Player',
2746 },
e568c223 2747 }]
0c148415
S
2748
2749
870f3bfc
S
2750class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2751 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2752
2753
2754class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
78caa52a 2755 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2756 # there doesn't appear to be a real limit, for example if you search for
2757 # 'python' you get more than 8.000.000 results
2758 _MAX_RESULTS = float('inf')
78caa52a 2759 IE_NAME = 'youtube:search'
b05654f0 2760 _SEARCH_KEY = 'ytsearch'
b4c08069 2761 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2762 _TESTS = []
b05654f0 2763
b05654f0
PH
2764 def _get_n_results(self, query, n):
2765 """Get a specified number of results for a query"""
2766
b4c08069 2767 videos = []
b05654f0
PH
2768 limit = n
2769
a22b2fd1
YCH
2770 url_query = {
2771 'search_query': query.encode('utf-8'),
2772 }
2773 url_query.update(self._EXTRA_QUERY_ARGS)
2774 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2775
b4c08069 2776 for pagenum in itertools.count(1):
b4c08069 2777 data = self._download_json(
69ea8ca4 2778 result_url, video_id='query "%s"' % query,
b4c08069 2779 note='Downloading page %s' % pagenum,
a22b2fd1
YCH
2780 errnote='Unable to download API page',
2781 query={'spf': 'navigate'})
b4c08069 2782 html_content = data[1]['body']['content']
7cc3570e 2783
b4c08069 2784 if 'class="search-message' in html_content:
07ad22b8 2785 raise ExtractorError(
78caa52a 2786 '[youtube] No video results', expected=True)
b05654f0 2787
870f3bfc 2788 new_videos = list(self._process_page(html_content))
b4c08069
JMF
2789 videos += new_videos
2790 if not new_videos or len(videos) > limit:
2791 break
a22b2fd1
YCH
2792 next_link = self._html_search_regex(
2793 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2794 html_content, 'next link', default=None)
2795 if next_link is None:
2796 break
2797 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
b05654f0 2798
b4c08069
JMF
2799 if len(videos) > n:
2800 videos = videos[:n]
b05654f0 2801 return self.playlist_result(videos, query)
75dff0ee 2802
c9ae7b95 2803
a3dd9248 2804class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2805 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2806 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2807 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2808 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2809
c9ae7b95 2810
870f3bfc 2811class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
78caa52a
PH
2812 IE_DESC = 'YouTube.com search URLs'
2813 IE_NAME = 'youtube:search_url'
d2c1f79f 2814 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
cdc628a4
PH
2815 _TESTS = [{
2816 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2817 'playlist_mincount': 5,
2818 'info_dict': {
2819 'title': 'youtube-dl test video',
2820 }
d2c1f79f
S
2821 }, {
2822 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2823 'only_matching': True,
cdc628a4 2824 }]
c9ae7b95
PH
2825
2826 def _real_extract(self, url):
2827 mobj = re.match(self._VALID_URL, url)
7fd002c0 2828 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2829 webpage = self._download_webpage(url, query)
175c2e9e 2830 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2831
2832
136dadde 2833class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2834 IE_DESC = 'YouTube.com (multi-season) shows'
92519402 2835 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2836 IE_NAME = 'youtube:show'
cdc628a4 2837 _TESTS = [{
4003bd82 2838 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2839 'playlist_mincount': 5,
cdc628a4
PH
2840 'info_dict': {
2841 'id': 'airdisasters',
2842 'title': 'Air Disasters',
2843 }
2844 }]
75dff0ee
JMF
2845
2846 def _real_extract(self, url):
136dadde
S
2847 playlist_id = self._match_id(url)
2848 return super(YoutubeShowIE, self)._real_extract(
2849 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2850
2851
b2e8bc1b 2852class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2853 """
25f14e9f 2854 Base class for feed extractors
d7ae0639
JMF
2855 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2856 """
b2e8bc1b 2857 _LOGIN_REQUIRED = True
d7ae0639
JMF
2858
2859 @property
2860 def IE_NAME(self):
78caa52a 2861 return 'youtube:%s' % self._FEED_NAME
04cc9617 2862
81f0259b 2863 def _real_initialize(self):
b2e8bc1b 2864 self._login()
81f0259b 2865
3853309f 2866 def _entries(self, page):
2bc43303
JMF
2867 # The extraction process is the same as for playlists, but the regex
2868 # for the video ids doesn't contain an index
2869 ids = []
2870 more_widget_html = content_html = page
2bc43303
JMF
2871 for page_num in itertools.count(1):
2872 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2873
2874 # 'recommended' feed has infinite 'load more' and each new portion spins
2875 # the same videos in (sometimes) slightly different order, so we'll check
2876 # for unicity and break when portion has no new videos
3853309f 2877 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
62c95fd5
S
2878 if not new_ids:
