]>
Commit | Line | Data |
---|---|---|
c5e8d7af | 1 | # coding: utf-8 |
c5e8d7af | 2 | |
78caa52a PH |
3 | from __future__ import unicode_literals |
4 | ||
5 | ||
0ca96d48 | 6 | import itertools |
c5e8d7af | 7 | import json |
c4417ddb | 8 | import os.path |
c5e8d7af | 9 | import re |
42939b61 | 10 | import time |
e0df6211 | 11 | import traceback |
c5e8d7af | 12 | |
b05654f0 | 13 | from .common import InfoExtractor, SearchInfoExtractor |
2b25cb5d | 14 | from ..jsinterp import JSInterpreter |
54256267 | 15 | from ..swfinterp import SWFInterpreter |
4bb4a188 | 16 | from ..compat import ( |
edf3e38e | 17 | compat_chr, |
c5e8d7af | 18 | compat_parse_qs, |
c5e8d7af | 19 | compat_urllib_parse, |
7fd002c0 S |
20 | compat_urllib_parse_unquote, |
21 | compat_urllib_parse_unquote_plus, | |
c5e8d7af | 22 | compat_urllib_request, |
7c61bd36 | 23 | compat_urlparse, |
c5e8d7af | 24 | compat_str, |
4bb4a188 PH |
25 | ) |
26 | from ..utils import ( | |
c5e8d7af | 27 | clean_html, |
c5e8d7af | 28 | ExtractorError, |
2d30521a | 29 | float_or_none, |
4bb4a188 PH |
30 | get_element_by_attribute, |
31 | get_element_by_id, | |
dd27fd17 | 32 | int_or_none, |
4bb4a188 | 33 | orderedSet, |
c93d53f5 | 34 | str_to_int, |
c5e8d7af PH |
35 | unescapeHTML, |
36 | unified_strdate, | |
81c2f20b | 37 | uppercase_escape, |
af214c3a | 38 | ISO3166Utils, |
c5e8d7af PH |
39 | ) |
40 | ||
5f6a1245 | 41 | |
de7f3446 | 42 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
43 | """Provide base functions for Youtube extractors""" |
44 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
83317f69 | 45 | _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' |
b2e8bc1b JMF |
46 | _NETRC_MACHINE = 'youtube' |
47 | # If True it will raise an error if no login info is provided | |
48 | _LOGIN_REQUIRED = False | |
49 | ||
b2e8bc1b | 50 | def _set_language(self): |
810fb84d PH |
51 | self._set_cookie( |
52 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
42939b61 | 53 | # YouTube sets the expire time to about two months |
810fb84d | 54 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 55 | |
25f14e9f S |
56 | def _ids_to_results(self, ids): |
57 | return [ | |
58 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
59 | for vid_id in ids] | |
60 | ||
b2e8bc1b | 61 | def _login(self): |
83317f69 | 62 | """ |
63 | Attempt to log in to YouTube. | |
64 | True is returned if successful or skipped. | |
65 | False is returned if login failed. | |
66 | ||
67 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
68 | """ | |
b2e8bc1b JMF |
69 | (username, password) = self._get_login_info() |
70 | # No authentication to be performed | |
71 | if username is None: | |
72 | if self._LOGIN_REQUIRED: | |
69ea8ca4 | 73 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 74 | return True |
b2e8bc1b | 75 | |
7cc3570e PH |
76 | login_page = self._download_webpage( |
77 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
78 | note='Downloading login page', |
79 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
80 | if login_page is False: |
81 | return | |
b2e8bc1b | 82 | |
795f28f8 | 83 | galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', |
78caa52a | 84 | login_page, 'Login GALX parameter') |
c5e8d7af | 85 | |
b2e8bc1b JMF |
86 | # Log in |
87 | login_form_strs = { | |
8bcc8756 JW |
88 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
89 | 'Email': username, | |
90 | 'GALX': galx, | |
91 | 'Passwd': password, | |
92 | ||
93 | 'PersistentCookie': 'yes', | |
94 | '_utf8': '霱', | |
95 | 'bgresponse': 'js_disabled', | |
96 | 'checkConnection': '', | |
97 | 'checkedDomains': 'youtube', | |
98 | 'dnConn': '', | |
99 | 'pstMsg': '0', | |
100 | 'rmShown': '1', | |
101 | 'secTok': '', | |
102 | 'signIn': 'Sign in', | |
103 | 'timeStmp': '', | |
104 | 'service': 'youtube', | |
105 | 'uilel': '3', | |
106 | 'hl': 'en_US', | |
b2e8bc1b | 107 | } |
83317f69 | 108 | |
b2e8bc1b JMF |
109 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode |
110 | # chokes on unicode | |
5f6a1245 | 111 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) |
b2e8bc1b | 112 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') |
7cc3570e PH |
113 | |
114 | req = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
115 | login_results = self._download_webpage( | |
116 | req, None, | |
69ea8ca4 | 117 | note='Logging in', errnote='unable to log in', fatal=False) |
7cc3570e PH |
118 | if login_results is False: |
119 | return False | |
83317f69 | 120 | |
121 | if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: | |
69ea8ca4 | 122 | raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) |
83317f69 | 123 | |
124 | # Two-Factor | |
125 | # TODO add SMS and phone call support - these require making a request and then prompting the user | |
126 | ||
127 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: | |
128 | tfa_code = self._get_tfa_info() | |
129 | ||
130 | if tfa_code is None: | |
69ea8ca4 PH |
131 | self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>') |
132 | self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
83317f69 | 133 | return False |
134 | ||
135 | # Unlike the first login form, secTok and timeStmp are both required for the TFA form | |
136 | ||
137 | match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
138 | if match is None: | |
69ea8ca4 | 139 | self._downloader.report_warning('Failed to get secTok - did the page structure change?') |
83317f69 | 140 | secTok = match.group(1) |
141 | match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
142 | if match is None: | |
69ea8ca4 | 143 | self._downloader.report_warning('Failed to get timeStmp - did the page structure change?') |
83317f69 | 144 | timeStmp = match.group(1) |
145 | ||
146 | tfa_form_strs = { | |
78caa52a PH |
147 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
148 | 'smsToken': '', | |
149 | 'smsUserPin': tfa_code, | |
150 | 'smsVerifyPin': 'Verify', | |
151 | ||
152 | 'PersistentCookie': 'yes', | |
153 | 'checkConnection': '', | |
154 | 'checkedDomains': 'youtube', | |
155 | 'pstMsg': '1', | |
156 | 'secTok': secTok, | |
157 | 'timeStmp': timeStmp, | |
158 | 'service': 'youtube', | |
159 | 'hl': 'en_US', | |
83317f69 | 160 | } |
5f6a1245 | 161 | tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items()) |
83317f69 | 162 | tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') |
163 | ||
164 | tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) | |
165 | tfa_results = self._download_webpage( | |
166 | tfa_req, None, | |
69ea8ca4 | 167 | note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) |
83317f69 | 168 | |
169 | if tfa_results is False: | |
170 | return False | |
171 | ||
172 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: | |
69ea8ca4 | 173 | self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.') |
83317f69 | 174 | return False |
175 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: | |
69ea8ca4 | 176 | self._downloader.report_warning('unable to log in - did the page structure change?') |
83317f69 | 177 | return False |
178 | if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: | |
69ea8ca4 | 179 | 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 | 180 | return False |
181 | ||
7cc3570e | 182 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: |
69ea8ca4 | 183 | self._downloader.report_warning('unable to log in: bad username or password') |
b2e8bc1b JMF |
184 | return False |
185 | return True | |
186 | ||
b2e8bc1b JMF |
187 | def _real_initialize(self): |
188 | if self._downloader is None: | |
189 | return | |
42939b61 | 190 | self._set_language() |
b2e8bc1b JMF |
191 | if not self._login(): |
192 | return | |
c5e8d7af | 193 | |
8377574c | 194 | |
360e1ca5 | 195 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 196 | IE_DESC = 'YouTube.com' |
cb7dfeea | 197 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 198 | ( |
edb53e2d | 199 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 200 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 201 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 202 | (?:www\.)?pwnyoutube\.com/| |
f7000f3a | 203 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 JMF |
204 | tube\.majestyc\.net/| |
205 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
206 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
207 | (?: # the various things that can precede the ID: | |
ac7553d0 | 208 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 209 | |(?: # or the v= param in all its forms |
f7000f3a | 210 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af PH |
211 | (?:\?|\#!?) # the params delimiter ? or # or #! |
212 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) | |
213 | v= | |
214 | ) | |
f4b05232 JMF |
215 | )) |
216 | |youtu\.be/ # just youtu.be/xxxx | |
edb53e2d | 217 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 218 | ) |
c5e8d7af | 219 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 220 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
9291475f | 221 | (?!.*?&list=) # combined list/video URLs are handled by the playlist IE |
c5e8d7af PH |
222 | (?(1).+)? # if we found the ID, everything can follow |
223 | $""" | |
c5e8d7af | 224 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 PH |
225 | _formats = { |
226 | '5': {'ext': 'flv', 'width': 400, 'height': 240}, | |
227 | '6': {'ext': 'flv', 'width': 450, 'height': 270}, | |
228 | '13': {'ext': '3gp'}, | |
229 | '17': {'ext': '3gp', 'width': 176, 'height': 144}, | |
230 | '18': {'ext': 'mp4', 'width': 640, 'height': 360}, | |
231 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720}, | |
232 | '34': {'ext': 'flv', 'width': 640, 'height': 360}, | |
233 | '35': {'ext': 'flv', 'width': 854, 'height': 480}, | |
234 | '36': {'ext': '3gp', 'width': 320, 'height': 240}, | |
235 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080}, | |
