]>
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 PH |
19 | compat_urllib_parse, |
20 | compat_urllib_request, | |
7c61bd36 | 21 | compat_urlparse, |
c5e8d7af | 22 | compat_str, |
4bb4a188 PH |
23 | ) |
24 | from ..utils import ( | |
c5e8d7af | 25 | clean_html, |
c5e8d7af | 26 | ExtractorError, |
2d30521a | 27 | float_or_none, |
4bb4a188 PH |
28 | get_element_by_attribute, |
29 | get_element_by_id, | |
dd27fd17 | 30 | int_or_none, |
9c44d242 | 31 | OnDemandPagedList, |
4bb4a188 | 32 | orderedSet, |
c5e8d7af PH |
33 | unescapeHTML, |
34 | unified_strdate, | |
81c2f20b | 35 | uppercase_escape, |
c5e8d7af PH |
36 | ) |
37 | ||
5f6a1245 | 38 | |
de7f3446 | 39 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
40 | """Provide base functions for Youtube extractors""" |
41 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
83317f69 | 42 | _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' |
b2e8bc1b JMF |
43 | _NETRC_MACHINE = 'youtube' |
44 | # If True it will raise an error if no login info is provided | |
45 | _LOGIN_REQUIRED = False | |
46 | ||
b2e8bc1b | 47 | def _set_language(self): |
810fb84d PH |
48 | self._set_cookie( |
49 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
42939b61 | 50 | # YouTube sets the expire time to about two months |
810fb84d | 51 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b JMF |
52 | |
53 | def _login(self): | |
83317f69 | 54 | """ |
55 | Attempt to log in to YouTube. | |
56 | True is returned if successful or skipped. | |
57 | False is returned if login failed. | |
58 | ||
59 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
60 | """ | |
b2e8bc1b JMF |
61 | (username, password) = self._get_login_info() |
62 | # No authentication to be performed | |
63 | if username is None: | |
64 | if self._LOGIN_REQUIRED: | |
69ea8ca4 | 65 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 66 | return True |
b2e8bc1b | 67 | |
7cc3570e PH |
68 | login_page = self._download_webpage( |
69 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
70 | note='Downloading login page', |
71 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
72 | if login_page is False: |
73 | return | |
b2e8bc1b | 74 | |
795f28f8 | 75 | galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', |
78caa52a | 76 | login_page, 'Login GALX parameter') |
c5e8d7af | 77 | |
b2e8bc1b JMF |
78 | # Log in |
79 | login_form_strs = { | |
8bcc8756 JW |
80 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
81 | 'Email': username, | |
82 | 'GALX': galx, | |
83 | 'Passwd': password, | |
84 | ||
85 | 'PersistentCookie': 'yes', | |
86 | '_utf8': '霱', | |
87 | 'bgresponse': 'js_disabled', | |
88 | 'checkConnection': '', | |
89 | 'checkedDomains': 'youtube', | |
90 | 'dnConn': '', | |
91 | 'pstMsg': '0', | |
92 | 'rmShown': '1', | |
93 | 'secTok': '', | |
94 | 'signIn': 'Sign in', | |
95 | 'timeStmp': '', | |
96 | 'service': 'youtube', | |
97 | 'uilel': '3', | |
98 | 'hl': 'en_US', | |
b2e8bc1b | 99 | } |
83317f69 | 100 | |
b2e8bc1b JMF |
101 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode |
102 | # chokes on unicode | |
5f6a1245 | 103 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) |
b2e8bc1b | 104 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') |
7cc3570e PH |
105 | |
106 | req = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
107 | login_results = self._download_webpage( | |
108 | req, None, | |
69ea8ca4 | 109 | note='Logging in', errnote='unable to log in', fatal=False) |
7cc3570e PH |
110 | if login_results is False: |
111 | return False | |
83317f69 | 112 | |
113 | if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: | |
69ea8ca4 | 114 | raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) |
83317f69 | 115 | |
116 | # Two-Factor | |
117 | # TODO add SMS and phone call support - these require making a request and then prompting the user | |
118 | ||
119 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: | |
120 | tfa_code = self._get_tfa_info() | |
121 | ||
122 | if tfa_code is None: | |
69ea8ca4 PH |
123 | self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>') |
124 | self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
83317f69 | 125 | return False |
126 | ||
127 | # Unlike the first login form, secTok and timeStmp are both required for the TFA form | |
128 | ||
129 | match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
130 | if match is None: | |
69ea8ca4 | 131 | self._downloader.report_warning('Failed to get secTok - did the page structure change?') |
83317f69 | 132 | secTok = match.group(1) |
133 | match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
134 | if match is None: | |
69ea8ca4 | 135 | self._downloader.report_warning('Failed to get timeStmp - did the page structure change?') |
