]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[dailymotion] Raise GeoRestrictedError
[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,
af214c3a 50 ISO3166Utils,
c5e8d7af
PH
51)
52
5f6a1245 53
de7f3446 54class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b
JMF
55 """Provide base functions for Youtube extractors"""
56 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
9303ce3e 57 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
e298d3a0 58 _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
b2e8bc1b
JMF
59 _NETRC_MACHINE = 'youtube'
60 # If True it will raise an error if no login info is provided
61 _LOGIN_REQUIRED = False
62
b2e8bc1b 63 def _set_language(self):
810fb84d
PH
64 self._set_cookie(
65 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
42939b61 66 # YouTube sets the expire time to about two months
810fb84d 67 expire_time=time.time() + 2 * 30 * 24 * 3600)
b2e8bc1b 68
25f14e9f
S
69 def _ids_to_results(self, ids):
70 return [
71 self.url_result(vid_id, 'Youtube', video_id=vid_id)
72 for vid_id in ids]
73
b2e8bc1b 74 def _login(self):
83317f69 75 """
76 Attempt to log in to YouTube.
77 True is returned if successful or skipped.
78 False is returned if login failed.
79
80 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
81 """
b2e8bc1b
JMF
82 (username, password) = self._get_login_info()
83 # No authentication to be performed
84 if username is None:
85 if self._LOGIN_REQUIRED:
69ea8ca4 86 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
83317f69 87 return True
b2e8bc1b 88
7cc3570e
PH
89 login_page = self._download_webpage(
90 self._LOGIN_URL, None,
69ea8ca4
PH
91 note='Downloading login page',
92 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
93 if login_page is False:
94 return
b2e8bc1b 95
1212e997 96 login_form = self._hidden_inputs(login_page)
c5e8d7af 97
1212e997 98 login_form.update({
05bddcc5 99 'checkConnection': 'youtube',
8bcc8756 100 'Email': username,
8bcc8756 101 'Passwd': password,
1212e997 102 })
83317f69 103
7cc3570e 104 login_results = self._download_webpage(
e298d3a0
S
105 self._PASSWORD_CHALLENGE_URL, None,
106 note='Logging in', errnote='unable to log in', fatal=False,
1212e997 107 data=urlencode_postdata(login_form))
7cc3570e
PH
108 if login_results is False:
109 return False
83317f69 110
494ab6db
S
111 error_msg = self._html_search_regex(
112 r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
113 login_results, 'error message', default=None)
114 if error_msg:
115 raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
116
83317f69 117 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
69ea8ca4 118 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
83317f69 119
120 # Two-Factor
121 # TODO add SMS and phone call support - these require making a request and then prompting the user
122
e9fb6a4b 123 if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
041bc3ad 124 tfa_code = self._get_tfa_info('2-step verification code')
83317f69 125
041bc3ad
S
126 if not tfa_code:
127 self._downloader.report_warning(
128 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
129 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
83317f69 130 return False
131
041bc3ad
S
132 tfa_code = remove_start(tfa_code, 'G-')
133
134 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
135
136 tfa_form_strs.update({
9303ce3e 137 'Pin': tfa_code,
138 'TrustDevice': 'on',
041bc3ad
S
139 })
140
6e6bc8da 141 tfa_data = urlencode_postdata(tfa_form_strs)
83317f69 142
5c2266df 143 tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
83317f69 144 tfa_results = self._download_webpage(
145 tfa_req, None,
69ea8ca4 146 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
83317f69 147
148 if tfa_results is False:
149 return False
150
e9fb6a4b 151 if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
041bc3ad 152 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
83317f69 153 return False
e9fb6a4b 154 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
69ea8ca4 155 self._downloader.report_warning('unable to log in - did the page structure change?')
83317f69 156 return False
157 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
69ea8ca4 158 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 159 return False
160
e9fb6a4b 161 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
69ea8ca4 162 self._downloader.report_warning('unable to log in: bad username or password')
b2e8bc1b
JMF
163 return False
164 return True
165
b2e8bc1b
JMF
166 def _real_initialize(self):
167 if self._downloader is None:
168 return
42939b61 169 self._set_language()
b2e8bc1b
JMF
170 if not self._login():
171 return
c5e8d7af 172
8377574c 173
8e7aad20 174class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
061a75ed 175 # Extract entries from page with "Load more" button
648e6a1f
S
176 def _entries(self, page, playlist_id):
177 more_widget_html = content_html = page
178 for page_num in itertools.count(1):
061a75ed
S
179 for entry in self._process_page(content_html):
180 yield entry
648e6a1f
S
181
182 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
183 if not mobj:
184 break
185
186 more = self._download_json(
187 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
188 'Downloading page #%s' % page_num,
189 transform_source=uppercase_escape)
190 content_html = more['content_html']
191 if not content_html.strip():
192 # Some webpages show a "Load more" button but they don't
193 # have more videos
194 break
195 more_widget_html = more['load_more_widget_html']
196
061a75ed
S
197
198class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
199 def _process_page(self, content):
200 for video_id, video_title in self.extract_videos_from_page(content):
201 yield self.url_result(video_id, 'Youtube', video_id, video_title)
202
648e6a1f
S
203 def extract_videos_from_page(self, page):
204 ids_in_page = []
205 titles_in_page = []
206 for mobj in re.finditer(self._VIDEO_RE, page):
207 # The link with index 0 is not the first video of the playlist (not sure if still actual)
208 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
209 continue
210 video_id = mobj.group('id')
211 video_title = unescapeHTML(mobj.group('title'))
212 if video_title:
213 video_title = video_title.strip()
214 try:
215 idx = ids_in_page.index(video_id)
216 if video_title and not titles_in_page[idx]:
217 titles_in_page[idx] = video_title
218 except ValueError:
219 ids_in_page.append(video_id)
220 titles_in_page.append(video_title)
221 return zip(ids_in_page, titles_in_page)
222
223
061a75ed
S
224class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
225 def _process_page(self, content):
6dee688e
S
226 for playlist_id in orderedSet(re.findall(
227 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
228 content)):
061a75ed
S
229 yield self.url_result(
230 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
231
0c148415
S
232 def _real_extract(self, url):
233 playlist_id = self._match_id(url)
234 webpage = self._download_webpage(url, playlist_id)
0c148415 235 title = self._og_search_title(webpage, fatal=False)
061a75ed 236 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
0c148415
S
237
238
360e1ca5 239class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 240 IE_DESC = 'YouTube.com'
cb7dfeea 241 _VALID_URL = r"""(?x)^
c5e8d7af 242 (
edb53e2d 243 (?:https?://|//) # http(s):// or protocol-independent URL
cb7dfeea 244 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
484aaeb2 245 (?:www\.)?deturl\.com/www\.youtube\.com/|
e70dc1d1 246 (?:www\.)?pwnyoutube\.com/|
f7000f3a 247 (?:www\.)?yourepeat\.com/|
e69ae5b9
JMF
248 tube\.majestyc\.net/|
249 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
c5e8d7af
PH
250 (?:.*?\#/)? # handle anchor (#/) redirect urls
251 (?: # the various things that can precede the ID:
ac7553d0 252 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 253 |(?: # or the v= param in all its forms
f7000f3a 254 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 255 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 256 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
257 v=
258 )
f4b05232 259 ))
cbaed4bb
S
260 |(?:
261 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
262 vid\.plus| # or vid.plus/xxxx
263 zwearz\.com/watch| # or zwearz.com/watch/xxxx
cbaed4bb 264 )/
edb53e2d 265 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 266 )
c5e8d7af 267 )? # all until now is optional -> you can pass the naked ID
8963d9c2 268 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
feaa5ad7 269 (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
c5e8d7af
PH
270 (?(1).+)? # if we found the ID, everything can follow
271 $"""
c5e8d7af 272 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
2c62dc26 273 _formats = {
c2d3cb4c 274 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
275 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
276 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
277 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
278 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
279 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
280 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
281 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 282 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 283 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
284 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
285 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
286 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
287 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
288 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 289 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 290 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
291 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 292
293
294 # 3D videos
c2d3cb4c 295 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
296 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
297 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
298 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 299 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
300 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
301 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 302
96fb5605 303 # Apple HTTP Live Streaming
11f12195 304 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 305 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
306 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
307 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
308 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
309 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 310 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
311 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
312
313 # DASH mp4 video
c2d3cb4c 314 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
315 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
316 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
317 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
318 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
319 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
320 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
8409b368 321 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
a6c2c244
YCH
322 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
323 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
324 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
325 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
836a086c 326
f6f1fc92 327 # Dash mp4 audio
c2d3cb4c 328 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
329 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
330 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
2c347352
S
331 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
332 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
605fd639
RA
333 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
334 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'preference': -50, 'container': 'm4a_dash'},
836a086c
AZ
335
336 # Dash webm
a6c2c244
YCH
337 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
338 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
339 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
340 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
341 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
342 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
343 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
344 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
345 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
346 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
347 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
348 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
349 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
350 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
351 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
4c6b4764 352 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
a6c2c244
YCH
353 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
354 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
355 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
356 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
357 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
358 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
2c62dc26
PH
359
360 # Dash webm audio
a6c2c244
YCH
361 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
362 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
ce6b9a2d 363
0857baad 364 # Dash webm audio with opus inside
a6c2c244
YCH
365 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
366 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