2879 break
2880
2bc43303
JMF
2881 ids.extend(new_ids)
2882
3853309f
S
2883 for entry in self._ids_to_results(new_ids):
2884 yield entry
2885
2bc43303
JMF
2886 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2887 if not mobj:
2888 break
2889
2890 more = self._download_json(
25f14e9f 2891 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2892 'Downloading page #%s' % page_num,
2893 transform_source=uppercase_escape)
2894 content_html = more['content_html']
2895 more_widget_html = more['load_more_widget_html']
2896
3853309f
S
2897 def _real_extract(self, url):
2898 page = self._download_webpage(
2899 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
2900 self._PLAYLIST_TITLE)
25f14e9f 2901 return self.playlist_result(
3853309f 2902 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
25f14e9f
S
2903
2904
2905class YoutubeWatchLaterIE(YoutubePlaylistIE):
2906 IE_NAME = 'youtube:watchlater'
2907 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
92519402 2908 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2909
bc7a9cd8
S
2910 _TESTS = [{
2911 'url': 'https://www.youtube.com/playlist?list=WL',
2912 'only_matching': True,
2913 }, {
2914 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2915 'only_matching': True,
2916 }]
25f14e9f
S
2917
2918 def _real_extract(self, url):
7e5dc339 2919 _, video = self._check_download_just_video(url, 'WL')
ebf1b291
S
2920 if video:
2921 return video
dacb3a86
S
2922 _, playlist = self._extract_playlist('WL')
2923 return playlist
f459d170 2924
5f6a1245 2925
c626a3d9 2926class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2927 IE_NAME = 'youtube:favorites'
f3a34072 2928 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
92519402 2929 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2930 _LOGIN_REQUIRED = True
2931
2932 def _real_extract(self, url):
2933 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2934 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2935 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2936
2937
25f14e9f
S
2938class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2939 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
92519402 2940 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
25f14e9f
S
2941 _FEED_NAME = 'recommended'
2942 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2943
1ed5b5c9 2944
25f14e9f
S
2945class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2946 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
92519402 2947 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
25f14e9f
S
2948 _FEED_NAME = 'subscriptions'
2949 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2950
1ed5b5c9 2951
25f14e9f
S
2952class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2953 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
92519402 2954 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
25f14e9f
S
2955 _FEED_NAME = 'history'
2956 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2957
2958
15870e90
PH
2959class YoutubeTruncatedURLIE(InfoExtractor):
2960 IE_NAME = 'youtube:truncated_url'
2961 IE_DESC = False # Do not list
975d35db 2962 _VALID_URL = r'''(?x)
b95aab84
PH
2963 (?:https?://)?
2964 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2965 (?:watch\?(?:
c4808c60 2966 feature=[a-z_]+|
b95aab84
PH
2967 annotation_id=annotation_[^&]+|
2968 x-yt-cl=[0-9]+|
c1708b89 2969 hl=[^&]*|
287be8c6 2970 t=[0-9]+
b95aab84
PH
2971 )?
2972 |
2973 attribution_link\?a=[^&]+
2974 )
2975 $
975d35db 2976 '''
15870e90 2977
c4808c60 2978 _TESTS = [{
2d3d2997 2979 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 2980 'only_matching': True,
dc2fc736 2981 }, {
2d3d2997 2982 'url': 'https://www.youtube.com/watch?',
dc2fc736 2983 'only_matching': True,
b95aab84
PH
2984 }, {
2985 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2986 'only_matching': True,
2987 }, {
2988 'url': 'https://www.youtube.com/watch?feature=foo',
2989 'only_matching': True,
c1708b89
PH
2990 }, {
2991 'url': 'https://www.youtube.com/watch?hl=en-GB',
2992 'only_matching': True,
287be8c6
PH
2993 }, {
2994 'url': 'https://www.youtube.com/watch?t=2372',
2995 'only_matching': True,
c4808c60
PH
2996 }]
2997
15870e90
PH
2998 def _real_extract(self, url):
2999 raise ExtractorError(
78caa52a
PH
3000 'Did you forget to quote the URL? Remember that & is a meta '
3001 'character in most shells, so you want to put the URL in quotes, '
3002 'like youtube-dl '
2d3d2997 3003 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
78caa52a 3004 ' or simply youtube-dl BaW_jenozKc .',
15870e90 3005 expected=True)
772fd5cc
PH
3006
3007
3008class YoutubeTruncatedIDIE(InfoExtractor):
3009 IE_NAME = 'youtube:truncated_id'
3010 IE_DESC = False # Do not list
b95aab84 3011 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
3012
3013 _TESTS = [{
3014 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3015 'only_matching': True,
3016 }]
3017
3018 def _real_extract(self, url):
3019 video_id = self._match_id(url)
3020 raise ExtractorError(
3021 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
3022 expected=True)