83317f69 | 136 | timeStmp = match.group(1) |
137 | ||
138 | tfa_form_strs = { | |
78caa52a PH |
139 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
140 | 'smsToken': '', | |
141 | 'smsUserPin': tfa_code, | |
142 | 'smsVerifyPin': 'Verify', | |
143 | ||
144 | 'PersistentCookie': 'yes', | |
145 | 'checkConnection': '', | |
146 | 'checkedDomains': 'youtube', | |
147 | 'pstMsg': '1', | |
148 | 'secTok': secTok, | |
149 | 'timeStmp': timeStmp, | |
150 | 'service': 'youtube', | |
151 | 'hl': 'en_US', | |
83317f69 | 152 | } |
5f6a1245 | 153 | tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items()) |
83317f69 | 154 | tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') |
155 | ||
156 | tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) | |
157 | tfa_results = self._download_webpage( | |
158 | tfa_req, None, | |
69ea8ca4 | 159 | note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) |
83317f69 | 160 | |
161 | if tfa_results is False: | |
162 | return False | |
163 | ||
164 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: | |
69ea8ca4 | 165 | self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.') |
83317f69 | 166 | return False |
167 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: | |
69ea8ca4 | 168 | self._downloader.report_warning('unable to log in - did the page structure change?') |
83317f69 | 169 | return False |
170 | if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: | |
69ea8ca4 | 171 | 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 | 172 | return False |
173 | ||
7cc3570e | 174 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: |
69ea8ca4 | 175 | self._downloader.report_warning('unable to log in: bad username or password') |
b2e8bc1b JMF |
176 | return False |
177 | return True | |
178 | ||
b2e8bc1b JMF |
179 | def _real_initialize(self): |
180 | if self._downloader is None: | |
181 | return | |
42939b61 | 182 | self._set_language() |
b2e8bc1b JMF |
183 | if not self._login(): |
184 | return | |
c5e8d7af | 185 | |
8377574c | 186 | |
360e1ca5 | 187 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 188 | IE_DESC = 'YouTube.com' |
cb7dfeea | 189 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 190 | ( |
edb53e2d | 191 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 192 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 193 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 194 | (?:www\.)?pwnyoutube\.com/| |
f7000f3a | 195 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 JMF |
196 | tube\.majestyc\.net/| |
197 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
198 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
199 | (?: # the various things that can precede the ID: | |
ac7553d0 | 200 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 201 | |(?: # or the v= param in all its forms |
f7000f3a | 202 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af PH |
203 | (?:\?|\#!?) # the params delimiter ? or # or #! |
204 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) | |
205 | v= | |
206 | ) | |
f4b05232 JMF |
207 | )) |
208 | |youtu\.be/ # just youtu.be/xxxx | |
edb53e2d | 209 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 210 | ) |
c5e8d7af | 211 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 212 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
9291475f | 213 | (?!.*?&list=) # combined list/video URLs are handled by the playlist IE |
c5e8d7af PH |
214 | (?(1).+)? # if we found the ID, everything can follow |
215 | $""" | |
c5e8d7af | 216 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 PH |
217 | _formats = { |
218 | '5': {'ext': 'flv', 'width': 400, 'height': 240}, | |
219 | '6': {'ext': 'flv', 'width': 450, 'height': 270}, | |
220 | '13': {'ext': '3gp'}, | |
221 | '17': {'ext': '3gp', 'width': 176, 'height': 144}, | |
222 | '18': {'ext': 'mp4', 'width': 640, 'height': 360}, | |
223 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720}, | |
224 | '34': {'ext': 'flv', 'width': 640, 'height': 360}, | |
225 | '35': {'ext': 'flv', 'width': 854, 'height': 480}, | |
226 | '36': {'ext': '3gp', 'width': 320, 'height': 240}, | |
227 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080}, | |
228 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072}, | |
229 | '43': {'ext': 'webm', 'width': 640, 'height': 360}, | |
230 | '44': {'ext': 'webm', 'width': 854, 'height': 480}, | |
231 | '45': {'ext': 'webm', 'width': 1280, 'height': 720}, | |
232 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080}, | |
233 | ||
1d043b93 | 234 | |
86fe61c8 | 235 | # 3d videos |
43b81eb9 PH |
236 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20}, |
237 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