367 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
0857baad 368
ce6b9a2d
PH
369 # RTMP (unnamed)
370 '_rtmp': {'protocol': 'rtmp'},
c5e8d7af 371 }
23d17e4b 372 _SUBTITLE_FORMATS = ('ttml', 'vtt')
836a086c 373
78caa52a 374 IE_NAME = 'youtube'
2eb88d95
PH
375 _TESTS = [
376 {
2d3d2997 377 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
378 'info_dict': {
379 'id': 'BaW_jenozKc',
380 'ext': 'mp4',
381 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
382 'uploader': 'Philipp Hagemeister',
383 'uploader_id': 'phihag',
ec85ded8 384 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
4bc3a23e 385 'upload_date': '20121002',
7caf9830 386 'license': 'Standard YouTube License',
4bc3a23e
PH
387 '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 .',
388 'categories': ['Science & Technology'],
000b6b5a 389 'tags': ['youtube-dl'],
556dbe7f 390 'duration': 10,
3e7c1224
PH
391 'like_count': int,
392 'dislike_count': int,
7c80519c 393 'start_time': 1,
297a564b 394 'end_time': 9,
2eb88d95 395 }
0e853ca4 396 },
0e853ca4 397 {
2d3d2997 398 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
4bc3a23e
PH
399 'note': 'Test generic use_cipher_signature video (#897)',
400 'info_dict': {
401 'id': 'UxxajLWwzqY',
402 'ext': 'mp4',
403 'upload_date': '20120506',
404 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
0cb58b02 405 'alt_title': 'I Love It (feat. Charli XCX)',
7caf9830 406 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
000b6b5a
S
407 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
408 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
409 'iconic ep', 'iconic', 'love', 'it'],
556dbe7f 410 'duration': 180,
4bc3a23e
PH
411 'uploader': 'Icona Pop',
412 'uploader_id': 'IconaPop',
ec85ded8 413 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
7caf9830 414 'license': 'Standard YouTube License',
0cb58b02 415 'creator': 'Icona Pop',
2eb88d95 416 }
c108eb73
JMF
417 },
418 {
4bc3a23e
PH
419 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
420 'note': 'Test VEVO video with age protection (#956)',
421 'info_dict': {
422 'id': '07FYdnEawAQ',
423 'ext': 'mp4',
424 'upload_date': '20130703',
425 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
0cb58b02 426 'alt_title': 'Tunnel Vision',
4bc3a23e 427 'description': 'md5:64249768eec3bc4276236606ea996373',
556dbe7f 428 'duration': 419,
4bc3a23e
PH
429 'uploader': 'justintimberlakeVEVO',
430 'uploader_id': 'justintimberlakeVEVO',
ec85ded8 431 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
7caf9830 432 'license': 'Standard YouTube License',
0cb58b02 433 'creator': 'Justin Timberlake',
34952f09 434 'age_limit': 18,
c108eb73
JMF
435 }
436 },
fccd3771 437 {
4bc3a23e
PH
438 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
439 'note': 'Embed-only video (#1746)',
440 'info_dict': {
441 'id': 'yZIXLfi8CZQ',
442 'ext': 'mp4',
443 'upload_date': '20120608',
444 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
445 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
446 'uploader': 'SET India',
94bfcd23 447 'uploader_id': 'setindia',
ec85ded8 448 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
7caf9830 449 'license': 'Standard YouTube License',
94bfcd23 450 'age_limit': 18,
fccd3771
PH
451 }
452 },
11b56058 453 {
2d3d2997 454 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
11b56058
PM
455 'note': 'Use the first video ID in the URL',
456 'info_dict': {
457 'id': 'BaW_jenozKc',
458 'ext': 'mp4',
459 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
460 'uploader': 'Philipp Hagemeister',
461 'uploader_id': 'phihag',
ec85ded8 462 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 463 'upload_date': '20121002',
7caf9830 464 'license': 'Standard YouTube License',
11b56058
PM
465 '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 .',
466 'categories': ['Science & Technology'],
467 'tags': ['youtube-dl'],
556dbe7f 468 'duration': 10,
11b56058
PM
469 'like_count': int,
470 'dislike_count': int,
34a7de29
S
471 },
472 'params': {
473 'skip_download': True,
474 },
11b56058 475 },
dd27fd17 476 {
2d3d2997 477 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
478 'note': '256k DASH audio (format 141) via DASH manifest',
479 'info_dict': {
480 'id': 'a9LDPn-MO4I',
481 'ext': 'm4a',
482 'upload_date': '20121002',
483 'uploader_id': '8KVIDEO',
ec85ded8 484 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
485 'description': '',
486 'uploader': '8KVIDEO',
7caf9830 487 'license': 'Standard YouTube License',
4bc3a23e 488 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 489 },
4bc3a23e
PH
490 'params': {
491 'youtube_include_dash_manifest': True,
492 'format': '141',
4919603f 493 },
de3c7fe0 494 'skip': 'format 141 not served anymore',
dd27fd17 495 },
3489b7d2
JMF
496 # DASH manifest with encrypted signature
497 {
78caa52a
PH
498 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
499 'info_dict': {
500 'id': 'IB3lcPjvWLA',
501 'ext': 'm4a',
b766eb27
JMF
502 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
503 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
556dbe7f 504 'duration': 244,
78caa52a
PH
505 'uploader': 'AfrojackVEVO',
506 'uploader_id': 'AfrojackVEVO',
507 'upload_date': '20131011',
7caf9830 508 'license': 'Standard YouTube License',
3489b7d2 509 },
4bc3a23e 510 'params': {
78caa52a 511 'youtube_include_dash_manifest': True,
de3c7fe0 512 'format': '141/bestaudio[ext=m4a]',
3489b7d2
JMF
513 },
514 },
aaeb86f6
S
515 # JS player signature function name containing $
516 {
517 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
518 'info_dict': {
519 'id': 'nfWlot6h_JM',
520 'ext': 'm4a',
521 'title': 'Taylor Swift - Shake It Off',
0cb58b02 522 'alt_title': 'Shake It Off',
f57b7835 523 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
556dbe7f 524 'duration': 242,
aaeb86f6
S
525 'uploader': 'TaylorSwiftVEVO',
526 'uploader_id': 'TaylorSwiftVEVO',
527 'upload_date': '20140818',
7caf9830 528 'license': 'Standard YouTube License',
0cb58b02 529 'creator': 'Taylor Swift',
aaeb86f6
S
530 },
531 'params': {
532 'youtube_include_dash_manifest': True,
de3c7fe0 533 'format': '141/bestaudio[ext=m4a]',
aaeb86f6
S
534 },
535 },
aa79ac0c
PH
536 # Controversy video
537 {
538 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
539 'info_dict': {
540 'id': 'T4XJQO3qol8',
541 'ext': 'mp4',
556dbe7f 542 'duration': 219,
aa79ac0c
PH
543 'upload_date': '20100909',
544 'uploader': 'The Amazing Atheist',
545 'uploader_id': 'TheAmazingAtheist',
ec85ded8 546 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
7caf9830 547 'license': 'Standard YouTube License',
aa79ac0c
PH
548 'title': 'Burning Everyone\'s Koran',
549 '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',
550 }
c522adb1
JMF
551 },
552 # Normal age-gate video (No vevo, embed allowed)
553 {
2d3d2997 554 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
555 'info_dict': {
556 'id': 'HtVdAasjOgU',
557 'ext': 'mp4',
558 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 559 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 560 'duration': 142,
c522adb1
JMF
561 'uploader': 'The Witcher',
562 'uploader_id': 'WitcherGame',
ec85ded8 563 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 564 'upload_date': '20140605',
7caf9830 565 'license': 'Standard YouTube License',
34952f09 566 'age_limit': 18,
c522adb1
JMF
567 },
568 },
fccae2b9
S
569 # Age-gate video with encrypted signature
570 {
2d3d2997 571 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
fccae2b9
S
572 'info_dict': {
573 'id': '6kLq3WMV1nU',
574 'ext': 'mp4',
575 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
576 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
556dbe7f 577 'duration': 247,
fccae2b9
S
578 'uploader': 'LloydVEVO',
579 'uploader_id': 'LloydVEVO',
ec85ded8 580 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
fccae2b9 581 'upload_date': '20110629',
7caf9830 582 'license': 'Standard YouTube License',
34952f09 583 'age_limit': 18,
fccae2b9
S
584 },
585 },
774e208f
PH
586 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
587 {
588 'url': '__2ABJjxzNo',
589 'info_dict': {
590 'id': '__2ABJjxzNo',
591 'ext': 'mp4',
556dbe7f 592 'duration': 266,
774e208f
PH
593 'upload_date': '20100430',
594 'uploader_id': 'deadmau5',
ec85ded8 595 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
0cb58b02 596 'creator': 'deadmau5',
774e208f
PH
597 'description': 'md5:12c56784b8032162bb936a5f76d55360',
598 'uploader': 'deadmau5',
7caf9830 599 'license': 'Standard YouTube License',
774e208f 600 'title': 'Deadmau5 - Some Chords (HD)',
0cb58b02 601 'alt_title': 'Some Chords',
774e208f
PH
602 },
603 'expected_warnings': [
604 'DASH manifest missing',
605 ]
e52a40ab
PH
606 },
607 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
608 {
609 'url': 'lqQg6PlCWgI',
610 'info_dict': {
611 'id': 'lqQg6PlCWgI',
612 'ext': 'mp4',
556dbe7f 613 'duration': 6085,
90227264 614 'upload_date': '20150827',
cbe2bd91 615 'uploader_id': 'olympic',
ec85ded8 616 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
7caf9830 617 'license': 'Standard YouTube License',
cbe2bd91 618 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
be49068d 619 'uploader': 'Olympic',
cbe2bd91
PH
620 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
621 },
622 'params': {
623 'skip_download': 'requires avconv',
e52a40ab 624 }
cbe2bd91 625 },
6271f1ca
PH
626 # Non-square pixels
627 {
628 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
629 'info_dict': {
630 'id': '_b-2C3KPAM0',
631 'ext': 'mp4',
632 'stretched_ratio': 16 / 9.,
556dbe7f 633 'duration': 85,
6271f1ca
PH
634 'upload_date': '20110310',
635 'uploader_id': 'AllenMeow',
ec85ded8 636 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca
PH
637 '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',
638 'uploader': '孫艾倫',
7caf9830 639 'license': 'Standard YouTube License',
6271f1ca
PH
640 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
641 },
06b491eb
S
642 },
643 # url_encoded_fmt_stream_map is empty string
644 {
645 'url': 'qEJwOuvDf7I',
646 'info_dict': {
647 'id': 'qEJwOuvDf7I',
f57b7835 648 'ext': 'webm',
06b491eb
S
649 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
650 'description': '',
651 'upload_date': '20150404',
652 'uploader_id': 'spbelect',
653 'uploader': 'Наблюдатели Петербурга',
654 },
655 'params': {
656 'skip_download': 'requires avconv',
e323cf3f
S
657 },
658 'skip': 'This live event has ended.',
06b491eb 659 },
da77d856
S
660 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
661 {
662 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
663 'info_dict': {
664 'id': 'FIl7x6_3R5Y',
665 'ext': 'mp4',
666 'title': 'md5:7b81415841e02ecd4313668cde88737a',
667 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 668 'duration': 220,
da77d856
S
669 'upload_date': '20150625',
670 'uploader_id': 'dorappi2000',
ec85ded8 671 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 672 'uploader': 'dorappi2000',
7caf9830 673 'license': 'Standard YouTube License',
be49068d 674 'formats': 'mincount:32',
da77d856 675 },
2ee8f5d8 676 },
8a1a26ce
YCH
677 # DASH manifest with segment_list
678 {
679 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
680 'md5': '8ce563a1d667b599d21064e982ab9e31',
681 'info_dict': {
682 'id': 'CsmdDsKjzN8',
683 'ext': 'mp4',
17ee98e1 684 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
685 'uploader': 'Airtek',
686 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
687 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
7caf9830 688 'license': 'Standard YouTube License',
8a1a26ce
YCH
689 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
690 },
691 'params': {
692 'youtube_include_dash_manifest': True,
693 'format': '135', # bestvideo
be49068d
S
694 },
695 'skip': 'This live event has ended.',
2ee8f5d8 696 },
cf7e015f
S
697 {
698 # Multifeed videos (multiple cameras), URL is for Main Camera
699 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
700 'info_dict': {
701 'id': 'jqWvoWXjCVs',
702 'title': 'teamPGP: Rocket League Noob Stream',
703 'description': 'md5:dc7872fb300e143831327f1bae3af010',
704 },
705 'playlist': [{
706 'info_dict': {
707 'id': 'jqWvoWXjCVs',
708 'ext': 'mp4',
709 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
710 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 711 'duration': 7335,
cf7e015f
S
712 'upload_date': '20150721',
713 'uploader': 'Beer Games Beer',
714 'uploader_id': 'beergamesbeer',
ec85ded8 715 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 716 'license': 'Standard YouTube License',
cf7e015f
S
717 },
718 }, {
719 'info_dict': {
720 'id': '6h8e8xoXJzg',
721 'ext': 'mp4',
722 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
723 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 724 'duration': 7337,
cf7e015f
S
725 'upload_date': '20150721',
726 'uploader': 'Beer Games Beer',
727 'uploader_id': 'beergamesbeer',
ec85ded8 728 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 729 'license': 'Standard YouTube License',
cf7e015f
S
730 },
731 }, {
732 'info_dict': {
733 'id': 'PUOgX5z9xZw',
734 'ext': 'mp4',
735 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
736 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 737 'duration': 7337,
cf7e015f
S
738 'upload_date': '20150721',
739 'uploader': 'Beer Games Beer',
740 'uploader_id': 'beergamesbeer',
ec85ded8 741 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 742 'license': 'Standard YouTube License',
cf7e015f
S
743 },
744 }, {
745 'info_dict': {
746 'id': 'teuwxikvS5k',
747 'ext': 'mp4',
748 'title': 'teamPGP: Rocket League Noob Stream (zim)',
749 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 750 'duration': 7334,
cf7e015f
S
751 'upload_date': '20150721',
752 'uploader': 'Beer Games Beer',