236 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072}, | |
237 | '43': {'ext': 'webm', 'width': 640, 'height': 360}, | |
238 | '44': {'ext': 'webm', 'width': 854, 'height': 480}, | |
239 | '45': {'ext': 'webm', 'width': 1280, 'height': 720}, | |
240 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080}, | |
c9bebed2 S |
241 | '59': {'ext': 'mp4', 'width': 854, 'height': 480}, |
242 | '78': {'ext': 'mp4', 'width': 854, 'height': 480}, | |
2c62dc26 | 243 | |
1d043b93 | 244 | |
86fe61c8 | 245 | # 3d videos |
43b81eb9 PH |
246 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20}, |
247 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
248 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
249 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20}, | |
250 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20}, | |
251 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
252 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
836a086c | 253 | |
96fb5605 | 254 | # Apple HTTP Live Streaming |
43b81eb9 PH |
255 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, |
256 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10}, | |
257 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10}, | |
258 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10}, | |
259 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10}, | |
260 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, | |
261 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10}, | |
2c62dc26 PH |
262 | |
263 | # DASH mp4 video | |
43b81eb9 PH |
264 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
265 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
266 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
267 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
268 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
e65566a9 | 269 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) |
43b81eb9 PH |
270 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
271 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
0d2c1418 PH |
272 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, |
273 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, | |
274 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, | |
836a086c | 275 | |
f6f1fc92 | 276 | # Dash mp4 audio |
62cd676c PH |
277 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}, |
278 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}, | |
279 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}, | |
836a086c AZ |
280 | |
281 | # Dash webm | |
e75cafe9 A |
282 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, |
283 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
284 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
285 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
286 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
287 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
1cc887cb | 288 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'}, |
e75cafe9 A |
289 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
290 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
291 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
292 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
293 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
294 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
295 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
3c80377b | 296 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
18061bba | 297 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
a51d3aa0 PH |
298 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
299 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, | |
76b3c610 | 300 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
10a404c3 | 301 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'}, |
76b3c610 | 302 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
2c62dc26 PH |
303 | |
304 | # Dash webm audio | |
55db73ef | 305 | '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, |
e75cafe9 | 306 | '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, |
ce6b9a2d | 307 | |
0857baad PH |
308 | # Dash webm audio with opus inside |
309 | '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, | |
310 | '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, | |
311 | '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, | |
312 | ||
ce6b9a2d PH |
313 | # RTMP (unnamed) |
314 | '_rtmp': {'protocol': 'rtmp'}, | |
c5e8d7af | 315 | } |
836a086c | 316 | |
78caa52a | 317 | IE_NAME = 'youtube' |
2eb88d95 PH |
318 | _TESTS = [ |
319 | { | |
4bc3a23e PH |
320 | 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', |
321 | 'info_dict': { | |
322 | 'id': 'BaW_jenozKc', | |
323 | 'ext': 'mp4', | |
324 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
325 | 'uploader': 'Philipp Hagemeister', | |
326 | 'uploader_id': 'phihag', | |
327 | 'upload_date': '20121002', | |
328 | '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 .', | |
329 | 'categories': ['Science & Technology'], | |
3e7c1224 PH |
330 | 'like_count': int, |
331 | 'dislike_count': int, | |
2eb88d95 | 332 | } |
0e853ca4 | 333 | }, |
0e853ca4 | 334 | { |
4bc3a23e PH |
335 | 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', |
336 | 'note': 'Test generic use_cipher_signature video (#897)', | |
337 | 'info_dict': { | |
338 | 'id': 'UxxajLWwzqY', | |
339 | 'ext': 'mp4', | |
340 | 'upload_date': '20120506', | |
341 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
342 | 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f', | |
343 | 'uploader': 'Icona Pop', | |
344 | 'uploader_id': 'IconaPop', | |
2eb88d95 | 345 | } |
c108eb73 JMF |
346 | }, |
347 | { | |
4bc3a23e PH |
348 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
349 | 'note': 'Test VEVO video with age protection (#956)', | |
350 | 'info_dict': { | |
351 | 'id': '07FYdnEawAQ', | |
352 | 'ext': 'mp4', | |
353 | 'upload_date': '20130703', | |
354 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
355 | 'description': 'md5:64249768eec3bc4276236606ea996373', | |
356 | 'uploader': 'justintimberlakeVEVO', | |
357 | 'uploader_id': 'justintimberlakeVEVO', | |
c108eb73 JMF |
358 | } |
359 | }, | |
fccd3771 | 360 | { |
4bc3a23e PH |
361 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
362 | 'note': 'Embed-only video (#1746)', | |
363 | 'info_dict': { | |
364 | 'id': 'yZIXLfi8CZQ', | |
365 | 'ext': 'mp4', | |
366 | 'upload_date': '20120608', | |
367 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
368 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
369 | 'uploader': 'SET India', | |
370 | 'uploader_id': 'setindia' | |
fccd3771 PH |
371 | } |
372 | }, | |
dd27fd17 | 373 | { |
4bc3a23e PH |
374 | 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', |
375 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
376 | 'info_dict': { | |
377 | 'id': 'a9LDPn-MO4I', | |
378 | 'ext': 'm4a', | |
379 | 'upload_date': '20121002', | |
380 | 'uploader_id': '8KVIDEO', | |
381 | 'description': '', | |
382 | 'uploader': '8KVIDEO', | |
383 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 384 | }, |
4bc3a23e PH |
385 | 'params': { |
386 | 'youtube_include_dash_manifest': True, | |
387 | 'format': '141', | |
4919603f | 388 | }, |
dd27fd17 | 389 | }, |
3489b7d2 JMF |
390 | # DASH manifest with encrypted signature |
391 | { | |
78caa52a PH |
392 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
393 | 'info_dict': { | |
394 | 'id': 'IB3lcPjvWLA', | |
395 | 'ext': 'm4a', | |
b766eb27 JMF |
396 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', |
397 | 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', | |
78caa52a PH |
398 | 'uploader': 'AfrojackVEVO', |
399 | 'uploader_id': 'AfrojackVEVO', | |
400 | 'upload_date': '20131011', | |
3489b7d2 | 401 | }, |
4bc3a23e | 402 | 'params': { |
78caa52a PH |
403 | 'youtube_include_dash_manifest': True, |
404 | 'format': '141', | |
3489b7d2 JMF |
405 | }, |
406 | }, | |
aaeb86f6 S |
407 | # JS player signature function name containing $ |
408 | { | |
409 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
410 | 'info_dict': { | |
411 | 'id': 'nfWlot6h_JM', | |
412 | 'ext': 'm4a', | |
413 | 'title': 'Taylor Swift - Shake It Off', | |
414 | 'description': 'md5:2acfda1b285bdd478ccec22f9918199d', | |
415 | 'uploader': 'TaylorSwiftVEVO', | |
416 | 'uploader_id': 'TaylorSwiftVEVO', | |
417 | 'upload_date': '20140818', | |
418 | }, | |
419 | 'params': { | |
420 | 'youtube_include_dash_manifest': True, | |
421 | 'format': '141', | |
422 | }, | |
423 | }, | |
aa79ac0c PH |
424 | # Controversy video |
425 | { | |
426 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
427 | 'info_dict': { | |
428 | 'id': 'T4XJQO3qol8', | |
429 | 'ext': 'mp4', | |
430 | 'upload_date': '20100909', | |
431 | 'uploader': 'The Amazing Atheist', | |
432 | 'uploader_id': 'TheAmazingAtheist', | |
433 | 'title': 'Burning Everyone\'s Koran', | |
434 | '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', | |
435 | } | |
c522adb1 JMF |
436 | }, |
437 | # Normal age-gate video (No vevo, embed allowed) | |
438 | { | |
439 | 'url': 'http://youtube.com/watch?v=HtVdAasjOgU', | |
440 | 'info_dict': { | |
441 | 'id': 'HtVdAasjOgU', | |
442 | 'ext': 'mp4', | |
443 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
9ed99402 | 444 | 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
c522adb1 JMF |
445 | 'uploader': 'The Witcher', |
446 | 'uploader_id': 'WitcherGame', | |
447 | 'upload_date': '20140605', | |
448 | }, | |
449 | }, | |
fccae2b9 S |
450 | # Age-gate video with encrypted signature |
451 | { | |
452 | 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', | |
453 | 'info_dict': { | |
454 | 'id': '6kLq3WMV1nU', | |
455 | 'ext': 'mp4', | |
456 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
457 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
