]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[youtube:playlist] Recognize another playlist pattern (closes #11928, closes #12286)
[yt-dlp.git] / youtube_dl / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
5
0ca96d48 6import itertools
c5e8d7af 7import json
c4417ddb 8import os.path
d77ab8e2 9import random
c5e8d7af 10import re
42939b61 11import time
e0df6211 12import traceback
c5e8d7af 13
b05654f0 14from .common import InfoExtractor, SearchInfoExtractor
2b25cb5d 15from ..jsinterp import JSInterpreter
54256267 16from ..swfinterp import SWFInterpreter
4bb4a188 17from ..compat import (
edf3e38e 18 compat_chr,
c5e8d7af 19 compat_parse_qs,
7fd002c0
S
20 compat_urllib_parse_unquote,
21 compat_urllib_parse_unquote_plus,
15707c7e 22 compat_urllib_parse_urlencode,
7c80519c 23 compat_urllib_parse_urlparse,
7c61bd36 24 compat_urlparse,
c5e8d7af 25 compat_str,
4bb4a188
PH
26)
27from ..utils import (
c5e8d7af 28 clean_html,
9b9c5355 29 error_to_compat_str,
c5e8d7af 30 ExtractorError,
2d30521a 31 float_or_none,
4bb4a188
PH
32 get_element_by_attribute,
33 get_element_by_id,
dd27fd17 34 int_or_none,
94278f72 35 mimetype2ext,
4bb4a188 36 orderedSet,
6310acf5 37 parse_codecs,
7c80519c 38 parse_duration,
0cb58b02 39 remove_quotes,
041bc3ad 40 remove_start,
5c2266df 41 sanitized_Request,
cf7e015f 42 smuggle_url,
c93d53f5 43 str_to_int,
556dbe7f 44 try_get,
c5e8d7af
PH
45 unescapeHTML,
46 unified_strdate,
cf7e015f 47 unsmuggle_url,
81c2f20b 48 uppercase_escape,
6e6bc8da 49 urlencode_postdata,
c5e8d7af
PH
50)
51
5f6a1245 52
de7f3446 53class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b
JMF
54 """Provide base functions for Youtube extractors"""
55 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
9303ce3e 56 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
e298d3a0 57 _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
b2e8bc1b
JMF
58 _NETRC_MACHINE = 'youtube'
59 # If True it will raise an error if no login info is provided
60 _LOGIN_REQUIRED = False
61
b2e8bc1b 62 def _set_language(self):
810fb84d
PH
63 self._set_cookie(
64 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
42939b61 65 # YouTube sets the expire time to about two months
810fb84d 66 expire_time=time.time() + 2 * 30 * 24 * 3600)
b2e8bc1b 67
25f14e9f
S
68 def _ids_to_results(self, ids):
69 return [
70 self.url_result(vid_id, 'Youtube', video_id=vid_id)
71 for vid_id in ids]
72
b2e8bc1b 73 def _login(self):
83317f69 74 """
75 Attempt to log in to YouTube.
76 True is returned if successful or skipped.
77 False is returned if login failed.
78
79 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
80 """
b2e8bc1b
JMF
81 (username, password) = self._get_login_info()
82 # No authentication to be performed
83 if username is None:
84 if self._LOGIN_REQUIRED:
69ea8ca4 85 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
83317f69 86 return True
b2e8bc1b 87
7cc3570e
PH
88 login_page = self._download_webpage(
89 self._LOGIN_URL, None,
69ea8ca4
PH
90 note='Downloading login page',
91 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
92 if login_page is False:
93 return
b2e8bc1b 94
1212e997 95 login_form = self._hidden_inputs(login_page)
c5e8d7af 96
1212e997 97 login_form.update({
05bddcc5 98 'checkConnection': 'youtube',
8bcc8756 99 'Email': username,
8bcc8756 100 'Passwd': password,
1212e997 101 })
83317f69 102
7cc3570e 103 login_results = self._download_webpage(
e298d3a0
S
104 self._PASSWORD_CHALLENGE_URL, None,
105 note='Logging in', errnote='unable to log in', fatal=False,
1212e997 106 data=urlencode_postdata(login_form))
7cc3570e
PH
107 if login_results is False:
108 return False
83317f69 109
494ab6db
S
110 error_msg = self._html_search_regex(
111 r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
112 login_results, 'error message', default=None)
113 if error_msg:
114 raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
115
83317f69 116 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
69ea8ca4 117 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
83317f69 118
119 # Two-Factor
120 # TODO add SMS and phone call support - these require making a request and then prompting the user
121
e9fb6a4b 122 if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
041bc3ad 123 tfa_code = self._get_tfa_info('2-step verification code')
83317f69 124
041bc3ad
S
125 if not tfa_code:
126 self._downloader.report_warning(
127 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
128 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
83317f69 129 return False
130
041bc3ad
S
131 tfa_code = remove_start(tfa_code, 'G-')
132
133 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
134
135 tfa_form_strs.update({
9303ce3e 136 'Pin': tfa_code,
137 'TrustDevice': 'on',
041bc3ad
S
138 })
139
6e6bc8da 140 tfa_data = urlencode_postdata(tfa_form_strs)
83317f69 141
5c2266df 142 tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
83317f69 143 tfa_results = self._download_webpage(
144 tfa_req, None,
69ea8ca4 145 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
83317f69 146
147 if tfa_results is False:
148 return False
149
e9fb6a4b 150 if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
041bc3ad 151 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
83317f69 152 return False
e9fb6a4b 153 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
69ea8ca4 154 self._downloader.report_warning('unable to log in - did the page structure change?')
83317f69 155 return False
156 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
69ea8ca4 157 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 158 return False
159
e9fb6a4b 160 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
69ea8ca4 161 self._downloader.report_warning('unable to log in: bad username or password')
b2e8bc1b
JMF
162 return False
163 return True
164
b2e8bc1b
JMF
165 def _real_initialize(self):
166 if self._downloader is None:
167 return
42939b61 168 self._set_language()
b2e8bc1b
JMF
169 if not self._login():
170 return
c5e8d7af 171
8377574c 172
8e7aad20 173class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
061a75ed 174 # Extract entries from page with "Load more" button
648e6a1f
S
175 def _entries(self, page, playlist_id):
176 more_widget_html = content_html = page
177 for page_num in itertools.count(1):
061a75ed
S
178 for entry in self._process_page(content_html):
179 yield entry
648e6a1f
S
180
181 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
182 if not mobj:
183 break
184
185 more = self._download_json(
186 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
187 'Downloading page #%s' % page_num,
188 transform_source=uppercase_escape)
189 content_html = more['content_html']
190 if not content_html.strip():
191 # Some webpages show a "Load more" button but they don't
192 # have more videos
193 break
194 more_widget_html = more['load_more_widget_html']
195
061a75ed
S
196
197class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
198 def _process_page(self, content):
199 for video_id, video_title in self.extract_videos_from_page(content):
200 yield self.url_result(video_id, 'Youtube', video_id, video_title)
201
648e6a1f
S
202 def extract_videos_from_page(self, page):
203 ids_in_page = []
204 titles_in_page = []
205 for mobj in re.finditer(self._VIDEO_RE, page):
206 # The link with index 0 is not the first video of the playlist (not sure if still actual)
207 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
208 continue
209 video_id = mobj.group('id')
210 video_title = unescapeHTML(mobj.group('title'))
211 if video_title:
212 video_title = video_title.strip()
213 try:
214 idx = ids_in_page.index(video_id)
215 if video_title and not titles_in_page[idx]:
216 titles_in_page[idx] = video_title
217 except ValueError:
218 ids_in_page.append(video_id)
219 titles_in_page.append(video_title)
220 return zip(ids_in_page, titles_in_page)
221
222
061a75ed
S
223class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
224 def _process_page(self, content):
6dee688e
S
225 for playlist_id in orderedSet(re.findall(
226 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
227 content)):
061a75ed
S
228 yield self.url_result(
229 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
230
0c148415
S
231 def _real_extract(self, url):
232 playlist_id = self._match_id(url)
233 webpage = self._download_webpage(url, playlist_id)
0c148415 234 title = self._og_search_title(webpage, fatal=False)
061a75ed 235 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
0c148415
S
236
237
360e1ca5 238class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 239 IE_DESC = 'YouTube.com'
cb7dfeea 240 _VALID_URL = r"""(?x)^
c5e8d7af 241 (
edb53e2d 242 (?:https?://|//) # http(s):// or protocol-independent URL
cb7dfeea 243 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
484aaeb2 244 (?:www\.)?deturl\.com/www\.youtube\.com/|
e70dc1d1 245 (?:www\.)?pwnyoutube\.com/|
f7000f3a 246 (?:www\.)?yourepeat\.com/|
e69ae5b9
JMF
247 tube\.majestyc\.net/|
248 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
c5e8d7af
PH
249 (?:.*?\#/)? # handle anchor (#/) redirect urls
250 (?: # the various things that can precede the ID:
ac7553d0 251 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 252 |(?: # or the v= param in all its forms
f7000f3a 253 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 254 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 255 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
256 v=
257 )
f4b05232 258 ))
cbaed4bb
S
259 |(?:
260 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
261 vid\.plus| # or vid.plus/xxxx
262 zwearz\.com/watch| # or zwearz.com/watch/xxxx
cbaed4bb 263 )/
edb53e2d 264 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 265 )
c5e8d7af 266 )? # all until now is optional -> you can pass the naked ID
8963d9c2 267 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
feaa5ad7 268 (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
c5e8d7af
PH
269 (?(1).+)? # if we found the ID, everything can follow
270 $"""
c5e8d7af 271 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
2c62dc26 272 _formats = {
c2d3cb4c 273 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
274 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
275 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
276 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
277 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
278 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
279 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
280 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 281 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 282 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
283 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
284 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
285 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
286 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
287 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 288 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 289 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
290 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 291
292
293 # 3D videos
c2d3cb4c 294 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
295 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
296 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
297 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 298 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
299 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
300 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 301
96fb5605 302 # Apple HTTP Live Streaming
11f12195 303 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 304 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