753 'uploader_id': 'beergamesbeer',
ec85ded8 754 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 755 'license': 'Standard YouTube License',
cf7e015f
S
756 },
757 }],
758 'params': {
759 'skip_download': True,
760 },
cbaed4bb 761 },
f9f49d87
S
762 {
763 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
764 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
765 'info_dict': {
766 'id': 'gVfLd0zydlo',
767 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
768 },
769 'playlist_count': 2,
be49068d 770 'skip': 'Not multifeed anymore',
f9f49d87 771 },
cbaed4bb 772 {
2d3d2997 773 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 774 'only_matching': True,
0e49d9a6 775 },
6d4fc66b 776 {
2d3d2997 777 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
778 'only_matching': True,
779 },
0e49d9a6 780 {
61f92af1 781 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
a8776b10
S
782 # Also tests cut-off URL expansion in video description (see
783 # https://github.com/rg3/youtube-dl/issues/1892,
784 # https://github.com/rg3/youtube-dl/issues/8164)
0e49d9a6
LL
785 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
786 'info_dict': {
787 'id': 'lsguqyKfVQg',
788 'ext': 'mp4',
789 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
0cb58b02 790 'alt_title': 'Dark Walk',
0e49d9a6 791 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 792 'duration': 133,
0e49d9a6
LL
793 'upload_date': '20151119',
794 'uploader_id': 'IronSoulElf',
ec85ded8 795 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 796 'uploader': 'IronSoulElf',
7caf9830 797 'license': 'Standard YouTube License',
0cb58b02 798 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
0e49d9a6
LL
799 },
800 'params': {
801 'skip_download': True,
802 },
803 },
61f92af1
S
804 {
805 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
806 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
807 'only_matching': True,
808 },
313dfc45
LL
809 {
810 # Video with yt:stretch=17:0
811 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
812 'info_dict': {
813 'id': 'Q39EVAstoRM',
814 'ext': 'mp4',
815 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
816 'description': 'md5:ee18a25c350637c8faff806845bddee9',
817 'upload_date': '20151107',
818 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
819 'uploader': 'CH GAMER DROID',
820 },
821 'params': {
822 'skip_download': True,
823 },
be49068d 824 'skip': 'This video does not exist.',
313dfc45 825 },
7caf9830
S
826 {
827 # Video licensed under Creative Commons
828 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
829 'info_dict': {
830 'id': 'M4gD1WSo5mA',
831 'ext': 'mp4',
832 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
833 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 834 'duration': 721,
7caf9830
S
835 'upload_date': '20150127',
836 'uploader_id': 'BerkmanCenter',
ec85ded8 837 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 838 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
839 'license': 'Creative Commons Attribution license (reuse allowed)',
840 },
841 'params': {
842 'skip_download': True,
843 },
844 },
fd050249
S
845 {
846 # Channel-like uploader_url
847 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
848 'info_dict': {
849 'id': 'eQcmzGIKrzg',
850 'ext': 'mp4',
851 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
852 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
556dbe7f 853 'duration': 4060,
fd050249
S
854 'upload_date': '20151119',
855 'uploader': 'Bernie 2016',
856 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 857 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
858 'license': 'Creative Commons Attribution license (reuse allowed)',
859 },
860 'params': {
861 'skip_download': True,
862 },
863 },
040ac686
S
864 {
865 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
866 'only_matching': True,
7f29cf54
S
867 },
868 {
869 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
870 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
871 'only_matching': True,
6496ccb4
S
872 },
873 {
874 # Rental video preview
875 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
876 'info_dict': {
877 'id': 'uGpuVWrhIzE',
878 'ext': 'mp4',
879 'title': 'Piku - Trailer',
880 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
881 'upload_date': '20150811',
882 'uploader': 'FlixMatrix',
883 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 884 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
885 'license': 'Standard YouTube License',
886 },
887 'params': {
888 'skip_download': True,
889 },
022a5d66 890 },
12afdc2a
S
891 {
892 # YouTube Red video with episode data
893 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
894 'info_dict': {
895 'id': 'iqKdEhx-dD4',
896 'ext': 'mp4',
897 'title': 'Isolation - Mind Field (Ep 1)',
556dbe7f
S
898 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
899 'duration': 2085,
12afdc2a
S
900 'upload_date': '20170118',
901 'uploader': 'Vsauce',
902 'uploader_id': 'Vsauce',
903 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
904 'license': 'Standard YouTube License',
905 'series': 'Mind Field',
906 'season_number': 1,
907 'episode_number': 1,
908 },
909 'params': {
910 'skip_download': True,
911 },
912 'expected_warnings': [
913 'Skipping DASH manifest',
914 ],
915 },
022a5d66
S
916 {
917 # itag 212
918 'url': '1t24XAntNCY',
919 'only_matching': True,
040ac686 920 }
2eb88d95
PH
921 ]
922
e0df6211
PH
923 def __init__(self, *args, **kwargs):
924 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 925 self._player_cache = {}
e0df6211 926
c5e8d7af
PH
927 def report_video_info_webpage_download(self, video_id):
928 """Report attempt to download video info webpage."""
69ea8ca4 929 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 930
c5e8d7af
PH
931 def report_information_extraction(self, video_id):
932 """Report attempt to extract video information."""
69ea8ca4 933 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
934
935 def report_unavailable_format(self, video_id, format):
936 """Report extracted video URL."""
69ea8ca4 937 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
938
939 def report_rtmp_download(self):
940 """Indicate the download will use the RTMP protocol."""
69ea8ca4 941 self.to_screen('RTMP download detected')
c5e8d7af 942
60064c53
PH
943 def _signature_cache_id(self, example_sig):
944 """ Return a string representation of a signature """
78caa52a 945 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
946
947 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 948 id_m = re.match(
50f84a9a 949 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
cf010131 950 player_url)
c081b35c
PH
951 if not id_m:
952 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
953 player_type = id_m.group('ext')
954 player_id = id_m.group('id')
955
c4417ddb 956 # Read from filesystem cache
60064c53
PH
957 func_id = '%s_%s_%s' % (
958 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 959 assert os.path.basename(func_id) == func_id
a0e07d31 960
69ea8ca4 961 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 962 if cache_spec is not None:
78caa52a 963 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 964
6d1a55a5
PH
965 download_note = (
966 'Downloading player %s' % player_url
967 if self._downloader.params.get('verbose') else
968 'Downloading %s player %s' % (player_type, player_id)
969 )
e0df6211
PH
970 if player_type == 'js':
971 code = self._download_webpage(
972 player_url, video_id,
6d1a55a5 973 note=download_note,
69ea8ca4 974 errnote='Download of %s failed' % player_url)
83799698 975 res = self._parse_sig_js(code)
c4417ddb 976 elif player_type == 'swf':
e0df6211
PH
977 urlh = self._request_webpage(
978 player_url, video_id,
6d1a55a5 979 note=download_note,
69ea8ca4 980 errnote='Download of %s failed' % player_url)
e0df6211 981 code = urlh.read()
83799698 982 res = self._parse_sig_swf(code)
e0df6211
PH
983 else:
984 assert False, 'Invalid player type %r' % player_type
985
785521bf
PH
986 test_string = ''.join(map(compat_chr, range(len(example_sig))))
987 cache_res = res(test_string)
988 cache_spec = [ord(c) for c in cache_res]
83799698 989
69ea8ca4 990 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
991 return res
992
60064c53 993 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
994 def gen_sig_code(idxs):
995 def _genslice(start, end, step):
78caa52a 996 starts = '' if start == 0 else str(start)
8bcc8756 997 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 998 steps = '' if step == 1 else (':%d' % step)
78caa52a 999 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1000
1001 step = None
7af808a5
PH
1002 # Quelch pyflakes warnings - start will be set when step is set
1003 start = '(Never used)'
edf3e38e
PH
1004 for i, prev in zip(idxs[1:], idxs[:-1]):
1005 if step is not None:
1006 if i - prev == step:
1007 continue
1008 yield _genslice(start, prev, step)
1009 step = None
1010 continue
1011 if i - prev in [-1, 1]:
1012 step = i - prev
1013 start = prev
1014 continue
1015 else:
78caa52a 1016 yield 's[%d]' % prev
edf3e38e 1017 if step is None:
78caa52a 1018 yield 's[%d]' % i
edf3e38e
PH
1019 else:
1020 yield _genslice(start, i, step)
1021
78caa52a 1022 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1023 cache_res = func(test_string)
edf3e38e 1024 cache_spec = [ord(c) for c in cache_res]
78caa52a 1025 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1026 signature_id_tuple = '(%s)' % (
1027 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1028 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1029 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1030 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1031
e0df6211
PH
1032 def _parse_sig_js(self, jscode):
1033 funcname = self._search_regex(
3c90cc8b
S
1034 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1035 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
1036 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1037
1038 jsi = JSInterpreter(jscode)
1039 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1040 return lambda s: initial_function([s])
1041
1042 def _parse_sig_swf(self, file_contents):
54256267 1043 swfi = SWFInterpreter(file_contents)
78caa52a 1044 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 1045 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 1046 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
1047 return lambda s: initial_function([s])
1048
83799698 1049 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 1050 """Turn the encrypted s field into a working signature"""
6b37f0be 1051
c8bf86d5 1052 if player_url is None:
69ea8ca4 1053 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1054
69ea8ca4 1055 if player_url.startswith('//'):
78caa52a 1056 player_url = 'https:' + player_url
3c90cc8b
S
1057 elif not re.match(r'https?://', player_url):
1058 player_url = compat_urlparse.urljoin(
1059 'https://www.youtube.com', player_url)
c8bf86d5 1060 try:
62af3a0e 1061 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1062 if player_id not in self._player_cache:
1063 func = self._extract_signature_function(
60064c53 1064 video_id, player_url, s
c8bf86d5
PH
1065 )
1066 self._player_cache[player_id] = func
1067 func = self._player_cache[player_id]
1068 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1069 self._print_sig_code(func, s)
c8bf86d5
PH
1070 return func(s)
1071 except Exception as e:
1072 tb = traceback.format_exc()
1073 raise ExtractorError(
78caa52a 1074 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1075
360e1ca5 1076 def _get_subtitles(self, video_id, webpage):
de7f3446 1077 try:
60e47a26 1078 subs_doc = self._download_xml(
38c2e5b8 1079 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1080 video_id, note=False)
1081 except ExtractorError as err:
9b9c5355 1082 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1083 return {}
de7f3446
JMF
1084
1085 sub_lang_list = {}
60e47a26
JMF
1086 for track in subs_doc.findall('track'):
1087 lang = track.attrib['lang_code']
7e660ac1
LD
1088 if lang in sub_lang_list:
1089 continue
360e1ca5 1090 sub_formats = []
23d17e4b 1091 for ext in self._SUBTITLE_FORMATS:
15707c7e 1092 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1093 'lang': lang,
1094 'v': video_id,
1095 'fmt': ext,
1096 'name': track.attrib['name'].encode('utf-8'),
1097 })
1098 sub_formats.append({
1099 'url': 'https://www.youtube.com/api/timedtext?' + params,
1100 'ext': ext,
1101 })
1102 sub_lang_list[lang] = sub_formats
de7f3446 1103 if not sub_lang_list:
69ea8ca4 1104 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1105 return {}
1106 return sub_lang_list
1107
a72778d3
S
1108 def _get_ytplayer_config(self, video_id, webpage):
1109 patterns = (
526b3b07
S
1110 # User data may contain arbitrary character sequences that may affect
1111 # JSON extraction with regex, e.g. when '};' is contained the second
1112 # regex won't capture the whole JSON. Yet working around by trying more
1113 # concrete regex first keeping in mind proper quoted string handling
1114 # to be implemented in future that will replace this workaround (see
1115 # https://github.com/rg3/youtube-dl/issues/7468,
1116 # https://github.com/rg3/youtube-dl/pull/7599)
a72778d3
S
1117 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1118 r';ytplayer\.config\s*=\s*({.+?});',
1119 )
1120 config = self._search_regex(
1121 patterns, webpage, 'ytplayer.config', default=None)
1122 if config:
1123 return self._parse_json(
1124 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1125
360e1ca5 1126 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1127 """We need the webpage for getting the captions url, pass it as an
1128 argument to speed up the process."""