458 | 'uploader': 'LloydVEVO', | |
459 | 'uploader_id': 'LloydVEVO', | |
460 | 'upload_date': '20110629', | |
461 | }, | |
462 | }, | |
774e208f PH |
463 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) |
464 | { | |
465 | 'url': '__2ABJjxzNo', | |
466 | 'info_dict': { | |
467 | 'id': '__2ABJjxzNo', | |
468 | 'ext': 'mp4', | |
469 | 'upload_date': '20100430', | |
470 | 'uploader_id': 'deadmau5', | |
471 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', | |
472 | 'uploader': 'deadmau5', | |
473 | 'title': 'Deadmau5 - Some Chords (HD)', | |
474 | }, | |
475 | 'expected_warnings': [ | |
476 | 'DASH manifest missing', | |
477 | ] | |
e52a40ab PH |
478 | }, |
479 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
480 | { | |
481 | 'url': 'lqQg6PlCWgI', | |
482 | 'info_dict': { | |
483 | 'id': 'lqQg6PlCWgI', | |
484 | 'ext': 'mp4', | |
cbe2bd91 PH |
485 | 'upload_date': '20120731', |
486 | 'uploader_id': 'olympic', | |
487 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
488 | 'uploader': 'Olympics', | |
489 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
490 | }, | |
491 | 'params': { | |
492 | 'skip_download': 'requires avconv', | |
e52a40ab | 493 | } |
cbe2bd91 | 494 | }, |
6271f1ca PH |
495 | # Non-square pixels |
496 | { | |
497 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
498 | 'info_dict': { | |
499 | 'id': '_b-2C3KPAM0', | |
500 | 'ext': 'mp4', | |
501 | 'stretched_ratio': 16 / 9., | |
502 | 'upload_date': '20110310', | |
503 | 'uploader_id': 'AllenMeow', | |
504 | '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', | |
505 | 'uploader': '孫艾倫', | |
506 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
507 | }, | |
06b491eb S |
508 | }, |
509 | # url_encoded_fmt_stream_map is empty string | |
510 | { | |
511 | 'url': 'qEJwOuvDf7I', | |
512 | 'info_dict': { | |
513 | 'id': 'qEJwOuvDf7I', | |
514 | 'ext': 'mp4', | |
515 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
516 | 'description': '', | |
517 | 'upload_date': '20150404', | |
518 | 'uploader_id': 'spbelect', | |
519 | 'uploader': 'Наблюдатели Петербурга', | |
520 | }, | |
521 | 'params': { | |
522 | 'skip_download': 'requires avconv', | |
523 | } | |
524 | }, | |
da77d856 S |
525 | # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097) |
526 | { | |
527 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
528 | 'info_dict': { | |
529 | 'id': 'FIl7x6_3R5Y', | |
530 | 'ext': 'mp4', | |
531 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
532 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
533 | 'upload_date': '20150625', | |
534 | 'uploader_id': 'dorappi2000', | |
535 | 'uploader': 'dorappi2000', | |
536 | 'formats': 'mincount:33', | |
537 | }, | |
538 | } | |
2eb88d95 PH |
539 | ] |
540 | ||
e0df6211 PH |
541 | def __init__(self, *args, **kwargs): |
542 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 543 | self._player_cache = {} |
e0df6211 | 544 | |
c5e8d7af PH |
545 | def report_video_info_webpage_download(self, video_id): |
546 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 547 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 548 | |
c5e8d7af PH |
549 | def report_information_extraction(self, video_id): |
550 | """Report attempt to extract video information.""" | |
69ea8ca4 | 551 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
552 | |
553 | def report_unavailable_format(self, video_id, format): | |
554 | """Report extracted video URL.""" | |
69ea8ca4 | 555 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
556 | |
557 | def report_rtmp_download(self): | |
558 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 559 | self.to_screen('RTMP download detected') |
c5e8d7af | 560 | |
60064c53 PH |
561 | def _signature_cache_id(self, example_sig): |
562 | """ Return a string representation of a signature """ | |
78caa52a | 563 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
564 | |
565 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 566 | id_m = re.match( |
60620368 | 567 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', |
cf010131 | 568 | player_url) |
c081b35c PH |
569 | if not id_m: |
570 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
571 | player_type = id_m.group('ext') |
572 | player_id = id_m.group('id') | |
573 | ||
c4417ddb | 574 | # Read from filesystem cache |
60064c53 PH |
575 | func_id = '%s_%s_%s' % ( |
576 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 577 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 578 | |
69ea8ca4 | 579 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 580 | if cache_spec is not None: |
78caa52a | 581 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 582 | |
6d1a55a5 PH |
583 | download_note = ( |
584 | 'Downloading player %s' % player_url | |
585 | if self._downloader.params.get('verbose') else | |
586 | 'Downloading %s player %s' % (player_type, player_id) | |
587 | ) | |
e0df6211 PH |
588 | if player_type == 'js': |
589 | code = self._download_webpage( | |
590 | player_url, video_id, | |
6d1a55a5 | 591 | note=download_note, |
69ea8ca4 | 592 | errnote='Download of %s failed' % player_url) |
83799698 | 593 | res = self._parse_sig_js(code) |
c4417ddb | 594 | elif player_type == 'swf': |
e0df6211 PH |
595 | urlh = self._request_webpage( |
596 | player_url, video_id, | |
6d1a55a5 | 597 | note=download_note, |
69ea8ca4 | 598 | errnote='Download of %s failed' % player_url) |
e0df6211 | 599 | code = urlh.read() |
83799698 | 600 | res = self._parse_sig_swf(code) |
e0df6211 PH |
601 | else: |
602 | assert False, 'Invalid player type %r' % player_type | |
603 | ||
785521bf PH |
604 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
605 | cache_res = res(test_string) | |
606 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 607 | |
69ea8ca4 | 608 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
609 | return res |
610 | ||
60064c53 | 611 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
612 | def gen_sig_code(idxs): |
613 | def _genslice(start, end, step): | |
78caa52a | 614 | starts = '' if start == 0 else str(start) |
8bcc8756 | 615 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 616 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 617 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
618 | |
619 | step = None | |
7af808a5 PH |
620 | # Quelch pyflakes warnings - start will be set when step is set |
621 | start = '(Never used)' | |
edf3e38e PH |
622 | for i, prev in zip(idxs[1:], idxs[:-1]): |
623 | if step is not None: | |
624 | if i - prev == step: | |
625 | continue | |
626 | yield _genslice(start, prev, step) | |
627 | step = None | |
628 | continue | |
629 | if i - prev in [-1, 1]: | |
630 | step = i - prev | |
631 | start = prev | |
632 | continue | |
633 | else: | |
78caa52a | 634 | yield 's[%d]' % prev |
edf3e38e | 635 | if step is None: |
78caa52a | 636 | yield 's[%d]' % i |
edf3e38e PH |
637 | else: |
638 | yield _genslice(start, i, step) | |
639 | ||
78caa52a | 640 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 641 | cache_res = func(test_string) |
edf3e38e | 642 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 643 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
644 | signature_id_tuple = '(%s)' % ( |
645 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 646 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 647 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 648 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 649 | |
e0df6211 PH |
650 | def _parse_sig_js(self, jscode): |
651 | funcname = self._search_regex( | |
aaeb86f6 | 652 | r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode, |
8bcc8756 | 653 | 'Initial JS player signature function name') |
2b25cb5d PH |
654 | |
655 | jsi = JSInterpreter(jscode) | |
656 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
657 | return lambda s: initial_function([s]) |
658 | ||
659 | def _parse_sig_swf(self, file_contents): | |
54256267 | 660 | swfi = SWFInterpreter(file_contents) |
78caa52a | 661 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 662 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 663 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
664 | return lambda s: initial_function([s]) |
665 | ||
83799698 | 666 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 667 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 668 | |
c8bf86d5 | 669 | if player_url is None: |
69ea8ca4 | 670 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 671 | |
69ea8ca4 | 672 | if player_url.startswith('//'): |
78caa52a | 673 | player_url = 'https:' + player_url |
c8bf86d5 | 674 | try: |
62af3a0e | 675 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
676 | if player_id not in self._player_cache: |
677 | func = self._extract_signature_function( | |
60064c53 | 678 | video_id, player_url, s |
c8bf86d5 PH |
679 | ) |
680 | self._player_cache[player_id] = func | |
681 | func = self._player_cache[player_id] | |
682 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 683 | self._print_sig_code(func, s) |
c8bf86d5 PH |
684 | return func(s) |
685 | except Exception as e: | |
686 | tb = traceback.format_exc() | |
687 | raise ExtractorError( | |
78caa52a | 688 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 689 | |
360e1ca5 | 690 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 691 | try: |
60e47a26 | 692 | subs_doc = self._download_xml( |
38c2e5b8 | 693 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
694 | video_id, note=False) |
695 | except ExtractorError as err: | |
69ea8ca4 | 696 | self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) |
de7f3446 | 697 | return {} |
de7f3446 JMF |
698 | |
699 | sub_lang_list = {} | |
60e47a26 JMF |
700 | for track in subs_doc.findall('track'): |
701 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
702 | if lang in sub_lang_list: |
703 | continue | |
360e1ca5 JMF |