305 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
306 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
307 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
308 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 309 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
310 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
311
312 # DASH mp4 video
c2d3cb4c 313 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
314 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
315 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
316 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
317 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
318 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
319 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
8409b368 320 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
a6c2c244
YCH
321 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
322 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
323 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
324 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
836a086c 325
f6f1fc92 326 # Dash mp4 audio
c2d3cb4c 327 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
328 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
329 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
2c347352
S
330 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
331 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
605fd639
RA
332 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
333 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'preference': -50, 'container': 'm4a_dash'},
836a086c
AZ
334
335 # Dash webm
a6c2c244
YCH
336 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
337 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
338 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
339 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
340 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
341 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
342 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
343 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
344 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
345 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
346 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
347 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
348 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
349 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
350 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
4c6b4764 351 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
a6c2c244
YCH
352 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
353 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
354 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
355 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
356 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
357 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
2c62dc26
PH
358
359 # Dash webm audio
a6c2c244
YCH
360 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
361 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
ce6b9a2d 362
0857baad 363 # Dash webm audio with opus inside
a6c2c244
YCH
364 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
365 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
366 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
0857baad 367
ce6b9a2d
PH
368 # RTMP (unnamed)
369 '_rtmp': {'protocol': 'rtmp'},
c5e8d7af 370 }
23d17e4b 371 _SUBTITLE_FORMATS = ('ttml', 'vtt')
836a086c 372
fd5c4aab
S
373 _GEO_BYPASS = False
374
78caa52a 375 IE_NAME = 'youtube'
2eb88d95
PH
376 _TESTS = [
377 {
2d3d2997 378 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
379 'info_dict': {
380 'id': 'BaW_jenozKc',
381 'ext': 'mp4',
382 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
383 'uploader': 'Philipp Hagemeister',
384 'uploader_id': 'phihag',
ec85ded8 385 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
4bc3a23e 386 'upload_date': '20121002',
7caf9830 387 'license': 'Standard YouTube License',
4bc3a23e
PH
388 '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 .',
389 'categories': ['Science & Technology'],
000b6b5a 390 'tags': ['youtube-dl'],
556dbe7f 391 'duration': 10,
3e7c1224
PH
392 'like_count': int,
393 'dislike_count': int,
7c80519c 394 'start_time': 1,
297a564b 395 'end_time': 9,
2eb88d95 396 }
0e853ca4 397 },
0e853ca4 398 {
2d3d2997 399 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
4bc3a23e
PH
400 'note': 'Test generic use_cipher_signature video (#897)',
401 'info_dict': {
402 'id': 'UxxajLWwzqY',
403 'ext': 'mp4',
404 'upload_date': '20120506',
405 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
0cb58b02 406 'alt_title': 'I Love It (feat. Charli XCX)',
7caf9830 407 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
000b6b5a
S
408 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
409 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
410 'iconic ep', 'iconic', 'love', 'it'],
556dbe7f 411 'duration': 180,
4bc3a23e
PH
412 'uploader': 'Icona Pop',
413 'uploader_id': 'IconaPop',
ec85ded8 414 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
7caf9830 415 'license': 'Standard YouTube License',
0cb58b02 416 'creator': 'Icona Pop',
2eb88d95 417 }
c108eb73
JMF
418 },
419 {
4bc3a23e
PH
420 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
421 'note': 'Test VEVO video with age protection (#956)',
422 'info_dict': {
423 'id': '07FYdnEawAQ',
424 'ext': 'mp4',
425 'upload_date': '20130703',
426 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
0cb58b02 427 'alt_title': 'Tunnel Vision',
4bc3a23e 428 'description': 'md5:64249768eec3bc4276236606ea996373',
556dbe7f 429 'duration': 419,
4bc3a23e
PH
430 'uploader': 'justintimberlakeVEVO',
431 'uploader_id': 'justintimberlakeVEVO',
ec85ded8 432 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
7caf9830 433 'license': 'Standard YouTube License',
0cb58b02 434 'creator': 'Justin Timberlake',
34952f09 435 'age_limit': 18,
c108eb73
JMF
436 }
437 },
fccd3771 438 {
4bc3a23e
PH
439 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
440 'note': 'Embed-only video (#1746)',
441 'info_dict': {
442 'id': 'yZIXLfi8CZQ',
443 'ext': 'mp4',
444 'upload_date': '20120608',
445 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
446 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
447 'uploader': 'SET India',
94bfcd23 448 'uploader_id': 'setindia',
ec85ded8 449 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
7caf9830 450 'license': 'Standard YouTube License',
94bfcd23 451 'age_limit': 18,
fccd3771
PH
452 }
453 },
11b56058 454 {
2d3d2997 455 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
11b56058
PM
456 'note': 'Use the first video ID in the URL',
457 'info_dict': {
458 'id': 'BaW_jenozKc',
459 'ext': 'mp4',
460 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
461 'uploader': 'Philipp Hagemeister',
462 'uploader_id': 'phihag',
ec85ded8 463 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 464 'upload_date': '20121002',
7caf9830 465 'license': 'Standard YouTube License',
11b56058
PM
466 '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 .',
467 'categories': ['Science & Technology'],
468 'tags': ['youtube-dl'],
556dbe7f 469 'duration': 10,
11b56058
PM
470 'like_count': int,
471 'dislike_count': int,
34a7de29
S
472 },
473 'params': {
474 'skip_download': True,
475 },
11b56058 476 },
dd27fd17 477 {
2d3d2997 478 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
479 'note': '256k DASH audio (format 141) via DASH manifest',
480 'info_dict': {
481 'id': 'a9LDPn-MO4I',
482 'ext': 'm4a',
483 'upload_date': '20121002',
484 'uploader_id': '8KVIDEO',
ec85ded8 485 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
486 'description': '',
487 'uploader': '8KVIDEO',
7caf9830 488 'license': 'Standard YouTube License',
4bc3a23e 489 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 490 },
4bc3a23e
PH
491 'params': {
492 'youtube_include_dash_manifest': True,
493 'format': '141',
4919603f 494 },
de3c7fe0 495 'skip': 'format 141 not served anymore',
dd27fd17 496 },
3489b7d2
JMF
497 # DASH manifest with encrypted signature
498 {
78caa52a
PH
499 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
500 'info_dict': {
501 'id': 'IB3lcPjvWLA',
502 'ext': 'm4a',
b766eb27
JMF
503 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
504 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
556dbe7f 505 'duration': 244,
78caa52a
PH
506 'uploader': 'AfrojackVEVO',
507 'uploader_id': 'AfrojackVEVO',
508 'upload_date': '20131011',
7caf9830 509 'license': 'Standard YouTube License',
3489b7d2 510 },
4bc3a23e 511 'params': {
78caa52a 512 'youtube_include_dash_manifest': True,
de3c7fe0 513 'format': '141/bestaudio[ext=m4a]',
3489b7d2
JMF
514 },
515 },
aaeb86f6
S
516 # JS player signature function name containing $
517 {
518 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
519 'info_dict': {
520 'id': 'nfWlot6h_JM',
521 'ext': 'm4a',
522 'title': 'Taylor Swift - Shake It Off',
0cb58b02 523 'alt_title': 'Shake It Off',
f57b7835 524 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
556dbe7f 525 'duration': 242,
aaeb86f6
S
526 'uploader': 'TaylorSwiftVEVO',
527 'uploader_id': 'TaylorSwiftVEVO',
528 'upload_date': '20140818',
7caf9830 529 'license': 'Standard YouTube License',
0cb58b02 530 'creator': 'Taylor Swift',
aaeb86f6
S
531 },
532 'params': {
533 'youtube_include_dash_manifest': True,
de3c7fe0 534 'format': '141/bestaudio[ext=m4a]',
aaeb86f6
S
535 },
536 },
aa79ac0c
PH
537 # Controversy video
538 {
539 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
540 'info_dict': {
541 'id': 'T4XJQO3qol8',
542 'ext': 'mp4',
556dbe7f 543 'duration': 219,
aa79ac0c
PH
544 'upload_date': '20100909',
545 'uploader': 'The Amazing Atheist',
546 'uploader_id': 'TheAmazingAtheist',
ec85ded8 547 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
7caf9830 548 'license': 'Standard YouTube License',
aa79ac0c
PH
549 'title': 'Burning Everyone\'s Koran',
550 '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',
551 }
c522adb1
JMF
552 },
553 # Normal age-gate video (No vevo, embed allowed)
554 {
2d3d2997 555 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
556 'info_dict': {
557 'id': 'HtVdAasjOgU',
558 'ext': 'mp4',
559 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 560 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 561 'duration': 142,
c522adb1
JMF
562 'uploader': 'The Witcher',
563 'uploader_id': 'WitcherGame',
ec85ded8 564 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 565 'upload_date': '20140605',
7caf9830 566 'license': 'Standard YouTube License',
34952f09 567 'age_limit': 18,
c522adb1
JMF
568 },
569 },
fccae2b9
S
570 # Age-gate video with encrypted signature
571 {
2d3d2997 572 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
fccae2b9
S
573 'info_dict': {
574 'id': '6kLq3WMV1nU',
575 'ext': 'mp4',
576 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
577 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
556dbe7f 578 'duration': 247,
fccae2b9
S
579 'uploader': 'LloydVEVO',
580 'uploader_id': 'LloydVEVO',
ec85ded8 581 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
fccae2b9 582 'upload_date': '20110629',
7caf9830 583 'license': 'Standard YouTube License',
34952f09 584 'age_limit': 18,
fccae2b9
S
585 },
586 },
774e208f
PH
587 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
588 {
589 'url': '__2ABJjxzNo',
590 'info_dict': {
591 'id': '__2ABJjxzNo',
592 'ext': 'mp4',
556dbe7f 593 'duration': 266,
774e208f
PH
594 'upload_date': '20100430',
595 'uploader_id': 'deadmau5',
ec85ded8 596 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
0cb58b02 597 'creator': 'deadmau5',