238 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
239 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20}, | |
240 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20}, | |
241 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
242 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
836a086c | 243 | |
96fb5605 | 244 | # Apple HTTP Live Streaming |
43b81eb9 PH |
245 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, |
246 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10}, | |
247 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10}, | |
248 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10}, | |
249 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10}, | |
250 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, | |
251 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10}, | |
2c62dc26 PH |
252 | |
253 | # DASH mp4 video | |
43b81eb9 PH |
254 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
255 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
256 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
257 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
258 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
e65566a9 | 259 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) |
43b81eb9 PH |
260 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
261 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
0d2c1418 PH |
262 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, |
263 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, | |
264 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, | |
836a086c | 265 | |
f6f1fc92 | 266 | # Dash mp4 audio |
62cd676c PH |
267 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}, |
268 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}, | |
269 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}, | |
836a086c AZ |
270 | |
271 | # Dash webm | |
e75cafe9 A |
272 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, |
273 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
274 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
275 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
276 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
277 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
1cc887cb | 278 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'}, |
e75cafe9 A |
279 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
280 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
281 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
282 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
283 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
284 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
285 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
3c80377b | 286 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
18061bba | 287 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
a51d3aa0 PH |
288 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
289 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, | |
76b3c610 | 290 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
10a404c3 | 291 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'}, |
76b3c610 | 292 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
2c62dc26 PH |
293 | |
294 | # Dash webm audio | |
55db73ef | 295 | '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, |
e75cafe9 | 296 | '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, |
ce6b9a2d | 297 | |
0857baad PH |
298 | # Dash webm audio with opus inside |
299 | '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, | |
300 | '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, | |
301 | '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, | |
302 | ||
ce6b9a2d PH |
303 | # RTMP (unnamed) |
304 | '_rtmp': {'protocol': 'rtmp'}, | |
c5e8d7af | 305 | } |
836a086c | 306 | |
78caa52a | 307 | IE_NAME = 'youtube' |
2eb88d95 PH |
308 | _TESTS = [ |
309 | { | |
4bc3a23e PH |
310 | 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', |
311 | 'info_dict': { | |
312 | 'id': 'BaW_jenozKc', | |
313 | 'ext': 'mp4', | |
314 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
315 | 'uploader': 'Philipp Hagemeister', | |
316 | 'uploader_id': 'phihag', | |
317 | 'upload_date': '20121002', | |
318 | '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 .', | |
319 | 'categories': ['Science & Technology'], | |
3e7c1224 PH |
320 | 'like_count': int, |
321 | 'dislike_count': int, | |
2eb88d95 | 322 | } |
0e853ca4 | 323 | }, |
0e853ca4 | 324 | { |
4bc3a23e PH |
325 | 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', |
326 | 'note': 'Test generic use_cipher_signature video (#897)', | |
327 | 'info_dict': { | |
328 | 'id': 'UxxajLWwzqY', | |