704 | sub_formats = [] |
705 | for ext in ['sbv', 'vtt', 'srt']: | |
706 | params = compat_urllib_parse.urlencode({ | |
707 | 'lang': lang, | |
708 | 'v': video_id, | |
709 | 'fmt': ext, | |
710 | 'name': track.attrib['name'].encode('utf-8'), | |
711 | }) | |
712 | sub_formats.append({ | |
713 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
714 | 'ext': ext, | |
715 | }) | |
716 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 717 | if not sub_lang_list: |
69ea8ca4 | 718 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
719 | return {} |
720 | return sub_lang_list | |
721 | ||
360e1ca5 | 722 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
723 | """We need the webpage for getting the captions url, pass it as an |
724 | argument to speed up the process.""" | |
69ea8ca4 | 725 | self.to_screen('%s: Looking for automatic captions' % video_id) |
de7f3446 | 726 | mobj = re.search(r';ytplayer.config = ({.*?});', webpage) |
78caa52a | 727 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
de7f3446 JMF |
728 | if mobj is None: |
729 | self._downloader.report_warning(err_msg) | |
730 | return {} | |
731 | player_config = json.loads(mobj.group(1)) | |
732 | try: | |
0792d563 PH |
733 | args = player_config['args'] |
734 | caption_url = args['ttsurl'] | |
735 | timestamp = args['timestamp'] | |
055e6f36 JMF |
736 | # We get the available subtitles |
737 | list_params = compat_urllib_parse.urlencode({ | |
738 | 'type': 'list', | |
739 | 'tlangs': 1, | |
740 | 'asrs': 1, | |
de7f3446 | 741 | }) |
055e6f36 | 742 | list_url = caption_url + '&' + list_params |
e26f8712 | 743 | caption_list = self._download_xml(list_url, video_id) |
e3dc22ca | 744 | original_lang_node = caption_list.find('track') |
7d900ef1 | 745 | if original_lang_node is None: |
69ea8ca4 | 746 | self._downloader.report_warning('Video doesn\'t have automatic captions') |
e3dc22ca JMF |
747 | return {} |
748 | original_lang = original_lang_node.attrib['lang_code'] | |
7d900ef1 | 749 | caption_kind = original_lang_node.attrib.get('kind', '') |
055e6f36 JMF |
750 | |
751 | sub_lang_list = {} | |
752 | for lang_node in caption_list.findall('target'): | |
753 | sub_lang = lang_node.attrib['lang_code'] | |
360e1ca5 JMF |
754 | sub_formats = [] |
755 | for ext in ['sbv', 'vtt', 'srt']: | |
756 | params = compat_urllib_parse.urlencode({ | |
757 | 'lang': original_lang, | |
758 | 'tlang': sub_lang, | |
759 | 'fmt': ext, | |
760 | 'ts': timestamp, | |
761 | 'kind': caption_kind, | |
762 | }) | |
763 | sub_formats.append({ | |
764 | 'url': caption_url + '&' + params, | |
765 | 'ext': ext, | |
766 | }) | |
767 | sub_lang_list[sub_lang] = sub_formats | |
055e6f36 | 768 | return sub_lang_list |
de7f3446 JMF |
769 | # An extractor error can be raise by the download process if there are |
770 | # no automatic captions but there are subtitles | |
771 | except (KeyError, ExtractorError): | |
772 | self._downloader.report_warning(err_msg) | |
773 | return {} | |
774 | ||
97665381 PH |
775 | @classmethod |
776 | def extract_id(cls, url): | |
777 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 778 | if mobj is None: |
69ea8ca4 | 779 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
780 | video_id = mobj.group(2) |
781 | return video_id | |
782 | ||
1d043b93 JMF |
783 | def _extract_from_m3u8(self, manifest_url, video_id): |
784 | url_map = {} | |
5f6a1245 | 785 | |
1d043b93 JMF |
786 | def _get_urls(_manifest): |
787 | lines = _manifest.split('\n') | |
788 | urls = filter(lambda l: l and not l.startswith('#'), | |
8bcc8756 | 789 | lines) |
1d043b93 | 790 | return urls |
78caa52a | 791 | manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') |
1d043b93 JMF |
792 | formats_urls = _get_urls(manifest) |
793 | for format_url in formats_urls: | |
890f62e8 | 794 | itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag') |
1d043b93 JMF |
795 | url_map[itag] = format_url |
796 | return url_map | |
797 | ||
1fb07d10 JG |
798 | def _extract_annotations(self, video_id): |
799 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
69ea8ca4 | 800 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') |
1fb07d10 | 801 | |
da276600 | 802 | def _parse_dash_manifest( |
77c6fb5b | 803 | self, video_id, dash_manifest_url, player_url, age_gate, fatal=True): |
774e208f PH |
804 | def decrypt_sig(mobj): |
805 | s = mobj.group(1) | |
806 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
807 | return '/signature/%s' % dec_s | |
e1b9322b | 808 | dash_manifest_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, dash_manifest_url) |
774e208f PH |
809 | dash_doc = self._download_xml( |
810 | dash_manifest_url, video_id, | |
811 | note='Downloading DASH manifest', | |
77c6fb5b S |
812 | errnote='Could not download DASH manifest', |
813 | fatal=fatal) | |
814 | ||
815 | if dash_doc is False: | |
816 | return [] | |
774e208f PH |
817 | |
818 | formats = [] | |
de5c5456 YCH |
819 | for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'): |
820 | mime_type = a.attrib.get('mimeType') | |
821 | for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'): | |
822 | url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') | |
823 | if url_el is None: | |
824 | continue | |
825 | if mime_type == 'text/vtt': | |
826 | # TODO implement WebVTT downloading | |
827 | pass | |
828 | elif mime_type.startswith('audio/') or mime_type.startswith('video/'): | |
829 | format_id = r.attrib['id'] | |
830 | video_url = url_el.text | |
831 | filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) | |
832 | f = { | |
833 | 'format_id': format_id, | |
834 | 'url': video_url, | |
835 | 'width': int_or_none(r.attrib.get('width')), | |
836 | 'height': int_or_none(r.attrib.get('height')), | |
837 | 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), | |
838 | 'asr': int_or_none(r.attrib.get('audioSamplingRate')), | |
839 | 'filesize': filesize, | |
840 | 'fps': int_or_none(r.attrib.get('frameRate')), | |
841 | } | |
842 | try: | |
843 | existing_format = next( | |
844 | fo for fo in formats | |
845 | if fo['format_id'] == format_id) | |
846 | except StopIteration: | |
847 | full_info = self._formats.get(format_id, {}).copy() | |
848 | full_info.update(f) | |
1b5a1ae2 S |
849 | codecs = r.attrib.get('codecs') |
850 | if codecs: | |
851 | if full_info.get('acodec') == 'none' and 'vcodec' not in full_info: | |
852 | full_info['vcodec'] = codecs | |
853 | elif full_info.get('vcodec') == 'none' and 'acodec' not in full_info: | |
854 | full_info['acodec'] = codecs | |
de5c5456 YCH |
855 | formats.append(full_info) |
856 | else: | |
857 | existing_format.update(f) | |
858 | else: | |
859 | self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) | |
774e208f PH |
860 | return formats |
861 | ||
c5e8d7af | 862 | def _real_extract(self, url): |
7e8c0af0 | 863 | proto = ( |
78caa52a PH |
864 | 'http' if self._downloader.params.get('prefer_insecure', False) |
865 | else 'https') | |
7e8c0af0 | 866 | |
c5e8d7af PH |
867 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
868 | mobj = re.search(self._NEXT_URL_RE, url) | |
869 | if mobj: | |
7fd002c0 | 870 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') |
97665381 | 871 | video_id = self.extract_id(url) |
c5e8d7af PH |
872 | |
873 | # Get video webpage | |
aa79ac0c | 874 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 875 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
876 | |
877 | # Attempt to extract SWF player URL | |
e0df6211 | 878 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
879 | if mobj is not None: |
880 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
881 | else: | |
882 | player_url = None | |
883 | ||
d8d24a92 S |
884 | dash_mpds = [] |
885 | ||
886 | def add_dash_mpd(video_info): | |
887 | dash_mpd = video_info.get('dashmpd') | |
888 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
889 | dash_mpds.append(dash_mpd[0]) | |
890 | ||
c5e8d7af | 891 | # Get video info |
6449cd80 | 892 | embed_webpage = None |
c108eb73 | 893 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
894 | age_gate = True |
895 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
896 | # this can be viewed without login into Youtube | |
beb95e77 CL |
897 | url = proto + '://www.youtube.com/embed/%s' % video_id |
898 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
2c57c7fa JMF |
899 | data = compat_urllib_parse.urlencode({ |
900 | 'video_id': video_id, | |
901 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 902 | 'sts': self._search_regex( |
beb95e77 | 903 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 904 | }) |
7e8c0af0 | 905 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
906 | video_info_webpage = self._download_webpage( |
907 | video_info_url, video_id, | |
20436c30 | 908 | note='Refetching age-gated info webpage', |
94bd3613 | 909 | errnote='unable to download video info webpage') |
c5e8d7af | 910 | video_info = compat_parse_qs(video_info_webpage) |
d8d24a92 | 911 | add_dash_mpd(video_info) |
c108eb73 JMF |
912 | else: |
913 | age_gate = False | |
bc93bdb5 | 914 | video_info = None |
d8d24a92 S |
915 | # Try looking directly into the video webpage |
916 | mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) | |
917 | if mobj: | |
4e62ebe2 JMF |
918 | json_code = uppercase_escape(mobj.group(1)) |
919 | ytplayer_config = json.loads(json_code) | |
920 | args = ytplayer_config['args'] | |
d8d24a92 S |
921 | if args.get('url_encoded_fmt_stream_map'): |
922 | # Convert to the same format returned by compat_parse_qs | |
923 | video_info = dict((k, [v]) for k, v in args.items()) | |
924 | add_dash_mpd(video_info) | |
0a3cf9ad S |
925 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
926 | # We also try looking in get_video_info since it may contain different dashmpd | |
927 | # URL that points to a DASH manifest with possibly different itag set (some itags | |
