]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[utils] Rename try_multipart_encode to _multipart_encode_impl
[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,
c5e8d7af 19 compat_parse_qs,
7fd002c0
S
20 compat_urllib_parse_unquote,
21 compat_urllib_parse_unquote_plus,
15707c7e 22 compat_urllib_parse_urlencode,
7c80519c 23 compat_urllib_parse_urlparse,
7c61bd36 24 compat_urlparse,
c5e8d7af 25 compat_str,
4bb4a188
PH
26)
27from ..utils import (
c5e8d7af 28 clean_html,
9b9c5355 29 error_to_compat_str,
c5e8d7af 30 ExtractorError,
2d30521a 31 float_or_none,
4bb4a188
PH
32 get_element_by_attribute,
33 get_element_by_id,
dd27fd17 34 int_or_none,
94278f72 35 mimetype2ext,
4bb4a188 36 orderedSet,
6310acf5 37 parse_codecs,
7c80519c 38 parse_duration,
0cb58b02 39 remove_quotes,
041bc3ad 40 remove_start,
5c2266df 41 sanitized_Request,
cf7e015f 42 smuggle_url,
c93d53f5 43 str_to_int,
556dbe7f 44 try_get,
c5e8d7af
PH
45 unescapeHTML,
46 unified_strdate,
cf7e015f 47 unsmuggle_url,
81c2f20b 48 uppercase_escape,
6e6bc8da 49 urlencode_postdata,
c5e8d7af
PH
50)
51
5f6a1245 52
de7f3446 53class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b
JMF
54 """Provide base functions for Youtube extractors"""
55 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
9303ce3e 56 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
e298d3a0 57 _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
b2e8bc1b
JMF
58 _NETRC_MACHINE = 'youtube'
59 # If True it will raise an error if no login info is provided
60 _LOGIN_REQUIRED = False
61
d0ba5587
S
62 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}'
63
b2e8bc1b 64 def _set_language(self):
810fb84d
PH
65 self._set_cookie(
66 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
42939b61 67 # YouTube sets the expire time to about two months
810fb84d 68 expire_time=time.time() + 2 * 30 * 24 * 3600)
b2e8bc1b 69
25f14e9f
S
70 def _ids_to_results(self, ids):
71 return [
72 self.url_result(vid_id, 'Youtube', video_id=vid_id)
73 for vid_id in ids]
74
b2e8bc1b 75 def _login(self):
83317f69 76 """
77 Attempt to log in to YouTube.
78 True is returned if successful or skipped.
79 False is returned if login failed.
80
81 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
82 """
b2e8bc1b
JMF
83 (username, password) = self._get_login_info()
84 # No authentication to be performed
85 if username is None:
86 if self._LOGIN_REQUIRED:
69ea8ca4 87 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
83317f69 88 return True
b2e8bc1b 89
7cc3570e
PH
90 login_page = self._download_webpage(
91 self._LOGIN_URL, None,
69ea8ca4
PH
92 note='Downloading login page',
93 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
94 if login_page is False:
95 return
b2e8bc1b 96
1212e997 97 login_form = self._hidden_inputs(login_page)
c5e8d7af 98
1212e997 99 login_form.update({
05bddcc5 100 'checkConnection': 'youtube',
8bcc8756 101 'Email': username,
8bcc8756 102 'Passwd': password,
1212e997 103 })
83317f69 104
7cc3570e 105 login_results = self._download_webpage(
e298d3a0
S
106 self._PASSWORD_CHALLENGE_URL, None,
107 note='Logging in', errnote='unable to log in', fatal=False,
1212e997 108 data=urlencode_postdata(login_form))
7cc3570e
PH
109 if login_results is False:
110 return False
83317f69 111
494ab6db
S
112 error_msg = self._html_search_regex(
113 r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
114 login_results, 'error message', default=None)
115 if error_msg:
116 raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
117
83317f69 118 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
69ea8ca4 119 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
83317f69 120
121 # Two-Factor
122 # TODO add SMS and phone call support - these require making a request and then prompting the user
123
e9fb6a4b 124 if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
041bc3ad 125 tfa_code = self._get_tfa_info('2-step verification code')
83317f69 126
041bc3ad
S
127 if not tfa_code:
128 self._downloader.report_warning(
129 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
130 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
83317f69 131 return False
132
041bc3ad
S
133 tfa_code = remove_start(tfa_code, 'G-')
134
135 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
136
137 tfa_form_strs.update({
9303ce3e 138 'Pin': tfa_code,
139 'TrustDevice': 'on',
041bc3ad
S
140 })
141
6e6bc8da 142 tfa_data = urlencode_postdata(tfa_form_strs)
83317f69 143
5c2266df 144 tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
83317f69 145 tfa_results = self._download_webpage(
146 tfa_req, None,
69ea8ca4 147 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
83317f69 148
149 if tfa_results is False:
150 return False
151
e9fb6a4b 152 if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
041bc3ad 153 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
83317f69 154 return False
e9fb6a4b 155 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
69ea8ca4 156 self._downloader.report_warning('unable to log in - did the page structure change?')
83317f69 157 return False
158 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
69ea8ca4 159 self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
83317f69 160 return False
161
e9fb6a4b 162 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
69ea8ca4 163 self._downloader.report_warning('unable to log in: bad username or password')
b2e8bc1b
JMF
164 return False
165 return True
166
b2e8bc1b
JMF
167 def _real_initialize(self):
168 if self._downloader is None:
169 return
42939b61 170 self._set_language()
b2e8bc1b
JMF
171 if not self._login():
172 return
c5e8d7af 173
8377574c 174
8e7aad20 175class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
061a75ed 176 # Extract entries from page with "Load more" button
648e6a1f
S
177 def _entries(self, page, playlist_id):
178 more_widget_html = content_html = page
179 for page_num in itertools.count(1):
061a75ed
S
180 for entry in self._process_page(content_html):
181 yield entry
648e6a1f
S
182
183 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
184 if not mobj:
185 break
186
187 more = self._download_json(
188 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
189 'Downloading page #%s' % page_num,
190 transform_source=uppercase_escape)
191 content_html = more['content_html']
192 if not content_html.strip():
193 # Some webpages show a "Load more" button but they don't
194 # have more videos
195 break
196 more_widget_html = more['load_more_widget_html']
197
061a75ed
S
198
199class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
200 def _process_page(self, content):
201 for video_id, video_title in self.extract_videos_from_page(content):
202 yield self.url_result(video_id, 'Youtube', video_id, video_title)
203
648e6a1f
S
204 def extract_videos_from_page(self, page):
205 ids_in_page = []
206 titles_in_page = []
207 for mobj in re.finditer(self._VIDEO_RE, page):
208 # The link with index 0 is not the first video of the playlist (not sure if still actual)
209 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
210 continue
211 video_id = mobj.group('id')
212 video_title = unescapeHTML(mobj.group('title'))
213 if video_title:
214 video_title = video_title.strip()
215 try:
216 idx = ids_in_page.index(video_id)
217 if video_title and not titles_in_page[idx]:
218 titles_in_page[idx] = video_title
219 except ValueError:
220 ids_in_page.append(video_id)
221 titles_in_page.append(video_title)
222 return zip(ids_in_page, titles_in_page)
223
224
061a75ed
S
225class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
226 def _process_page(self, content):
6dee688e
S
227 for playlist_id in orderedSet(re.findall(
228 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
229 content)):
061a75ed
S
230 yield self.url_result(
231 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
232
0c148415
S
233 def _real_extract(self, url):
234 playlist_id = self._match_id(url)
235 webpage = self._download_webpage(url, playlist_id)
0c148415 236 title = self._og_search_title(webpage, fatal=False)
061a75ed 237 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
0c148415
S
238
239
360e1ca5 240class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 241 IE_DESC = 'YouTube.com'
cb7dfeea 242 _VALID_URL = r"""(?x)^
c5e8d7af 243 (
edb53e2d 244 (?:https?://|//) # http(s):// or protocol-independent URL
cb7dfeea 245 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
484aaeb2 246 (?:www\.)?deturl\.com/www\.youtube\.com/|
e70dc1d1 247 (?:www\.)?pwnyoutube\.com/|
f7000f3a 248 (?:www\.)?yourepeat\.com/|
e69ae5b9
JMF
249 tube\.majestyc\.net/|
250 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
c5e8d7af
PH
251 (?:.*?\#/)? # handle anchor (#/) redirect urls
252 (?: # the various things that can precede the ID:
ac7553d0 253 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 254 |(?: # or the v= param in all its forms
f7000f3a 255 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 256 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 257 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
258 v=
259 )
f4b05232 260 ))
cbaed4bb
S
261 |(?:
262 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
263 vid\.plus| # or vid.plus/xxxx
264 zwearz\.com/watch| # or zwearz.com/watch/xxxx
cbaed4bb 265 )/
edb53e2d 266 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 267 )
c5e8d7af 268 )? # all until now is optional -> you can pass the naked ID
8963d9c2 269 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
d0ba5587
S
270 (?!.*?\blist=
271 (?:
272 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
273 WL # WL are handled by the watch later IE
274 )
275 )
c5e8d7af 276 (?(1).+)? # if we found the ID, everything can follow
d0ba5587 277 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
c5e8d7af 278 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
2c62dc26 279 _formats = {
c2d3cb4c 280 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
281 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
282 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
283 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
284 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
285 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
286 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
287 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 288 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 289 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
290 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
291 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
292 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
293 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
294 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 295 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 296 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
297 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 298
299
300 # 3D videos
c2d3cb4c 301 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
302 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
303 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
304 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 305 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
306 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
307 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 308
96fb5605 309 # Apple HTTP Live Streaming
11f12195 310 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 311 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
312 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
313 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
314 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
315 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 316 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
317 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
318
319 # DASH mp4 video
d23028a8
S
320 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
321 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
322 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
323 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
324 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
325 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
326 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
327 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
328 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
329 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
330 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
331 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 332
f6f1fc92 333 # Dash mp4 audio
d23028a8
S
334 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
335 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
336 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
337 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
338 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
339 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
340 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
341
342 # Dash webm
d23028a8
S
343 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
344 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
345 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
346 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
347 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
348 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
349 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
350 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
351 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
352 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
353 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
354 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
355 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
356 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
357 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 358 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
359 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
360 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