329 | 'ext': 'mp4', | |
330 | 'upload_date': '20120506', | |
331 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
332 | 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f', | |
333 | 'uploader': 'Icona Pop', | |
334 | 'uploader_id': 'IconaPop', | |
2eb88d95 | 335 | } |
c108eb73 JMF |
336 | }, |
337 | { | |
4bc3a23e PH |
338 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
339 | 'note': 'Test VEVO video with age protection (#956)', | |
340 | 'info_dict': { | |
341 | 'id': '07FYdnEawAQ', | |
342 | 'ext': 'mp4', | |
343 | 'upload_date': '20130703', | |
344 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
345 | 'description': 'md5:64249768eec3bc4276236606ea996373', | |
346 | 'uploader': 'justintimberlakeVEVO', | |
347 | 'uploader_id': 'justintimberlakeVEVO', | |
c108eb73 JMF |
348 | } |
349 | }, | |
fccd3771 | 350 | { |
4bc3a23e PH |
351 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
352 | 'note': 'Embed-only video (#1746)', | |
353 | 'info_dict': { | |
354 | 'id': 'yZIXLfi8CZQ', | |
355 | 'ext': 'mp4', | |
356 | 'upload_date': '20120608', | |
357 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
358 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
359 | 'uploader': 'SET India', | |
360 | 'uploader_id': 'setindia' | |
fccd3771 PH |
361 | } |
362 | }, | |
dd27fd17 | 363 | { |
4bc3a23e PH |
364 | 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', |
365 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
366 | 'info_dict': { | |
367 | 'id': 'a9LDPn-MO4I', | |
368 | 'ext': 'm4a', | |
369 | 'upload_date': '20121002', | |
370 | 'uploader_id': '8KVIDEO', | |
371 | 'description': '', | |
372 | 'uploader': '8KVIDEO', | |
373 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 374 | }, |
4bc3a23e PH |
375 | 'params': { |
376 | 'youtube_include_dash_manifest': True, | |
377 | 'format': '141', | |
4919603f | 378 | }, |
dd27fd17 | 379 | }, |
3489b7d2 JMF |
380 | # DASH manifest with encrypted signature |
381 | { | |
78caa52a PH |
382 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
383 | 'info_dict': { | |
384 | 'id': 'IB3lcPjvWLA', | |
385 | 'ext': 'm4a', | |
b766eb27 JMF |
386 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', |
387 | 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', | |
78caa52a PH |
388 | 'uploader': 'AfrojackVEVO', |
389 | 'uploader_id': 'AfrojackVEVO', | |
390 | 'upload_date': '20131011', | |
3489b7d2 | 391 | }, |
4bc3a23e | 392 | 'params': { |
78caa52a PH |
393 | 'youtube_include_dash_manifest': True, |
394 | 'format': '141', | |
3489b7d2 JMF |
395 | }, |
396 | }, | |
aaeb86f6 S |
397 | # JS player signature function name containing $ |
398 | { | |
399 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
400 | 'info_dict': { | |
401 | 'id': 'nfWlot6h_JM', | |
402 | 'ext': 'm4a', | |
403 | 'title': 'Taylor Swift - Shake It Off', | |
404 | 'description': 'md5:2acfda1b285bdd478ccec22f9918199d', | |
405 | 'uploader': 'TaylorSwiftVEVO', | |
406 | 'uploader_id': 'TaylorSwiftVEVO', | |
407 | 'upload_date': '20140818', | |
408 | }, | |
409 | 'params': { | |
410 | 'youtube_include_dash_manifest': True, | |
411 | 'format': '141', | |
412 | }, | |
413 | }, | |
aa79ac0c PH |
414 | # Controversy video |
415 | { | |
416 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
417 | 'info_dict': { | |
418 | 'id': 'T4XJQO3qol8', | |
419 | 'ext': 'mp4', | |
420 | 'upload_date': '20100909', | |
421 | 'uploader': 'The Amazing Atheist', | |
422 | 'uploader_id': 'TheAmazingAtheist', | |
423 | 'title': 'Burning Everyone\'s Koran', | |
424 | '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', | |
425 | } | |
c522adb1 JMF |
426 | }, |
427 | # Normal age-gate video (No vevo, embed allowed) | |
428 | { | |
429 | 'url': 'http://youtube.com/watch?v=HtVdAasjOgU', | |
430 | 'info_dict': { | |
431 | 'id': 'HtVdAasjOgU', | |
432 | 'ext': 'mp4', | |
433 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
9ed99402 | 434 | 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
c522adb1 JMF |
435 | 'uploader': 'The Witcher', |
436 | 'uploader_id': 'WitcherGame', | |
437 | 'upload_date': '20140605', | |
438 | }, | |
439 | }, | |
fccae2b9 S |
440 | # Age-gate video with encrypted signature |
441 | { | |
442 | 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', | |
443 | 'info_dict': { | |
444 | 'id': '6kLq3WMV1nU', | |
445 | 'ext': 'mp4', | |
446 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
447 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
448 | 'uploader': 'LloydVEVO', | |
449 | 'uploader_id': 'LloydVEVO', | |
450 | 'upload_date': '20110629', | |
451 | }, | |
452 | }, | |
774e208f PH |
453 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) |
454 | { | |
455 | 'url': '__2ABJjxzNo', | |