69ea8ca4 1129 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1130 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1131 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1132 if not player_config:
de7f3446
JMF
1133 self._downloader.report_warning(err_msg)
1134 return {}
de7f3446 1135 try:
0792d563 1136 args = player_config['args']
b78b292f
S
1137 caption_url = args.get('ttsurl')
1138 if caption_url:
1139 timestamp = args['timestamp']
1140 # We get the available subtitles
15707c7e 1141 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1142 'type': 'list',
1143 'tlangs': 1,
1144 'asrs': 1,
1145 })
1146 list_url = caption_url + '&' + list_params
1147 caption_list = self._download_xml(list_url, video_id)
1148 original_lang_node = caption_list.find('track')
1149 if original_lang_node is None:
1150 self._downloader.report_warning('Video doesn\'t have automatic captions')
1151 return {}
1152 original_lang = original_lang_node.attrib['lang_code']
1153 caption_kind = original_lang_node.attrib.get('kind', '')
1154
1155 sub_lang_list = {}
1156 for lang_node in caption_list.findall('target'):
1157 sub_lang = lang_node.attrib['lang_code']
1158 sub_formats = []
1159 for ext in self._SUBTITLE_FORMATS:
15707c7e 1160 params = compat_urllib_parse_urlencode({
b78b292f
S
1161 'lang': original_lang,
1162 'tlang': sub_lang,
1163 'fmt': ext,
1164 'ts': timestamp,
1165 'kind': caption_kind,
1166 })
1167 sub_formats.append({
1168 'url': caption_url + '&' + params,
1169 'ext': ext,
1170 })
1171 sub_lang_list[sub_lang] = sub_formats
1172 return sub_lang_list
1173
1174 # Some videos don't provide ttsurl but rather caption_tracks and
1175 # caption_translation_languages (e.g. 20LmZk1hakA)
1176 caption_tracks = args['caption_tracks']
1177 caption_translation_languages = args['caption_translation_languages']
1178 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
15707c7e 1179 parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
b78b292f 1180 caption_qs = compat_parse_qs(parsed_caption_url.query)
055e6f36
JMF
1181
1182 sub_lang_list = {}
b78b292f
S
1183 for lang in caption_translation_languages.split(','):
1184 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1185 sub_lang = lang_qs.get('lc', [None])[0]
1186 if not sub_lang:
1187 continue
360e1ca5 1188 sub_formats = []
23d17e4b 1189 for ext in self._SUBTITLE_FORMATS:
b78b292f
S
1190 caption_qs.update({
1191 'tlang': [sub_lang],
1192 'fmt': [ext],
360e1ca5 1193 })
b78b292f 1194 sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
15707c7e 1195 query=compat_urllib_parse_urlencode(caption_qs, True)))
360e1ca5 1196 sub_formats.append({
b78b292f 1197 'url': sub_url,
360e1ca5
JMF
1198 'ext': ext,
1199 })
1200 sub_lang_list[sub_lang] = sub_formats
055e6f36 1201 return sub_lang_list
de7f3446
JMF
1202 # An extractor error can be raise by the download process if there are
1203 # no automatic captions but there are subtitles
1204 except (KeyError, ExtractorError):
1205 self._downloader.report_warning(err_msg)
1206 return {}
1207
d77ab8e2
S
1208 def _mark_watched(self, video_id, video_info):
1209 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1210 if not playback_url:
1211 return
1212 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1213 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1214
1215 # cpn generation algorithm is reverse engineered from base.js.
1216 # In fact it works even with dummy cpn.
1217 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1218 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1219
1220 qs.update({
1221 'ver': ['2'],
1222 'cpn': [cpn],
1223 })
1224 playback_url = compat_urlparse.urlunparse(
15707c7e 1225 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1226
1227 self._download_webpage(
1228 playback_url, video_id, 'Marking watched',
1229 'Unable to mark watched', fatal=False)
1230
97665381
PH
1231 @classmethod
1232 def extract_id(cls, url):
1233 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1234 if mobj is None:
69ea8ca4 1235 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1236 video_id = mobj.group(2)
1237 return video_id
1238
1d043b93
JMF
1239 def _extract_from_m3u8(self, manifest_url, video_id):
1240 url_map = {}
5f6a1245 1241
1d043b93
JMF
1242 def _get_urls(_manifest):
1243 lines = _manifest.split('\n')
1244 urls = filter(lambda l: l and not l.startswith('#'),
8bcc8756 1245 lines)
1d043b93 1246 return urls
78caa52a 1247 manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
1d043b93
JMF
1248 formats_urls = _get_urls(manifest)
1249 for format_url in formats_urls:
890f62e8 1250 itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
1d043b93
JMF
1251 url_map[itag] = format_url
1252 return url_map
1253
1fb07d10
JG
1254 def _extract_annotations(self, video_id):
1255 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1256 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1257
c5e8d7af 1258 def _real_extract(self, url):
cf7e015f
S
1259 url, smuggled_data = unsmuggle_url(url, {})
1260
7e8c0af0 1261 proto = (
78caa52a
PH
1262 'http' if self._downloader.params.get('prefer_insecure', False)
1263 else 'https')
7e8c0af0 1264
7c80519c 1265 start_time = None
297a564b 1266 end_time = None
7c80519c
JMF
1267 parsed_url = compat_urllib_parse_urlparse(url)
1268 for component in [parsed_url.fragment, parsed_url.query]:
1269 query = compat_parse_qs(component)
297a564b 1270 if start_time is None and 't' in query:
7c80519c 1271 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1272 if start_time is None and 'start' in query:
1273 start_time = parse_duration(query['start'][0])
297a564b
JMF
1274 if end_time is None and 'end' in query:
1275 end_time = parse_duration(query['end'][0])
7c80519c 1276
c5e8d7af
PH
1277 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1278 mobj = re.search(self._NEXT_URL_RE, url)
1279 if mobj:
7fd002c0 1280 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1281 video_id = self.extract_id(url)
c5e8d7af
PH
1282
1283 # Get video webpage
aa79ac0c 1284 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1285 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1286
1287 # Attempt to extract SWF player URL
e0df6211 1288 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1289 if mobj is not None:
1290 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1291 else:
1292 player_url = None
1293
d8d24a92
S
1294 dash_mpds = []
1295
1296 def add_dash_mpd(video_info):
1297 dash_mpd = video_info.get('dashmpd')
1298 if dash_mpd and dash_mpd[0] not in dash_mpds:
1299 dash_mpds.append(dash_mpd[0])
1300
c5e8d7af 1301 # Get video info
6449cd80 1302 embed_webpage = None
2fe1ff85 1303 is_live = None
c108eb73 1304 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1305 age_gate = True
1306 # We simulate the access to the video from www.youtube.com/v/{video_id}
1307 # this can be viewed without login into Youtube
beb95e77
CL
1308 url = proto + '://www.youtube.com/embed/%s' % video_id
1309 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1310 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1311 'video_id': video_id,
1312 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1313 'sts': self._search_regex(
beb95e77 1314 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1315 })
7e8c0af0 1316 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1317 video_info_webpage = self._download_webpage(
1318 video_info_url, video_id,
20436c30 1319 note='Refetching age-gated info webpage',
94bd3613 1320 errnote='unable to download video info webpage')
c5e8d7af 1321 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1322 add_dash_mpd(video_info)
c108eb73
JMF
1323 else:
1324 age_gate = False
bc93bdb5 1325 video_info = None
d8d24a92 1326 # Try looking directly into the video webpage
a72778d3
S
1327 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1328 if ytplayer_config:
4e62ebe2 1329 args = ytplayer_config['args']
d8d24a92
S
1330 if args.get('url_encoded_fmt_stream_map'):
1331 # Convert to the same format returned by compat_parse_qs
1332 video_info = dict((k, [v]) for k, v in args.items())
1333 add_dash_mpd(video_info)
6496ccb4
S
1334 # Rental video is not rented but preview is available (e.g.
1335 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1336 # https://github.com/rg3/youtube-dl/issues/10532)
1337 if not video_info and args.get('ypc_vid'):
1338 return self.url_result(
1339 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
2fe1ff85
JMF
1340 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1341 is_live = True
0a3cf9ad
S
1342 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1343 # We also try looking in get_video_info since it may contain different dashmpd
1344 # URL that points to a DASH manifest with possibly different itag set (some itags
1345 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1346 # manifest pointed by get_video_info's dashmpd).
1347 # The general idea is to take a union of itags of both DASH manifests (for example
1348 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
4e62ebe2 1349 self.report_video_info_webpage_download(video_id)
0a3cf9ad 1350 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
810fb84d
PH
1351 video_info_url = (
1352 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1353 % (proto, video_id, el_type))
1354 video_info_webpage = self._download_webpage(
1355 video_info_url,
4e62ebe2
JMF
1356 video_id, note=False,
1357 errnote='unable to download video info webpage')
0a3cf9ad 1358 get_video_info = compat_parse_qs(video_info_webpage)
87dc4511
JMF
1359 if get_video_info.get('use_cipher_signature') != ['True']:
1360 add_dash_mpd(get_video_info)
0a3cf9ad
S
1361 if not video_info:
1362 video_info = get_video_info
1363 if 'token' in get_video_info:
89ea063e
S
1364 # Different get_video_info requests may report different results, e.g.