361 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
362 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
363 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
364 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
365
366 # Dash webm audio
d23028a8
S
367 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
368 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 369
0857baad 370 # Dash webm audio with opus inside
d23028a8
S
371 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
372 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
373 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 374
ce6b9a2d
PH
375 # RTMP (unnamed)
376 '_rtmp': {'protocol': 'rtmp'},
c5e8d7af 377 }
23d17e4b 378 _SUBTITLE_FORMATS = ('ttml', 'vtt')
836a086c 379
fd5c4aab
S
380 _GEO_BYPASS = False
381
78caa52a 382 IE_NAME = 'youtube'
2eb88d95
PH
383 _TESTS = [
384 {
2d3d2997 385 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
386 'info_dict': {
387 'id': 'BaW_jenozKc',
388 'ext': 'mp4',
389 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
390 'uploader': 'Philipp Hagemeister',
391 'uploader_id': 'phihag',
ec85ded8 392 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
4bc3a23e 393 'upload_date': '20121002',
7caf9830 394 'license': 'Standard YouTube License',
4bc3a23e
PH
395 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
396 'categories': ['Science & Technology'],
000b6b5a 397 'tags': ['youtube-dl'],
556dbe7f 398 'duration': 10,
3e7c1224
PH
399 'like_count': int,
400 'dislike_count': int,
7c80519c 401 'start_time': 1,
297a564b 402 'end_time': 9,
2eb88d95 403 }
0e853ca4 404 },
0e853ca4 405 {
2d3d2997 406 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
4bc3a23e
PH
407 'note': 'Test generic use_cipher_signature video (#897)',
408 'info_dict': {
409 'id': 'UxxajLWwzqY',
410 'ext': 'mp4',
411 'upload_date': '20120506',
412 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
0cb58b02 413 'alt_title': 'I Love It (feat. Charli XCX)',
7caf9830 414 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
000b6b5a
S
415 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
416 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
417 'iconic ep', 'iconic', 'love', 'it'],
556dbe7f 418 'duration': 180,
4bc3a23e
PH
419 'uploader': 'Icona Pop',
420 'uploader_id': 'IconaPop',
ec85ded8 421 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
7caf9830 422 'license': 'Standard YouTube License',
0cb58b02 423 'creator': 'Icona Pop',
2eb88d95 424 }
c108eb73
JMF
425 },
426 {
4bc3a23e
PH
427 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
428 'note': 'Test VEVO video with age protection (#956)',
429 'info_dict': {
430 'id': '07FYdnEawAQ',
431 'ext': 'mp4',
432 'upload_date': '20130703',
433 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
0cb58b02 434 'alt_title': 'Tunnel Vision',
4bc3a23e 435 'description': 'md5:64249768eec3bc4276236606ea996373',
556dbe7f 436 'duration': 419,
4bc3a23e
PH
437 'uploader': 'justintimberlakeVEVO',
438 'uploader_id': 'justintimberlakeVEVO',
ec85ded8 439 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
7caf9830 440 'license': 'Standard YouTube License',
0cb58b02 441 'creator': 'Justin Timberlake',
34952f09 442 'age_limit': 18,
c108eb73
JMF
443 }
444 },
fccd3771 445 {
4bc3a23e
PH
446 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
447 'note': 'Embed-only video (#1746)',
448 'info_dict': {
449 'id': 'yZIXLfi8CZQ',
450 'ext': 'mp4',
451 'upload_date': '20120608',
452 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
453 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
454 'uploader': 'SET India',
94bfcd23 455 'uploader_id': 'setindia',
ec85ded8 456 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
7caf9830 457 'license': 'Standard YouTube License',
94bfcd23 458 'age_limit': 18,
fccd3771
PH
459 }
460 },
11b56058 461 {
2d3d2997 462 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
11b56058
PM
463 'note': 'Use the first video ID in the URL',
464 'info_dict': {
465 'id': 'BaW_jenozKc',
466 'ext': 'mp4',
467 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
468 'uploader': 'Philipp Hagemeister',
469 'uploader_id': 'phihag',
ec85ded8 470 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 471 'upload_date': '20121002',
7caf9830 472 'license': 'Standard YouTube License',
11b56058
PM
473 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
474 'categories': ['Science & Technology'],
475 'tags': ['youtube-dl'],
556dbe7f 476 'duration': 10,
11b56058
PM
477 'like_count': int,
478 'dislike_count': int,
34a7de29
S
479 },
480 'params': {
481 'skip_download': True,
482 },
11b56058 483 },
dd27fd17 484 {
2d3d2997 485 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
486 'note': '256k DASH audio (format 141) via DASH manifest',
487 'info_dict': {
488 'id': 'a9LDPn-MO4I',
489 'ext': 'm4a',
490 'upload_date': '20121002',
491 'uploader_id': '8KVIDEO',
ec85ded8 492 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
493 'description': '',
494 'uploader': '8KVIDEO',
7caf9830 495 'license': 'Standard YouTube License',
4bc3a23e 496 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 497 },
4bc3a23e
PH
498 'params': {
499 'youtube_include_dash_manifest': True,
500 'format': '141',
4919603f 501 },
de3c7fe0 502 'skip': 'format 141 not served anymore',
dd27fd17 503 },
3489b7d2
JMF
504 # DASH manifest with encrypted signature
505 {
78caa52a
PH
506 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
507 'info_dict': {
508 'id': 'IB3lcPjvWLA',
509 'ext': 'm4a',
b766eb27
JMF
510 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
511 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
556dbe7f 512 'duration': 244,
78caa52a
PH
513 'uploader': 'AfrojackVEVO',
514 'uploader_id': 'AfrojackVEVO',
515 'upload_date': '20131011',
7caf9830 516 'license': 'Standard YouTube License',
3489b7d2 517 },
4bc3a23e 518 'params': {
78caa52a 519 'youtube_include_dash_manifest': True,
de3c7fe0 520 'format': '141/bestaudio[ext=m4a]',
3489b7d2
JMF
521 },
522 },
aaeb86f6
S
523 # JS player signature function name containing $
524 {
525 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
526 'info_dict': {
527 'id': 'nfWlot6h_JM',
528 'ext': 'm4a',
529 'title': 'Taylor Swift - Shake It Off',
0cb58b02 530 'alt_title': 'Shake It Off',
f57b7835 531 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
556dbe7f 532 'duration': 242,
aaeb86f6
S
533 'uploader': 'TaylorSwiftVEVO',
534 'uploader_id': 'TaylorSwiftVEVO',
535 'upload_date': '20140818',
7caf9830 536 'license': 'Standard YouTube License',
0cb58b02 537 'creator': 'Taylor Swift',
aaeb86f6
S
538 },
539 'params': {
540 'youtube_include_dash_manifest': True,
de3c7fe0 541 'format': '141/bestaudio[ext=m4a]',
aaeb86f6
S
542 },
543 },
aa79ac0c
PH
544 # Controversy video
545 {
546 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
547 'info_dict': {
548 'id': 'T4XJQO3qol8',
549 'ext': 'mp4',
556dbe7f 550 'duration': 219,
aa79ac0c
PH
551 'upload_date': '20100909',
552 'uploader': 'The Amazing Atheist',
553 'uploader_id': 'TheAmazingAtheist',
ec85ded8 554 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
7caf9830 555 'license': 'Standard YouTube License',
aa79ac0c
PH
556 'title': 'Burning Everyone\'s Koran',
557 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
558 }
c522adb1
JMF
559 },
560 # Normal age-gate video (No vevo, embed allowed)
561 {
2d3d2997 562 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
563 'info_dict': {
564 'id': 'HtVdAasjOgU',
565 'ext': 'mp4',
566 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 567 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 568 'duration': 142,
c522adb1
JMF
569 'uploader': 'The Witcher',
570 'uploader_id': 'WitcherGame',
ec85ded8 571 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 572 'upload_date': '20140605',
7caf9830 573 'license': 'Standard YouTube License',
34952f09 574 'age_limit': 18,
c522adb1
JMF
575 },
576 },
fccae2b9
S
577 # Age-gate video with encrypted signature
578 {
2d3d2997 579 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
fccae2b9
S
580 'info_dict': {
581 'id': '6kLq3WMV1nU',
582 'ext': 'mp4',
583 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
584 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
556dbe7f 585 'duration': 247,
fccae2b9
S
586 'uploader': 'LloydVEVO',
587 'uploader_id': 'LloydVEVO',
ec85ded8 588 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
fccae2b9 589 'upload_date': '20110629',
7caf9830 590 'license': 'Standard YouTube License',
34952f09 591 'age_limit': 18,
fccae2b9
S
592 },
593 },
774e208f
PH
594 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
595 {
596 'url': '__2ABJjxzNo',
597 'info_dict': {
598 'id': '__2ABJjxzNo',
599 'ext': 'mp4',
556dbe7f 600 'duration': 266,
774e208f
PH
601 'upload_date': '20100430',
602 'uploader_id': 'deadmau5',
ec85ded8 603 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
0cb58b02 604 'creator': 'deadmau5',
774e208f
PH
605 'description': 'md5:12c56784b8032162bb936a5f76d55360',
606 'uploader': 'deadmau5',
7caf9830 607 'license': 'Standard YouTube License',
774e208f 608 'title': 'Deadmau5 - Some Chords (HD)',
0cb58b02 609 'alt_title': 'Some Chords',
774e208f
PH
610 },
611 'expected_warnings': [
612 'DASH manifest missing',
613 ]
e52a40ab
PH
614 },
615 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
616 {
617 'url': 'lqQg6PlCWgI',
618 'info_dict': {
619 'id': 'lqQg6PlCWgI',
620 'ext': 'mp4',
556dbe7f 621 'duration': 6085,
90227264 622 'upload_date': '20150827',
cbe2bd91 623 'uploader_id': 'olympic',
ec85ded8 624 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
7caf9830 625 'license': 'Standard YouTube License',
cbe2bd91 626 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
be49068d 627 'uploader': 'Olympic',
cbe2bd91
PH
628 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
629 },
630 'params': {
631 'skip_download': 'requires avconv',
e52a40ab 632 }
cbe2bd91 633 },
6271f1ca
PH
634 # Non-square pixels
635 {
636 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
637 'info_dict': {
638 'id': '_b-2C3KPAM0',
639 'ext': 'mp4',
640 'stretched_ratio': 16 / 9.,
556dbe7f 641 'duration': 85,
6271f1ca
PH
642 'upload_date': '20110310',
643 'uploader_id': 'AllenMeow',
ec85ded8 644 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca
PH
645 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
646 'uploader': '孫艾倫',
7caf9830 647 'license': 'Standard YouTube License',
6271f1ca
PH
648 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
649 },
06b491eb
S
650 },
651 # url_encoded_fmt_stream_map is empty string
652 {
653 'url': 'qEJwOuvDf7I',
654 'info_dict': {
655 'id': 'qEJwOuvDf7I',
f57b7835 656 'ext': 'webm',
06b491eb
S
657 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
658 'description': '',
659 'upload_date': '20150404',
660 'uploader_id': 'spbelect',
661 'uploader': 'Наблюдатели Петербурга',
662 },
663 'params': {
664 'skip_download': 'requires avconv',
e323cf3f
S
665 },
666 'skip': 'This live event has ended.',
06b491eb 667 },
da77d856
S
668 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
669 {
670 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
671 'info_dict': {
672 'id': 'FIl7x6_3R5Y',
673 'ext': 'mp4',
674 'title': 'md5:7b81415841e02ecd4313668cde88737a',
675 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 676 'duration': 220,
da77d856
S
677 'upload_date': '20150625',
678 'uploader_id': 'dorappi2000',
ec85ded8 679 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 680 'uploader': 'dorappi2000',
7caf9830 681 'license': 'Standard YouTube License',
be49068d 682 'formats': 'mincount:32',
da77d856 683 },
2ee8f5d8 684 },
8a1a26ce
YCH
685 # DASH manifest with segment_list
686 {
687 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
688 'md5': '8ce563a1d667b599d21064e982ab9e31',
689 'info_dict': {
690 'id': 'CsmdDsKjzN8',
691 'ext': 'mp4',
17ee98e1 692 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
693 'uploader': 'Airtek',
694 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
695 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
7caf9830 696 'license': 'Standard YouTube License',
8a1a26ce
YCH
697 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
698 },
699 'params': {
700 'youtube_include_dash_manifest': True,
701 'format': '135', # bestvideo
be49068d
S
702 },
703 'skip': 'This live event has ended.',
2ee8f5d8 704 },
cf7e015f
S
705 {
706 # Multifeed videos (multiple cameras), URL is for Main Camera
707 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
708 'info_dict': {
709 'id': 'jqWvoWXjCVs',
710 'title': 'teamPGP: Rocket League Noob Stream',
711 'description': 'md5:dc7872fb300e143831327f1bae3af010',
712 },
713 'playlist': [{
714 'info_dict': {
715 'id': 'jqWvoWXjCVs',
716 'ext': 'mp4',
717 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
718 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 719 'duration': 7335,
cf7e015f
S
720 'upload_date': '20150721',
721 'uploader': 'Beer Games Beer',
722 'uploader_id': 'beergamesbeer',
ec85ded8 723 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 724 'license': 'Standard YouTube License',
cf7e015f
S
725 },
726 }, {
727 'info_dict': {
728 'id': '6h8e8xoXJzg',
729 'ext': 'mp4',
730 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
731 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 732 'duration': 7337,
cf7e015f
S
733 'upload_date': '20150721',
734 'uploader': 'Beer Games Beer',
735 'uploader_id': 'beergamesbeer',
ec85ded8 736 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 737 'license': 'Standard YouTube License',
cf7e015f
S
738 },
739 }, {
740 'info_dict': {
741 'id': 'PUOgX5z9xZw',
742 'ext': 'mp4',
743 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
744 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 745 'duration': 7337,
cf7e015f
S
746 'upload_date': '20150721',
747 'uploader': 'Beer Games Beer',
748 'uploader_id': 'beergamesbeer',
ec85ded8 749 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 750 'license': 'Standard YouTube License',
cf7e015f
S
751 },
752 }, {
753 'info_dict': {
754 'id': 'teuwxikvS5k',
755 'ext': 'mp4',