774e208f
PH
598 'description': 'md5:12c56784b8032162bb936a5f76d55360',
599 'uploader': 'deadmau5',
7caf9830 600 'license': 'Standard YouTube License',
774e208f 601 'title': 'Deadmau5 - Some Chords (HD)',
0cb58b02 602 'alt_title': 'Some Chords',
774e208f
PH
603 },
604 'expected_warnings': [
605 'DASH manifest missing',
606 ]
e52a40ab
PH
607 },
608 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
609 {
610 'url': 'lqQg6PlCWgI',
611 'info_dict': {
612 'id': 'lqQg6PlCWgI',
613 'ext': 'mp4',
556dbe7f 614 'duration': 6085,
90227264 615 'upload_date': '20150827',
cbe2bd91 616 'uploader_id': 'olympic',
ec85ded8 617 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
7caf9830 618 'license': 'Standard YouTube License',
cbe2bd91 619 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
be49068d 620 'uploader': 'Olympic',
cbe2bd91
PH
621 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
622 },
623 'params': {
624 'skip_download': 'requires avconv',
e52a40ab 625 }
cbe2bd91 626 },
6271f1ca
PH
627 # Non-square pixels
628 {
629 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
630 'info_dict': {
631 'id': '_b-2C3KPAM0',
632 'ext': 'mp4',
633 'stretched_ratio': 16 / 9.,
556dbe7f 634 'duration': 85,
6271f1ca
PH
635 'upload_date': '20110310',
636 'uploader_id': 'AllenMeow',
ec85ded8 637 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca
PH
638 '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',
639 'uploader': '孫艾倫',
7caf9830 640 'license': 'Standard YouTube License',
6271f1ca
PH
641 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
642 },
06b491eb
S
643 },
644 # url_encoded_fmt_stream_map is empty string
645 {
646 'url': 'qEJwOuvDf7I',
647 'info_dict': {
648 'id': 'qEJwOuvDf7I',
f57b7835 649 'ext': 'webm',
06b491eb
S
650 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
651 'description': '',
652 'upload_date': '20150404',
653 'uploader_id': 'spbelect',
654 'uploader': 'Наблюдатели Петербурга',
655 },
656 'params': {
657 'skip_download': 'requires avconv',
e323cf3f
S
658 },
659 'skip': 'This live event has ended.',
06b491eb 660 },
da77d856
S
661 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
662 {
663 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
664 'info_dict': {
665 'id': 'FIl7x6_3R5Y',
666 'ext': 'mp4',
667 'title': 'md5:7b81415841e02ecd4313668cde88737a',
668 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 669 'duration': 220,
da77d856
S
670 'upload_date': '20150625',
671 'uploader_id': 'dorappi2000',
ec85ded8 672 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 673 'uploader': 'dorappi2000',
7caf9830 674 'license': 'Standard YouTube License',
be49068d 675 'formats': 'mincount:32',
da77d856 676 },
2ee8f5d8 677 },
8a1a26ce
YCH
678 # DASH manifest with segment_list
679 {
680 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
681 'md5': '8ce563a1d667b599d21064e982ab9e31',
682 'info_dict': {
683 'id': 'CsmdDsKjzN8',
684 'ext': 'mp4',
17ee98e1 685 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
686 'uploader': 'Airtek',
687 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
688 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
7caf9830 689 'license': 'Standard YouTube License',
8a1a26ce
YCH
690 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
691 },
692 'params': {
693 'youtube_include_dash_manifest': True,
694 'format': '135', # bestvideo
be49068d
S
695 },
696 'skip': 'This live event has ended.',
2ee8f5d8 697 },
cf7e015f
S
698 {
699 # Multifeed videos (multiple cameras), URL is for Main Camera
700 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
701 'info_dict': {
702 'id': 'jqWvoWXjCVs',
703 'title': 'teamPGP: Rocket League Noob Stream',
704 'description': 'md5:dc7872fb300e143831327f1bae3af010',
705 },
706 'playlist': [{
707 'info_dict': {
708 'id': 'jqWvoWXjCVs',
709 'ext': 'mp4',
710 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
711 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 712 'duration': 7335,
cf7e015f
S
713 'upload_date': '20150721',
714 'uploader': 'Beer Games Beer',
715 'uploader_id': 'beergamesbeer',
ec85ded8 716 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 717 'license': 'Standard YouTube License',
cf7e015f
S
718 },
719 }, {
720 'info_dict': {
721 'id': '6h8e8xoXJzg',
722 'ext': 'mp4',
723 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
724 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 725 'duration': 7337,
cf7e015f
S
726 'upload_date': '20150721',
727 'uploader': 'Beer Games Beer',
728 'uploader_id': 'beergamesbeer',
ec85ded8 729 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 730 'license': 'Standard YouTube License',
cf7e015f
S
731 },
732 }, {
733 'info_dict': {
734 'id': 'PUOgX5z9xZw',
735 'ext': 'mp4',
736 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
737 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 738 'duration': 7337,
cf7e015f
S
739 'upload_date': '20150721',
740 'uploader': 'Beer Games Beer',
741 'uploader_id': 'beergamesbeer',
ec85ded8 742 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 743 'license': 'Standard YouTube License',
cf7e015f
S
744 },
745 }, {
746 'info_dict': {
747 'id': 'teuwxikvS5k',
748 'ext': 'mp4',
749 'title': 'teamPGP: Rocket League Noob Stream (zim)',
750 'description': 'md5:dc7872fb300e143831327f1bae3af010',
556dbe7f 751 'duration': 7334,
cf7e015f
S
752 'upload_date': '20150721',
753 'uploader': 'Beer Games Beer',
754 'uploader_id': 'beergamesbeer',
ec85ded8 755 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 756 'license': 'Standard YouTube License',
cf7e015f
S
757 },
758 }],
759 'params': {
760 'skip_download': True,
761 },
cbaed4bb 762 },
f9f49d87
S
763 {
764 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
765 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
766 'info_dict': {
767 'id': 'gVfLd0zydlo',
768 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
769 },
770 'playlist_count': 2,
be49068d 771 'skip': 'Not multifeed anymore',
f9f49d87 772 },
cbaed4bb 773 {
2d3d2997 774 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 775 'only_matching': True,
0e49d9a6 776 },
6d4fc66b 777 {
2d3d2997 778 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
779 'only_matching': True,
780 },
0e49d9a6 781 {
61f92af1 782 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
a8776b10
S
783 # Also tests cut-off URL expansion in video description (see
784 # https://github.com/rg3/youtube-dl/issues/1892,
785 # https://github.com/rg3/youtube-dl/issues/8164)
0e49d9a6
LL
786 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
787 'info_dict': {
788 'id': 'lsguqyKfVQg',
789 'ext': 'mp4',
790 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
0cb58b02 791 'alt_title': 'Dark Walk',
0e49d9a6 792 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 793 'duration': 133,
0e49d9a6
LL
794 'upload_date': '20151119',
795 'uploader_id': 'IronSoulElf',
ec85ded8 796 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 797 'uploader': 'IronSoulElf',
7caf9830 798 'license': 'Standard YouTube License',
0cb58b02 799 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
0e49d9a6
LL
800 },
801 'params': {
802 'skip_download': True,
803 },
804 },
61f92af1
S
805 {
806 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
807 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
808 'only_matching': True,
809 },
313dfc45
LL
810 {
811 # Video with yt:stretch=17:0
812 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
813 'info_dict': {
814 'id': 'Q39EVAstoRM',
815 'ext': 'mp4',
816 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
817 'description': 'md5:ee18a25c350637c8faff806845bddee9',
818 'upload_date': '20151107',
819 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
820 'uploader': 'CH GAMER DROID',
821 },
822 'params': {
823 'skip_download': True,
824 },
be49068d 825 'skip': 'This video does not exist.',
313dfc45 826 },
7caf9830
S
827 {
828 # Video licensed under Creative Commons
829 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
830 'info_dict': {
831 'id': 'M4gD1WSo5mA',
832 'ext': 'mp4',
833 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
834 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 835 'duration': 721,
7caf9830
S
836 'upload_date': '20150127',
837 'uploader_id': 'BerkmanCenter',
ec85ded8 838 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 839 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
840 'license': 'Creative Commons Attribution license (reuse allowed)',
841 },
842 'params': {
843 'skip_download': True,
844 },
845 },
fd050249
S
846 {
847 # Channel-like uploader_url
848 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
849 'info_dict': {
850 'id': 'eQcmzGIKrzg',
851 'ext': 'mp4',
852 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
853 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
556dbe7f 854 'duration': 4060,
fd050249
S
855 'upload_date': '20151119',
856 'uploader': 'Bernie 2016',
857 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 858 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
859 'license': 'Creative Commons Attribution license (reuse allowed)',
860 },
861 'params': {
862 'skip_download': True,
863 },
864 },
040ac686
S
865 {
866 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
867 'only_matching': True,
7f29cf54
S
868 },
869 {
870 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
871 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
872 'only_matching': True,
6496ccb4
S
873 },
874 {
875 # Rental video preview
876 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
877 'info_dict': {
878 'id': 'uGpuVWrhIzE',
879 'ext': 'mp4',
880 'title': 'Piku - Trailer',
881 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
882 'upload_date': '20150811',
883 'uploader': 'FlixMatrix',
884 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 885 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
886 'license': 'Standard YouTube License',
887 },
888 'params': {
889 'skip_download': True,
890 },
022a5d66 891 },
12afdc2a
S
892 {
893 # YouTube Red video with episode data
894 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
895 'info_dict': {
896 'id': 'iqKdEhx-dD4',
897 'ext': 'mp4',
898 'title': 'Isolation - Mind Field (Ep 1)',
556dbe7f
S
899 'description': 'md5:8013b7ddea787342608f63a13ddc9492',
900 'duration': 2085,
12afdc2a
S
901 'upload_date': '20170118',
902 'uploader': 'Vsauce',
903 'uploader_id': 'Vsauce',
904 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
905 'license': 'Standard YouTube License',
906 'series': 'Mind Field',
907 'season_number': 1,
908 'episode_number': 1,
909 },
910 'params': {
911 'skip_download': True,
912 },
913 'expected_warnings': [
914 'Skipping DASH manifest',
915 ],
916 },
022a5d66
S
917 {
918 # itag 212
919 'url': '1t24XAntNCY',
920 'only_matching': True,
fd5c4aab
S
921 },
922 {
923 # geo restricted to JP
924 'url': 'sJL6WA-aGkQ',
925 'only_matching': True,
926 },
2eb88d95
PH
927 ]
928
e0df6211
PH
929 def __init__(self, *args, **kwargs):
930 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 931 self._player_cache = {}
e0df6211 932
c5e8d7af
PH
933 def report_video_info_webpage_download(self, video_id):
934 """Report attempt to download video info webpage."""
69ea8ca4 935 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 936
c5e8d7af
PH
937 def report_information_extraction(self, video_id):
938 """Report attempt to extract video information."""
69ea8ca4 939 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
940
941 def report_unavailable_format(self, video_id, format):
942 """Report extracted video URL."""
69ea8ca4 943 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
944
945 def report_rtmp_download(self):
946 """Indicate the download will use the RTMP protocol."""