1365 # some may report video unavailability, but some may serve it without
1366 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1367 # the original webpage as well as el=info and el=embedded get_video_info
1368 # requests report video unavailability due to geo restriction while
1369 # el=detailpage succeeds and returns valid data). This is probably
1370 # due to YouTube measures against IP ranges of hosting providers.
1371 # Working around by preferring the first succeeded video_info containing
1372 # the token if no such video_info yet was found.
44b2264f
S
1373 if 'token' not in video_info:
1374 video_info = get_video_info
4e62ebe2 1375 break
c5e8d7af
PH
1376 if 'token' not in video_info:
1377 if 'reason' in video_info:
af214c3a
YCH
1378 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1379 regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
678e436f 1380 if regions_allowed:
af214c3a
YCH
1381 raise ExtractorError('YouTube said: This video is available in %s only' % (
1382 ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
1383 expected=True)
d11271dd 1384 raise ExtractorError(
78caa52a 1385 'YouTube said: %s' % video_info['reason'][0],
d11271dd 1386 expected=True, video_id=video_id)
c5e8d7af 1387 else:
d11271dd 1388 raise ExtractorError(
78caa52a 1389 '"token" parameter not in video info for unknown reason',
d11271dd 1390 video_id=video_id)
c5e8d7af 1391
cf7e015f
S
1392 # title
1393 if 'title' in video_info:
1394 video_title = video_info['title'][0]
1395 else:
1396 self._downloader.report_warning('Unable to extract video title')
1397 video_title = '_'
1398
1399 # description
1400 video_description = get_element_by_id("eow-description", video_webpage)
1401 if video_description:
1402 video_description = re.sub(r'''(?x)
1403 <a\s+
25cb7a0e 1404 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1405 (?:title|href)="([^"]+)"\s+
25cb7a0e 1406 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1407 class="[^"]*"[^>]*>
23f13e97 1408 [^<]+\.{3}\s*
cf7e015f
S
1409 </a>
1410 ''', r'\1', video_description)
1411 video_description = clean_html(video_description)
1412 else:
1413 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1414 if fd_mobj:
1415 video_description = unescapeHTML(fd_mobj.group(1))
1416 else:
1417 video_description = ''
1418
5e1eddb9
S
1419 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1420 if not self._downloader.params.get('noplaylist'):
1421 entries = []
1422 feed_ids = []
6863631c 1423 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
5e1eddb9 1424 for feed in multifeed_metadata_list.split(','):
6863631c
S
1425 # Unquote should take place before split on comma (,) since textual
1426 # fields may contain comma as well (see
1427 # https://github.com/rg3/youtube-dl/issues/8536)
1428 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
5e1eddb9
S
1429 entries.append({
1430 '_type': 'url_transparent',
1431 'ie_key': 'Youtube',
1432 'url': smuggle_url(
1433 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1434 {'force_singlefeed': True}),
1435 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1436 })
1437 feed_ids.append(feed_data['id'][0])
1438 self.to_screen(
1439 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1440 % (', '.join(feed_ids), video_id))
1441 return self.playlist_result(entries, video_id, video_title, video_description)
1442 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1443
1d699755
PH
1444 if 'view_count' in video_info:
1445 view_count = int(video_info['view_count'][0])
1446 else:
1447 view_count = None
1448
c5e8d7af
PH
1449 # Check for "rental" videos
1450 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
69ea8ca4 1451 raise ExtractorError('"rental" videos not supported')
c5e8d7af
PH
1452
1453 # Start extracting information
1454 self.report_information_extraction(video_id)
1455
1456 # uploader
1457 if 'author' not in video_info:
69ea8ca4 1458 raise ExtractorError('Unable to extract uploader name')
7fd002c0 1459 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
c5e8d7af
PH
1460
1461 # uploader_id
1462 video_uploader_id = None
fd050249
S
1463 video_uploader_url = None
1464 mobj = re.search(
1465 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1466 video_webpage)
c5e8d7af 1467 if mobj is not None:
fd050249
S
1468 video_uploader_id = mobj.group('uploader_id')
1469 video_uploader_url = mobj.group('uploader_url')
c5e8d7af 1470 else:
69ea8ca4 1471 self._downloader.report_warning('unable to extract uploader nickname')
c5e8d7af 1472
c5e8d7af 1473 # thumbnail image
7763b04e
JMF
1474 # We try first to get a high quality image:
1475 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1476 video_webpage, re.DOTALL)
1477 if m_thumb is not None:
1478 video_thumbnail = m_thumb.group(1)
1479 elif 'thumbnail_url' not in video_info:
69ea8ca4 1480 self._downloader.report_warning('unable to extract video thumbnail')
f490e77e 1481 video_thumbnail = None
c5e8d7af 1482 else: # don't panic if we can't find it
7fd002c0 1483 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
c5e8d7af
PH
1484
1485 # upload date
9d0b581f
S
1486 upload_date = self._html_search_meta(
1487 'datePublished', video_webpage, 'upload date', default=None)
1488 if not upload_date:
1489 upload_date = self._search_regex(
1490 [r'(?s)id="eow-date.*?>(.*?)</span>',
1491 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1492 video_webpage, 'upload date', default=None)
1493 if upload_date:
1494 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1495 upload_date = unified_strdate(upload_date)
c5e8d7af 1496
7caf9830
S
1497 video_license = self._html_search_regex(
1498 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1499 video_webpage, 'license', default=None)
1500
0cb58b02
S
1501 m_music = re.search(
1502 r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1503 video_webpage)
1504 if m_music:
1505 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1506 video_creator = clean_html(m_music.group('creator'))
1507 else:
1508 video_alt_title = video_creator = None
1509
12afdc2a
S
1510 m_episode = re.search(
1511 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1512 video_webpage)
1513 if m_episode:
1514 series = m_episode.group('series')
1515 season_number = int(m_episode.group('season'))
1516 episode_number = int(m_episode.group('episode'))
1517 else:
1518 series = season_number = episode_number = None
1519
55f7bd2d
PH
1520 m_cat_container = self._search_regex(
1521 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
624dcebf 1522 video_webpage, 'categories', default=None)
ec8deefc 1523 if m_cat_container:
ad3bc6ac 1524 category = self._html_search_regex(
01ed5c9b 1525 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
ad3bc6ac
PH
1526 default=None)
1527 video_categories = None if category is None else [category]
1528 else:
1529 video_categories = None
ec8deefc 1530
000b6b5a
S
1531 video_tags = [
1532 unescapeHTML(m.group('content'))
1533 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1534
f30a38be 1535 def _extract_count(count_name):
c93d53f5
S
1536 return str_to_int(self._search_regex(
1537 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1538 % re.escape(count_name),
1539 video_webpage, count_name, default=None))
1540
69ea8ca4
PH
1541 like_count = _extract_count('like')
1542 dislike_count = _extract_count('dislike')
336c3a69 1543
c5e8d7af 1544 # subtitles
d82134c3 1545 video_subtitles = self.extract_subtitles(video_id, video_webpage)
360e1ca5 1546 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
c5e8d7af 1547
556dbe7f
S
1548 video_duration = try_get(
1549 video_info, lambda x: int_or_none(x['length_seconds'][0]))
1550 if not video_duration:
1551 video_duration = parse_duration(self._html_search_meta(
1552 'duration', video_webpage, 'video duration'))
c5e8d7af 1553
1fb07d10
JG
1554 # annotations
1555 video_annotations = None
1556 if self._downloader.params.get('writeannotations', False):
5f6a1245 1557 video_annotations = self._extract_annotations(video_id)
1fb07d10 1558
dd27fd17
PH
1559 def _map_to_format_list(urlmap):
1560 formats = []
1561 for itag, video_real_url in urlmap.items():
1562 dct = {
1563 'format_id': itag,
1564 'url': video_real_url,
1565 'player_url': player_url,
1566 }
0b65e5d4
PH
1567 if itag in self._formats:
1568 dct.update(self._formats[itag])
dd27fd17
PH
1569 formats.append(dct)
1570 return formats
1571
c5e8d7af
PH
1572 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1573 self.report_rtmp_download()
dd27fd17
PH
1574 formats = [{
1575 'format_id': '_rtmp',
1576 'protocol': 'rtmp',
1577 'url': video_info['conn'][0],
1578 'player_url': player_url,
1579 }]
24270b03 1580 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
5f6a1245 1581 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1582 if 'rtmpe%3Dyes' in encoded_url_map:
a7055eb9 1583 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1584 formats_spec = {}
82156fdb 1585 fmt_list = video_info.get('fmt_list', [''])[0]
1586 if fmt_list:
1587 for fmt in fmt_list.split(','):
1588 spec = fmt.split('/')
3318832e 1589 if len(spec) > 1:
1590 width_height = spec[1].split('x')
1591 if len(width_height) == 2:
1592 formats_spec[spec[0]] = {
1593 'resolution': spec[1],
1594 'width': int_or_none(width_height[0]),
1595 'height': int_or_none(width_height[1]),
1596 }
c9afb51c 1597 formats = []
00fe14fc 1598 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1599 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1600 if 'itag' not in url_data or 'url' not in url_data:
1601 continue
1602 format_id = url_data['itag'][0]
1603 url = url_data['url'][0]
1604
1605 if 'sig' in url_data:
1606 url += '&signature=' + url_data['sig'][0]
1607 elif 's' in url_data:
1608 encrypted_sig = url_data['s'][0]
6449cd80 1609 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
201e9eaa 1610
beb95e77 1611 jsplayer_url_json = self._search_regex(
6449cd80
PH
1612 ASSETS_RE,
1613 embed_webpage if age_gate else video_webpage,
1614 'JS player URL (1)', default=None)
1615 if not jsplayer_url_json and not age_gate:
1616 # We need the embed website after all
1617 if embed_webpage is None:
1618 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1619 embed_webpage = self._download_webpage(
1620 embed_url, video_id, 'Downloading embed webpage')
1621 jsplayer_url_json = self._search_regex(
1622 ASSETS_RE, embed_webpage, 'JS player URL')
1623
beb95e77 1624 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1625 if player_url is None:
1626 player_url_json = self._search_regex(
1627 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1628 video_webpage, 'age gate player URL')
201e9eaa
PH
1629 player_url = json.loads(player_url_json)
1630
1631 if self._downloader.params.get('verbose'):
cf010131 1632 if player_url is None:
201e9eaa
PH
1633 player_version = 'unknown'
1634 player_desc = 'unknown'
1635 else:
1636 if player_url.endswith('swf'):
1637 player_version = self._search_regex(
1638 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1639 'flash player', fatal=False)
201e9eaa 1640 player_desc = 'flash player %s' % player_version
cf010131 1641 else:
201e9eaa 1642 player_version = self._search_regex(
50f84a9a 1643 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
201e9eaa
PH
1644 player_url,
1645 'html5 player', fatal=False)
78caa52a 1646 player_desc = 'html5 player %s' % player_version
201e9eaa 1647
60064c53 1648 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1649 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1650 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1651
1652 signature = self._decrypt_signature(
1653 encrypted_sig, video_id, player_url, age_gate)
1654 url += '&signature=' + signature
1655 if 'ratebypass' not in url:
1656 url += '&ratebypass=yes'
c9afb51c 1657
94278f72
YCH
1658 dct = {
1659 'format_id': format_id,
1660 'url': url,
1661 'player_url': player_url,
1662 }
1663 if format_id in self._formats:
1664 dct.update(self._formats[format_id])
3318832e 1665 if format_id in formats_spec:
1666 dct.update(formats_spec[format_id])
94278f72 1667
aabc2be6
S
1668 # Some itags are not included in DASH manifest thus corresponding formats will
1669 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1670 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1671 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1672 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72