756 'title': 'teamPGP: Rocket League Noob Stream (zim)',
757 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 758 'duration': 7334,
cf7e015f
S
759 'upload_date': '20150721',
760 'uploader': 'Beer Games Beer',
761 'uploader_id': 'beergamesbeer',
ec85ded8 762 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 763 'license': 'Standard YouTube License',
cf7e015f
S
764 },
765 }],
766 'params': {
767 'skip_download': True,
768 },
cbaed4bb 769 },
f9f49d87
S
770 {
771 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
772 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
773 'info_dict': {
774 'id': 'gVfLd0zydlo',
775 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
776 },
777 'playlist_count': 2,
be49068d 778 'skip': 'Not multifeed anymore',
f9f49d87 779 },
cbaed4bb 780 {
2d3d2997 781 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 782 'only_matching': True,
0e49d9a6 783 },
6d4fc66b 784 {
2d3d2997 785 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
786 'only_matching': True,
787 },
0e49d9a6 788 {
61f92af1 789 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
a8776b10
S
790 # Also tests cut-off URL expansion in video description (see
791 # https://github.com/rg3/youtube-dl/issues/1892,
792 # https://github.com/rg3/youtube-dl/issues/8164)
0e49d9a6
LL
793 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
794 'info_dict': {
795 'id': 'lsguqyKfVQg',
796 'ext': 'mp4',
797 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
0cb58b02 798 'alt_title': 'Dark Walk',
0e49d9a6 799 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 800 'duration': 133,
0e49d9a6
LL
801 'upload_date': '20151119',
802 'uploader_id': 'IronSoulElf',
ec85ded8 803 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 804 'uploader': 'IronSoulElf',
7caf9830 805 'license': 'Standard YouTube License',
0cb58b02 806 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
0e49d9a6
LL
807 },
808 'params': {
809 'skip_download': True,
810 },
811 },
61f92af1
S
812 {
813 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
814 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
815 'only_matching': True,
816 },
313dfc45
LL
817 {
818 # Video with yt:stretch=17:0
819 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
820 'info_dict': {
821 'id': 'Q39EVAstoRM',
822 'ext': 'mp4',
823 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
824 'description': 'md5:ee18a25c350637c8faff806845bddee9',
825 'upload_date': '20151107',
826 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
827 'uploader': 'CH GAMER DROID',
828 },
829 'params': {
830 'skip_download': True,
831 },
be49068d 832 'skip': 'This video does not exist.',
313dfc45 833 },
7caf9830
S
834 {
835 # Video licensed under Creative Commons
836 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
837 'info_dict': {
838 'id': 'M4gD1WSo5mA',
839 'ext': 'mp4',
840 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
841 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 842 'duration': 721,
7caf9830
S
843 'upload_date': '20150127',
844 'uploader_id': 'BerkmanCenter',
ec85ded8 845 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 846 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
847 'license': 'Creative Commons Attribution license (reuse allowed)',
848 },
849 'params': {
850 'skip_download': True,
851 },
852 },
fd050249
S
853 {
854 # Channel-like uploader_url
855 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
856 'info_dict': {
857 'id': 'eQcmzGIKrzg',
858 'ext': 'mp4',
859 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
860 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
556dbe7f 861 'duration': 4060,
fd050249
S
862 'upload_date': '20151119',
863 'uploader': 'Bernie 2016',
864 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 865 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
866 'license': 'Creative Commons Attribution license (reuse allowed)',
867 },
868 'params': {
869 'skip_download': True,
870 },
871 },
040ac686
S
872 {
873 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
874 'only_matching': True,
7f29cf54
S
875 },
876 {
877 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
878 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
879 'only_matching': True,
6496ccb4
S
880 },
881 {
882 # Rental video preview
883 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
884 'info_dict': {
885 'id': 'uGpuVWrhIzE',
886 'ext': 'mp4',
887 'title': 'Piku - Trailer',
888 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
889 'upload_date': '20150811',
890 'uploader': 'FlixMatrix',
891 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 892 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
893 'license': 'Standard YouTube License',
894 },
895 'params': {
896 'skip_download': True,
897 },
022a5d66 898 },
12afdc2a
S
899 {
900 # YouTube Red video with episode data
901 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
902 'info_dict': {
903 'id': 'iqKdEhx-dD4',
904 'ext': 'mp4',
905 'title': 'Isolation - Mind Field (Ep 1)',
556dbe7f
S
906 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
907 'duration': 2085,
12afdc2a
S
908 'upload_date': '20170118',
909 'uploader': 'Vsauce',
910 'uploader_id': 'Vsauce',
911 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
912 'license': 'Standard YouTube License',
913 'series': 'Mind Field',
914 'season_number': 1,
915 'episode_number': 1,
916 },
917 'params': {
918 'skip_download': True,
919 },
920 'expected_warnings': [
921 'Skipping DASH manifest',
922 ],
923 },
022a5d66
S
924 {
925 # itag 212
926 'url': '1t24XAntNCY',
927 'only_matching': True,
fd5c4aab
S
928 },
929 {
930 # geo restricted to JP
931 'url': 'sJL6WA-aGkQ',
932 'only_matching': True,
933 },
d0ba5587
S
934 {
935 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
936 'only_matching': True,
937 },
2eb88d95
PH
938 ]
939
e0df6211
PH
940 def __init__(self, *args, **kwargs):
941 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 942 self._player_cache = {}
e0df6211 943
c5e8d7af
PH
944 def report_video_info_webpage_download(self, video_id):
945 """Report attempt to download video info webpage."""
69ea8ca4 946 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 947
c5e8d7af
PH
948 def report_information_extraction(self, video_id):
949 """Report attempt to extract video information."""
69ea8ca4 950 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
951
952 def report_unavailable_format(self, video_id, format):
953 """Report extracted video URL."""
69ea8ca4 954 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
955
956 def report_rtmp_download(self):
957 """Indicate the download will use the RTMP protocol."""
69ea8ca4 958 self.to_screen('RTMP download detected')
c5e8d7af 959
60064c53
PH
960 def _signature_cache_id(self, example_sig):
961 """ Return a string representation of a signature """
78caa52a 962 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
963
964 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 965 id_m = re.match(
e31fed95 966 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
cf010131 967 player_url)
c081b35c
PH
968 if not id_m:
969 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
970 player_type = id_m.group('ext')
971 player_id = id_m.group('id')
972
c4417ddb 973 # Read from filesystem cache
60064c53
PH
974 func_id = '%s_%s_%s' % (
975 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 976 assert os.path.basename(func_id) == func_id
a0e07d31 977
69ea8ca4 978 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 979 if cache_spec is not None:
78caa52a 980 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 981
6d1a55a5
PH
982 download_note = (
983 'Downloading player %s' % player_url
984 if self._downloader.params.get('verbose') else
985 'Downloading %s player %s' % (player_type, player_id)
986 )
e0df6211
PH
987 if player_type == 'js':
988 code = self._download_webpage(
989 player_url, video_id,
6d1a55a5 990 note=download_note,
69ea8ca4 991 errnote='Download of %s failed' % player_url)
83799698 992 res = self._parse_sig_js(code)
c4417ddb 993 elif player_type == 'swf':
e0df6211
PH
994 urlh = self._request_webpage(
995 player_url, video_id,
6d1a55a5 996 note=download_note,
69ea8ca4 997 errnote='Download of %s failed' % player_url)
e0df6211 998 code = urlh.read()
83799698 999 res = self._parse_sig_swf(code)
e0df6211
PH
1000 else:
1001 assert False, 'Invalid player type %r' % player_type
1002
785521bf
PH
1003 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1004 cache_res = res(test_string)
1005 cache_spec = [ord(c) for c in cache_res]
83799698 1006
69ea8ca4 1007 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
1008 return res
1009
60064c53 1010 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1011 def gen_sig_code(idxs):
1012 def _genslice(start, end, step):
78caa52a 1013 starts = '' if start == 0 else str(start)
8bcc8756 1014 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1015 steps = '' if step == 1 else (':%d' % step)
78caa52a 1016 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1017
1018 step = None
7af808a5
PH
1019 # Quelch pyflakes warnings - start will be set when step is set
1020 start = '(Never used)'
edf3e38e
PH
1021 for i, prev in zip(idxs[1:], idxs[:-1]):
1022 if step is not None:
1023 if i - prev == step:
1024 continue
1025 yield _genslice(start, prev, step)
1026 step = None
1027 continue
1028 if i - prev in [-1, 1]:
1029 step = i - prev
1030 start = prev
1031 continue
1032 else:
78caa52a 1033 yield 's[%d]' % prev
edf3e38e 1034 if step is None:
78caa52a 1035 yield 's[%d]' % i
edf3e38e
PH
1036 else:
1037 yield _genslice(start, i, step)
1038
78caa52a 1039 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1040 cache_res = func(test_string)
edf3e38e 1041 cache_spec = [ord(c) for c in cache_res]
78caa52a 1042 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1043 signature_id_tuple = '(%s)' % (
1044 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1045 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1046 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1047 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1048
e0df6211
PH
1049 def _parse_sig_js(self, jscode):
1050 funcname = self._search_regex(
3c90cc8b
S
1051 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1052 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
1053 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1054
1055 jsi = JSInterpreter(jscode)
1056 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1057 return lambda s: initial_function([s])
1058
1059 def _parse_sig_swf(self, file_contents):
54256267 1060 swfi = SWFInterpreter(file_contents)
78caa52a 1061 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 1062 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 1063 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
1064 return lambda s: initial_function([s])
1065
83799698 1066 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 1067 """Turn the encrypted s field into a working signature"""
6b37f0be 1068
c8bf86d5 1069 if player_url is None:
69ea8ca4 1070 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1071
69ea8ca4 1072 if player_url.startswith('//'):
78caa52a 1073 player_url = 'https:' + player_url
3c90cc8b
S
1074 elif not re.match(r'https?://', player_url):
1075 player_url = compat_urlparse.urljoin(
1076 'https://www.youtube.com', player_url)
c8bf86d5 1077 try:
62af3a0e 1078 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1079 if player_id not in self._player_cache:
1080 func = self._extract_signature_function(
60064c53 1081 video_id, player_url, s
c8bf86d5
PH
1082 )
1083 self._player_cache[player_id] = func
1084 func = self._player_cache[player_id]
1085 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1086 self._print_sig_code(func, s)
c8bf86d5
PH
1087 return func(s)
1088 except Exception as e:
1089 tb = traceback.format_exc()
1090 raise ExtractorError(
78caa52a 1091 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1092
360e1ca5 1093 def _get_subtitles(self, video_id, webpage):
de7f3446 1094 try:
60e47a26 1095 subs_doc = self._download_xml(
38c2e5b8 1096 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1097 video_id, note=False)
1098 except ExtractorError as err:
9b9c5355 1099 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1100 return {}
de7f3446
JMF
1101
1102 sub_lang_list = {}
60e47a26
JMF
1103 for track in subs_doc.findall('track'):
1104 lang = track.attrib['lang_code']
7e660ac1
LD
1105 if lang in sub_lang_list:
1106 continue
360e1ca5 1107 sub_formats = []
23d17e4b 1108 for ext in self._SUBTITLE_FORMATS:
15707c7e 1109 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1110 'lang': lang,
1111 'v': video_id,
1112 'fmt': ext,
1113 'name': track.attrib['name'].encode('utf-8'),
1114 })
1115 sub_formats.append({
1116 'url': 'https://www.youtube.com/api/timedtext?' + params,
1117 'ext': ext,
1118 })
1119 sub_lang_list[lang] = sub_formats
de7f3446 1120 if not sub_lang_list:
69ea8ca4 1121 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1122 return {}
1123 return sub_lang_list
1124
a72778d3
S
1125 def _get_ytplayer_config(self, video_id, webpage):
1126 patterns = (
526b3b07
S
1127 # User data may contain arbitrary character sequences that may affect
1128 # JSON extraction with regex, e.g. when '};' is contained the second
1129 # regex won't capture the whole JSON. Yet working around by trying more
1130 # concrete regex first keeping in mind proper quoted string handling
1131 # to be implemented in future that will replace this workaround (see
1132 # https://github.com/rg3/youtube-dl/issues/7468,
1133 # https://github.com/rg3/youtube-dl/pull/7599)
a72778d3
S
1134 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1135 r';ytplayer\.config\s*=\s*({.+?});',
1136 )
1137 config = self._search_regex(
1138 patterns, webpage, 'ytplayer.config', default=None)
1139 if config:
1140 return self._parse_json(
1141 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1142
360e1ca5 1143 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1144 """We need the webpage for getting the captions url, pass it as an
1145 argument to speed up the process."""