928 | # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH | |
929 | # manifest pointed by get_video_info's dashmpd). | |
930 | # The general idea is to take a union of itags of both DASH manifests (for example | |
931 | # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093) | |
4e62ebe2 | 932 | self.report_video_info_webpage_download(video_id) |
0a3cf9ad | 933 | for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']: |
810fb84d PH |
934 | video_info_url = ( |
935 | '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
936 | % (proto, video_id, el_type)) | |
937 | video_info_webpage = self._download_webpage( | |
938 | video_info_url, | |
4e62ebe2 JMF |
939 | video_id, note=False, |
940 | errnote='unable to download video info webpage') | |
0a3cf9ad S |
941 | get_video_info = compat_parse_qs(video_info_webpage) |
942 | add_dash_mpd(get_video_info) | |
943 | if not video_info: | |
944 | video_info = get_video_info | |
945 | if 'token' in get_video_info: | |
4e62ebe2 | 946 | break |
c5e8d7af PH |
947 | if 'token' not in video_info: |
948 | if 'reason' in video_info: | |
af214c3a YCH |
949 | if 'The uploader has not made this video available in your country.' in video_info['reason']: |
950 | regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None) | |
951 | if regions_allowed is not None: | |
952 | raise ExtractorError('YouTube said: This video is available in %s only' % ( | |
953 | ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))), | |
954 | expected=True) | |
d11271dd | 955 | raise ExtractorError( |
78caa52a | 956 | 'YouTube said: %s' % video_info['reason'][0], |
d11271dd | 957 | expected=True, video_id=video_id) |
c5e8d7af | 958 | else: |
d11271dd | 959 | raise ExtractorError( |
78caa52a | 960 | '"token" parameter not in video info for unknown reason', |
d11271dd | 961 | video_id=video_id) |
c5e8d7af | 962 | |
1d699755 PH |
963 | if 'view_count' in video_info: |
964 | view_count = int(video_info['view_count'][0]) | |
965 | else: | |
966 | view_count = None | |
967 | ||
c5e8d7af PH |
968 | # Check for "rental" videos |
969 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
69ea8ca4 | 970 | raise ExtractorError('"rental" videos not supported') |
c5e8d7af PH |
971 | |
972 | # Start extracting information | |
973 | self.report_information_extraction(video_id) | |
974 | ||
975 | # uploader | |
976 | if 'author' not in video_info: | |
69ea8ca4 | 977 | raise ExtractorError('Unable to extract uploader name') |
7fd002c0 | 978 | video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0]) |
c5e8d7af PH |
979 | |
980 | # uploader_id | |
981 | video_uploader_id = None | |
982 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) | |
983 | if mobj is not None: | |
984 | video_uploader_id = mobj.group(1) | |
985 | else: | |
69ea8ca4 | 986 | self._downloader.report_warning('unable to extract uploader nickname') |
c5e8d7af PH |
987 | |
988 | # title | |
a8c6b241 | 989 | if 'title' in video_info: |
aa92f063 | 990 | video_title = video_info['title'][0] |
a8c6b241 | 991 | else: |
69ea8ca4 | 992 | self._downloader.report_warning('Unable to extract video title') |
78caa52a | 993 | video_title = '_' |
c5e8d7af PH |
994 | |
995 | # thumbnail image | |
7763b04e JMF |
996 | # We try first to get a high quality image: |
997 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
998 | video_webpage, re.DOTALL) | |
999 | if m_thumb is not None: | |
1000 | video_thumbnail = m_thumb.group(1) | |
1001 | elif 'thumbnail_url' not in video_info: | |
69ea8ca4 | 1002 | self._downloader.report_warning('unable to extract video thumbnail') |
f490e77e | 1003 | video_thumbnail = None |
c5e8d7af | 1004 | else: # don't panic if we can't find it |
7fd002c0 | 1005 | video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) |
c5e8d7af PH |
1006 | |
1007 | # upload date | |
9d0b581f S |
1008 | upload_date = self._html_search_meta( |
1009 | 'datePublished', video_webpage, 'upload date', default=None) | |
1010 | if not upload_date: | |
1011 | upload_date = self._search_regex( | |
1012 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
1013 | r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'], | |
1014 | video_webpage, 'upload date', default=None) | |
1015 | if upload_date: | |
1016 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
1017 | upload_date = unified_strdate(upload_date) | |
c5e8d7af | 1018 | |
55f7bd2d PH |
1019 | m_cat_container = self._search_regex( |
1020 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
624dcebf | 1021 | video_webpage, 'categories', default=None) |
ec8deefc | 1022 | if m_cat_container: |
ad3bc6ac | 1023 | category = self._html_search_regex( |
01ed5c9b | 1024 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', |
ad3bc6ac PH |
1025 | default=None) |
1026 | video_categories = None if category is None else [category] | |
1027 | else: | |
1028 | video_categories = None | |
ec8deefc | 1029 | |
c5e8d7af PH |
1030 | # description |
1031 | video_description = get_element_by_id("eow-description", video_webpage) | |
1032 | if video_description: | |
27dcce19 PH |
1033 | video_description = re.sub(r'''(?x) |
1034 | <a\s+ | |
1035 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
1036 | title="([^"]+)"\s+ | |
1037 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
1038 | class="yt-uix-redirect-link"\s*> | |
1039 | [^<]+ | |
1040 | </a> | |
1041 | ''', r'\1', video_description) | |
c5e8d7af PH |
1042 | video_description = clean_html(video_description) |
1043 | else: | |
1044 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
1045 | if fd_mobj: | |
1046 | video_description = unescapeHTML(fd_mobj.group(1)) | |
1047 | else: | |
78caa52a | 1048 | video_description = '' |
c5e8d7af | 1049 | |
f30a38be | 1050 | def _extract_count(count_name): |
c93d53f5 S |
1051 | return str_to_int(self._search_regex( |
1052 | r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' | |
1053 | % re.escape(count_name), | |
1054 | video_webpage, count_name, default=None)) | |
1055 | ||
69ea8ca4 PH |
1056 | like_count = _extract_count('like') |
1057 | dislike_count = _extract_count('dislike') | |
336c3a69 | 1058 | |
c5e8d7af | 1059 | # subtitles |
d82134c3 | 1060 | video_subtitles = self.extract_subtitles(video_id, video_webpage) |
360e1ca5 | 1061 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) |
c5e8d7af PH |
1062 | |
1063 | if 'length_seconds' not in video_info: | |
69ea8ca4 | 1064 | self._downloader.report_warning('unable to extract video duration') |
b466b702 | 1065 | video_duration = None |
c5e8d7af | 1066 | else: |
7fd002c0 | 1067 | video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0])) |
c5e8d7af | 1068 | |
1fb07d10 JG |
1069 | # annotations |
1070 | video_annotations = None | |
1071 | if self._downloader.params.get('writeannotations', False): | |
5f6a1245 | 1072 | video_annotations = self._extract_annotations(video_id) |
1fb07d10 | 1073 | |
dd27fd17 PH |
1074 | def _map_to_format_list(urlmap): |
1075 | formats = [] | |
1076 | for itag, video_real_url in urlmap.items(): | |
1077 | dct = { | |
1078 | 'format_id': itag, | |
1079 | 'url': video_real_url, | |
1080 | 'player_url': player_url, | |
1081 | } | |
0b65e5d4 PH |
1082 | if itag in self._formats: |
1083 | dct.update(self._formats[itag]) | |
dd27fd17 PH |
1084 | formats.append(dct) |
1085 | return formats | |
1086 | ||
c5e8d7af PH |
1087 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1088 | self.report_rtmp_download() | |
dd27fd17 PH |
1089 | formats = [{ |
1090 | 'format_id': '_rtmp', | |
1091 | 'protocol': 'rtmp', | |
1092 | 'url': video_info['conn'][0], | |
1093 | 'player_url': player_url, | |
1094 | }] | |
24270b03 | 1095 | elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: |
5f6a1245 | 1096 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1097 | if 'rtmpe%3Dyes' in encoded_url_map: |
a7055eb9 | 1098 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) |
c5e8d7af | 1099 | url_map = {} |
00fe14fc | 1100 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1101 | url_data = compat_parse_qs(url_data_str) |
201e9eaa PH |
1102 | if 'itag' not in url_data or 'url' not in url_data: |
1103 | continue | |
1104 | format_id = url_data['itag'][0] | |
1105 | url = url_data['url'][0] | |
1106 | ||
1107 | if 'sig' in url_data: | |
1108 | url += '&signature=' + url_data['sig'][0] | |
1109 | elif 's' in url_data: | |
1110 | encrypted_sig = url_data['s'][0] | |
6449cd80 | 1111 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
201e9eaa | 1112 | |
beb95e77 | 1113 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1114 | ASSETS_RE, |
1115 | embed_webpage if age_gate else video_webpage, | |
1116 | 'JS player URL (1)', default=None) | |
1117 | if not jsplayer_url_json and not age_gate: | |
1118 | # We need the embed website after all | |
1119 | if embed_webpage is None: | |
1120 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1121 | embed_webpage = self._download_webpage( | |
1122 | embed_url, video_id, 'Downloading embed webpage') | |
1123 | jsplayer_url_json = self._search_regex( | |
1124 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1125 | ||
beb95e77 | 1126 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1127 | if player_url is None: |
1128 | player_url_json = self._search_regex( | |
1129 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1130 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1131 | player_url = json.loads(player_url_json) |
1132 | ||
1133 | if self._downloader.params.get('verbose'): | |
cf010131 | 1134 | if player_url is None: |
201e9eaa PH |
1135 | player_version = 'unknown' |
1136 | player_desc = 'unknown' | |
1137 | else: | |
1138 | if player_url.endswith('swf'): | |
1139 | player_version = self._search_regex( | |
1140 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 1141 | 'flash player', fatal=False) |