YCH
1673
1674 more_fields = {
c9afb51c 1675 'filesize': int_or_none(url_data.get('clen', [None])[0]),
aabc2be6 1676 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1677 'width': width,
1678 'height': height,
1679 'fps': int_or_none(url_data.get('fps', [None])[0]),
aabc2be6 1680 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
c9afb51c 1681 }
94278f72
YCH
1682 for key, value in more_fields.items():
1683 if value:
1684 dct[key] = value
aabc2be6
S
1685 type_ = url_data.get('type', [None])[0]
1686 if type_:
1687 type_split = type_.split(';')
1688 kind_ext = type_split[0].split('/')
1689 if len(kind_ext) == 2:
94278f72
YCH
1690 kind, _ = kind_ext
1691 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1692 if kind in ('audio', 'video'):
1693 codecs = None
1694 for mobj in re.finditer(
1695 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1696 if mobj.group('key') == 'codecs':
1697 codecs = mobj.group('val')
1698 break
1699 if codecs:
6310acf5 1700 dct.update(parse_codecs(codecs))
aabc2be6 1701 formats.append(dct)
1d043b93
JMF
1702 elif video_info.get('hlsvp'):
1703 manifest_url = video_info['hlsvp'][0]
1704 url_map = self._extract_from_m3u8(manifest_url, video_id)
dd27fd17 1705 formats = _map_to_format_list(url_map)
ac5a69af
YCH
1706 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1707 for a_format in formats:
049d71d8 1708 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
c5e8d7af 1709 else:
8ceabd4d
S
1710 unavailable_message = self._html_search_regex(
1711 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1712 video_webpage, 'unavailable message', default=None)
1713 if unavailable_message:
1714 raise ExtractorError(unavailable_message, expected=True)
69ea8ca4 1715 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1716
dd27fd17 1717 # Look for the DASH manifest
203fb43f 1718 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 1719 dash_mpd_fatal = True
8ff648e4 1720 for mpd_url in dash_mpds:
d8d24a92 1721 dash_formats = {}
774e208f 1722 try:
05d0d131
YCH
1723 def decrypt_sig(mobj):
1724 s = mobj.group(1)
1725 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1726 return '/signature/%s' % dec_s
1727
8ff648e4 1728 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 1729
8ff648e4 1730 for df in self._extract_mpd_formats(
1731 mpd_url, video_id, fatal=dash_mpd_fatal,
1732 formats_dict=self._formats):
d8d24a92
S
1733 # Do not overwrite DASH format found in some previous DASH manifest
1734 if df['format_id'] not in dash_formats:
1735 dash_formats[df['format_id']] = df
77c6fb5b
S
1736 # Additional DASH manifests may end up in HTTP Error 403 therefore
1737 # allow them to fail without bug report message if we already have
1738 # some DASH manifest succeeded. This is temporary workaround to reduce
1739 # burst of bug reports until we figure out the reason and whether it
1740 # can be fixed at all.
1741 dash_mpd_fatal = False
774e208f
PH
1742 except (ExtractorError, KeyError) as e:
1743 self.report_warning(
1744 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 1745 if dash_formats:
04b3b3df
JMF
1746 # Remove the formats we found through non-DASH, they
1747 # contain less info and it can be wrong, because we use
1748 # fixed values (for example the resolution). See
1749 # https://github.com/rg3/youtube-dl/issues/5774 for an
1750 # example.
d80265cc 1751 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 1752 formats.extend(dash_formats.values())
d80044c2 1753
6271f1ca
PH
1754 # Check for malformed aspect ratio
1755 stretched_m = re.search(
1756 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1757 video_webpage)
1758 if stretched_m:
313dfc45
LL
1759 w = float(stretched_m.group('w'))
1760 h = float(stretched_m.group('h'))
5faf9fed
S
1761 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1762 # We will only process correct ratios.
313dfc45 1763 if w > 0 and h > 0:
41f24c32 1764 ratio = w / h
313dfc45
LL
1765 for f in formats:
1766 if f.get('vcodec') != 'none':
1767 f['stretched_ratio'] = ratio
6271f1ca 1768
4bcc7bd1 1769 self._sort_formats(formats)
4ea3be0a 1770
d77ab8e2
S
1771 self.mark_watched(video_id, video_info)
1772
4ea3be0a 1773 return {
8bcc8756
JW
1774 'id': video_id,
1775 'uploader': video_uploader,
1776 'uploader_id': video_uploader_id,
fd050249 1777 'uploader_url': video_uploader_url,
8bcc8756 1778 'upload_date': upload_date,
7caf9830 1779 'license': video_license,
0cb58b02 1780 'creator': video_creator,
8bcc8756 1781 'title': video_title,
0cb58b02 1782 'alt_title': video_alt_title,
8bcc8756
JW
1783 'thumbnail': video_thumbnail,
1784 'description': video_description,
1785 'categories': video_categories,
000b6b5a 1786 'tags': video_tags,
8bcc8756 1787 'subtitles': video_subtitles,
360e1ca5 1788 'automatic_captions': automatic_captions,
8bcc8756
JW
1789 'duration': video_duration,
1790 'age_limit': 18 if age_gate else 0,
1791 'annotations': video_annotations,
7e8c0af0 1792 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 1793 'view_count': view_count,
4ea3be0a 1794 'like_count': like_count,
1795 'dislike_count': dislike_count,
2d30521a 1796 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 1797 'formats': formats,
2fe1ff85 1798 'is_live': is_live,
7c80519c 1799 'start_time': start_time,
297a564b 1800 'end_time': end_time,
12afdc2a
S
1801 'series': series,
1802 'season_number': season_number,
1803 'episode_number': episode_number,
4ea3be0a 1804 }
c5e8d7af 1805
5f6a1245 1806
40805306 1807class YoutubeSharedVideoIE(InfoExtractor):
fd8c8c7d 1808 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
40805306
YCH
1809 IE_NAME = 'youtube:shared'
1810
1811 _TEST = {
1812 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1813 'info_dict': {
1814 'id': 'uPDB5I9wfp8',
1815 'ext': 'webm',
1816 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1817 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1818 'upload_date': '20160219',
1819 'uploader': 'Pocoyo - Português (BR)',
1820 'uploader_id': 'PocoyoBrazil',
1821 },
1822 'add_ie': ['Youtube'],
1823 'params': {
1824 # There are already too many Youtube downloads
1825 'skip_download': True,
1826 },
1827 }
1828
1829 def _real_extract(self, url):
1830 video_id = self._match_id(url)
1831
1832 webpage = self._download_webpage(url, video_id)
1833
1834 real_video_id = self._html_search_meta(
1835 'videoId', webpage, 'YouTube video id', fatal=True)
1836
1837 return self.url_result(real_video_id, YoutubeIE.ie_key())
1838
1839
8e7aad20 1840class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 1841 IE_DESC = 'YouTube.com playlists'
d67cc9fa 1842 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
1843 (?:https?://)?
1844 (?:\w+\.)?
c5e8d7af 1845 (?:
feaa5ad7
S
1846 youtube\.com/
1847 (?:
1848 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1849 \? (?:.*?[&;])*? (?:p|a|list)=
1850 | p/
1851 )|
1852 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
c5e8d7af 1853 )
d67cc9fa 1854 (
a6857510 1855 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
5f6a1245 1856 # Top tracks, they can also include dots
d67cc9fa
JMF
1857 |(?:MC)[\w\.]*
1858 )
c5e8d7af
PH
1859 .*
1860 |
a6857510 1861 ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
c5e8d7af 1862 )"""
c867adc6 1863 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
648e6a1f 1864 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 1865 IE_NAME = 'youtube:playlist'
81127aa5
PH
1866 _TESTS = [{
1867 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1868 'info_dict': {
1869 'title': 'ytdl test PL',
a1cf99d0 1870 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
1871 },
1872 'playlist_count': 3,
9291475f
PH
1873 }, {
1874 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1875 'info_dict': {
acf757f4 1876 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
1877 'title': 'YDL_Empty_List',
1878 },
1879 'playlist_count': 0,
4201ba13 1880 'skip': 'This playlist is private',
9291475f
PH
1881 }, {
1882 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1883 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1884 'info_dict': {
1885 'title': '29C3: Not my department',
acf757f4 1886 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
1887 },
1888 'playlist_count': 95,
1889 }, {
1890 'note': 'issue #673',
1891 'url': 'PLBB231211A4F62143',
1892 'info_dict': {
f46a8702 1893 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 1894 'id': 'PLBB231211A4F62143',
9291475f
PH
1895 },
1896 'playlist_mincount': 26,
1897 }, {
1898 'note': 'Large playlist',
1899 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1900 'info_dict': {
1901 'title': 'Uploads from Cauchemar',
acf757f4 1902 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
1903 },
1904 'playlist_mincount': 799,
1905 }, {
1906 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1907 'info_dict': {
1908 'title': 'YDL_safe_search',
acf757f4 1909 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
1910 },
1911 'playlist_count': 2,
4201ba13 1912 'skip': 'This playlist is private',
ac7553d0
PH
1913 }, {
1914 'note': 'embedded',
2d3d2997 1915 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0
PH
1916 'playlist_count': 4,
1917 'info_dict': {
1918 'title': 'JODA15',
acf757f4 1919 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 1920 }
6b08cdf6
PH
1921 }, {
1922 'note': 'Embedded SWF player',
2d3d2997 1923 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
6b08cdf6
PH
1924 'playlist_count': 4,
1925 'info_dict': {
1926 'title': 'JODA7',
acf757f4 1927 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 1928 }
4b7df0d3
JMF
1929 }, {
1930 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1931 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1932 'info_dict': {
acf757f4
PH
1933 'title': 'Uploads from Interstellar Movie',
1934 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 1935 },
481cc733 1936 'playlist_mincount': 21,
dacb3a86
S
1937 }, {
1938 # Playlist URL that does not actually serve a playlist
1939 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1940 'info_dict': {
1941 'id': 'FqZTN594JQw',
1942 'ext': 'webm',
1943 'title': "Smiley's People 01 detective, Adventure Series, Action",
1944 'uploader': 'STREEM',
1945 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 1946 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
1947 'upload_date': '20150526',
1948 'license': 'Standard YouTube License',
1949 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1950 'categories': ['People & Blogs'],
1951 'tags': list,
1952 'like_count': int,
1953 'dislike_count': int,
1954 },
1955 'params': {
1956 'skip_download': True,
1957 },
1958 'add_ie': [YoutubeIE.ie_key()],
481cc733
S
1959 }, {
1960 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1961 'info_dict': {
1962 'id': 'yeWKywCrFtk',
1963 'ext': 'mp4',
1964 'title': 'Small Scale Baler and Braiding Rugs',
1965 'uploader': 'Backus-Page House Museum',
1966 'uploader_id': 'backuspagemuseum',
ec85ded8 1967 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
481cc733
S
1968 'upload_date': '20161008',
1969 'license': 'Standard YouTube License',
1970 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1971 'categories': ['Nonprofits & Activism'],
1972 'tags': list,
1973 'like_count': int,
1974 'dislike_count': int,
1975 },
1976 'params': {
1977 'noplaylist': True,
1978 'skip_download': True,
1979 },
feaa5ad7
S
1980 }, {
1981 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1982 'only_matching': True,
a6857510
S
1983 }, {
1984 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
1985 'only_matching': True,
81127aa5 1986 }]
c5e8d7af 1987
880e1c52
JMF
1988 def _real_initialize(self):
1989 self._login()
1990
652cdaa2 1991 def _extract_mix(self, playlist_id):
99209c29 1992 # The mixes are generated from a single video
652cdaa2 1993 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
1994 ids = []
1995 last_id = playlist_id[-11:]
1996 for n in itertools.count(1):
1997 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
1998 webpage = self._download_webpage(
1999 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2000 new_ids = orderedSet(re.findall(
2001 r'''(?xs)data-video-username=".*?".*?