69ea8ca4 1146 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1147 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1148 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1149 if not player_config:
de7f3446
JMF
1150 self._downloader.report_warning(err_msg)
1151 return {}
de7f3446 1152 try:
0792d563 1153 args = player_config['args']
b78b292f
S
1154 caption_url = args.get('ttsurl')
1155 if caption_url:
1156 timestamp = args['timestamp']
1157 # We get the available subtitles
15707c7e 1158 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1159 'type': 'list',
1160 'tlangs': 1,
1161 'asrs': 1,
1162 })
1163 list_url = caption_url + '&' + list_params
1164 caption_list = self._download_xml(list_url, video_id)
1165 original_lang_node = caption_list.find('track')
1166 if original_lang_node is None:
1167 self._downloader.report_warning('Video doesn\'t have automatic captions')
1168 return {}
1169 original_lang = original_lang_node.attrib['lang_code']
1170 caption_kind = original_lang_node.attrib.get('kind', '')
1171
1172 sub_lang_list = {}
1173 for lang_node in caption_list.findall('target'):
1174 sub_lang = lang_node.attrib['lang_code']
1175 sub_formats = []
1176 for ext in self._SUBTITLE_FORMATS:
15707c7e 1177 params = compat_urllib_parse_urlencode({
b78b292f
S
1178 'lang': original_lang,
1179 'tlang': sub_lang,
1180 'fmt': ext,
1181 'ts': timestamp,
1182 'kind': caption_kind,
1183 })
1184 sub_formats.append({
1185 'url': caption_url + '&' + params,
1186 'ext': ext,
1187 })
1188 sub_lang_list[sub_lang] = sub_formats
1189 return sub_lang_list
1190
1191 # Some videos don't provide ttsurl but rather caption_tracks and
1192 # caption_translation_languages (e.g. 20LmZk1hakA)
1193 caption_tracks = args['caption_tracks']
1194 caption_translation_languages = args['caption_translation_languages']
1195 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
15707c7e 1196 parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
b78b292f 1197 caption_qs = compat_parse_qs(parsed_caption_url.query)
055e6f36
JMF
1198
1199 sub_lang_list = {}
b78b292f
S
1200 for lang in caption_translation_languages.split(','):
1201 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1202 sub_lang = lang_qs.get('lc', [None])[0]
1203 if not sub_lang:
1204 continue
360e1ca5 1205 sub_formats = []
23d17e4b 1206 for ext in self._SUBTITLE_FORMATS:
b78b292f
S
1207 caption_qs.update({
1208 'tlang': [sub_lang],
1209 'fmt': [ext],
360e1ca5 1210 })
b78b292f 1211 sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
15707c7e 1212 query=compat_urllib_parse_urlencode(caption_qs, True)))
360e1ca5 1213 sub_formats.append({
b78b292f 1214 'url': sub_url,
360e1ca5
JMF
1215 'ext': ext,
1216 })
1217 sub_lang_list[sub_lang] = sub_formats
055e6f36 1218 return sub_lang_list
de7f3446
JMF
1219 # An extractor error can be raise by the download process if there are
1220 # no automatic captions but there are subtitles
1221 except (KeyError, ExtractorError):
1222 self._downloader.report_warning(err_msg)
1223 return {}
1224
d77ab8e2
S
1225 def _mark_watched(self, video_id, video_info):
1226 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1227 if not playback_url:
1228 return
1229 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1230 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1231
1232 # cpn generation algorithm is reverse engineered from base.js.
1233 # In fact it works even with dummy cpn.
1234 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1235 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1236
1237 qs.update({
1238 'ver': ['2'],
1239 'cpn': [cpn],
1240 })
1241 playback_url = compat_urlparse.urlunparse(
15707c7e 1242 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1243
1244 self._download_webpage(
1245 playback_url, video_id, 'Marking watched',
1246 'Unable to mark watched', fatal=False)
1247
97665381
PH
1248 @classmethod
1249 def extract_id(cls, url):
1250 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1251 if mobj is None:
69ea8ca4 1252 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1253 video_id = mobj.group(2)
1254 return video_id
1255
1fb07d10
JG
1256 def _extract_annotations(self, video_id):
1257 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1258 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1259
9cafc3fd
S
1260 @staticmethod
1261 def _extract_chapters(description, duration):
1262 if not description:
1263 return None
1264 chapter_lines = re.findall(
1265 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1266 description)
1267 if not chapter_lines:
1268 return None
1269 chapters = []
1270 for next_num, (chapter_line, time_point) in enumerate(
1271 chapter_lines, start=1):
1272 start_time = parse_duration(time_point)
1273 if start_time is None:
1274 continue
1275 end_time = (duration if next_num == len(chapter_lines)
1276 else parse_duration(chapter_lines[next_num][1]))
1277 if end_time is None:
1278 continue
1279 chapter_title = re.sub(
1280 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1281 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1282 chapters.append({
1283 'start_time': start_time,
1284 'end_time': end_time,
1285 'title': chapter_title,
1286 })
1287 return chapters
1288
c5e8d7af 1289 def _real_extract(self, url):
cf7e015f
S
1290 url, smuggled_data = unsmuggle_url(url, {})
1291
7e8c0af0 1292 proto = (
78caa52a
PH
1293 'http' if self._downloader.params.get('prefer_insecure', False)
1294 else 'https')
7e8c0af0 1295
7c80519c 1296 start_time = None
297a564b 1297 end_time = None
7c80519c
JMF
1298 parsed_url = compat_urllib_parse_urlparse(url)
1299 for component in [parsed_url.fragment, parsed_url.query]:
1300 query = compat_parse_qs(component)
297a564b 1301 if start_time is None and 't' in query:
7c80519c 1302 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1303 if start_time is None and 'start' in query:
1304 start_time = parse_duration(query['start'][0])
297a564b
JMF
1305 if end_time is None and 'end' in query:
1306 end_time = parse_duration(query['end'][0])
7c80519c 1307
c5e8d7af
PH
1308 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1309 mobj = re.search(self._NEXT_URL_RE, url)
1310 if mobj:
7fd002c0 1311 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1312 video_id = self.extract_id(url)
c5e8d7af
PH
1313
1314 # Get video webpage
aa79ac0c 1315 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1316 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1317
1318 # Attempt to extract SWF player URL
e0df6211 1319 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1320 if mobj is not None:
1321 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1322 else:
1323 player_url = None
1324
d8d24a92
S
1325 dash_mpds = []
1326
1327 def add_dash_mpd(video_info):
1328 dash_mpd = video_info.get('dashmpd')
1329 if dash_mpd and dash_mpd[0] not in dash_mpds:
1330 dash_mpds.append(dash_mpd[0])
1331
c5e8d7af 1332 # Get video info
6449cd80 1333 embed_webpage = None
2fe1ff85 1334 is_live = None
c108eb73 1335 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1336 age_gate = True
1337 # We simulate the access to the video from www.youtube.com/v/{video_id}
1338 # this can be viewed without login into Youtube
beb95e77
CL
1339 url = proto + '://www.youtube.com/embed/%s' % video_id
1340 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1341 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1342 'video_id': video_id,
1343 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1344 'sts': self._search_regex(
beb95e77 1345 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1346 })
7e8c0af0 1347 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1348 video_info_webpage = self._download_webpage(
1349 video_info_url, video_id,
20436c30 1350 note='Refetching age-gated info webpage',
94bd3613 1351 errnote='unable to download video info webpage')
c5e8d7af 1352 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1353 add_dash_mpd(video_info)
c108eb73
JMF
1354 else:
1355 age_gate = False
bc93bdb5 1356 video_info = None
d8d24a92 1357 # Try looking directly into the video webpage
a72778d3
S
1358 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1359 if ytplayer_config:
4e62ebe2 1360 args = ytplayer_config['args']
d8d24a92
S
1361 if args.get('url_encoded_fmt_stream_map'):
1362 # Convert to the same format returned by compat_parse_qs
1363 video_info = dict((k, [v]) for k, v in args.items())
1364 add_dash_mpd(video_info)
6496ccb4
S
1365 # Rental video is not rented but preview is available (e.g.
1366 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1367 # https://github.com/rg3/youtube-dl/issues/10532)
1368 if not video_info and args.get('ypc_vid'):
1369 return self.url_result(
1370 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
2fe1ff85
JMF
1371 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1372 is_live = True
0a3cf9ad
S
1373 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1374 # We also try looking in get_video_info since it may contain different dashmpd
1375 # URL that points to a DASH manifest with possibly different itag set (some itags
1376 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1377 # manifest pointed by get_video_info's dashmpd).