201e9eaa | 1142 | player_desc = 'flash player %s' % player_version |
cf010131 | 1143 | else: |
201e9eaa PH |
1144 | player_version = self._search_regex( |
1145 | r'html5player-([^/]+?)(?:/html5player)?\.js', | |
1146 | player_url, | |
1147 | 'html5 player', fatal=False) | |
78caa52a | 1148 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 1149 | |
60064c53 | 1150 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 1151 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 1152 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
1153 | |
1154 | signature = self._decrypt_signature( | |
1155 | encrypted_sig, video_id, player_url, age_gate) | |
1156 | url += '&signature=' + signature | |
1157 | if 'ratebypass' not in url: | |
1158 | url += '&ratebypass=yes' | |
1159 | url_map[format_id] = url | |
dd27fd17 | 1160 | formats = _map_to_format_list(url_map) |
1d043b93 JMF |
1161 | elif video_info.get('hlsvp'): |
1162 | manifest_url = video_info['hlsvp'][0] | |
1163 | url_map = self._extract_from_m3u8(manifest_url, video_id) | |
dd27fd17 | 1164 | formats = _map_to_format_list(url_map) |
c5e8d7af | 1165 | else: |
69ea8ca4 | 1166 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') |
c5e8d7af | 1167 | |
dd27fd17 | 1168 | # Look for the DASH manifest |
203fb43f | 1169 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
77c6fb5b | 1170 | dash_mpd_fatal = True |
d8d24a92 S |
1171 | for dash_manifest_url in dash_mpds: |
1172 | dash_formats = {} | |
774e208f | 1173 | try: |
d8d24a92 | 1174 | for df in self._parse_dash_manifest( |
77c6fb5b | 1175 | video_id, dash_manifest_url, player_url, age_gate, dash_mpd_fatal): |
d8d24a92 S |
1176 | # Do not overwrite DASH format found in some previous DASH manifest |
1177 | if df['format_id'] not in dash_formats: | |
1178 | dash_formats[df['format_id']] = df | |
77c6fb5b S |
1179 | # Additional DASH manifests may end up in HTTP Error 403 therefore |
1180 | # allow them to fail without bug report message if we already have | |
1181 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
1182 | # burst of bug reports until we figure out the reason and whether it | |
1183 | # can be fixed at all. | |
1184 | dash_mpd_fatal = False | |
774e208f PH |
1185 | except (ExtractorError, KeyError) as e: |
1186 | self.report_warning( | |
1187 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 1188 | if dash_formats: |
04b3b3df JMF |
1189 | # Remove the formats we found through non-DASH, they |
1190 | # contain less info and it can be wrong, because we use | |
1191 | # fixed values (for example the resolution). See | |
1192 | # https://github.com/rg3/youtube-dl/issues/5774 for an | |
1193 | # example. | |
d80265cc | 1194 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 1195 | formats.extend(dash_formats.values()) |
d80044c2 | 1196 | |
6271f1ca PH |
1197 | # Check for malformed aspect ratio |
1198 | stretched_m = re.search( | |
1199 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
1200 | video_webpage) | |
1201 | if stretched_m: | |
1202 | ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) | |
1203 | for f in formats: | |
1204 | if f.get('vcodec') != 'none': | |
1205 | f['stretched_ratio'] = ratio | |
1206 | ||
4bcc7bd1 | 1207 | self._sort_formats(formats) |
4ea3be0a | 1208 | |
1209 | return { | |
8bcc8756 JW |
1210 | 'id': video_id, |
1211 | 'uploader': video_uploader, | |
1212 | 'uploader_id': video_uploader_id, | |
1213 | 'upload_date': upload_date, | |
1214 | 'title': video_title, | |
1215 | 'thumbnail': video_thumbnail, | |
1216 | 'description': video_description, | |
1217 | 'categories': video_categories, | |
1218 | 'subtitles': video_subtitles, | |
360e1ca5 | 1219 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
1220 | 'duration': video_duration, |
1221 | 'age_limit': 18 if age_gate else 0, | |
1222 | 'annotations': video_annotations, | |
7e8c0af0 | 1223 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 1224 | 'view_count': view_count, |
4ea3be0a | 1225 | 'like_count': like_count, |
1226 | 'dislike_count': dislike_count, | |
2d30521a | 1227 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), |
8bcc8756 | 1228 | 'formats': formats, |
4ea3be0a | 1229 | } |
c5e8d7af | 1230 | |
5f6a1245 | 1231 | |
880e1c52 | 1232 | class YoutubePlaylistIE(YoutubeBaseInfoExtractor): |
78caa52a | 1233 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 1234 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
1235 | (?:https?://)? |
1236 | (?:\w+\.)? | |
1237 | youtube\.com/ | |
1238 | (?: | |
ac7553d0 | 1239 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) |
c5e8d7af PH |
1240 | \? (?:.*?&)*? (?:p|a|list)= |
1241 | | p/ | |
1242 | ) | |
d67cc9fa | 1243 | ( |
99209c29 | 1244 | (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 1245 | # Top tracks, they can also include dots |
d67cc9fa JMF |
1246 | |(?:MC)[\w\.]* |
1247 | ) | |
c5e8d7af PH |
1248 | .* |
1249 | | | |
99209c29 | 1250 | ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) |
c5e8d7af | 1251 | )""" |
dbb94fb0 | 1252 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
dbb94fb0 | 1253 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' |
78caa52a | 1254 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
1255 | _TESTS = [{ |
1256 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
1257 | 'info_dict': { | |
1258 | 'title': 'ytdl test PL', | |
a1cf99d0 | 1259 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
1260 | }, |
1261 | 'playlist_count': 3, | |
9291475f PH |
1262 | }, { |
1263 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
1264 | 'info_dict': { | |
acf757f4 | 1265 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
1266 | 'title': 'YDL_Empty_List', |
1267 | }, | |
1268 | 'playlist_count': 0, | |
1269 | }, { | |
1270 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
1271 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
1272 | 'info_dict': { | |
1273 | 'title': '29C3: Not my department', | |
acf757f4 | 1274 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
9291475f PH |
1275 | }, |
1276 | 'playlist_count': 95, | |
1277 | }, { | |
1278 | 'note': 'issue #673', | |
1279 | 'url': 'PLBB231211A4F62143', | |
1280 | 'info_dict': { | |
f46a8702 | 1281 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 1282 | 'id': 'PLBB231211A4F62143', |
9291475f PH |
1283 | }, |
1284 | 'playlist_mincount': 26, | |
1285 | }, { | |
1286 | 'note': 'Large playlist', | |
1287 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
1288 | 'info_dict': { | |
1289 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 1290 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
9291475f PH |
1291 | }, |
1292 | 'playlist_mincount': 799, | |
1293 | }, { | |
1294 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
1295 | 'info_dict': { | |
1296 | 'title': 'YDL_safe_search', | |
acf757f4 | 1297 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
1298 | }, |
1299 | 'playlist_count': 2, | |
ac7553d0 PH |
1300 | }, { |
1301 | 'note': 'embedded', | |
1302 | 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
1303 | 'playlist_count': 4, | |
1304 | 'info_dict': { | |
1305 | 'title': 'JODA15', | |
acf757f4 | 1306 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 | 1307 | } |
6b08cdf6 PH |
1308 | }, { |
1309 | 'note': 'Embedded SWF player', | |
1310 | 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', | |
1311 | 'playlist_count': 4, | |
1312 | 'info_dict': { | |
1313 | 'title': 'JODA7', | |
acf757f4 | 1314 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
6b08cdf6 | 1315 | } |
4b7df0d3 JMF |
1316 | }, { |
1317 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
1318 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
1319 | 'info_dict': { | |
acf757f4 PH |
1320 | 'title': 'Uploads from Interstellar Movie', |
1321 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4b7df0d3 JMF |
1322 | }, |
1323 | 'playlist_mincout': 21, | |
81127aa5 | 1324 | }] |
c5e8d7af | 1325 | |
880e1c52 JMF |
1326 | def _real_initialize(self): |
1327 | self._login() | |
1328 | ||
652cdaa2 | 1329 | def _extract_mix(self, playlist_id): |
99209c29 | 1330 | # The mixes are generated from a single video |
652cdaa2 | 1331 | # the id of the playlist is just 'RD' + video_id |
7d4afc55 | 1332 | url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) |
c9cc0bf5 | 1333 | webpage = self._download_webpage( |
78caa52a | 1334 | url, playlist_id, 'Downloading Youtube mix') |
bc2f773b | 1335 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 PH |
1336 | title_span = ( |
1337 | search_title('playlist-title') or | |
1338 | search_title('title long-title') or | |
1339 | search_title('title')) | |
76d1700b | 1340 | title = clean_html(title_span) |
c9cc0bf5 PH |
1341 | ids = orderedSet(re.findall( |
1342 | r'''(?xs)data-video-username=".*?".*? | |
1343 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
1344 | webpage)) | |
652cdaa2 JMF |
1345 | url_results = self._ids_to_results(ids) |
1346 | ||
1347 | return self.playlist_result(url_results, playlist_id, title) | |
1348 | ||
448830ce | 1349 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
1350 | url = self._TEMPLATE_URL % playlist_id |
1351 | page = self._download_webpage(url, playlist_id) | |
dbb94fb0 | 1352 | |
39b62db1 YCH |
1353 | for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page): |
1354 | match = match.strip() | |
1355 | # Check if the playlist exists or is private | |
1356 | if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match): | |
1357 | raise ExtractorError( | |
1358 | 'The playlist doesn\'t exist or is private, use --username or ' | |
1359 | '--netrc to access it.', | |
1360 | expected=True) | |
1361 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): | |
1362 | raise ExtractorError( | |
1363 | 'Invalid parameters. Maybe URL is incorrect.', | |
1364 | expected=True) | |
1365 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