69ea8ca4 947 self.to_screen('RTMP download detected')
c5e8d7af 948
60064c53
PH
949 def _signature_cache_id(self, example_sig):
950 """ Return a string representation of a signature """
78caa52a 951 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
952
953 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 954 id_m = re.match(
50f84a9a 955 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
cf010131 956 player_url)
c081b35c
PH
957 if not id_m:
958 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
959 player_type = id_m.group('ext')
960 player_id = id_m.group('id')
961
c4417ddb 962 # Read from filesystem cache
60064c53
PH
963 func_id = '%s_%s_%s' % (
964 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 965 assert os.path.basename(func_id) == func_id
a0e07d31 966
69ea8ca4 967 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 968 if cache_spec is not None:
78caa52a 969 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 970
6d1a55a5
PH
971 download_note = (
972 'Downloading player %s' % player_url
973 if self._downloader.params.get('verbose') else
974 'Downloading %s player %s' % (player_type, player_id)
975 )
e0df6211
PH
976 if player_type == 'js':
977 code = self._download_webpage(
978 player_url, video_id,
6d1a55a5 979 note=download_note,
69ea8ca4 980 errnote='Download of %s failed' % player_url)
83799698 981 res = self._parse_sig_js(code)
c4417ddb 982 elif player_type == 'swf':
e0df6211
PH
983 urlh = self._request_webpage(
984 player_url, video_id,
6d1a55a5 985 note=download_note,
69ea8ca4 986 errnote='Download of %s failed' % player_url)
e0df6211 987 code = urlh.read()
83799698 988 res = self._parse_sig_swf(code)
e0df6211
PH
989 else:
990 assert False, 'Invalid player type %r' % player_type
991
785521bf
PH
992 test_string = ''.join(map(compat_chr, range(len(example_sig))))
993 cache_res = res(test_string)
994 cache_spec = [ord(c) for c in cache_res]
83799698 995
69ea8ca4 996 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
997 return res
998
60064c53 999 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1000 def gen_sig_code(idxs):
1001 def _genslice(start, end, step):
78caa52a 1002 starts = '' if start == 0 else str(start)
8bcc8756 1003 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1004 steps = '' if step == 1 else (':%d' % step)
78caa52a 1005 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1006
1007 step = None
7af808a5
PH
1008 # Quelch pyflakes warnings - start will be set when step is set
1009 start = '(Never used)'
edf3e38e
PH
1010 for i, prev in zip(idxs[1:], idxs[:-1]):
1011 if step is not None:
1012 if i - prev == step:
1013 continue
1014 yield _genslice(start, prev, step)
1015 step = None
1016 continue
1017 if i - prev in [-1, 1]:
1018 step = i - prev
1019 start = prev
1020 continue
1021 else:
78caa52a 1022 yield 's[%d]' % prev
edf3e38e 1023 if step is None:
78caa52a 1024 yield 's[%d]' % i
edf3e38e
PH
1025 else:
1026 yield _genslice(start, i, step)
1027
78caa52a 1028 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1029 cache_res = func(test_string)
edf3e38e 1030 cache_spec = [ord(c) for c in cache_res]
78caa52a 1031 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1032 signature_id_tuple = '(%s)' % (
1033 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1034 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1035 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1036 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1037
e0df6211
PH
1038 def _parse_sig_js(self, jscode):
1039 funcname = self._search_regex(
3c90cc8b
S
1040 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1041 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
1042 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1043
1044 jsi = JSInterpreter(jscode)
1045 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1046 return lambda s: initial_function([s])
1047
1048 def _parse_sig_swf(self, file_contents):
54256267 1049 swfi = SWFInterpreter(file_contents)
78caa52a 1050 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 1051 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 1052 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
1053 return lambda s: initial_function([s])
1054
83799698 1055 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 1056 """Turn the encrypted s field into a working signature"""
6b37f0be 1057
c8bf86d5 1058 if player_url is None:
69ea8ca4 1059 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1060
69ea8ca4 1061 if player_url.startswith('//'):
78caa52a 1062 player_url = 'https:' + player_url
3c90cc8b
S
1063 elif not re.match(r'https?://', player_url):
1064 player_url = compat_urlparse.urljoin(
1065 'https://www.youtube.com', player_url)
c8bf86d5 1066 try:
62af3a0e 1067 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1068 if player_id not in self._player_cache:
1069 func = self._extract_signature_function(
60064c53 1070 video_id, player_url, s
c8bf86d5
PH
1071 )
1072 self._player_cache[player_id] = func
1073 func = self._player_cache[player_id]
1074 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1075 self._print_sig_code(func, s)
c8bf86d5
PH
1076 return func(s)
1077 except Exception as e:
1078 tb = traceback.format_exc()
1079 raise ExtractorError(
78caa52a 1080 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1081
360e1ca5 1082 def _get_subtitles(self, video_id, webpage):
de7f3446 1083 try:
60e47a26 1084 subs_doc = self._download_xml(
38c2e5b8 1085 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1086 video_id, note=False)
1087 except ExtractorError as err:
9b9c5355 1088 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1089 return {}
de7f3446
JMF
1090
1091 sub_lang_list = {}
60e47a26
JMF
1092 for track in subs_doc.findall('track'):
1093 lang = track.attrib['lang_code']
7e660ac1
LD
1094 if lang in sub_lang_list:
1095 continue
360e1ca5 1096 sub_formats = []
23d17e4b 1097 for ext in self._SUBTITLE_FORMATS:
15707c7e 1098 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1099 'lang': lang,
1100 'v': video_id,
1101 'fmt': ext,
1102 'name': track.attrib['name'].encode('utf-8'),
1103 })
1104 sub_formats.append({
1105 'url': 'https://www.youtube.com/api/timedtext?' + params,
1106 'ext': ext,
1107 })
1108 sub_lang_list[lang] = sub_formats
de7f3446 1109 if not sub_lang_list:
69ea8ca4 1110 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1111 return {}
1112 return sub_lang_list
1113
a72778d3
S
1114 def _get_ytplayer_config(self, video_id, webpage):
1115 patterns = (
526b3b07
S
1116 # User data may contain arbitrary character sequences that may affect
1117 # JSON extraction with regex, e.g. when '};' is contained the second
1118 # regex won't capture the whole JSON. Yet working around by trying more
1119 # concrete regex first keeping in mind proper quoted string handling
1120 # to be implemented in future that will replace this workaround (see
1121 # https://github.com/rg3/youtube-dl/issues/7468,
1122 # https://github.com/rg3/youtube-dl/pull/7599)
a72778d3
S
1123 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1124 r';ytplayer\.config\s*=\s*({.+?});',
1125 )
1126 config = self._search_regex(
1127 patterns, webpage, 'ytplayer.config', default=None)
1128 if config:
1129 return self._parse_json(
1130 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1131
360e1ca5 1132 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1133 """We need the webpage for getting the captions url, pass it as an
1134 argument to speed up the process."""
69ea8ca4 1135 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1136 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1137 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1138 if not player_config:
de7f3446
JMF
1139 self._downloader.report_warning(err_msg)
1140 return {}
de7f3446 1141 try:
0792d563 1142 args = player_config['args']
b78b292f
S
1143 caption_url = args.get('ttsurl')
1144 if caption_url:
1145 timestamp = args['timestamp']
1146 # We get the available subtitles
15707c7e 1147 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1148 'type': 'list',
1149 'tlangs': 1,
1150 'asrs': 1,
1151 })
1152 list_url = caption_url + '&' + list_params
1153 caption_list = self._download_xml(list_url, video_id)
1154 original_lang_node = caption_list.find('track')
1155 if original_lang_node is None:
1156 self._downloader.report_warning('Video doesn\'t have automatic captions')
1157 return {}
1158 original_lang = original_lang_node.attrib['lang_code']
1159 caption_kind = original_lang_node.attrib.get('kind', '')
1160
1161 sub_lang_list = {}
1162 for lang_node in caption_list.findall('target'):
1163 sub_lang = lang_node.attrib['lang_code']
1164 sub_formats = []
1165 for ext in self._SUBTITLE_FORMATS:
15707c7e 1166 params = compat_urllib_parse_urlencode({
b78b292f
S
1167 'lang': original_lang,
1168 'tlang': sub_lang,
1169 'fmt': ext,
1170 'ts': timestamp,
1171 'kind': caption_kind,
1172 })
1173 sub_formats.append({
1174 'url': caption_url + '&' + params,
1175 'ext': ext,
1176 })
1177 sub_lang_list[sub_lang] = sub_formats
1178 return sub_lang_list
1179
1180 # Some videos don't provide ttsurl but rather caption_tracks and
1181 # caption_translation_languages (e.g. 20LmZk1hakA)
1182 caption_tracks = args['caption_tracks']
1183 caption_translation_languages = args['caption_translation_languages']
1184 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
15707c7e 1185 parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
b78b292f 1186 caption_qs = compat_parse_qs(parsed_caption_url.query)
055e6f36
JMF
1187
1188 sub_lang_list = {}
b78b292f
S
1189 for lang in caption_translation_languages.split(','):
1190 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1191 sub_lang = lang_qs.get('lc', [None])[0]
1192 if not sub_lang:
1193 continue
360e1ca5 1194 sub_formats = []
23d17e4b 1195 for ext in self._SUBTITLE_FORMATS:
b78b292f
S
1196 caption_qs.update({
1197 'tlang': [sub_lang],
1198 'fmt': [ext],
360e1ca5 1199 })
b78b292f 1200 sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
15707c7e 1201 query=compat_urllib_parse_urlencode(caption_qs, True)))
360e1ca5 1202 sub_formats.append({
b78b292f 1203 'url': sub_url,
360e1ca5
JMF
1204 'ext': ext,
1205 })
1206 sub_lang_list[sub_lang] = sub_formats
055e6f36 1207 return sub_lang_list
de7f3446
JMF
1208 # An extractor error can be raise by the download process if there are
1209 # no automatic captions but there are subtitles
1210 except (KeyError, ExtractorError):
1211 self._downloader.report_warning(err_msg)
1212 return {}
1213
d77ab8e2
S
1214 def _mark_watched(self, video_id, video_info):
1215 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1216 if not playback_url:
1217 return
1218 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1219 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1220
1221 # cpn generation algorithm is reverse engineered from base.js.
1222 # In fact it works even with dummy cpn.
1223 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1224 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1225
1226 qs.update({
1227 'ver': ['2'],
1228 'cpn': [cpn],
1229 })
1230 playback_url = compat_urlparse.urlunparse(
15707c7e 1231 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1232
1233 self._download_webpage(
1234 playback_url, video_id, 'Marking watched',
1235 'Unable to mark watched', fatal=False)
1236
97665381
PH
1237 @classmethod
1238 def extract_id(cls, url):
1239 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1240 if mobj is None:
69ea8ca4 1241 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1242 video_id = mobj.group(2)
1243 return video_id
1244
1d043b93
JMF
1245 def _extract_from_m3u8(self, manifest_url, video_id):
1246 url_map = {}
5f6a1245 1247
1d043b93
JMF
1248 def _get_urls(_manifest):
1249 lines = _manifest.split('\n')
1250 urls = filter(lambda l: l and not l.startswith('#'),
8bcc8756 1251 lines)
1d043b93 1252 return urls
78caa52a 1253 manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
1d043b93
JMF
1254 formats_urls = _get_urls(manifest)
1255 for format_url in formats_urls:
890f62e8 1256 itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
1d043b93
JMF
1257 url_map[itag] = format_url
1258 return url_map
1259
1fb07d10
JG
1260 def _extract_annotations(self, video_id):
1261 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1262 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1263
c5e8d7af 1264 def _real_extract(self, url):
cf7e015f
S
1265 url, smuggled_data = unsmuggle_url(url, {})
1266
7e8c0af0 1267 proto = (
78caa52a
PH
1268 'http' if self._downloader.params.get('prefer_insecure', False)
1269 else 'https')
7e8c0af0 1270
7c80519c 1271 start_time = None
297a564b 1272 end_time = None
7c80519c
JMF
1273 parsed_url = compat_urllib_parse_urlparse(url)
1274 for component in [parsed_url.fragment, parsed_url.query]:
1275 query = compat_parse_qs(component)
297a564b 1276 if start_time is None and 't' in query:
7c80519c 1277 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1278 if start_time is None and 'start' in query:
1279 start_time = parse_duration(query['start'][0])
297a564b
JMF
1280 if end_time is None and 'end' in query:
1281 end_time = parse_duration(query['end'][0])
7c80519c 1282
c5e8d7af
PH
1283 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1284 mobj = re.search(self._NEXT_URL_RE, url)
1285 if mobj:
7fd002c0 1286 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1287 video_id = self.extract_id(url)
c5e8d7af
PH
1288
1289 # Get video webpage
aa79ac0c 1290 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1291 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1292
1293 # Attempt to extract SWF player URL
e0df6211 1294 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1295 if mobj is not None:
1296 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1297 else:
1298 player_url = None
1299
d8d24a92
S
1300 dash_mpds = []
1301
1302 def add_dash_mpd(video_info):
1303 dash_mpd = video_info.get('dashmpd')
1304 if dash_mpd and dash_mpd[0] not in dash_mpds:
1305 dash_mpds.append(dash_mpd[0])
1306
c5e8d7af 1307 # Get video info
6449cd80 1308 embed_webpage = None
2fe1ff85 1309 is_live = None
c108eb73 1310 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1311 age_gate = True
1312 # We simulate the access to the video from www.youtube.com/v/{video_id}
1313 # this can be viewed without login into Youtube
beb95e77
CL
1314 url = proto + '://www.youtube.com/embed/%s' % video_id
1315 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1316 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1317 'video_id': video_id,
1318 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1319 'sts': self._search_regex(
beb95e77 1320 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1321 })
7e8c0af0 1322 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1323 video_info_webpage = self._download_webpage(
1324 video_info_url, video_id,
20436c30 1325 note='Refetching age-gated info webpage',
94bd3613 1326 errnote='unable to download video info webpage')
c5e8d7af 1327 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1328 add_dash_mpd(video_info)
c108eb73
JMF
1329 else:
1330 age_gate = False
bc93bdb5 1331 video_info = None
d8d24a92 1332 # Try looking directly into the video webpage
a72778d3
S
1333 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1334 if ytplayer_config:
4e62ebe2 1335 args = ytplayer_config['args']
d8d24a92
S
1336 if args.get('url_encoded_fmt_stream_map'):
1337 # Convert to the same format returned by compat_parse_qs
1338 video_info = dict((k, [v]) for k, v in args.items())
1339 add_dash_mpd(video_info)
6496ccb4
S
1340 # Rental video is not rented but preview is available (e.g.