1378 # The general idea is to take a union of itags of both DASH manifests (for example
1379 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
4e62ebe2 1380 self.report_video_info_webpage_download(video_id)
0a3cf9ad 1381 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
810fb84d
PH
1382 video_info_url = (
1383 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1384 % (proto, video_id, el_type))
1385 video_info_webpage = self._download_webpage(
1386 video_info_url,
4e62ebe2
JMF
1387 video_id, note=False,
1388 errnote='unable to download video info webpage')
0a3cf9ad 1389 get_video_info = compat_parse_qs(video_info_webpage)
87dc4511
JMF
1390 if get_video_info.get('use_cipher_signature') != ['True']:
1391 add_dash_mpd(get_video_info)
0a3cf9ad
S
1392 if not video_info:
1393 video_info = get_video_info
1394 if 'token' in get_video_info:
89ea063e
S
1395 # Different get_video_info requests may report different results, e.g.
1396 # some may report video unavailability, but some may serve it without
1397 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1398 # the original webpage as well as el=info and el=embedded get_video_info
1399 # requests report video unavailability due to geo restriction while
1400 # el=detailpage succeeds and returns valid data). This is probably
1401 # due to YouTube measures against IP ranges of hosting providers.
1402 # Working around by preferring the first succeeded video_info containing
1403 # the token if no such video_info yet was found.
44b2264f
S
1404 if 'token' not in video_info:
1405 video_info = get_video_info
4e62ebe2 1406 break
c5e8d7af
PH
1407 if 'token' not in video_info:
1408 if 'reason' in video_info:
af214c3a 1409 if 'The uploader has not made this video available in your country.' in video_info['reason']:
fd5c4aab
S
1410 regions_allowed = self._html_search_meta(
1411 'regionsAllowed', video_webpage, default=None)
1412 countries = regions_allowed.split(',') if regions_allowed else None
1413 self.raise_geo_restricted(
1414 msg=video_info['reason'][0], countries=countries)
d11271dd 1415 raise ExtractorError(
78caa52a 1416 'YouTube said: %s' % video_info['reason'][0],
d11271dd 1417 expected=True, video_id=video_id)
c5e8d7af 1418 else:
d11271dd 1419 raise ExtractorError(
78caa52a 1420 '"token" parameter not in video info for unknown reason',
d11271dd 1421 video_id=video_id)
c5e8d7af 1422
cf7e015f
S
1423 # title
1424 if 'title' in video_info:
1425 video_title = video_info['title'][0]
1426 else:
1427 self._downloader.report_warning('Unable to extract video title')
1428 video_title = '_'
1429
1430 # description
9cafc3fd 1431 description_original = video_description = get_element_by_id("eow-description", video_webpage)
cf7e015f 1432 if video_description:
9cafc3fd 1433 description_original = video_description = re.sub(r'''(?x)
cf7e015f 1434 <a\s+
25cb7a0e 1435 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1436 (?:title|href)="([^"]+)"\s+
25cb7a0e 1437 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1438 class="[^"]*"[^>]*>
23f13e97 1439 [^<]+\.{3}\s*
cf7e015f
S
1440 </a>
1441 ''', r'\1', video_description)
1442 video_description = clean_html(video_description)
1443 else:
1444 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1445 if fd_mobj:
1446 video_description = unescapeHTML(fd_mobj.group(1))
1447 else:
1448 video_description = ''
1449
5e1eddb9
S
1450 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1451 if not self._downloader.params.get('noplaylist'):
1452 entries = []
1453 feed_ids = []
6863631c 1454 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
5e1eddb9 1455 for feed in multifeed_metadata_list.split(','):
6863631c
S
1456 # Unquote should take place before split on comma (,) since textual
1457 # fields may contain comma as well (see
1458 # https://github.com/rg3/youtube-dl/issues/8536)
1459 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
5e1eddb9
S
1460 entries.append({
1461 '_type': 'url_transparent',
1462 'ie_key': 'Youtube',
1463 'url': smuggle_url(
1464 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1465 {'force_singlefeed': True}),
1466 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1467 })
1468 feed_ids.append(feed_data['id'][0])
1469 self.to_screen(
1470 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1471 % (', '.join(feed_ids), video_id))
1472 return self.playlist_result(entries, video_id, video_title, video_description)
1473 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1474
1d699755
PH
1475 if 'view_count' in video_info:
1476 view_count = int(video_info['view_count'][0])
1477 else:
1478 view_count = None
1479
c5e8d7af
PH
1480 # Check for "rental" videos
1481 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
c9612c04 1482 raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
c5e8d7af
PH
1483
1484 # Start extracting information
1485 self.report_information_extraction(video_id)
1486
1487 # uploader
1488 if 'author' not in video_info:
69ea8ca4 1489 raise ExtractorError('Unable to extract uploader name')
7fd002c0 1490 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
c5e8d7af
PH
1491
1492 # uploader_id
1493 video_uploader_id = None
fd050249
S
1494 video_uploader_url = None
1495 mobj = re.search(
1496 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1497 video_webpage)
c5e8d7af 1498 if mobj is not None:
fd050249
S
1499 video_uploader_id = mobj.group('uploader_id')
1500 video_uploader_url = mobj.group('uploader_url')
c5e8d7af 1501 else:
69ea8ca4 1502 self._downloader.report_warning('unable to extract uploader nickname')
c5e8d7af 1503
c5e8d7af 1504 # thumbnail image
7763b04e
JMF
1505 # We try first to get a high quality image:
1506 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1507 video_webpage, re.DOTALL)
1508 if m_thumb is not None:
1509 video_thumbnail = m_thumb.group(1)
1510 elif 'thumbnail_url' not in video_info:
69ea8ca4 1511 self._downloader.report_warning('unable to extract video thumbnail')
f490e77e 1512 video_thumbnail = None
c5e8d7af 1513 else: # don't panic if we can't find it
7fd002c0 1514 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
c5e8d7af
PH
1515
1516 # upload date
9d0b581f
S
1517 upload_date = self._html_search_meta(
1518 'datePublished', video_webpage, 'upload date', default=None)
1519 if not upload_date:
1520 upload_date = self._search_regex(
1521 [r'(?s)id="eow-date.*?>(.*?)</span>',
1522 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1523 video_webpage, 'upload date', default=None)
1524 if upload_date:
1525 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1526 upload_date = unified_strdate(upload_date)
c5e8d7af 1527
7caf9830
S
1528 video_license = self._html_search_regex(
1529 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1530 video_webpage, 'license', default=None)
1531
0cb58b02
S
1532 m_music = re.search(
1533 r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1534 video_webpage)
1535 if m_music:
1536 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1537 video_creator = clean_html(m_music.group('creator'))
1538 else:
1539 video_alt_title = video_creator = None
1540
12afdc2a
S
1541 m_episode = re.search(
1542 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1543 video_webpage)
1544 if m_episode:
1545 series = m_episode.group('series')
1546 season_number = int(m_episode.group('season'))
1547 episode_number = int(m_episode.group('episode'))
1548 else:
1549 series = season_number = episode_number = None
1550
55f7bd2d
PH
1551 m_cat_container = self._search_regex(
1552 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
624dcebf 1553 video_webpage, 'categories', default=None)
ec8deefc 1554 if m_cat_container:
ad3bc6ac 1555 category = self._html_search_regex(
01ed5c9b 1556 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
ad3bc6ac
PH
1557 default=None)
1558 video_categories = None if category is None else [category]
1559 else:
1560 video_categories = None
ec8deefc 1561
000b6b5a
S
1562 video_tags = [
1563 unescapeHTML(m.group('content'))
1564 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1565
f30a38be 1566 def _extract_count(count_name):
c93d53f5
S
1567 return str_to_int(self._search_regex(
1568 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1569 % re.escape(count_name),
1570 video_webpage, count_name, default=None))
1571
69ea8ca4
PH
1572 like_count = _extract_count('like')
1573 dislike_count = _extract_count('dislike')
336c3a69 1574
c5e8d7af 1575 # subtitles
d82134c3 1576 video_subtitles = self.extract_subtitles(video_id, video_webpage)
360e1ca5 1577 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
c5e8d7af 1578
556dbe7f
S
1579 video_duration = try_get(
1580 video_info, lambda x: int_or_none(x['length_seconds'][0]))
1581 if not video_duration:
1582 video_duration = parse_duration(self._html_search_meta(
1583 'duration', video_webpage, 'video duration'))
c5e8d7af 1584
1fb07d10
JG
1585 # annotations
1586 video_annotations = None
1587 if self._downloader.params.get('writeannotations', False):
5f6a1245 1588 video_annotations = self._extract_annotations(video_id)
1fb07d10 1589
9cafc3fd
S
1590 chapters = self._extract_chapters(description_original, video_duration)
1591
c5e8d7af
PH
1592 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1593 self.report_rtmp_download()
dd27fd17
PH
1594 formats = [{
1595 'format_id': '_rtmp',
1596 'protocol': 'rtmp',
1597 'url': video_info['conn'][0],
1598 'player_url': player_url,
1599 }]
24270b03 1600 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
5f6a1245 1601 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1602 if 'rtmpe%3Dyes' in encoded_url_map:
a7055eb9 1603 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1604 formats_spec = {}
82156fdb 1605 fmt_list = video_info.get('fmt_list', [''])[0]
1606 if fmt_list:
1607 for fmt in fmt_list.split(','):
1608 spec = fmt.split('/')
3318832e 1609 if len(spec) > 1:
1610 width_height = spec[1].split('x')
1611 if len(width_height) == 2:
1612 formats_spec[spec[0]] = {
1613 'resolution': spec[1],
1614 'width': int_or_none(width_height[0]),
1615 'height': int_or_none(width_height[1]),
1616 }
c9afb51c 1617 formats = []
00fe14fc 1618 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1619 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1620 if 'itag' not in url_data or 'url' not in url_data:
1621 continue
1622 format_id = url_data['itag'][0]
1623 url = url_data['url'][0]
1624
1625 if 'sig' in url_data:
1626 url += '&signature=' + url_data['sig'][0]
1627 elif 's' in url_data:
1628 encrypted_sig = url_data['s'][0]
6449cd80 1629 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
201e9eaa 1630
beb95e77 1631 jsplayer_url_json = self._search_regex(
6449cd80
PH
1632 ASSETS_RE,
1633 embed_webpage if age_gate else video_webpage,
1634 'JS player URL (1)', default=None)
1635 if not jsplayer_url_json and not age_gate:
1636 # We need the embed website after all
1637 if embed_webpage is None:
1638 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1639 embed_webpage = self._download_webpage(
1640 embed_url, video_id, 'Downloading embed webpage')
1641 jsplayer_url_json = self._search_regex(
1642 ASSETS_RE, embed_webpage, 'JS player URL')
1643
beb95e77 1644 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1645 if player_url is None:
1646 player_url_json = self._search_regex(
1647 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1648 video_webpage, 'age gate player URL')
201e9eaa
PH
1649 player_url = json.loads(player_url_json)
1650
1651 if self._downloader.params.get('verbose'):
cf010131 1652 if player_url is None:
201e9eaa
PH
1653 player_version = 'unknown'
1654 player_desc = 'unknown'
1655 else:
1656 if player_url.endswith('swf'):
1657 player_version = self._search_regex(
1658 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1659 'flash player', fatal=False)
201e9eaa 1660 player_desc = 'flash player %s' % player_version
cf010131 1661 else:
201e9eaa 1662 player_version = self._search_regex(
b62985a9
YCH
1663 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1664 r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
201e9eaa
PH
1665 player_url,
1666 'html5 player', fatal=False)
78caa52a 1667 player_desc = 'html5 player %s' % player_version
201e9eaa 1668
60064c53 1669 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1670 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1671 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1672
1673 signature = self._decrypt_signature(
1674 encrypted_sig, video_id, player_url, age_gate)
1675 url += '&signature=' + signature
1676 if 'ratebypass' not in url:
1677 url += '&ratebypass=yes'
c9afb51c 1678
94278f72
YCH
1679 dct = {
1680 'format_id': format_id,
1681 'url': url,
1682 'player_url': player_url,
1683 }
1684 if format_id in self._formats:
1685 dct.update(self._formats[format_id])
3318832e 1686 if format_id in formats_spec:
1687 dct.update(formats_spec[format_id])
94278f72 1688
aabc2be6
S
1689 # Some itags are not included in DASH manifest thus corresponding formats will