2002 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
2003 webpage))
2004 # Fetch new pages until all the videos are repeated, it seems that
2005 # there are always 51 unique videos.
2006 new_ids = [_id for _id in new_ids if _id not in ids]
2007 if not new_ids:
2008 break
2009 ids.extend(new_ids)
2010 last_id = ids[-1]
2011
2012 url_results = self._ids_to_results(ids)
2013
bc2f773b 2014 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
2015 title_span = (
2016 search_title('playlist-title') or
2017 search_title('title long-title') or
2018 search_title('title'))
76d1700b 2019 title = clean_html(title_span)
652cdaa2
JMF
2020
2021 return self.playlist_result(url_results, playlist_id, title)
2022
448830ce 2023 def _extract_playlist(self, playlist_id):
dbb94fb0
S
2024 url = self._TEMPLATE_URL % playlist_id
2025 page = self._download_webpage(url, playlist_id)
dbb94fb0 2026
8bc0800d
G
2027 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2028 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
39b62db1
YCH
2029 match = match.strip()
2030 # Check if the playlist exists or is private
4201ba13
S
2031 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2032 if mobj:
2033 reason = mobj.group('reason')
2034 message = 'This playlist %s' % reason
2035 if 'private' in reason:
2036 message += ', use --username or --netrc to access it'
2037 message += '.'
2038 raise ExtractorError(message, expected=True)
39b62db1
YCH
2039 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2040 raise ExtractorError(
2041 'Invalid parameters. Maybe URL is incorrect.',
2042 expected=True)
2043 elif re.match(r'[^<]*Choose your language[^<]*', match):
2044 continue
2045 else:
2046 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 2047
dbb94fb0 2048 playlist_title = self._html_search_regex(
63b4295d 2049 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
dacb3a86 2050 page, 'title', default=None)
c5e8d7af 2051
dacb3a86
S
2052 has_videos = True
2053
2054 if not playlist_title:
2055 try:
2056 # Some playlist URLs don't actually serve a playlist (e.g.
2057 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2058 next(self._entries(page, playlist_id))
2059 except StopIteration:
2060 has_videos = False
2061
2062 return has_videos, self.playlist_result(
2063 self._entries(page, playlist_id), playlist_id, playlist_title)
c5e8d7af 2064
ebf1b291 2065 def _check_download_just_video(self, url, playlist_id):
448830ce
S
2066 # Check if it's a video-specific URL
2067 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
481cc733
S
2068 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2069 r'(?:^|//)youtu\.be/([0-9A-Za-z_-]{11})', url,
2070 'video id', default=None)
2071 if video_id:
448830ce
S
2072 if self._downloader.params.get('noplaylist'):
2073 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
dacb3a86 2074 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce
S
2075 else:
2076 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
dacb3a86
S
2077 return video_id, None
2078 return None, None
448830ce 2079
ebf1b291
S
2080 def _real_extract(self, url):
2081 # Extract playlist id
2082 mobj = re.match(self._VALID_URL, url)
2083 if mobj is None:
2084 raise ExtractorError('Invalid URL: %s' % url)
2085 playlist_id = mobj.group(1) or mobj.group(2)
2086
dacb3a86 2087 video_id, video = self._check_download_just_video(url, playlist_id)
ebf1b291
S
2088 if video:
2089 return video
2090
466a6145 2091 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
2092 # Mixes require a custom extraction process
2093 return self._extract_mix(playlist_id)
2094
dacb3a86
S
2095 has_videos, playlist = self._extract_playlist(playlist_id)
2096 if has_videos or not video_id:
2097 return playlist
2098
2099 # Some playlist URLs don't actually serve a playlist (see
2100 # https://github.com/rg3/youtube-dl/issues/10537).
2101 # Fallback to plain video extraction if there is a video id
2102 # along with playlist id.
2103 return self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce 2104
c5e8d7af 2105
648e6a1f 2106class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2107 IE_DESC = 'YouTube.com channels'
9ff67727 2108 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 2109 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 2110 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 2111 IE_NAME = 'youtube:channel'
cdc628a4
PH
2112 _TESTS = [{
2113 'note': 'paginated channel',
2114 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2115 'playlist_mincount': 91,
acf757f4 2116 'info_dict': {
9170ca5b
JMF
2117 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2118 'title': 'Uploads from lex will',
acf757f4 2119 }
5c43afd4
JMF
2120 }, {
2121 'note': 'Age restricted channel',
2122 # from https://www.youtube.com/user/DeusExOfficial
2123 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2124 'playlist_mincount': 64,
2125 'info_dict': {
2126 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2127 'title': 'Uploads from Deus Ex',
2128 },
cdc628a4 2129 }]
c5e8d7af 2130
e462474e
S
2131 @classmethod
2132 def suitable(cls, url):
f07e276a
S
2133 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2134 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 2135
9558dcec
S
2136 def _build_template_url(self, url, channel_id):
2137 return self._TEMPLATE_URL % channel_id
2138
c5e8d7af 2139 def _real_extract(self, url):
9ff67727 2140 channel_id = self._match_id(url)
c5e8d7af 2141
9558dcec 2142 url = self._build_template_url(url, channel_id)
386bdfa6
S
2143
2144 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2145 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2146 # otherwise fallback on channel by page extraction
2147 channel_page = self._download_webpage(
2148 url + '?view=57', channel_id,
2149 'Downloading channel page', fatal=False)
2b3c2546
PH
2150 if channel_page is False:
2151 channel_playlist_id = False
2152 else:
2153 channel_playlist_id = self._html_search_meta(
2154 'channelId', channel_page, 'channel id', default=None)
2155 if not channel_playlist_id:
73c4ac2c
S
2156 channel_url = self._html_search_meta(
2157 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2158 channel_page, 'channel url', default=None)
2159 if channel_url:
2160 channel_playlist_id = self._search_regex(
2161 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2162 channel_url, 'channel id', default=None)
386bdfa6
S
2163 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2164 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2165 return self.url_result(
2166 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2167
60bf45c8 2168 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2169 autogenerated = re.search(r'''(?x)
2170 class="[^"]*?(?:
2171 channel-header-autogenerated-label|
2172 yt-channel-title-autogenerated
2173 )[^"]*"''', channel_page) is not None
c5e8d7af 2174
b9643eed
JMF
2175 if autogenerated:
2176 # The videos are contained in a single page
2177 # the ajax pages can't be used, they are empty
b82f815f 2178 entries = [
fb69240c
S
2179 self.url_result(
2180 video_id, 'Youtube', video_id=video_id,
2181 video_title=video_title)
8f02ad4f 2182 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2183 return self.playlist_result(entries, channel_id)
2184
73c4ac2c
S
2185 try:
2186 next(self._entries(channel_page, channel_id))
2187 except StopIteration:
2188 alert_message = self._html_search_regex(
2189 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2190 channel_page, 'alert', default=None, group='alert')
2191 if alert_message:
2192 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2193
648e6a1f 2194 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2195
2196
eb0f3e7e 2197class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2198 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
9558dcec
S
2199 _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_-]+)'
2200 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
78caa52a 2201 IE_NAME = 'youtube:user'
c5e8d7af 2202
cdc628a4
PH
2203 _TESTS = [{
2204 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2205 'playlist_mincount': 320,
2206 'info_dict': {
73c4ac2c
S
2207 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2208 'title': 'Uploads from The Linux Foundation',
cdc628a4 2209 }
9558dcec
S
2210 }, {
2211 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2212 # but not https://www.youtube.com/user/12minuteathlete/videos
2213 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2214 'playlist_mincount': 249,
2215 'info_dict': {
2216 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2217 'title': 'Uploads from 12 Minute Athlete',
2218 }
cdc628a4
PH
2219 }, {
2220 'url': 'ytuser:phihag',
2221 'only_matching': True,
daa0df9e
YCH
2222 }, {
2223 'url': 'https://www.youtube.com/c/gametrailers',
2224 'only_matching': True,
9558dcec
S
2225 }, {
2226 'url': 'https://www.youtube.com/gametrailers',
2227 'only_matching': True,
73c4ac2c
S
2228 }, {
2229 # This channel is not available.