1341 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1342 # https://github.com/rg3/youtube-dl/issues/10532)
1343 if not video_info and args.get('ypc_vid'):
1344 return self.url_result(
1345 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
2fe1ff85
JMF
1346 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1347 is_live = True
0a3cf9ad
S
1348 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1349 # We also try looking in get_video_info since it may contain different dashmpd
1350 # URL that points to a DASH manifest with possibly different itag set (some itags
1351 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1352 # manifest pointed by get_video_info's dashmpd).
1353 # The general idea is to take a union of itags of both DASH manifests (for example
1354 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
4e62ebe2 1355 self.report_video_info_webpage_download(video_id)
0a3cf9ad 1356 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
810fb84d
PH
1357 video_info_url = (
1358 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1359 % (proto, video_id, el_type))
1360 video_info_webpage = self._download_webpage(
1361 video_info_url,
4e62ebe2
JMF
1362 video_id, note=False,
1363 errnote='unable to download video info webpage')
0a3cf9ad 1364 get_video_info = compat_parse_qs(video_info_webpage)
87dc4511
JMF
1365 if get_video_info.get('use_cipher_signature') != ['True']:
1366 add_dash_mpd(get_video_info)
0a3cf9ad
S
1367 if not video_info:
1368 video_info = get_video_info
1369 if 'token' in get_video_info:
89ea063e
S
1370 # Different get_video_info requests may report different results, e.g.
1371 # some may report video unavailability, but some may serve it without
1372 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1373 # the original webpage as well as el=info and el=embedded get_video_info
1374 # requests report video unavailability due to geo restriction while
1375 # el=detailpage succeeds and returns valid data). This is probably
1376 # due to YouTube measures against IP ranges of hosting providers.
1377 # Working around by preferring the first succeeded video_info containing
1378 # the token if no such video_info yet was found.
44b2264f
S
1379 if 'token' not in video_info:
1380 video_info = get_video_info
4e62ebe2 1381 break
c5e8d7af
PH
1382 if 'token' not in video_info:
1383 if 'reason' in video_info:
af214c3a 1384 if 'The uploader has not made this video available in your country.' in video_info['reason']:
fd5c4aab
S
1385 regions_allowed = self._html_search_meta(
1386 'regionsAllowed', video_webpage, default=None)
1387 countries = regions_allowed.split(',') if regions_allowed else None
1388 self.raise_geo_restricted(
1389 msg=video_info['reason'][0], countries=countries)
d11271dd 1390 raise ExtractorError(
78caa52a 1391 'YouTube said: %s' % video_info['reason'][0],
d11271dd 1392 expected=True, video_id=video_id)
c5e8d7af 1393 else:
d11271dd 1394 raise ExtractorError(
78caa52a 1395 '"token" parameter not in video info for unknown reason',
d11271dd 1396 video_id=video_id)
c5e8d7af 1397
cf7e015f
S
1398 # title
1399 if 'title' in video_info:
1400 video_title = video_info['title'][0]
1401 else:
1402 self._downloader.report_warning('Unable to extract video title')
1403 video_title = '_'
1404
1405 # description
1406 video_description = get_element_by_id("eow-description", video_webpage)
1407 if video_description:
1408 video_description = re.sub(r'''(?x)
1409 <a\s+
25cb7a0e 1410 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1411 (?:title|href)="([^"]+)"\s+
25cb7a0e 1412 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1413 class="[^"]*"[^>]*>
23f13e97 1414 [^<]+\.{3}\s*
cf7e015f
S
1415 </a>
1416 ''', r'\1', video_description)
1417 video_description = clean_html(video_description)
1418 else:
1419 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1420 if fd_mobj:
1421 video_description = unescapeHTML(fd_mobj.group(1))
1422 else:
1423 video_description = ''
1424
5e1eddb9
S
1425 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1426 if not self._downloader.params.get('noplaylist'):
1427 entries = []
1428 feed_ids = []
6863631c 1429 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
5e1eddb9 1430 for feed in multifeed_metadata_list.split(','):
6863631c
S
1431 # Unquote should take place before split on comma (,) since textual
1432 # fields may contain comma as well (see
1433 # https://github.com/rg3/youtube-dl/issues/8536)
1434 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
5e1eddb9
S
1435 entries.append({
1436 '_type': 'url_transparent',
1437 'ie_key': 'Youtube',
1438 'url': smuggle_url(
1439 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1440 {'force_singlefeed': True}),
1441 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1442 })
1443 feed_ids.append(feed_data['id'][0])
1444 self.to_screen(
1445 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1446 % (', '.join(feed_ids), video_id))
1447 return self.playlist_result(entries, video_id, video_title, video_description)
1448 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1449
1d699755
PH
1450 if 'view_count' in video_info:
1451 view_count = int(video_info['view_count'][0])
1452 else:
1453 view_count = None
1454
c5e8d7af
PH
1455 # Check for "rental" videos
1456 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
69ea8ca4 1457 raise ExtractorError('"rental" videos not supported')
c5e8d7af
PH
1458
1459 # Start extracting information
1460 self.report_information_extraction(video_id)
1461
1462 # uploader
1463 if 'author' not in video_info:
69ea8ca4 1464 raise ExtractorError('Unable to extract uploader name')
7fd002c0 1465 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
c5e8d7af
PH
1466
1467 # uploader_id
1468 video_uploader_id = None
fd050249
S
1469 video_uploader_url = None
1470 mobj = re.search(
1471 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1472 video_webpage)
c5e8d7af 1473 if mobj is not None:
fd050249
S
1474 video_uploader_id = mobj.group('uploader_id')
1475 video_uploader_url = mobj.group('uploader_url')
c5e8d7af 1476 else:
69ea8ca4 1477 self._downloader.report_warning('unable to extract uploader nickname')
c5e8d7af 1478
c5e8d7af 1479 # thumbnail image
7763b04e
JMF
1480 # We try first to get a high quality image:
1481 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1482 video_webpage, re.DOTALL)
1483 if m_thumb is not None:
1484 video_thumbnail = m_thumb.group(1)
1485 elif 'thumbnail_url' not in video_info:
69ea8ca4 1486 self._downloader.report_warning('unable to extract video thumbnail')
f490e77e 1487 video_thumbnail = None
c5e8d7af 1488 else: # don't panic if we can't find it
7fd002c0 1489 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
c5e8d7af
PH
1490
1491 # upload date
9d0b581f
S
1492 upload_date = self._html_search_meta(
1493 'datePublished', video_webpage, 'upload date', default=None)
1494 if not upload_date:
1495 upload_date = self._search_regex(
1496 [r'(?s)id="eow-date.*?>(.*?)</span>',
1497 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1498 video_webpage, 'upload date', default=None)
1499 if upload_date:
1500 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1501 upload_date = unified_strdate(upload_date)
c5e8d7af 1502
7caf9830
S
1503 video_license = self._html_search_regex(
1504 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1505 video_webpage, 'license', default=None)
1506
0cb58b02
S
1507 m_music = re.search(
1508 r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1509 video_webpage)
1510 if m_music:
1511 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1512 video_creator = clean_html(m_music.group('creator'))
1513 else:
1514 video_alt_title = video_creator = None
1515
12afdc2a
S
1516 m_episode = re.search(
1517 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1518 video_webpage)
1519 if m_episode:
1520 series = m_episode.group('series')
1521 season_number = int(m_episode.group('season'))
1522 episode_number = int(m_episode.group('episode'))
1523 else:
1524 series = season_number = episode_number = None
1525
55f7bd2d
PH
1526 m_cat_container = self._search_regex(
1527 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
624dcebf 1528 video_webpage, 'categories', default=None)
ec8deefc 1529 if m_cat_container:
ad3bc6ac 1530 category = self._html_search_regex(
01ed5c9b 1531 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
ad3bc6ac
PH
1532 default=None)
1533 video_categories = None if category is None else [category]
1534 else:
1535 video_categories = None
ec8deefc 1536
000b6b5a
S
1537 video_tags = [
1538 unescapeHTML(m.group('content'))
1539 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1540
f30a38be 1541 def _extract_count(count_name):
c93d53f5
S
1542 return str_to_int(self._search_regex(
1543 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1544 % re.escape(count_name),
1545 video_webpage, count_name, default=None))
1546
69ea8ca4
PH
1547 like_count = _extract_count('like')
1548 dislike_count = _extract_count('dislike')
336c3a69 1549
c5e8d7af 1550 # subtitles
d82134c3 1551 video_subtitles = self.extract_subtitles(video_id, video_webpage)
360e1ca5 1552 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
c5e8d7af 1553
556dbe7f
S
1554 video_duration = try_get(
1555 video_info, lambda x: int_or_none(x['length_seconds'][0]))
1556 if not video_duration:
1557 video_duration = parse_duration(self._html_search_meta(
1558 'duration', video_webpage, 'video duration'))
c5e8d7af 1559
1fb07d10
JG
1560 # annotations
1561 video_annotations = None
1562 if self._downloader.params.get('writeannotations', False):
5f6a1245 1563 video_annotations = self._extract_annotations(video_id)
1fb07d10 1564
dd27fd17
PH
1565 def _map_to_format_list(urlmap):
1566 formats = []
1567 for itag, video_real_url in urlmap.items():
1568 dct = {
1569 'format_id': itag,
1570 'url': video_real_url,
1571 'player_url': player_url,
1572 }
0b65e5d4
PH
1573 if itag in self._formats:
1574 dct.update(self._formats[itag])
dd27fd17
PH
1575 formats.append(dct)
1576 return formats
1577
c5e8d7af
PH
1578 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1579 self.report_rtmp_download()
dd27fd17
PH
1580 formats = [{
1581 'format_id': '_rtmp',
1582 'protocol': 'rtmp',
1583 'url': video_info['conn'][0],
1584 'player_url': player_url,
1585 }]
24270b03 1586 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
5f6a1245 1587 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1588 if 'rtmpe%3Dyes' in encoded_url_map:
a7055eb9 1589 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1590 formats_spec = {}
82156fdb 1591 fmt_list = video_info.get('fmt_list', [''])[0]
1592 if fmt_list:
1593 for fmt in fmt_list.split(','):
1594 spec = fmt.split('/')
3318832e 1595 if len(spec) > 1:
1596 width_height = spec[1].split('x')
1597 if len(width_height) == 2:
1598 formats_spec[spec[0]] = {
1599 'resolution': spec[1],
1600 'width': int_or_none(width_height[0]),
1601 'height': int_or_none(width_height[1]),
1602 }
c9afb51c 1603 formats = []
00fe14fc 1604 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1605 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1606 if 'itag' not in url_data or 'url' not in url_data:
1607 continue
1608 format_id = url_data['itag'][0]
1609 url = url_data['url'][0]
1610
1611 if 'sig' in url_data:
1612 url += '&signature=' + url_data['sig'][0]
1613 elif 's' in url_data:
1614 encrypted_sig = url_data['s'][0]
6449cd80 1615 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
201e9eaa 1616
beb95e77 1617 jsplayer_url_json = self._search_regex(
6449cd80
PH
1618 ASSETS_RE,
1619 embed_webpage if age_gate else video_webpage,
1620 'JS player URL (1)', default=None)
1621 if not jsplayer_url_json and not age_gate:
1622 # We need the embed website after all
1623 if embed_webpage is None:
1624 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1625 embed_webpage = self._download_webpage(
1626 embed_url, video_id, 'Downloading embed webpage')
1627 jsplayer_url_json = self._search_regex(
1628 ASSETS_RE, embed_webpage, 'JS player URL')
1629
beb95e77 1630 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1631 if player_url is None:
1632 player_url_json = self._search_regex(
1633 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1634 video_webpage, 'age gate player URL')
201e9eaa
PH
1635 player_url = json.loads(player_url_json)
1636
1637 if self._downloader.params.get('verbose'):
cf010131 1638 if player_url is None:
201e9eaa
PH
1639 player_version = 'unknown'
1640 player_desc = 'unknown'
1641 else:
1642 if player_url.endswith('swf'):
1643 player_version = self._search_regex(
1644 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1645 'flash player', fatal=False)
201e9eaa 1646 player_desc = 'flash player %s' % player_version
cf010131 1647 else:
201e9eaa 1648 player_version = self._search_regex(
50f84a9a 1649 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
201e9eaa
PH
1650 player_url,
1651 'html5 player', fatal=False)
78caa52a 1652 player_desc = 'html5 player %s' % player_version
201e9eaa 1653
60064c53 1654 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1655 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1656 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1657