1690 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1691 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1692 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1693 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72
YCH
1694
1695 more_fields = {
c9afb51c 1696 'filesize': int_or_none(url_data.get('clen', [None])[0]),
aabc2be6 1697 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1698 'width': width,
1699 'height': height,
1700 'fps': int_or_none(url_data.get('fps', [None])[0]),
aabc2be6 1701 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
c9afb51c 1702 }
94278f72
YCH
1703 for key, value in more_fields.items():
1704 if value:
1705 dct[key] = value
aabc2be6
S
1706 type_ = url_data.get('type', [None])[0]
1707 if type_:
1708 type_split = type_.split(';')
1709 kind_ext = type_split[0].split('/')
1710 if len(kind_ext) == 2:
94278f72
YCH
1711 kind, _ = kind_ext
1712 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1713 if kind in ('audio', 'video'):
1714 codecs = None
1715 for mobj in re.finditer(
1716 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1717 if mobj.group('key') == 'codecs':
1718 codecs = mobj.group('val')
1719 break
1720 if codecs:
6310acf5 1721 dct.update(parse_codecs(codecs))
aabc2be6 1722 formats.append(dct)
1d043b93
JMF
1723 elif video_info.get('hlsvp'):
1724 manifest_url = video_info['hlsvp'][0]
89beedd3
RA
1725 formats = []
1726 m3u8_formats = self._extract_m3u8_formats(
1727 manifest_url, video_id, 'mp4', fatal=False)
1728 for a_format in m3u8_formats:
1729 itag = self._search_regex(
1730 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
1731 if itag:
1732 a_format['format_id'] = itag
1733 if itag in self._formats:
1734 dct = self._formats[itag].copy()
1735 dct.update(a_format)
1736 a_format = dct
1737 a_format['player_url'] = player_url
1738 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
049d71d8 1739 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
89beedd3 1740 formats.append(a_format)
c5e8d7af 1741 else:
8ceabd4d
S
1742 unavailable_message = self._html_search_regex(
1743 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1744 video_webpage, 'unavailable message', default=None)
1745 if unavailable_message:
1746 raise ExtractorError(unavailable_message, expected=True)
69ea8ca4 1747 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1748
dd27fd17 1749 # Look for the DASH manifest
203fb43f 1750 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 1751 dash_mpd_fatal = True
8ff648e4 1752 for mpd_url in dash_mpds:
d8d24a92 1753 dash_formats = {}
774e208f 1754 try:
05d0d131
YCH
1755 def decrypt_sig(mobj):
1756 s = mobj.group(1)
1757 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1758 return '/signature/%s' % dec_s
1759
8ff648e4 1760 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 1761
8ff648e4 1762 for df in self._extract_mpd_formats(
1763 mpd_url, video_id, fatal=dash_mpd_fatal,
1764 formats_dict=self._formats):
d8d24a92
S
1765 # Do not overwrite DASH format found in some previous DASH manifest
1766 if df['format_id'] not in dash_formats:
1767 dash_formats[df['format_id']] = df
77c6fb5b
S
1768 # Additional DASH manifests may end up in HTTP Error 403 therefore
1769 # allow them to fail without bug report message if we already have
1770 # some DASH manifest succeeded. This is temporary workaround to reduce
1771 # burst of bug reports until we figure out the reason and whether it
1772 # can be fixed at all.
1773 dash_mpd_fatal = False
774e208f
PH
1774 except (ExtractorError, KeyError) as e:
1775 self.report_warning(
1776 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 1777 if dash_formats:
04b3b3df
JMF
1778 # Remove the formats we found through non-DASH, they
1779 # contain less info and it can be wrong, because we use
1780 # fixed values (for example the resolution). See
1781 # https://github.com/rg3/youtube-dl/issues/5774 for an
1782 # example.
d80265cc 1783 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 1784 formats.extend(dash_formats.values())
d80044c2 1785
6271f1ca
PH
1786 # Check for malformed aspect ratio
1787 stretched_m = re.search(
1788 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1789 video_webpage)
1790 if stretched_m:
313dfc45
LL
1791 w = float(stretched_m.group('w'))
1792 h = float(stretched_m.group('h'))
5faf9fed
S
1793 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1794 # We will only process correct ratios.
313dfc45 1795 if w > 0 and h > 0:
41f24c32 1796 ratio = w / h
313dfc45
LL
1797 for f in formats:
1798 if f.get('vcodec') != 'none':
1799 f['stretched_ratio'] = ratio
6271f1ca 1800
4bcc7bd1 1801 self._sort_formats(formats)
4ea3be0a 1802
d77ab8e2
S
1803 self.mark_watched(video_id, video_info)
1804
4ea3be0a 1805 return {
8bcc8756
JW
1806 'id': video_id,
1807 'uploader': video_uploader,
1808 'uploader_id': video_uploader_id,
fd050249 1809 'uploader_url': video_uploader_url,
8bcc8756 1810 'upload_date': upload_date,
7caf9830 1811 'license': video_license,
0cb58b02 1812 'creator': video_creator,
8bcc8756 1813 'title': video_title,
0cb58b02 1814 'alt_title': video_alt_title,
8bcc8756
JW
1815 'thumbnail': video_thumbnail,
1816 'description': video_description,
1817 'categories': video_categories,
000b6b5a 1818 'tags': video_tags,
8bcc8756 1819 'subtitles': video_subtitles,
360e1ca5 1820 'automatic_captions': automatic_captions,
8bcc8756
JW
1821 'duration': video_duration,
1822 'age_limit': 18 if age_gate else 0,
1823 'annotations': video_annotations,
9cafc3fd 1824 'chapters': chapters,
7e8c0af0 1825 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 1826 'view_count': view_count,
4ea3be0a 1827 'like_count': like_count,
1828 'dislike_count': dislike_count,
2d30521a 1829 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 1830 'formats': formats,
2fe1ff85 1831 'is_live': is_live,
7c80519c 1832 'start_time': start_time,
297a564b 1833 'end_time': end_time,
12afdc2a
S
1834 'series': series,
1835 'season_number': season_number,
1836 'episode_number': episode_number,
4ea3be0a 1837 }
c5e8d7af 1838
5f6a1245 1839
40805306 1840class YoutubeSharedVideoIE(InfoExtractor):
fd8c8c7d 1841 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
40805306
YCH
1842 IE_NAME = 'youtube:shared'
1843
1844 _TEST = {
1845 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1846 'info_dict': {
1847 'id': 'uPDB5I9wfp8',
1848 'ext': 'webm',
1849 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1850 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1851 'upload_date': '20160219',
1852 'uploader': 'Pocoyo - Português (BR)',
1853 'uploader_id': 'PocoyoBrazil',
1854 },
1855 'add_ie': ['Youtube'],
1856 'params': {
1857 # There are already too many Youtube downloads
1858 'skip_download': True,
1859 },
1860 }
1861
1862 def _real_extract(self, url):
1863 video_id = self._match_id(url)
1864
1865 webpage = self._download_webpage(url, video_id)
1866
1867 real_video_id = self._html_search_meta(
1868 'videoId', webpage, 'YouTube video id', fatal=True)
1869
1870 return self.url_result(real_video_id, YoutubeIE.ie_key())
1871
1872
8e7aad20 1873class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 1874 IE_DESC = 'YouTube.com playlists'
d67cc9fa 1875 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
1876 (?:https?://)?
1877 (?:\w+\.)?
c5e8d7af 1878 (?:
feaa5ad7
S
1879 youtube\.com/
1880 (?:
87dadd45 1881 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
feaa5ad7
S
1882 \? (?:.*?[&;])*? (?:p|a|list)=
1883 | p/
1884 )|
1885 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
c5e8d7af 1886 )
d67cc9fa 1887 (
a6857510 1888 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
5f6a1245 1889 # Top tracks, they can also include dots
d67cc9fa
JMF
1890 |(?:MC)[\w\.]*
1891 )
c5e8d7af
PH
1892 .*
1893 |
d0ba5587
S
1894 (%(playlist_id)s)
1895 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
c867adc6 1896 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
648e6a1f 1897 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 1898 IE_NAME = 'youtube:playlist'
81127aa5
PH
1899 _TESTS = [{
1900 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1901 'info_dict': {
1902 'title': 'ytdl test PL',
a1cf99d0 1903 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
1904 },
1905 'playlist_count': 3,
9291475f
PH
1906 }, {
1907 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1908 'info_dict': {
acf757f4 1909 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
1910 'title': 'YDL_Empty_List',
1911 },
1912 'playlist_count': 0,
4201ba13 1913 'skip': 'This playlist is private',
9291475f
PH
1914 }, {
1915 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1916 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1917 'info_dict': {
1918 'title': '29C3: Not my department',
acf757f4 1919 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
1920 },
1921 'playlist_count': 95,
1922 }, {
1923 'note': 'issue #673',
1924 'url': 'PLBB231211A4F62143',
1925 'info_dict': {
f46a8702 1926 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 1927 'id': 'PLBB231211A4F62143',
9291475f
PH
1928 },
1929 'playlist_mincount': 26,
1930 }, {
1931 'note': 'Large playlist',
1932 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1933 'info_dict': {
1934 'title': 'Uploads from Cauchemar',
acf757f4 1935 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
1936 },
1937 'playlist_mincount': 799,
1938 }, {
1939 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1940 'info_dict': {
1941 'title': 'YDL_safe_search',
acf757f4 1942 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
1943 },
1944 'playlist_count': 2,
4201ba13 1945 'skip': 'This playlist is private',
ac7553d0
PH
1946 }, {
1947 'note': 'embedded',
2d3d2997 1948 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0
PH
1949 'playlist_count': 4,
1950 'info_dict': {
1951 'title': 'JODA15',
acf757f4 1952 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 1953 }
87dadd45
S
1954 }, {
1955 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1956 'playlist_mincount': 485,
1957 'info_dict': {
1958 'title': '2017 華語最新單曲 (2/24更新)',
1959 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1960 }
6b08cdf6
PH
1961 }, {
1962 'note': 'Embedded SWF player',
2d3d2997 1963 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
6b08cdf6
PH
1964 'playlist_count': 4,
1965 'info_dict': {
1966 'title': 'JODA7',
acf757f4 1967 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 1968 }
4b7df0d3
JMF
1969 }, {
1970 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1971 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1972 'info_dict': {
acf757f4
PH
1973 'title': 'Uploads from Interstellar Movie',
1974 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 1975 },
481cc733 1976 'playlist_mincount': 21,
dacb3a86
S
1977 }, {
1978 # Playlist URL that does not actually serve a playlist
1979 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1980 'info_dict': {
1981 'id': 'FqZTN594JQw',
1982 'ext': 'webm',
1983 'title': "Smiley's People 01 detective, Adventure Series, Action",
1984 'uploader': 'STREEM',
1985 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 1986 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
1987 'upload_date': '20150526',
1988 'license': 'Standard YouTube License',
1989 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1990 'categories': ['People & Blogs'],
1991 'tags': list,
1992 'like_count': int,
1993 'dislike_count': int,
1994 },
1995 'params': {
1996 'skip_download': True,
1997 },
1998 'add_ie': [YoutubeIE.ie_key()],
481cc733
S
1999 }, {
2000 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2001 'info_dict': {
2002 'id': 'yeWKywCrFtk',
2003 'ext': 'mp4',
2004 'title': 'Small Scale Baler and Braiding Rugs',
2005 'uploader': 'Backus-Page House Museum',
2006 'uploader_id': 'backuspagemuseum',
ec85ded8 2007 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
481cc733
S
2008 'upload_date': '20161008',
2009 'license': 'Standard YouTube License',
2010 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2011 'categories': ['Nonprofits & Activism'],
2012 'tags': list,
2013 'like_count': int,
2014 'dislike_count': int,
2015 },
2016 'params': {
2017 'noplaylist': True,
2018 'skip_download': True,
2019 },
feaa5ad7
S
2020 }, {
2021 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2022 'only_matching': True,
a6857510
S
2023 }, {
2024 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2025 'only_matching': True,
81127aa5 2026 }]
c5e8d7af 2027
880e1c52
JMF
2028 def _real_initialize(self):
2029 self._login()
2030
652cdaa2 2031 def _extract_mix(self, playlist_id):
99209c29 2032 # The mixes are generated from a single video
652cdaa2 2033 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
2034 ids = []
2035 last_id = playlist_id[-11:]
2036 for n in itertools.count(1):
2037 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2038 webpage = self._download_webpage(
2039 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2040 new_ids = orderedSet(re.findall(
2041 r'''(?xs)data-video-username=".*?".*?