2230 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2231 'only_matching': True,
cdc628a4
PH
2232 }]
2233
e3ea4790 2234 @classmethod
f4b05232 2235 def suitable(cls, url):
e3ea4790
JMF
2236 # Don't return True if the url can be extracted with other youtube
2237 # extractor, the regex would is too permissive and it would match.
f3a58d46 2238 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2239 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2240 return False
2241 else:
2242 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2243
9558dcec
S
2244 def _build_template_url(self, url, channel_id):
2245 mobj = re.match(self._VALID_URL, url)
2246 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2247
b05654f0 2248
f07e276a
S
2249class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2250 IE_DESC = 'YouTube.com live streams'
073d5bf5 2251 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
f07e276a
S
2252 IE_NAME = 'youtube:live'
2253
2254 _TESTS = [{
2d3d2997 2255 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
f07e276a
S
2256 'info_dict': {
2257 'id': 'a48o2S1cPoo',
2258 'ext': 'mp4',
2259 'title': 'The Young Turks - Live Main Show',
2260 'uploader': 'The Young Turks',
2261 'uploader_id': 'TheYoungTurks',
ec85ded8 2262 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
f07e276a
S
2263 'upload_date': '20150715',
2264 'license': 'Standard YouTube License',
2265 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2266 'categories': ['News & Politics'],
2267 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2268 'like_count': int,
2269 'dislike_count': int,
2270 },
2271 'params': {
2272 'skip_download': True,
2273 },
2274 }, {
2d3d2997 2275 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
f07e276a 2276 'only_matching': True,
c1b2a085
S
2277 }, {
2278 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2279 'only_matching': True,
073d5bf5
S
2280 }, {
2281 'url': 'https://www.youtube.com/TheYoungTurks/live',
2282 'only_matching': True,
f07e276a
S
2283 }]
2284
2285 def _real_extract(self, url):
2286 mobj = re.match(self._VALID_URL, url)
2287 channel_id = mobj.group('id')
2288 base_url = mobj.group('base_url')
2289 webpage = self._download_webpage(url, channel_id, fatal=False)
2290 if webpage:
2291 page_type = self._og_search_property(
2292 'type', webpage, 'page type', default=None)
2293 video_id = self._html_search_meta(
2294 'videoId', webpage, 'video id', default=None)
2295 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2296 return self.url_result(video_id, YoutubeIE.ie_key())
2297 return self.url_result(base_url)
2298
2299
e462474e
S
2300class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2301 IE_DESC = 'YouTube.com user/channel playlists'
2302 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2303 IE_NAME = 'youtube:playlists'
0c148415 2304
e568c223 2305 _TESTS = [{
2d3d2997 2306 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
0c148415
S
2307 'playlist_mincount': 4,
2308 'info_dict': {
2309 'id': 'ThirstForScience',
2310 'title': 'Thirst for Science',
2311 },
e568c223
S
2312 }, {
2313 # with "Load more" button
2d3d2997 2314 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
e568c223
S
2315 'playlist_mincount': 70,
2316 'info_dict': {
2317 'id': 'igorkle1',
2318 'title': 'Игорь Клейнер',
2319 },
e462474e
S
2320 }, {
2321 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2322 'playlist_mincount': 17,
2323 'info_dict': {
2324 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2325 'title': 'Chem Player',
2326 },
e568c223 2327 }]
0c148415
S
2328
2329
b4c08069 2330class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
78caa52a 2331 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2332 # there doesn't appear to be a real limit, for example if you search for
2333 # 'python' you get more than 8.000.000 results
2334 _MAX_RESULTS = float('inf')
78caa52a 2335 IE_NAME = 'youtube:search'
b05654f0 2336 _SEARCH_KEY = 'ytsearch'
b4c08069 2337 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2338 _TESTS = []
b05654f0 2339
b05654f0
PH
2340 def _get_n_results(self, query, n):
2341 """Get a specified number of results for a query"""
2342
b4c08069 2343 videos = []
b05654f0
PH
2344 limit = n
2345
a22b2fd1
YCH
2346 url_query = {
2347 'search_query': query.encode('utf-8'),
2348 }
2349 url_query.update(self._EXTRA_QUERY_ARGS)
2350 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2351
b4c08069 2352 for pagenum in itertools.count(1):
b4c08069 2353 data = self._download_json(
69ea8ca4 2354 result_url, video_id='query "%s"' % query,
b4c08069 2355 note='Downloading page %s' % pagenum,
a22b2fd1
YCH
2356 errnote='Unable to download API page',
2357 query={'spf': 'navigate'})
b4c08069 2358 html_content = data[1]['body']['content']
7cc3570e 2359
b4c08069 2360 if 'class="search-message' in html_content:
07ad22b8 2361 raise ExtractorError(
78caa52a 2362 '[youtube] No video results', expected=True)
b05654f0 2363
b4c08069
JMF
2364 new_videos = self._ids_to_results(orderedSet(re.findall(
2365 r'href="/watch\?v=(.{11})', html_content)))
2366 videos += new_videos
2367 if not new_videos or len(videos) > limit:
2368 break
a22b2fd1
YCH
2369 next_link = self._html_search_regex(
2370 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2371 html_content, 'next link', default=None)
2372 if next_link is None:
2373 break
2374 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
b05654f0 2375
b4c08069
JMF
2376 if len(videos) > n:
2377 videos = videos[:n]
b05654f0 2378 return self.playlist_result(videos, query)
75dff0ee 2379
c9ae7b95 2380
a3dd9248 2381class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2382 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2383 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2384 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2385 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2386
c9ae7b95 2387
175c2e9e 2388class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
78caa52a
PH
2389 IE_DESC = 'YouTube.com search URLs'
2390 IE_NAME = 'youtube:search_url'
d2c1f79f 2391 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
175c2e9e 2392 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
cdc628a4
PH
2393 _TESTS = [{
2394 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2395 'playlist_mincount': 5,
2396 'info_dict': {
2397 'title': 'youtube-dl test video',
2398 }
d2c1f79f
S
2399 }, {
2400 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2401 'only_matching': True,
cdc628a4 2402 }]
c9ae7b95
PH
2403
2404 def _real_extract(self, url):
2405 mobj = re.match(self._VALID_URL, url)
7fd002c0 2406 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2407 webpage = self._download_webpage(url, query)
175c2e9e 2408 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2409
2410
136dadde 2411class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2412 IE_DESC = 'YouTube.com (multi-season) shows'
92519402 2413 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2414 IE_NAME = 'youtube:show'
cdc628a4 2415 _TESTS = [{
4003bd82 2416 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2417 'playlist_mincount': 5,
cdc628a4
PH
2418 'info_dict': {
2419 'id': 'airdisasters',
2420 'title': 'Air Disasters',
2421 }
2422 }]
75dff0ee
JMF
2423
2424 def _real_extract(self, url):
136dadde
S
2425 playlist_id = self._match_id(url)
2426 return super(YoutubeShowIE, self)._real_extract(
2427 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2428
2429
b2e8bc1b 2430class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2431 """
25f14e9f 2432 Base class for feed extractors
d7ae0639
JMF
2433 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2434 """
b2e8bc1b 2435 _LOGIN_REQUIRED = True
d7ae0639
JMF
2436
2437 @property
2438 def IE_NAME(self):
78caa52a 2439 return 'youtube:%s' % self._FEED_NAME
04cc9617 2440
81f0259b 2441 def _real_initialize(self):
b2e8bc1b 2442 self._login()
81f0259b 2443
04cc9617 2444 def _real_extract(self, url):
25f14e9f
S
2445 page = self._download_webpage(
2446 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2bc43303
JMF
2447
2448 # The extraction process is the same as for playlists, but the regex
2449 # for the video ids doesn't contain an index
2450 ids = []
2451 more_widget_html = content_html = page
2bc43303
JMF
2452 for page_num in itertools.count(1):
2453 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2454
2455 # 'recommended' feed has infinite 'load more' and each new portion spins
2456 # the same videos in (sometimes) slightly different order, so we'll check
2457 # for unicity and break when portion has no new videos
2458 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2459 if not new_ids:
2460 break
2461
2bc43303
JMF
2462 ids.extend(new_ids)
2463
2464 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2465 if not mobj:
2466 break
2467
2468 more = self._download_json(
25f14e9f 2469 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2470 'Downloading page #%s' % page_num,
2471 transform_source=uppercase_escape)
2472 content_html = more['content_html']
2473 more_widget_html = more['load_more_widget_html']
2474
25f14e9f
S
2475 return self.playlist_result(
2476 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2477
2478
2479class YoutubeWatchLaterIE(YoutubePlaylistIE):
2480 IE_NAME = 'youtube:watchlater'
2481 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
92519402 2482 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2483
bc7a9cd8
S
2484 _TESTS = [{
2485 'url': 'https://www.youtube.com/playlist?list=WL',
2486 'only_matching': True,
2487 }, {
2488 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2489 'only_matching': True,
2490 }]
25f14e9f
S
2491
2492 def _real_extract(self, url):
7e5dc339 2493 _, video = self._check_download_just_video(url, 'WL')
ebf1b291
S
2494 if video:
2495 return video
dacb3a86
S
2496 _, playlist = self._extract_playlist('WL')
2497 return playlist
f459d170 2498
5f6a1245 2499
c626a3d9 2500class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2501 IE_NAME = 'youtube:favorites'
f3a34072 2502 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
92519402 2503 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2504 _LOGIN_REQUIRED = True
2505
2506 def _real_extract(self, url):
2507 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2508 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2509 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2510
2511
25f14e9f
S
2512class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2513 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
92519402 2514 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
25f14e9f
S
2515 _FEED_NAME = 'recommended'
2516 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2517
1ed5b5c9 2518
25f14e9f
S
2519class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2520 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
92519402 2521 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
25f14e9f
S
2522 _FEED_NAME = 'subscriptions'
2523 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2524
1ed5b5c9 2525
25f14e9f
S
2526class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2527 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
92519402 2528 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
25f14e9f
S
2529 _FEED_NAME = 'history'
2530 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2531
2532
15870e90
PH
2533class YoutubeTruncatedURLIE(InfoExtractor):
2534 IE_NAME = 'youtube:truncated_url'
2535 IE_DESC = False # Do not list
975d35db 2536 _VALID_URL = r'''(?x)
b95aab84
PH
2537 (?:https?://)?
2538 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2539 (?:watch\?(?:
c4808c60 2540 feature=[a-z_]+|
b95aab84
PH
2541 annotation_id=annotation_[^&]+|
2542 x-yt-cl=[0-9]+|
c1708b89 2543 hl=[^&]*|
287be8c6 2544 t=[0-9]+
b95aab84
PH
2545 )?
2546 |
2547 attribution_link\?a=[^&]+
2548 )
2549 $
975d35db 2550 '''
15870e90 2551
c4808c60 2552 _TESTS = [{
2d3d2997 2553 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 2554 'only_matching': True,
dc2fc736 2555 }, {
2d3d2997 2556 'url': 'https://www.youtube.com/watch?',
dc2fc736 2557 'only_matching': True,
b95aab84
PH
2558 }, {
2559 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2560 'only_matching': True,
2561 }, {
2562 'url': 'https://www.youtube.com/watch?feature=foo',
2563 'only_matching': True,
c1708b89
PH
2564 }, {
2565 'url': 'https://www.youtube.com/watch?hl=en-GB',
2566 'only_matching': True,
287be8c6
PH
2567 }, {
2568 'url': 'https://www.youtube.com/watch?t=2372',
2569 'only_matching': True,
c4808c60
PH
2570 }]
2571
15870e90
PH
2572 def _real_extract(self, url):
2573 raise ExtractorError(
78caa52a
PH
2574 'Did you forget to quote the URL? Remember that & is a meta '
2575 'character in most shells, so you want to put the URL in quotes, '
2576 'like youtube-dl '
2d3d2997 2577 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
78caa52a 2578 ' or simply youtube-dl BaW_jenozKc .',
15870e90 2579 expected=True)
772fd5cc
PH
2580
2581
2582class YoutubeTruncatedIDIE(InfoExtractor):
2583 IE_NAME = 'youtube:truncated_id'
2584 IE_DESC = False # Do not list
b95aab84 2585 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
2586
2587 _TESTS = [{
2588 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2589 'only_matching': True,
2590 }]
2591
2592 def _real_extract(self, url):
2593 video_id = self._match_id(url)
2594 raise ExtractorError(
2595 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
2596 expected=True)