1366 | continue | |
1367 | else: | |
1368 | self.report_warning('Youtube gives an alert message: ' + match) | |
10c0e2d8 | 1369 | |
dcbb4580 | 1370 | # Extract the video ids from the playlist pages |
70219b0f JMF |
1371 | def _entries(): |
1372 | more_widget_html = content_html = page | |
1373 | for page_num in itertools.count(1): | |
1374 | matches = re.finditer(self._VIDEO_RE, content_html) | |
1375 | # We remove the duplicates and the link with index 0 | |
1376 | # (it's not the first video of the playlist) | |
1377 | new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0') | |
1378 | for vid_id in new_ids: | |
1379 | yield self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
1380 | ||
1381 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
1382 | if not mobj: | |
1383 | break | |
1384 | ||
1385 | more = self._download_json( | |
1386 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, | |
1387 | 'Downloading page #%s' % page_num, | |
1388 | transform_source=uppercase_escape) | |
1389 | content_html = more['content_html'] | |
1390 | if not content_html.strip(): | |
1391 | # Some webpages show a "Load more" button but they don't | |
1392 | # have more videos | |
1393 | break | |
1394 | more_widget_html = more['load_more_widget_html'] | |
dbb94fb0 S |
1395 | |
1396 | playlist_title = self._html_search_regex( | |
68eb8e90 | 1397 | r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', |
78caa52a | 1398 | page, 'title') |
c5e8d7af | 1399 | |
70219b0f | 1400 | return self.playlist_result(_entries(), playlist_id, playlist_title) |
c5e8d7af | 1401 | |
448830ce S |
1402 | def _real_extract(self, url): |
1403 | # Extract playlist id | |
1404 | mobj = re.match(self._VALID_URL, url) | |
1405 | if mobj is None: | |
1406 | raise ExtractorError('Invalid URL: %s' % url) | |
1407 | playlist_id = mobj.group(1) or mobj.group(2) | |
1408 | ||
1409 | # Check if it's a video-specific URL | |
1410 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
1411 | if 'v' in query_dict: | |
1412 | video_id = query_dict['v'][0] | |
1413 | if self._downloader.params.get('noplaylist'): | |
1414 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
1415 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
1416 | else: | |
1417 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
1418 | ||
1419 | if playlist_id.startswith('RD') or playlist_id.startswith('UL'): | |
1420 | # Mixes require a custom extraction process | |
1421 | return self._extract_mix(playlist_id) | |
1422 | ||
1423 | return self._extract_playlist(playlist_id) | |
1424 | ||
c5e8d7af PH |
1425 | |
1426 | class YoutubeChannelIE(InfoExtractor): | |
78caa52a | 1427 | IE_DESC = 'YouTube.com channels' |
9ff67727 | 1428 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 1429 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
78caa52a | 1430 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
1431 | _TESTS = [{ |
1432 | 'note': 'paginated channel', | |
1433 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
1434 | 'playlist_mincount': 91, | |
acf757f4 PH |
1435 | 'info_dict': { |
1436 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
1437 | } | |
cdc628a4 | 1438 | }] |
c5e8d7af | 1439 | |
6de5dbaf S |
1440 | @staticmethod |
1441 | def extract_videos_from_page(page): | |
c5e8d7af | 1442 | ids_in_page = [] |
fb69240c S |
1443 | titles_in_page = [] |
1444 | for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page): | |
1445 | video_id = mobj.group('id') | |
1446 | video_title = unescapeHTML(mobj.group('title')) | |
1447 | try: | |
1448 | idx = ids_in_page.index(video_id) | |
1449 | if video_title and not titles_in_page[idx]: | |
1450 | titles_in_page[idx] = video_title | |
1451 | except ValueError: | |
1452 | ids_in_page.append(video_id) | |
1453 | titles_in_page.append(video_title) | |
1454 | return zip(ids_in_page, titles_in_page) | |
c5e8d7af PH |
1455 | |
1456 | def _real_extract(self, url): | |
9ff67727 | 1457 | channel_id = self._match_id(url) |
c5e8d7af | 1458 | |
eb0f3e7e | 1459 | url = self._TEMPLATE_URL % channel_id |
386bdfa6 S |
1460 | |
1461 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
1462 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
1463 | # otherwise fallback on channel by page extraction | |
1464 | channel_page = self._download_webpage( | |
1465 | url + '?view=57', channel_id, | |
1466 | 'Downloading channel page', fatal=False) | |
3d8e9573 S |
1467 | channel_playlist_id = self._html_search_meta( |
1468 | 'channelId', channel_page, 'channel id', default=None) | |
1469 | if not channel_playlist_id: | |
1470 | channel_playlist_id = self._search_regex( | |
1471 | r'data-channel-external-id="([^"]+)"', | |
1472 | channel_page, 'channel id', default=None) | |
386bdfa6 S |
1473 | if channel_playlist_id and channel_playlist_id.startswith('UC'): |
1474 | playlist_id = 'UU' + channel_playlist_id[2:] | |
d2a9de78 IK |
1475 | return self.url_result( |
1476 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
386bdfa6 | 1477 | |
60bf45c8 | 1478 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
1479 | autogenerated = re.search(r'''(?x) |
1480 | class="[^"]*?(?: | |
1481 | channel-header-autogenerated-label| | |
1482 | yt-channel-title-autogenerated | |
1483 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 1484 | |
b9643eed JMF |
1485 | if autogenerated: |
1486 | # The videos are contained in a single page | |
1487 | # the ajax pages can't be used, they are empty | |
b82f815f | 1488 | entries = [ |
fb69240c S |
1489 | self.url_result( |
1490 | video_id, 'Youtube', video_id=video_id, | |
1491 | video_title=video_title) | |
8f02ad4f | 1492 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
1493 | return self.playlist_result(entries, channel_id) |
1494 | ||
1495 | def _entries(): | |
23d3608c | 1496 | more_widget_html = content_html = channel_page |
b9643eed | 1497 | for pagenum in itertools.count(1): |
81c2f20b | 1498 | |
8f02ad4f | 1499 | for video_id, video_title in self.extract_videos_from_page(content_html): |
b82f815f | 1500 | yield self.url_result( |
fb69240c S |
1501 | video_id, 'Youtube', video_id=video_id, |
1502 | video_title=video_title) | |
5f6a1245 | 1503 | |
23d3608c JMF |
1504 | mobj = re.search( |
1505 | r'data-uix-load-more-href="/?(?P<more>[^"]+)"', | |
1506 | more_widget_html) | |
1507 | if not mobj: | |
b9643eed | 1508 | break |
c5e8d7af | 1509 | |
23d3608c JMF |
1510 | more = self._download_json( |
1511 | 'https://youtube.com/%s' % mobj.group('more'), channel_id, | |
1512 | 'Downloading page #%s' % (pagenum + 1), | |
1513 | transform_source=uppercase_escape) | |
1514 | content_html = more['content_html'] | |
1515 | more_widget_html = more['load_more_widget_html'] | |
1516 | ||
b82f815f | 1517 | return self.playlist_result(_entries(), channel_id) |
c5e8d7af PH |
1518 | |
1519 | ||
eb0f3e7e | 1520 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 1521 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
9ff67727 | 1522 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' |
eb0f3e7e | 1523 | _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos' |
78caa52a | 1524 | IE_NAME = 'youtube:user' |
c5e8d7af | 1525 | |
cdc628a4 PH |
1526 | _TESTS = [{ |
1527 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
1528 | 'playlist_mincount': 320, | |
1529 | 'info_dict': { | |
1530 | 'title': 'TheLinuxFoundation', | |
1531 | } | |
1532 | }, { | |
1533 | 'url': 'ytuser:phihag', | |
1534 | 'only_matching': True, | |
1535 | }] | |
1536 | ||
e3ea4790 | 1537 | @classmethod |
f4b05232 | 1538 | def suitable(cls, url): |
e3ea4790 JMF |
1539 | # Don't return True if the url can be extracted with other youtube |
1540 | # extractor, the regex would is too permissive and it would match. | |
1541 | other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) | |
5f6a1245 JW |
1542 | if any(ie.suitable(url) for ie in other_ies): |
1543 | return False | |
1544 | else: | |
1545 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 1546 | |
b05654f0 | 1547 | |
b4c08069 | 1548 | class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE): |
78caa52a | 1549 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
1550 | # there doesn't appear to be a real limit, for example if you search for |
1551 | # 'python' you get more than 8.000.000 results | |
1552 | _MAX_RESULTS = float('inf') | |
78caa52a | 1553 | IE_NAME = 'youtube:search' |
b05654f0 | 1554 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 1555 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 1556 | _TESTS = [] |
b05654f0 | 1557 | |
b05654f0 PH |
1558 | def _get_n_results(self, query, n): |
1559 | """Get a specified number of results for a query""" | |
1560 | ||
b4c08069 | 1561 | videos = [] |
b05654f0 PH |
1562 | limit = n |
1563 | ||
b4c08069 JMF |
1564 | for pagenum in itertools.count(1): |
1565 | url_query = { | |
02175a79 | 1566 | 'search_query': query.encode('utf-8'), |
b4c08069 JMF |
1567 | 'page': pagenum, |
1568 | 'spf': 'navigate', | |
1569 | } | |
1570 | url_query.update(self._EXTRA_QUERY_ARGS) | |
1571 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse.urlencode(url_query) | |
1572 | data = self._download_json( | |
69ea8ca4 | 1573 | result_url, video_id='query "%s"' % query, |
b4c08069 | 1574 | note='Downloading page %s' % pagenum, |
69ea8ca4 | 1575 | errnote='Unable to download API page') |
b4c08069 | 1576 | html_content = data[1]['body']['content'] |
7cc3570e | 1577 | |
b4c08069 | 1578 | if 'class="search-message' in html_content: |
07ad22b8 | 1579 | raise ExtractorError( |
78caa52a | 1580 | '[youtube] No video results', expected=True) |
b05654f0 | 1581 | |
b4c08069 JMF |
1582 | new_videos = self._ids_to_results(orderedSet(re.findall( |
1583 | r'href="/watch\?v=(.{11})', html_content))) | |
1584 | videos += new_videos | |
1585 | if not new_videos or len(videos) > limit: | |
1586 | break | |