2042 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
2043 webpage))
2044 # Fetch new pages until all the videos are repeated, it seems that
2045 # there are always 51 unique videos.
2046 new_ids = [_id for _id in new_ids if _id not in ids]
2047 if not new_ids:
2048 break
2049 ids.extend(new_ids)
2050 last_id = ids[-1]
2051
2052 url_results = self._ids_to_results(ids)
2053
bc2f773b 2054 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
2055 title_span = (
2056 search_title('playlist-title') or
2057 search_title('title long-title') or
2058 search_title('title'))
76d1700b 2059 title = clean_html(title_span)
652cdaa2
JMF
2060
2061 return self.playlist_result(url_results, playlist_id, title)
2062
448830ce 2063 def _extract_playlist(self, playlist_id):
dbb94fb0
S
2064 url = self._TEMPLATE_URL % playlist_id
2065 page = self._download_webpage(url, playlist_id)
dbb94fb0 2066
8bc0800d
G
2067 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2068 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
39b62db1
YCH
2069 match = match.strip()
2070 # Check if the playlist exists or is private
4201ba13
S
2071 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2072 if mobj:
2073 reason = mobj.group('reason')
2074 message = 'This playlist %s' % reason
2075 if 'private' in reason:
2076 message += ', use --username or --netrc to access it'
2077 message += '.'
2078 raise ExtractorError(message, expected=True)
39b62db1
YCH
2079 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2080 raise ExtractorError(
2081 'Invalid parameters. Maybe URL is incorrect.',
2082 expected=True)
2083 elif re.match(r'[^<]*Choose your language[^<]*', match):
2084 continue
2085 else:
2086 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 2087
dbb94fb0 2088 playlist_title = self._html_search_regex(
63b4295d 2089 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
dacb3a86 2090 page, 'title', default=None)
c5e8d7af 2091
dacb3a86
S
2092 has_videos = True
2093
2094 if not playlist_title:
2095 try:
2096 # Some playlist URLs don't actually serve a playlist (e.g.
2097 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2098 next(self._entries(page, playlist_id))
2099 except StopIteration:
2100 has_videos = False
2101
2102 return has_videos, self.playlist_result(
2103 self._entries(page, playlist_id), playlist_id, playlist_title)
c5e8d7af 2104
ebf1b291 2105 def _check_download_just_video(self, url, playlist_id):
448830ce
S
2106 # Check if it's a video-specific URL
2107 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
481cc733 2108 video_id = query_dict.get('v', [None])[0] or self._search_regex(
87dadd45 2109 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
481cc733
S
2110 'video id', default=None)
2111 if video_id:
448830ce
S
2112 if self._downloader.params.get('noplaylist'):
2113 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
dacb3a86 2114 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce
S
2115 else:
2116 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
dacb3a86
S
2117 return video_id, None
2118 return None, None
448830ce 2119
ebf1b291
S
2120 def _real_extract(self, url):
2121 # Extract playlist id
2122 mobj = re.match(self._VALID_URL, url)
2123 if mobj is None:
2124 raise ExtractorError('Invalid URL: %s' % url)
2125 playlist_id = mobj.group(1) or mobj.group(2)
2126
dacb3a86 2127 video_id, video = self._check_download_just_video(url, playlist_id)
ebf1b291
S
2128 if video:
2129 return video
2130
466a6145 2131 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
2132 # Mixes require a custom extraction process
2133 return self._extract_mix(playlist_id)
2134
dacb3a86
S
2135 has_videos, playlist = self._extract_playlist(playlist_id)
2136 if has_videos or not video_id:
2137 return playlist
2138
2139 # Some playlist URLs don't actually serve a playlist (see
2140 # https://github.com/rg3/youtube-dl/issues/10537).
2141 # Fallback to plain video extraction if there is a video id
2142 # along with playlist id.
2143 return self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce 2144
c5e8d7af 2145
648e6a1f 2146class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2147 IE_DESC = 'YouTube.com channels'
9ff67727 2148 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 2149 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 2150 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 2151 IE_NAME = 'youtube:channel'
cdc628a4
PH
2152 _TESTS = [{
2153 'note': 'paginated channel',
2154 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2155 'playlist_mincount': 91,
acf757f4 2156 'info_dict': {
9170ca5b
JMF
2157 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2158 'title': 'Uploads from lex will',
acf757f4 2159 }
5c43afd4
JMF
2160 }, {
2161 'note': 'Age restricted channel',
2162 # from https://www.youtube.com/user/DeusExOfficial
2163 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2164 'playlist_mincount': 64,
2165 'info_dict': {
2166 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2167 'title': 'Uploads from Deus Ex',
2168 },
cdc628a4 2169 }]
c5e8d7af 2170
e462474e
S
2171 @classmethod
2172 def suitable(cls, url):
f07e276a
S
2173 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2174 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 2175
9558dcec
S
2176 def _build_template_url(self, url, channel_id):
2177 return self._TEMPLATE_URL % channel_id
2178
c5e8d7af 2179 def _real_extract(self, url):
9ff67727 2180 channel_id = self._match_id(url)
c5e8d7af 2181
9558dcec 2182 url = self._build_template_url(url, channel_id)
386bdfa6
S
2183
2184 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2185 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2186 # otherwise fallback on channel by page extraction
2187 channel_page = self._download_webpage(
2188 url + '?view=57', channel_id,
2189 'Downloading channel page', fatal=False)
2b3c2546
PH
2190 if channel_page is False:
2191 channel_playlist_id = False
2192 else:
2193 channel_playlist_id = self._html_search_meta(
2194 'channelId', channel_page, 'channel id', default=None)
2195 if not channel_playlist_id:
73c4ac2c
S
2196 channel_url = self._html_search_meta(
2197 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2198 channel_page, 'channel url', default=None)
2199 if channel_url:
2200 channel_playlist_id = self._search_regex(
2201 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2202 channel_url, 'channel id', default=None)
386bdfa6
S
2203 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2204 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2205 return self.url_result(
2206 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2207
60bf45c8 2208 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2209 autogenerated = re.search(r'''(?x)
2210 class="[^"]*?(?:
2211 channel-header-autogenerated-label|
2212 yt-channel-title-autogenerated
2213 )[^"]*"''', channel_page) is not None
c5e8d7af 2214
b9643eed
JMF
2215 if autogenerated:
2216 # The videos are contained in a single page
2217 # the ajax pages can't be used, they are empty
b82f815f 2218 entries = [
fb69240c
S
2219 self.url_result(
2220 video_id, 'Youtube', video_id=video_id,
2221 video_title=video_title)
8f02ad4f 2222 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2223 return self.playlist_result(entries, channel_id)
2224
73c4ac2c
S
2225 try:
2226 next(self._entries(channel_page, channel_id))
2227 except StopIteration:
2228 alert_message = self._html_search_regex(
2229 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2230 channel_page, 'alert', default=None, group='alert')
2231 if alert_message:
2232 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2233
648e6a1f 2234 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2235
2236
eb0f3e7e 2237class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2238 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
9558dcec
S
2239 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
2240 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
78caa52a 2241 IE_NAME = 'youtube:user'
c5e8d7af 2242
cdc628a4
PH
2243 _TESTS = [{
2244 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2245 'playlist_mincount': 320,
2246 'info_dict': {
73c4ac2c
S
2247 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2248 'title': 'Uploads from The Linux Foundation',
cdc628a4 2249 }
9558dcec
S
2250 }, {
2251 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2252 # but not https://www.youtube.com/user/12minuteathlete/videos
2253 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2254 'playlist_mincount': 249,
2255 'info_dict': {
2256 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2257 'title': 'Uploads from 12 Minute Athlete',
2258 }
cdc628a4
PH
2259 }, {
2260 'url': 'ytuser:phihag',
2261 'only_matching': True,
daa0df9e
YCH
2262 }, {
2263 'url': 'https://www.youtube.com/c/gametrailers',
2264 'only_matching': True,
9558dcec
S
2265 }, {
2266 'url': 'https://www.youtube.com/gametrailers',
2267 'only_matching': True,
73c4ac2c 2268 }, {
0e879f43 2269 # This channel is not available, geo restricted to JP
73c4ac2c
S
2270 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2271 'only_matching': True,
cdc628a4
PH
2272 }]
2273
e3ea4790 2274 @classmethod
f4b05232 2275 def suitable(cls, url):
e3ea4790
JMF
2276 # Don't return True if the url can be extracted with other youtube
2277 # extractor, the regex would is too permissive and it would match.