1658 signature = self._decrypt_signature(
1659 encrypted_sig, video_id, player_url, age_gate)
1660 url += '&signature=' + signature
1661 if 'ratebypass' not in url:
1662 url += '&ratebypass=yes'
c9afb51c 1663
94278f72
YCH
1664 dct = {
1665 'format_id': format_id,
1666 'url': url,
1667 'player_url': player_url,
1668 }
1669 if format_id in self._formats:
1670 dct.update(self._formats[format_id])
3318832e 1671 if format_id in formats_spec:
1672 dct.update(formats_spec[format_id])
94278f72 1673
aabc2be6
S
1674 # Some itags are not included in DASH manifest thus corresponding formats will
1675 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1676 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1677 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1678 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72
YCH
1679
1680 more_fields = {
c9afb51c 1681 'filesize': int_or_none(url_data.get('clen', [None])[0]),
aabc2be6 1682 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1683 'width': width,
1684 'height': height,
1685 'fps': int_or_none(url_data.get('fps', [None])[0]),
aabc2be6 1686 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
c9afb51c 1687 }
94278f72
YCH
1688 for key, value in more_fields.items():
1689 if value:
1690 dct[key] = value
aabc2be6
S
1691 type_ = url_data.get('type', [None])[0]
1692 if type_:
1693 type_split = type_.split(';')
1694 kind_ext = type_split[0].split('/')
1695 if len(kind_ext) == 2:
94278f72
YCH
1696 kind, _ = kind_ext
1697 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1698 if kind in ('audio', 'video'):
1699 codecs = None
1700 for mobj in re.finditer(
1701 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1702 if mobj.group('key') == 'codecs':
1703 codecs = mobj.group('val')
1704 break
1705 if codecs:
6310acf5 1706 dct.update(parse_codecs(codecs))
aabc2be6 1707 formats.append(dct)
1d043b93
JMF
1708 elif video_info.get('hlsvp'):
1709 manifest_url = video_info['hlsvp'][0]
1710 url_map = self._extract_from_m3u8(manifest_url, video_id)
dd27fd17 1711 formats = _map_to_format_list(url_map)
ac5a69af
YCH
1712 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1713 for a_format in formats:
049d71d8 1714 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
c5e8d7af 1715 else:
8ceabd4d
S
1716 unavailable_message = self._html_search_regex(
1717 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1718 video_webpage, 'unavailable message', default=None)
1719 if unavailable_message:
1720 raise ExtractorError(unavailable_message, expected=True)
69ea8ca4 1721 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1722
dd27fd17 1723 # Look for the DASH manifest
203fb43f 1724 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 1725 dash_mpd_fatal = True
8ff648e4 1726 for mpd_url in dash_mpds:
d8d24a92 1727 dash_formats = {}
774e208f 1728 try:
05d0d131
YCH
1729 def decrypt_sig(mobj):
1730 s = mobj.group(1)
1731 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1732 return '/signature/%s' % dec_s
1733
8ff648e4 1734 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 1735
8ff648e4 1736 for df in self._extract_mpd_formats(
1737 mpd_url, video_id, fatal=dash_mpd_fatal,
1738 formats_dict=self._formats):
d8d24a92
S
1739 # Do not overwrite DASH format found in some previous DASH manifest
1740 if df['format_id'] not in dash_formats:
1741 dash_formats[df['format_id']] = df
77c6fb5b
S
1742 # Additional DASH manifests may end up in HTTP Error 403 therefore
1743 # allow them to fail without bug report message if we already have
1744 # some DASH manifest succeeded. This is temporary workaround to reduce
1745 # burst of bug reports until we figure out the reason and whether it
1746 # can be fixed at all.
1747 dash_mpd_fatal = False
774e208f
PH
1748 except (ExtractorError, KeyError) as e:
1749 self.report_warning(
1750 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 1751 if dash_formats:
04b3b3df
JMF
1752 # Remove the formats we found through non-DASH, they
1753 # contain less info and it can be wrong, because we use
1754 # fixed values (for example the resolution). See
1755 # https://github.com/rg3/youtube-dl/issues/5774 for an
1756 # example.
d80265cc 1757 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 1758 formats.extend(dash_formats.values())
d80044c2 1759
6271f1ca
PH
1760 # Check for malformed aspect ratio
1761 stretched_m = re.search(
1762 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1763 video_webpage)
1764 if stretched_m:
313dfc45
LL
1765 w = float(stretched_m.group('w'))
1766 h = float(stretched_m.group('h'))
5faf9fed
S
1767 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1768 # We will only process correct ratios.
313dfc45 1769 if w > 0 and h > 0:
41f24c32 1770 ratio = w / h
313dfc45
LL
1771 for f in formats:
1772 if f.get('vcodec') != 'none':
1773 f['stretched_ratio'] = ratio
6271f1ca 1774
4bcc7bd1 1775 self._sort_formats(formats)
4ea3be0a 1776
d77ab8e2
S
1777 self.mark_watched(video_id, video_info)
1778
4ea3be0a 1779 return {
8bcc8756
JW
1780 'id': video_id,
1781 'uploader': video_uploader,
1782 'uploader_id': video_uploader_id,
fd050249 1783 'uploader_url': video_uploader_url,
8bcc8756 1784 'upload_date': upload_date,
7caf9830 1785 'license': video_license,
0cb58b02 1786 'creator': video_creator,
8bcc8756 1787 'title': video_title,
0cb58b02 1788 'alt_title': video_alt_title,
8bcc8756
JW
1789 'thumbnail': video_thumbnail,
1790 'description': video_description,
1791 'categories': video_categories,
000b6b5a 1792 'tags': video_tags,
8bcc8756 1793 'subtitles': video_subtitles,
360e1ca5 1794 'automatic_captions': automatic_captions,
8bcc8756
JW
1795 'duration': video_duration,
1796 'age_limit': 18 if age_gate else 0,
1797 'annotations': video_annotations,
7e8c0af0 1798 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 1799 'view_count': view_count,
4ea3be0a 1800 'like_count': like_count,
1801 'dislike_count': dislike_count,
2d30521a 1802 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 1803 'formats': formats,
2fe1ff85 1804 'is_live': is_live,
7c80519c 1805 'start_time': start_time,
297a564b 1806 'end_time': end_time,
12afdc2a
S
1807 'series': series,
1808 'season_number': season_number,
1809 'episode_number': episode_number,
4ea3be0a 1810 }
c5e8d7af 1811
5f6a1245 1812
40805306 1813class YoutubeSharedVideoIE(InfoExtractor):
fd8c8c7d 1814 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
40805306
YCH
1815 IE_NAME = 'youtube:shared'
1816
1817 _TEST = {
1818 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1819 'info_dict': {
1820 'id': 'uPDB5I9wfp8',
1821 'ext': 'webm',
1822 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1823 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1824 'upload_date': '20160219',
1825 'uploader': 'Pocoyo - Português (BR)',
1826 'uploader_id': 'PocoyoBrazil',
1827 },
1828 'add_ie': ['Youtube'],
1829 'params': {
1830 # There are already too many Youtube downloads
1831 'skip_download': True,
1832 },
1833 }
1834
1835 def _real_extract(self, url):
1836 video_id = self._match_id(url)
1837
1838 webpage = self._download_webpage(url, video_id)
1839
1840 real_video_id = self._html_search_meta(
1841 'videoId', webpage, 'YouTube video id', fatal=True)
1842
1843 return self.url_result(real_video_id, YoutubeIE.ie_key())
1844
1845
8e7aad20 1846class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 1847 IE_DESC = 'YouTube.com playlists'
d67cc9fa 1848 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
1849 (?:https?://)?
1850 (?:\w+\.)?
c5e8d7af 1851 (?:
feaa5ad7
S
1852 youtube\.com/
1853 (?:
87dadd45 1854 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
feaa5ad7
S
1855 \? (?:.*?[&;])*? (?:p|a|list)=
1856 | p/
1857 )|
1858 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
c5e8d7af 1859 )
d67cc9fa 1860 (
a6857510 1861 (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
5f6a1245 1862 # Top tracks, they can also include dots
d67cc9fa
JMF
1863 |(?:MC)[\w\.]*
1864 )
c5e8d7af
PH
1865 .*
1866 |
a6857510 1867 ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
c5e8d7af 1868 )"""
c867adc6 1869 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
648e6a1f 1870 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 1871 IE_NAME = 'youtube:playlist'
81127aa5
PH
1872 _TESTS = [{
1873 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1874 'info_dict': {
1875 'title': 'ytdl test PL',
a1cf99d0 1876 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
1877 },
1878 'playlist_count': 3,
9291475f
PH
1879 }, {
1880 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1881 'info_dict': {
acf757f4 1882 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
1883 'title': 'YDL_Empty_List',
1884 },
1885 'playlist_count': 0,
4201ba13 1886 'skip': 'This playlist is private',
9291475f
PH
1887 }, {
1888 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1889 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1890 'info_dict': {
1891 'title': '29C3: Not my department',
acf757f4 1892 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
1893 },
1894 'playlist_count': 95,
1895 }, {
1896 'note': 'issue #673',
1897 'url': 'PLBB231211A4F62143',
1898 'info_dict': {
f46a8702 1899 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 1900 'id': 'PLBB231211A4F62143',
9291475f
PH
1901 },
1902 'playlist_mincount': 26,
1903 }, {
1904 'note': 'Large playlist',
1905 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1906 'info_dict': {
1907 'title': 'Uploads from Cauchemar',
acf757f4 1908 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
1909 },
1910 'playlist_mincount': 799,
1911 }, {
1912 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1913 'info_dict': {
1914 'title': 'YDL_safe_search',
acf757f4 1915 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
1916 },
1917 'playlist_count': 2,
4201ba13 1918 'skip': 'This playlist is private',
ac7553d0
PH
1919 }, {
1920 'note': 'embedded',
2d3d2997 1921 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0
PH
1922 'playlist_count': 4,
1923 'info_dict': {
1924 'title': 'JODA15',
acf757f4 1925 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 1926 }
87dadd45
S
1927 }, {
1928 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1929 'playlist_mincount': 485,
1930 'info_dict': {
1931 'title': '2017 華語最新單曲 (2/24更新)',
1932 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
1933 }
6b08cdf6
PH
1934 }, {
1935 'note': 'Embedded SWF player',
2d3d2997 1936 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
6b08cdf6
PH
1937 'playlist_count': 4,
1938 'info_dict': {
1939 'title': 'JODA7',
acf757f4 1940 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 1941 }
4b7df0d3
JMF
1942 }, {
1943 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1944 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1945 'info_dict': {
acf757f4
PH
1946 'title': 'Uploads from Interstellar Movie',
1947 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 1948 },
481cc733 1949 'playlist_mincount': 21,
dacb3a86
S
1950 }, {
1951 # Playlist URL that does not actually serve a playlist
1952 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1953 'info_dict': {
1954 'id': 'FqZTN594JQw',
1955 'ext': 'webm',
1956 'title': "Smiley's People 01 detective, Adventure Series, Action",
1957 'uploader': 'STREEM',
1958 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 1959 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
1960 'upload_date': '20150526',
1961 'license': 'Standard YouTube License',
1962 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1963 'categories': ['People & Blogs'],
1964 'tags': list,
1965 'like_count': int,
1966 'dislike_count': int,
1967 },
1968 'params': {
1969 'skip_download': True,
1970 },
1971 'add_ie': [YoutubeIE.ie_key()],
481cc733
S
1972 }, {
1973 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1974 'info_dict': {
1975 'id': 'yeWKywCrFtk',
1976 'ext': 'mp4',
1977 'title': 'Small Scale Baler and Braiding Rugs',
1978 'uploader': 'Backus-Page House Museum',
1979 'uploader_id': 'backuspagemuseum',
ec85ded8 1980 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
481cc733
S
1981 'upload_date': '20161008',
1982 'license': 'Standard YouTube License',
1983 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1984 'categories': ['Nonprofits & Activism'],
1985 'tags': list,
1986 'like_count': int,
1987 'dislike_count': int,
1988 },
1989 'params': {
1990 'noplaylist': True,
1991 'skip_download': True,
1992 },
feaa5ad7
S
1993 }, {
1994 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1995 'only_matching': True,
a6857510
S
1996 }, {
1997 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
1998 'only_matching': True,
81127aa5 1999 }]
c5e8d7af 2000
880e1c52
JMF
2001 def _real_initialize(self):
2002 self._login()
2003
652cdaa2 2004 def _extract_mix(self, playlist_id):
99209c29 2005 # The mixes are generated from a single video
652cdaa2 2006 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
2007 ids = []
2008 last_id = playlist_id[-11:]
2009 for n in itertools.count(1):
2010 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2011 webpage = self._download_webpage(
2012 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2013 new_ids = orderedSet(re.findall(
2014 r'''(?xs)data-video-username=".*?".*?