b05654f0 | 1587 | |
b4c08069 JMF |
1588 | if len(videos) > n: |
1589 | videos = videos[:n] | |
b05654f0 | 1590 | return self.playlist_result(videos, query) |
75dff0ee | 1591 | |
c9ae7b95 | 1592 | |
a3dd9248 | 1593 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 1594 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 1595 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 1596 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 1597 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 1598 | |
c9ae7b95 PH |
1599 | |
1600 | class YoutubeSearchURLIE(InfoExtractor): | |
78caa52a PH |
1601 | IE_DESC = 'YouTube.com search URLs' |
1602 | IE_NAME = 'youtube:search_url' | |
c9ae7b95 | 1603 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
1604 | _TESTS = [{ |
1605 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
1606 | 'playlist_mincount': 5, | |
1607 | 'info_dict': { | |
1608 | 'title': 'youtube-dl test video', | |
1609 | } | |
1610 | }] | |
c9ae7b95 PH |
1611 | |
1612 | def _real_extract(self, url): | |
1613 | mobj = re.match(self._VALID_URL, url) | |
7fd002c0 | 1614 | query = compat_urllib_parse_unquote_plus(mobj.group('query')) |
c9ae7b95 PH |
1615 | |
1616 | webpage = self._download_webpage(url, query) | |
1617 | result_code = self._search_regex( | |
98998cde | 1618 | r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML') |
c9ae7b95 PH |
1619 | |
1620 | part_codes = re.findall( | |
1621 | r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) | |
1622 | entries = [] | |
1623 | for part_code in part_codes: | |
1624 | part_title = self._html_search_regex( | |
6feb2d5e | 1625 | [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) |
c9ae7b95 PH |
1626 | part_url_snippet = self._html_search_regex( |
1627 | r'(?s)href="([^"]+)"', part_code, 'item URL') | |
1628 | part_url = compat_urlparse.urljoin( | |
1629 | 'https://www.youtube.com/', part_url_snippet) | |
1630 | entries.append({ | |
1631 | '_type': 'url', | |
1632 | 'url': part_url, | |
1633 | 'title': part_title, | |
1634 | }) | |
1635 | ||
1636 | return { | |
1637 | '_type': 'playlist', | |
1638 | 'entries': entries, | |
1639 | 'title': query, | |
1640 | } | |
1641 | ||
1642 | ||
75dff0ee | 1643 | class YoutubeShowIE(InfoExtractor): |
78caa52a | 1644 | IE_DESC = 'YouTube.com (multi-season) shows' |
cdc628a4 | 1645 | _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 1646 | IE_NAME = 'youtube:show' |
cdc628a4 PH |
1647 | _TESTS = [{ |
1648 | 'url': 'http://www.youtube.com/show/airdisasters', | |
1649 | 'playlist_mincount': 3, | |
1650 | 'info_dict': { | |
1651 | 'id': 'airdisasters', | |
1652 | 'title': 'Air Disasters', | |
1653 | } | |
1654 | }] | |
75dff0ee JMF |
1655 | |
1656 | def _real_extract(self, url): | |
1657 | mobj = re.match(self._VALID_URL, url) | |
cdc628a4 PH |
1658 | playlist_id = mobj.group('id') |
1659 | webpage = self._download_webpage( | |
1660 | url, playlist_id, 'Downloading show webpage') | |
75dff0ee JMF |
1661 | # There's one playlist for each season of the show |
1662 | m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) | |
cdc628a4 PH |
1663 | self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) |
1664 | entries = [ | |
1665 | self.url_result( | |
1666 | 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') | |
1667 | for season in m_seasons | |
1668 | ] | |
1669 | title = self._og_search_title(webpage, fatal=False) | |
1670 | ||
1671 | return { | |
1672 | '_type': 'playlist', | |
1673 | 'id': playlist_id, | |
1674 | 'title': title, | |
1675 | 'entries': entries, | |
1676 | } | |
04cc9617 JMF |
1677 | |
1678 | ||
b2e8bc1b | 1679 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 | 1680 | """ |
25f14e9f | 1681 | Base class for feed extractors |
d7ae0639 JMF |
1682 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. |
1683 | """ | |
b2e8bc1b | 1684 | _LOGIN_REQUIRED = True |
d7ae0639 JMF |
1685 | |
1686 | @property | |
1687 | def IE_NAME(self): | |
78caa52a | 1688 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 1689 | |
81f0259b | 1690 | def _real_initialize(self): |
b2e8bc1b | 1691 | self._login() |
81f0259b | 1692 | |
04cc9617 | 1693 | def _real_extract(self, url): |
25f14e9f S |
1694 | page = self._download_webpage( |
1695 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE) | |
2bc43303 JMF |
1696 | |
1697 | # The extraction process is the same as for playlists, but the regex | |
1698 | # for the video ids doesn't contain an index | |
1699 | ids = [] | |
1700 | more_widget_html = content_html = page | |
2bc43303 JMF |
1701 | for page_num in itertools.count(1): |
1702 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
62c95fd5 S |
1703 | |
1704 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
1705 | # the same videos in (sometimes) slightly different order, so we'll check | |
1706 | # for unicity and break when portion has no new videos | |
1707 | new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches)) | |
1708 | if not new_ids: | |
1709 | break | |
1710 | ||
2bc43303 JMF |
1711 | ids.extend(new_ids) |
1712 | ||
1713 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
1714 | if not mobj: | |
1715 | break | |
1716 | ||
1717 | more = self._download_json( | |
25f14e9f | 1718 | 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, |
2bc43303 JMF |
1719 | 'Downloading page #%s' % page_num, |
1720 | transform_source=uppercase_escape) | |
1721 | content_html = more['content_html'] | |
1722 | more_widget_html = more['load_more_widget_html'] | |
1723 | ||
25f14e9f S |
1724 | return self.playlist_result( |
1725 | self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE) | |
1726 | ||
1727 | ||
1728 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
1729 | IE_NAME = 'youtube:watchlater' | |
1730 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
1731 | _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater' | |
1732 | ||
1733 | _TESTS = [] # override PlaylistIE tests | |
1734 | ||
1735 | def _real_extract(self, url): | |
1736 | return self._extract_playlist('WL') | |
f459d170 | 1737 | |
5f6a1245 | 1738 | |
c626a3d9 | 1739 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 1740 | IE_NAME = 'youtube:favorites' |
f3a34072 | 1741 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
c7a7750d | 1742 | _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
1743 | _LOGIN_REQUIRED = True |
1744 | ||
1745 | def _real_extract(self, url): | |
1746 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 1747 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 1748 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
1749 | |
1750 | ||
25f14e9f S |
1751 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
1752 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
1753 | _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' | |
1754 | _FEED_NAME = 'recommended' | |
1755 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
1ed5b5c9 | 1756 | |
1ed5b5c9 | 1757 | |
25f14e9f S |
1758 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
1759 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
1760 | _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' | |
1761 | _FEED_NAME = 'subscriptions' | |
1762 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
1ed5b5c9 | 1763 | |
1ed5b5c9 | 1764 | |
25f14e9f S |
1765 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
1766 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
1767 | _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' | |
1768 | _FEED_NAME = 'history' | |
1769 | _PLAYLIST_TITLE = 'Youtube History' | |
1ed5b5c9 JMF |
1770 | |
1771 | ||
15870e90 PH |
1772 | class YoutubeTruncatedURLIE(InfoExtractor): |
1773 | IE_NAME = 'youtube:truncated_url' | |
1774 | IE_DESC = False # Do not list | |
975d35db | 1775 | _VALID_URL = r'''(?x) |
b95aab84 PH |
1776 | (?:https?://)? |
1777 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
1778 | (?:watch\?(?: | |
c4808c60 | 1779 | feature=[a-z_]+| |
b95aab84 PH |
1780 | annotation_id=annotation_[^&]+| |
1781 | x-yt-cl=[0-9]+| | |
c1708b89 | 1782 | hl=[^&]*| |
b95aab84 PH |
1783 | )? |
1784 | | | |
1785 | attribution_link\?a=[^&]+ | |
1786 | ) | |
1787 | $ | |
975d35db | 1788 | ''' |
15870e90 | 1789 | |
c4808c60 PH |
1790 | _TESTS = [{ |
1791 | 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
1792 | 'only_matching': True, | |
dc2fc736 PH |
1793 | }, { |
1794 | 'url': 'http://www.youtube.com/watch?', | |
1795 | 'only_matching': True, | |
b95aab84 PH |
1796 | }, { |
1797 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
1798 | 'only_matching': True, | |
1799 | }, { | |
1800 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
1801 | 'only_matching': True, | |
c1708b89 PH |
1802 | }, { |
1803 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
1804 | 'only_matching': True, | |
c4808c60 PH |
1805 | }] |
1806 | ||
15870e90 PH |
1807 | def _real_extract(self, url): |
1808 | raise ExtractorError( | |
78caa52a PH |
1809 | 'Did you forget to quote the URL? Remember that & is a meta ' |
1810 | 'character in most shells, so you want to put the URL in quotes, ' | |
1811 | 'like youtube-dl ' | |
1812 | '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
1813 | ' or simply youtube-dl BaW_jenozKc .', | |
15870e90 | 1814 | expected=True) |
772fd5cc PH |
1815 | |
1816 | ||
1817 | class YoutubeTruncatedIDIE(InfoExtractor): | |
1818 | IE_NAME = 'youtube:truncated_id' | |
1819 | IE_DESC = False # Do not list | |
b95aab84 | 1820 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
1821 | |
1822 | _TESTS = [{ | |
1823 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
1824 | 'only_matching': True, | |
1825 | }] | |
1826 | ||
1827 | def _real_extract(self, url): | |
1828 | video_id = self._match_id(url) | |
1829 | raise ExtractorError( | |
1830 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
1831 | expected=True) |