f3a58d46 2278 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2279 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2280 return False
2281 else:
2282 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2283
9558dcec
S
2284 def _build_template_url(self, url, channel_id):
2285 mobj = re.match(self._VALID_URL, url)
2286 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2287
b05654f0 2288
f07e276a
S
2289class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2290 IE_DESC = 'YouTube.com live streams'
073d5bf5 2291 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
f07e276a
S
2292 IE_NAME = 'youtube:live'
2293
2294 _TESTS = [{
2d3d2997 2295 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
f07e276a
S
2296 'info_dict': {
2297 'id': 'a48o2S1cPoo',
2298 'ext': 'mp4',
2299 'title': 'The Young Turks - Live Main Show',
2300 'uploader': 'The Young Turks',
2301 'uploader_id': 'TheYoungTurks',
ec85ded8 2302 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
f07e276a
S
2303 'upload_date': '20150715',
2304 'license': 'Standard YouTube License',
2305 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2306 'categories': ['News & Politics'],
2307 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2308 'like_count': int,
2309 'dislike_count': int,
2310 },
2311 'params': {
2312 'skip_download': True,
2313 },
2314 }, {
2d3d2997 2315 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
f07e276a 2316 'only_matching': True,
c1b2a085
S
2317 }, {
2318 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2319 'only_matching': True,
073d5bf5
S
2320 }, {
2321 'url': 'https://www.youtube.com/TheYoungTurks/live',
2322 'only_matching': True,
f07e276a
S
2323 }]
2324
2325 def _real_extract(self, url):
2326 mobj = re.match(self._VALID_URL, url)
2327 channel_id = mobj.group('id')
2328 base_url = mobj.group('base_url')
2329 webpage = self._download_webpage(url, channel_id, fatal=False)
2330 if webpage:
2331 page_type = self._og_search_property(
2332 'type', webpage, 'page type', default=None)
2333 video_id = self._html_search_meta(
2334 'videoId', webpage, 'video id', default=None)
2335 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2336 return self.url_result(video_id, YoutubeIE.ie_key())
2337 return self.url_result(base_url)
2338
2339
e462474e
S
2340class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2341 IE_DESC = 'YouTube.com user/channel playlists'
2342 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2343 IE_NAME = 'youtube:playlists'
0c148415 2344
e568c223 2345 _TESTS = [{
2d3d2997 2346 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
0c148415
S
2347 'playlist_mincount': 4,
2348 'info_dict': {
2349 'id': 'ThirstForScience',
2350 'title': 'Thirst for Science',
2351 },
e568c223
S
2352 }, {
2353 # with "Load more" button
2d3d2997 2354 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
e568c223
S
2355 'playlist_mincount': 70,
2356 'info_dict': {
2357 'id': 'igorkle1',
2358 'title': 'Игорь Клейнер',
2359 },
e462474e
S
2360 }, {
2361 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2362 'playlist_mincount': 17,
2363 'info_dict': {
2364 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2365 'title': 'Chem Player',
2366 },
e568c223 2367 }]
0c148415
S
2368
2369
b4c08069 2370class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
78caa52a 2371 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2372 # there doesn't appear to be a real limit, for example if you search for
2373 # 'python' you get more than 8.000.000 results
2374 _MAX_RESULTS = float('inf')
78caa52a 2375 IE_NAME = 'youtube:search'
b05654f0 2376 _SEARCH_KEY = 'ytsearch'
b4c08069 2377 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2378 _TESTS = []
b05654f0 2379
b05654f0
PH
2380 def _get_n_results(self, query, n):
2381 """Get a specified number of results for a query"""
2382
b4c08069 2383 videos = []
b05654f0
PH
2384 limit = n
2385
a22b2fd1
YCH
2386 url_query = {
2387 'search_query': query.encode('utf-8'),
2388 }
2389 url_query.update(self._EXTRA_QUERY_ARGS)
2390 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2391
b4c08069 2392 for pagenum in itertools.count(1):
b4c08069 2393 data = self._download_json(
69ea8ca4 2394 result_url, video_id='query "%s"' % query,
b4c08069 2395 note='Downloading page %s' % pagenum,
a22b2fd1
YCH
2396 errnote='Unable to download API page',
2397 query={'spf': 'navigate'})
b4c08069 2398 html_content = data[1]['body']['content']
7cc3570e 2399
b4c08069 2400 if 'class="search-message' in html_content:
07ad22b8 2401 raise ExtractorError(
78caa52a 2402 '[youtube] No video results', expected=True)
b05654f0 2403
b4c08069
JMF
2404 new_videos = self._ids_to_results(orderedSet(re.findall(
2405 r'href="/watch\?v=(.{11})', html_content)))
2406 videos += new_videos
2407 if not new_videos or len(videos) > limit:
2408 break
a22b2fd1
YCH
2409 next_link = self._html_search_regex(
2410 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2411 html_content, 'next link', default=None)
2412 if next_link is None:
2413 break
2414 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
b05654f0 2415
b4c08069
JMF
2416 if len(videos) > n:
2417 videos = videos[:n]
b05654f0 2418 return self.playlist_result(videos, query)
75dff0ee 2419
c9ae7b95 2420
a3dd9248 2421class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2422 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2423 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2424 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2425 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2426
c9ae7b95 2427
175c2e9e 2428class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
78caa52a
PH
2429 IE_DESC = 'YouTube.com search URLs'
2430 IE_NAME = 'youtube:search_url'
d2c1f79f 2431 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
175c2e9e 2432 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
cdc628a4
PH
2433 _TESTS = [{
2434 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2435 'playlist_mincount': 5,
2436 'info_dict': {
2437 'title': 'youtube-dl test video',
2438 }
d2c1f79f
S
2439 }, {
2440 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2441 'only_matching': True,
cdc628a4 2442 }]
c9ae7b95
PH
2443
2444 def _real_extract(self, url):
2445 mobj = re.match(self._VALID_URL, url)
7fd002c0 2446 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2447 webpage = self._download_webpage(url, query)
175c2e9e 2448 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2449
2450
136dadde 2451class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2452 IE_DESC = 'YouTube.com (multi-season) shows'
92519402 2453 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2454 IE_NAME = 'youtube:show'
cdc628a4 2455 _TESTS = [{
4003bd82 2456 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2457 'playlist_mincount': 5,
cdc628a4
PH
2458 'info_dict': {
2459 'id': 'airdisasters',
2460 'title': 'Air Disasters',
2461 }
2462 }]
75dff0ee
JMF
2463
2464 def _real_extract(self, url):
136dadde
S
2465 playlist_id = self._match_id(url)
2466 return super(YoutubeShowIE, self)._real_extract(
2467 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2468
2469
b2e8bc1b 2470class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2471 """
25f14e9f 2472 Base class for feed extractors
d7ae0639
JMF
2473 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2474 """
b2e8bc1b 2475 _LOGIN_REQUIRED = True
d7ae0639
JMF
2476
2477 @property
2478 def IE_NAME(self):
78caa52a 2479 return 'youtube:%s' % self._FEED_NAME
04cc9617 2480
81f0259b 2481 def _real_initialize(self):
b2e8bc1b 2482 self._login()
81f0259b 2483
04cc9617 2484 def _real_extract(self, url):
25f14e9f
S
2485 page = self._download_webpage(
2486 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2bc43303
JMF
2487
2488 # The extraction process is the same as for playlists, but the regex
2489 # for the video ids doesn't contain an index
2490 ids = []
2491 more_widget_html = content_html = page
2bc43303
JMF
2492 for page_num in itertools.count(1):
2493 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2494
2495 # 'recommended' feed has infinite 'load more' and each new portion spins
2496 # the same videos in (sometimes) slightly different order, so we'll check
2497 # for unicity and break when portion has no new videos
2498 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2499 if not new_ids:
2500 break
2501
2bc43303
JMF
2502 ids.extend(new_ids)
2503
2504 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2505 if not mobj:
2506 break
2507
2508 more = self._download_json(
25f14e9f 2509 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2510 'Downloading page #%s' % page_num,
2511 transform_source=uppercase_escape)
2512 content_html = more['content_html']
2513 more_widget_html = more['load_more_widget_html']
2514
25f14e9f
S
2515 return self.playlist_result(
2516 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2517
2518
2519class YoutubeWatchLaterIE(YoutubePlaylistIE):
2520 IE_NAME = 'youtube:watchlater'
2521 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
92519402 2522 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2523
bc7a9cd8
S
2524 _TESTS = [{
2525 'url': 'https://www.youtube.com/playlist?list=WL',
2526 'only_matching': True,
2527 }, {
2528 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2529 'only_matching': True,
2530 }]
25f14e9f
S
2531
2532 def _real_extract(self, url):
7e5dc339 2533 _, video = self._check_download_just_video(url, 'WL')
ebf1b291
S
2534 if video:
2535 return video
dacb3a86
S
2536 _, playlist = self._extract_playlist('WL')
2537 return playlist
f459d170 2538
5f6a1245 2539
c626a3d9 2540class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2541 IE_NAME = 'youtube:favorites'
f3a34072 2542 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
92519402 2543 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2544 _LOGIN_REQUIRED = True
2545
2546 def _real_extract(self, url):
2547 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2548 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2549 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2550
2551
25f14e9f
S
2552class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2553 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
92519402 2554 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
25f14e9f
S
2555 _FEED_NAME = 'recommended'
2556 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2557
1ed5b5c9 2558
25f14e9f
S
2559class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2560 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
92519402 2561 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
25f14e9f
S
2562 _FEED_NAME = 'subscriptions'
2563 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2564
1ed5b5c9 2565
25f14e9f
S
2566class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2567 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
92519402 2568 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
25f14e9f
S
2569 _FEED_NAME = 'history'
2570 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2571
2572
15870e90
PH
2573class YoutubeTruncatedURLIE(InfoExtractor):
2574 IE_NAME = 'youtube:truncated_url'
2575 IE_DESC = False # Do not list
975d35db 2576 _VALID_URL = r'''(?x)
b95aab84
PH
2577 (?:https?://)?
2578 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2579 (?:watch\?(?:
c4808c60 2580 feature=[a-z_]+|
b95aab84
PH
2581 annotation_id=annotation_[^&]+|
2582 x-yt-cl=[0-9]+|
c1708b89 2583 hl=[^&]*|
287be8c6 2584 t=[0-9]+
b95aab84
PH
2585 )?
2586 |
2587 attribution_link\?a=[^&]+
2588 )
2589 $
975d35db 2590 '''
15870e90 2591
c4808c60 2592 _TESTS = [{
2d3d2997 2593 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 2594 'only_matching': True,
dc2fc736 2595 }, {
2d3d2997 2596 'url': 'https://www.youtube.com/watch?',
dc2fc736 2597 'only_matching': True,
b95aab84
PH
2598 }, {
2599 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2600 'only_matching': True,
2601 }, {
2602 'url': 'https://www.youtube.com/watch?feature=foo',
2603 'only_matching': True,
c1708b89
PH
2604 }, {
2605 'url': 'https://www.youtube.com/watch?hl=en-GB',
2606 'only_matching': True,
287be8c6
PH
2607 }, {
2608 'url': 'https://www.youtube.com/watch?t=2372',
2609 'only_matching': True,
c4808c60
PH
2610 }]
2611
15870e90
PH
2612 def _real_extract(self, url):
2613 raise ExtractorError(
78caa52a
PH
2614 'Did you forget to quote the URL? Remember that & is a meta '
2615 'character in most shells, so you want to put the URL in quotes, '
2616 'like youtube-dl '
2d3d2997 2617 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
78caa52a 2618 ' or simply youtube-dl BaW_jenozKc .',
15870e90 2619 expected=True)
772fd5cc
PH
2620
2621
2622class YoutubeTruncatedIDIE(InfoExtractor):
2623 IE_NAME = 'youtube:truncated_id'
2624 IE_DESC = False # Do not list
b95aab84 2625 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
2626
2627 _TESTS = [{
2628 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2629 'only_matching': True,
2630 }]
2631
2632 def _real_extract(self, url):
2633 video_id = self._match_id(url)
2634 raise ExtractorError(
2635 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
2636 expected=True)