456 | 'info_dict': { | |
457 | 'id': '__2ABJjxzNo', | |
458 | 'ext': 'mp4', | |
459 | 'upload_date': '20100430', | |
460 | 'uploader_id': 'deadmau5', | |
461 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', | |
462 | 'uploader': 'deadmau5', | |
463 | 'title': 'Deadmau5 - Some Chords (HD)', | |
464 | }, | |
465 | 'expected_warnings': [ | |
466 | 'DASH manifest missing', | |
467 | ] | |
e52a40ab PH |
468 | }, |
469 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
470 | { | |
471 | 'url': 'lqQg6PlCWgI', | |
472 | 'info_dict': { | |
473 | 'id': 'lqQg6PlCWgI', | |
474 | 'ext': 'mp4', | |
cbe2bd91 PH |
475 | 'upload_date': '20120731', |
476 | 'uploader_id': 'olympic', | |
477 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
478 | 'uploader': 'Olympics', | |
479 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
480 | }, | |
481 | 'params': { | |
482 | 'skip_download': 'requires avconv', | |
e52a40ab | 483 | } |
cbe2bd91 | 484 | }, |
6271f1ca PH |
485 | # Non-square pixels |
486 | { | |
487 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
488 | 'info_dict': { | |
489 | 'id': '_b-2C3KPAM0', | |
490 | 'ext': 'mp4', | |
491 | 'stretched_ratio': 16 / 9., | |
492 | 'upload_date': '20110310', | |
493 | 'uploader_id': 'AllenMeow', | |
494 | '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', | |
495 | 'uploader': '孫艾倫', | |
496 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
497 | }, | |
498 | } | |
2eb88d95 PH |
499 | ] |
500 | ||
e0df6211 PH |
501 | def __init__(self, *args, **kwargs): |
502 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 503 | self._player_cache = {} |
e0df6211 | 504 | |
c5e8d7af PH |
505 | def report_video_info_webpage_download(self, video_id): |
506 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 507 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 508 | |
c5e8d7af PH |
509 | def report_information_extraction(self, video_id): |
510 | """Report attempt to extract video information.""" | |
69ea8ca4 | 511 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
512 | |
513 | def report_unavailable_format(self, video_id, format): | |
514 | """Report extracted video URL.""" | |
69ea8ca4 | 515 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
516 | |
517 | def report_rtmp_download(self): | |
518 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 519 | self.to_screen('RTMP download detected') |
c5e8d7af | 520 | |
60064c53 PH |
521 | def _signature_cache_id(self, example_sig): |
522 | """ Return a string representation of a signature """ | |
78caa52a | 523 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
524 | |
525 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 526 | id_m = re.match( |
60620368 | 527 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', |
cf010131 | 528 | player_url) |
c081b35c PH |
529 | if not id_m: |
530 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
531 | player_type = id_m.group('ext') |
532 | player_id = id_m.group('id') | |
533 | ||
c4417ddb | 534 | # Read from filesystem cache |
60064c53 PH |
535 | func_id = '%s_%s_%s' % ( |
536 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 537 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 538 | |
69ea8ca4 | 539 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 540 | if cache_spec is not None: |
78caa52a | 541 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 542 | |
6d1a55a5 PH |
543 | download_note = ( |
544 | 'Downloading player %s' % player_url | |
545 | if self._downloader.params.get('verbose') else | |
546 | 'Downloading %s player %s' % (player_type, player_id) | |
547 | ) | |
e0df6211 PH |
548 | if player_type == 'js': |
549 | code = self._download_webpage( | |
550 | player_url, video_id, | |
6d1a55a5 | 551 | note=download_note, |
69ea8ca4 | 552 | errnote='Download of %s failed' % player_url) |
83799698 | 553 | res = self._parse_sig_js(code) |
c4417ddb | 554 | elif player_type == 'swf': |
e0df6211 PH |
555 | urlh = self._request_webpage( |
556 | player_url, video_id, | |
6d1a55a5 | 557 | note=download_note, |
69ea8ca4 | 558 | errnote='Download of %s failed' % player_url) |
e0df6211 | 559 | code = urlh.read() |
83799698 | 560 | res = self._parse_sig_swf(code) |
e0df6211 PH |
561 | else: |
562 | assert False, 'Invalid player type %r' % player_type | |
563 | ||
785521bf PH |
564 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
565 | cache_res = res(test_string) | |
566 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 567 | |
69ea8ca4 | 568 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
569 | return res |
570 | ||
60064c53 | 571 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
572 | def gen_sig_code(idxs): |
573 | def _genslice(start, end, step): | |