2015 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
2016 webpage))
2017 # Fetch new pages until all the videos are repeated, it seems that
2018 # there are always 51 unique videos.
2019 new_ids = [_id for _id in new_ids if _id not in ids]
2020 if not new_ids:
2021 break
2022 ids.extend(new_ids)
2023 last_id = ids[-1]
2024
2025 url_results = self._ids_to_results(ids)
2026
bc2f773b 2027 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
2028 title_span = (
2029 search_title('playlist-title') or
2030 search_title('title long-title') or
2031 search_title('title'))
76d1700b 2032 title = clean_html(title_span)
652cdaa2
JMF
2033
2034 return self.playlist_result(url_results, playlist_id, title)
2035
448830ce 2036 def _extract_playlist(self, playlist_id):
dbb94fb0
S
2037 url = self._TEMPLATE_URL % playlist_id
2038 page = self._download_webpage(url, playlist_id)
dbb94fb0 2039
8bc0800d
G
2040 # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
2041 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
39b62db1
YCH
2042 match = match.strip()
2043 # Check if the playlist exists or is private
4201ba13
S
2044 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2045 if mobj:
2046 reason = mobj.group('reason')
2047 message = 'This playlist %s' % reason
2048 if 'private' in reason:
2049 message += ', use --username or --netrc to access it'
2050 message += '.'
2051 raise ExtractorError(message, expected=True)
39b62db1
YCH
2052 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2053 raise ExtractorError(
2054 'Invalid parameters. Maybe URL is incorrect.',
2055 expected=True)
2056 elif re.match(r'[^<]*Choose your language[^<]*', match):
2057 continue
2058 else:
2059 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 2060
dbb94fb0 2061 playlist_title = self._html_search_regex(
63b4295d 2062 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
dacb3a86 2063 page, 'title', default=None)
c5e8d7af 2064
dacb3a86
S
2065 has_videos = True
2066
2067 if not playlist_title:
2068 try:
2069 # Some playlist URLs don't actually serve a playlist (e.g.
2070 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2071 next(self._entries(page, playlist_id))
2072 except StopIteration:
2073 has_videos = False
2074
2075 return has_videos, self.playlist_result(
2076 self._entries(page, playlist_id), playlist_id, playlist_title)
c5e8d7af 2077
ebf1b291 2078 def _check_download_just_video(self, url, playlist_id):
448830ce
S
2079 # Check if it's a video-specific URL
2080 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
481cc733 2081 video_id = query_dict.get('v', [None])[0] or self._search_regex(
87dadd45 2082 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
481cc733
S
2083 'video id', default=None)
2084 if video_id:
448830ce
S
2085 if self._downloader.params.get('noplaylist'):
2086 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
dacb3a86 2087 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce
S
2088 else:
2089 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
dacb3a86
S
2090 return video_id, None
2091 return None, None
448830ce 2092
ebf1b291
S
2093 def _real_extract(self, url):
2094 # Extract playlist id
2095 mobj = re.match(self._VALID_URL, url)
2096 if mobj is None:
2097 raise ExtractorError('Invalid URL: %s' % url)
2098 playlist_id = mobj.group(1) or mobj.group(2)
2099
dacb3a86 2100 video_id, video = self._check_download_just_video(url, playlist_id)
ebf1b291
S
2101 if video:
2102 return video
2103
466a6145 2104 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
2105 # Mixes require a custom extraction process
2106 return self._extract_mix(playlist_id)
2107
dacb3a86
S
2108 has_videos, playlist = self._extract_playlist(playlist_id)
2109 if has_videos or not video_id:
2110 return playlist
2111
2112 # Some playlist URLs don't actually serve a playlist (see
2113 # https://github.com/rg3/youtube-dl/issues/10537).
2114 # Fallback to plain video extraction if there is a video id
2115 # along with playlist id.
2116 return self.url_result(video_id, 'Youtube', video_id=video_id)
448830ce 2117
c5e8d7af 2118
648e6a1f 2119class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 2120 IE_DESC = 'YouTube.com channels'
9ff67727 2121 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 2122 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 2123 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 2124 IE_NAME = 'youtube:channel'
cdc628a4
PH
2125 _TESTS = [{
2126 'note': 'paginated channel',
2127 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2128 'playlist_mincount': 91,
acf757f4 2129 'info_dict': {
9170ca5b
JMF
2130 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2131 'title': 'Uploads from lex will',
acf757f4 2132 }
5c43afd4
JMF
2133 }, {
2134 'note': 'Age restricted channel',
2135 # from https://www.youtube.com/user/DeusExOfficial
2136 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2137 'playlist_mincount': 64,
2138 'info_dict': {
2139 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2140 'title': 'Uploads from Deus Ex',
2141 },
cdc628a4 2142 }]
c5e8d7af 2143
e462474e
S
2144 @classmethod
2145 def suitable(cls, url):
f07e276a
S
2146 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2147 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 2148
9558dcec
S
2149 def _build_template_url(self, url, channel_id):
2150 return self._TEMPLATE_URL % channel_id
2151
c5e8d7af 2152 def _real_extract(self, url):
9ff67727 2153 channel_id = self._match_id(url)
c5e8d7af 2154
9558dcec 2155 url = self._build_template_url(url, channel_id)
386bdfa6
S
2156
2157 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2158 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2159 # otherwise fallback on channel by page extraction
2160 channel_page = self._download_webpage(
2161 url + '?view=57', channel_id,
2162 'Downloading channel page', fatal=False)
2b3c2546
PH
2163 if channel_page is False:
2164 channel_playlist_id = False
2165 else:
2166 channel_playlist_id = self._html_search_meta(
2167 'channelId', channel_page, 'channel id', default=None)
2168 if not channel_playlist_id:
73c4ac2c
S
2169 channel_url = self._html_search_meta(
2170 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2171 channel_page, 'channel url', default=None)
2172 if channel_url:
2173 channel_playlist_id = self._search_regex(
2174 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2175 channel_url, 'channel id', default=None)
386bdfa6
S
2176 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2177 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2178 return self.url_result(
2179 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2180
60bf45c8 2181 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2182 autogenerated = re.search(r'''(?x)
2183 class="[^"]*?(?:
2184 channel-header-autogenerated-label|
2185 yt-channel-title-autogenerated
2186 )[^"]*"''', channel_page) is not None
c5e8d7af 2187
b9643eed
JMF
2188 if autogenerated:
2189 # The videos are contained in a single page
2190 # the ajax pages can't be used, they are empty
b82f815f 2191 entries = [
fb69240c
S
2192 self.url_result(
2193 video_id, 'Youtube', video_id=video_id,
2194 video_title=video_title)
8f02ad4f 2195 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2196 return self.playlist_result(entries, channel_id)
2197
73c4ac2c
S
2198 try:
2199 next(self._entries(channel_page, channel_id))
2200 except StopIteration:
2201 alert_message = self._html_search_regex(
2202 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2203 channel_page, 'alert', default=None, group='alert')
2204 if alert_message:
2205 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2206
648e6a1f 2207 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2208
2209
eb0f3e7e 2210class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2211 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
9558dcec
S
2212 _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_-]+)'
2213 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
78caa52a 2214 IE_NAME = 'youtube:user'
c5e8d7af 2215
cdc628a4
PH
2216 _TESTS = [{
2217 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2218 'playlist_mincount': 320,
2219 'info_dict': {
73c4ac2c
S
2220 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2221 'title': 'Uploads from The Linux Foundation',
cdc628a4 2222 }
9558dcec
S
2223 }, {
2224 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2225 # but not https://www.youtube.com/user/12minuteathlete/videos
2226 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2227 'playlist_mincount': 249,
2228 'info_dict': {
2229 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2230 'title': 'Uploads from 12 Minute Athlete',
2231 }
cdc628a4
PH
2232 }, {
2233 'url': 'ytuser:phihag',
2234 'only_matching': True,
daa0df9e
YCH
2235 }, {
2236 'url': 'https://www.youtube.com/c/gametrailers',
2237 'only_matching': True,
9558dcec
S
2238 }, {
2239 'url': 'https://www.youtube.com/gametrailers',
2240 'only_matching': True,
73c4ac2c 2241 }, {
0e879f43 2242 # This channel is not available, geo restricted to JP
73c4ac2c
S
2243 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2244 'only_matching': True,
cdc628a4
PH
2245 }]
2246
e3ea4790 2247 @classmethod
f4b05232 2248 def suitable(cls, url):
e3ea4790
JMF
2249 # Don't return True if the url can be extracted with other youtube
2250 # extractor, the regex would is too permissive and it would match.
f3a58d46 2251 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2252 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2253 return False
2254 else:
2255 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2256
9558dcec
S
2257 def _build_template_url(self, url, channel_id):
2258 mobj = re.match(self._VALID_URL, url)
2259 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2260
b05654f0 2261
f07e276a
S
2262class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2263 IE_DESC = 'YouTube.com live streams'
073d5bf5 2264 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
f07e276a
S
2265 IE_NAME = 'youtube:live'
2266
2267 _TESTS = [{
2d3d2997 2268 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
f07e276a
S
2269 'info_dict': {
2270 'id': 'a48o2S1cPoo',
2271 'ext': 'mp4',
2272 'title': 'The Young Turks - Live Main Show',
2273 'uploader': 'The Young Turks',
2274 'uploader_id': 'TheYoungTurks',
ec85ded8 2275 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
f07e276a
S
2276 'upload_date': '20150715',
2277 'license': 'Standard YouTube License',
2278 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2279 'categories': ['News & Politics'],
2280 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2281 'like_count': int,
2282 'dislike_count': int,
2283 },
2284 'params': {
2285 'skip_download': True,
2286 },
2287 }, {
2d3d2997 2288 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
f07e276a 2289 'only_matching': True,
c1b2a085
S
2290 }, {
2291 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2292 'only_matching': True,
073d5bf5
S
2293 }, {
2294 'url': 'https://www.youtube.com/TheYoungTurks/live',
2295 'only_matching': True,
f07e276a
S
2296 }]
2297
2298 def _real_extract(self, url):
2299 mobj = re.match(self._VALID_URL, url)
2300 channel_id = mobj.group('id')
2301 base_url = mobj.group('base_url')
2302 webpage = self._download_webpage(url, channel_id, fatal=False)
2303 if webpage:
2304 page_type = self._og_search_property(
2305 'type', webpage, 'page type', default=None)
2306 video_id = self._html_search_meta(
2307 'videoId', webpage, 'video id', default=None)
2308 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2309 return self.url_result(video_id, YoutubeIE.ie_key())
2310 return self.url_result(base_url)
2311
2312
e462474e
S
2313class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2314 IE_DESC = 'YouTube.com user/channel playlists'
2315 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2316 IE_NAME = 'youtube:playlists'
0c148415 2317
e568c223 2318 _TESTS = [{
2d3d2997 2319 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
0c148415
S
2320 'playlist_mincount': 4,
2321 'info_dict': {
2322 'id': 'ThirstForScience',
2323 'title': 'Thirst for Science',
2324 },
e568c223
S
2325 }, {
2326 # with "Load more" button
2d3d2997 2327 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
e568c223
S
2328 'playlist_mincount': 70,
2329 'info_dict': {
2330 'id': 'igorkle1',
2331 'title': 'Игорь Клейнер',
2332 },
e462474e
S
2333 }, {
2334 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2335 'playlist_mincount': 17,
2336 'info_dict': {
2337 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2338 'title': 'Chem Player',
2339 },
e568c223 2340 }]
0c148415
S
2341
2342
b4c08069 2343class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
78caa52a 2344 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2345 # there doesn't appear to be a real limit, for example if you search for
2346 # 'python' you get more than 8.000.000 results
2347 _MAX_RESULTS = float('inf')
78caa52a 2348 IE_NAME = 'youtube:search'
b05654f0 2349 _SEARCH_KEY = 'ytsearch'
b4c08069 2350 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2351 _TESTS = []
b05654f0 2352
b05654f0
PH
2353 def _get_n_results(self, query, n):
2354 """Get a specified number of results for a query"""
2355
b4c08069 2356 videos = []
b05654f0
PH
2357 limit = n
2358
a22b2fd1
YCH
2359 url_query = {
2360 'search_query': query.encode('utf-8'),
2361 }
2362 url_query.update(self._EXTRA_QUERY_ARGS)
2363 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2364
b4c08069 2365 for pagenum in itertools.count(1):
b4c08069 2366 data = self._download_json(
69ea8ca4 2367 result_url, video_id='query "%s"' % query,
b4c08069 2368 note='Downloading page %s' % pagenum,
a22b2fd1
YCH
2369 errnote='Unable to download API page',
2370 query={'spf': 'navigate'})
b4c08069 2371 html_content = data[1]['body']['content']
7cc3570e 2372
b4c08069 2373 if 'class="search-message' in html_content:
07ad22b8 2374 raise ExtractorError(
78caa52a 2375 '[youtube] No video results', expected=True)
b05654f0 2376
b4c08069
JMF
2377 new_videos = self._ids_to_results(orderedSet(re.findall(
2378 r'href="/watch\?v=(.{11})', html_content)))
2379 videos += new_videos
2380 if not new_videos or len(videos) > limit:
2381 break
a22b2fd1
YCH
2382 next_link = self._html_search_regex(
2383 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2384 html_content, 'next link', default=None)
2385 if next_link is None:
2386 break
2387 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
b05654f0 2388
b4c08069
JMF
2389 if len(videos) > n:
2390 videos = videos[:n]
b05654f0 2391 return self.playlist_result(videos, query)
75dff0ee 2392
c9ae7b95 2393
a3dd9248 2394class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2395 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2396 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2397 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2398 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2399
c9ae7b95 2400
175c2e9e 2401class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
78caa52a
PH
2402 IE_DESC = 'YouTube.com search URLs'
2403 IE_NAME = 'youtube:search_url'
d2c1f79f 2404 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
175c2e9e 2405 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
cdc628a4
PH
2406 _TESTS = [{
2407 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2408 'playlist_mincount': 5,
2409 'info_dict': {
2410 'title': 'youtube-dl test video',
2411 }
d2c1f79f
S
2412 }, {
2413 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2414 'only_matching': True,
cdc628a4 2415 }]
c9ae7b95
PH
2416
2417 def _real_extract(self, url):
2418 mobj = re.match(self._VALID_URL, url)
7fd002c0 2419 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2420 webpage = self._download_webpage(url, query)
175c2e9e 2421 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2422
2423
136dadde 2424class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2425 IE_DESC = 'YouTube.com (multi-season) shows'
92519402 2426 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2427 IE_NAME = 'youtube:show'
cdc628a4 2428 _TESTS = [{
4003bd82 2429 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2430 'playlist_mincount': 5,
cdc628a4
PH
2431 'info_dict': {
2432 'id': 'airdisasters',
2433 'title': 'Air Disasters',
2434 }
2435 }]
75dff0ee
JMF
2436
2437 def _real_extract(self, url):
136dadde
S
2438 playlist_id = self._match_id(url)
2439 return super(YoutubeShowIE, self)._real_extract(
2440 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2441
2442
b2e8bc1b 2443class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2444 """
25f14e9f 2445 Base class for feed extractors
d7ae0639
JMF
2446 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2447 """
b2e8bc1b 2448 _LOGIN_REQUIRED = True
d7ae0639
JMF
2449
2450 @property
2451 def IE_NAME(self):
78caa52a 2452 return 'youtube:%s' % self._FEED_NAME
04cc9617 2453
81f0259b 2454 def _real_initialize(self):
b2e8bc1b 2455 self._login()
81f0259b 2456
04cc9617 2457 def _real_extract(self, url):
25f14e9f
S
2458 page = self._download_webpage(
2459 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2bc43303
JMF
2460
2461 # The extraction process is the same as for playlists, but the regex
2462 # for the video ids doesn't contain an index
2463 ids = []
2464 more_widget_html = content_html = page
2bc43303
JMF
2465 for page_num in itertools.count(1):
2466 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2467
2468 # 'recommended' feed has infinite 'load more' and each new portion spins
2469 # the same videos in (sometimes) slightly different order, so we'll check
2470 # for unicity and break when portion has no new videos
2471 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2472 if not new_ids:
2473 break
2474
2bc43303
JMF
2475 ids.extend(new_ids)
2476
2477 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2478 if not mobj:
2479 break
2480
2481 more = self._download_json(
25f14e9f 2482 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2483 'Downloading page #%s' % page_num,
2484 transform_source=uppercase_escape)
2485 content_html = more['content_html']
2486 more_widget_html = more['load_more_widget_html']
2487
25f14e9f
S
2488 return self.playlist_result(
2489 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2490
2491
2492class YoutubeWatchLaterIE(YoutubePlaylistIE):
2493 IE_NAME = 'youtube:watchlater'
2494 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
92519402 2495 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2496
bc7a9cd8
S
2497 _TESTS = [{
2498 'url': 'https://www.youtube.com/playlist?list=WL',
2499 'only_matching': True,
2500 }, {
2501 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2502 'only_matching': True,
2503 }]
25f14e9f
S
2504
2505 def _real_extract(self, url):
7e5dc339 2506 _, video = self._check_download_just_video(url, 'WL')
ebf1b291
S
2507 if video:
2508 return video
dacb3a86
S
2509 _, playlist = self._extract_playlist('WL')
2510 return playlist
f459d170 2511
5f6a1245 2512
c626a3d9 2513class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2514 IE_NAME = 'youtube:favorites'
f3a34072 2515 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
92519402 2516 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2517 _LOGIN_REQUIRED = True
2518
2519 def _real_extract(self, url):
2520 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2521 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2522 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2523
2524
25f14e9f
S
2525class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2526 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
92519402 2527 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
25f14e9f
S
2528 _FEED_NAME = 'recommended'
2529 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2530
1ed5b5c9 2531
25f14e9f
S
2532class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2533 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
92519402 2534 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
25f14e9f
S
2535 _FEED_NAME = 'subscriptions'
2536 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2537
1ed5b5c9 2538
25f14e9f
S
2539class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2540 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
92519402 2541 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
25f14e9f
S
2542 _FEED_NAME = 'history'
2543 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2544
2545
15870e90
PH
2546class YoutubeTruncatedURLIE(InfoExtractor):
2547 IE_NAME = 'youtube:truncated_url'
2548 IE_DESC = False # Do not list
975d35db 2549 _VALID_URL = r'''(?x)
b95aab84
PH
2550 (?:https?://)?
2551 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2552 (?:watch\?(?:
c4808c60 2553 feature=[a-z_]+|
b95aab84
PH
2554 annotation_id=annotation_[^&]+|
2555 x-yt-cl=[0-9]+|
c1708b89 2556 hl=[^&]*|
287be8c6 2557 t=[0-9]+
b95aab84
PH
2558 )?
2559 |
2560 attribution_link\?a=[^&]+
2561 )
2562 $
975d35db 2563 '''
15870e90 2564
c4808c60 2565 _TESTS = [{
2d3d2997 2566 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 2567 'only_matching': True,
dc2fc736 2568 }, {
2d3d2997 2569 'url': 'https://www.youtube.com/watch?',
dc2fc736 2570 'only_matching': True,
b95aab84
PH
2571 }, {
2572 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2573 'only_matching': True,
2574 }, {
2575 'url': 'https://www.youtube.com/watch?feature=foo',
2576 'only_matching': True,
c1708b89
PH
2577 }, {
2578 'url': 'https://www.youtube.com/watch?hl=en-GB',
2579 'only_matching': True,
287be8c6
PH
2580 }, {
2581 'url': 'https://www.youtube.com/watch?t=2372',
2582 'only_matching': True,
c4808c60
PH
2583 }]
2584
15870e90
PH
2585 def _real_extract(self, url):
2586 raise ExtractorError(
78caa52a
PH
2587 'Did you forget to quote the URL? Remember that & is a meta '
2588 'character in most shells, so you want to put the URL in quotes, '
2589 'like youtube-dl '
2d3d2997 2590 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
78caa52a 2591 ' or simply youtube-dl BaW_jenozKc .',
15870e90 2592 expected=True)
772fd5cc
PH
2593
2594
2595class YoutubeTruncatedIDIE(InfoExtractor):
2596 IE_NAME = 'youtube:truncated_id'
2597 IE_DESC = False # Do not list
b95aab84 2598 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
2599
2600 _TESTS = [{
2601 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2602 'only_matching': True,
2603 }]
2604
2605 def _real_extract(self, url):
2606 video_id = self._match_id(url)
2607 raise ExtractorError(
2608 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
2609 expected=True)