78caa52a | 574 | starts = '' if start == 0 else str(start) |
8bcc8756 | 575 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 576 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 577 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
578 | |
579 | step = None | |
7af808a5 PH |
580 | # Quelch pyflakes warnings - start will be set when step is set |
581 | start = '(Never used)' | |
edf3e38e PH |
582 | for i, prev in zip(idxs[1:], idxs[:-1]): |
583 | if step is not None: | |
584 | if i - prev == step: | |
585 | continue | |
586 | yield _genslice(start, prev, step) | |
587 | step = None | |
588 | continue | |
589 | if i - prev in [-1, 1]: | |
590 | step = i - prev | |
591 | start = prev | |
592 | continue | |
593 | else: | |
78caa52a | 594 | yield 's[%d]' % prev |
edf3e38e | 595 | if step is None: |
78caa52a | 596 | yield 's[%d]' % i |
edf3e38e PH |
597 | else: |
598 | yield _genslice(start, i, step) | |
599 | ||
78caa52a | 600 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 601 | cache_res = func(test_string) |
edf3e38e | 602 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 603 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
604 | signature_id_tuple = '(%s)' % ( |
605 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 606 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 607 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 608 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 609 | |
e0df6211 PH |
610 | def _parse_sig_js(self, jscode): |
611 | funcname = self._search_regex( | |
aaeb86f6 | 612 | r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode, |
8bcc8756 | 613 | 'Initial JS player signature function name') |
2b25cb5d PH |
614 | |
615 | jsi = JSInterpreter(jscode) | |
616 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
617 | return lambda s: initial_function([s]) |
618 | ||
619 | def _parse_sig_swf(self, file_contents): | |
54256267 | 620 | swfi = SWFInterpreter(file_contents) |
78caa52a | 621 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 622 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 623 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
624 | return lambda s: initial_function([s]) |
625 | ||
83799698 | 626 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 627 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 628 | |
c8bf86d5 | 629 | if player_url is None: |
69ea8ca4 | 630 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 631 | |
69ea8ca4 | 632 | if player_url.startswith('//'): |
78caa52a | 633 | player_url = 'https:' + player_url |
c8bf86d5 | 634 | try: |
62af3a0e | 635 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
636 | if player_id not in self._player_cache: |
637 | func = self._extract_signature_function( | |
60064c53 | 638 | video_id, player_url, s |
c8bf86d5 PH |
639 | ) |
640 | self._player_cache[player_id] = func | |
641 | func = self._player_cache[player_id] | |
642 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 643 | self._print_sig_code(func, s) |
c8bf86d5 PH |
644 | return func(s) |
645 | except Exception as e: | |
646 | tb = traceback.format_exc() | |
647 | raise ExtractorError( | |
78caa52a | 648 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 649 | |
360e1ca5 | 650 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 651 | try: |
60e47a26 | 652 | subs_doc = self._download_xml( |
38c2e5b8 | 653 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
654 | video_id, note=False) |
655 | except ExtractorError as err: | |
69ea8ca4 | 656 | self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) |
de7f3446 | 657 | return {} |
de7f3446 JMF |
658 | |
659 | sub_lang_list = {} | |
60e47a26 JMF |
660 | for track in subs_doc.findall('track'): |
661 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
662 | if lang in sub_lang_list: |
663 | continue | |
360e1ca5 JMF |
664 | sub_formats = [] |
665 | for ext in ['sbv', 'vtt', 'srt']: | |
666 | params = compat_urllib_parse.urlencode({ | |
667 | 'lang': lang, | |
668 | 'v': video_id, | |
669 | 'fmt': ext, | |
670 | 'name': track.attrib['name'].encode('utf-8'), | |
671 | }) | |
672 | sub_formats.append({ | |
673 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
674 | 'ext': ext, | |
675 | }) | |
676 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 677 | if not sub_lang_list: |
69ea8ca4 | 678 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
679 | return {} |
680 | return sub_lang_list | |
681 | ||
360e1ca5 | 682 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
683 | """We need the webpage for getting the captions url, pass it as an |
684 | argument to speed up the process.""" | |
69ea8ca4 | 685 | self.to_screen('%s: Looking for automatic captions' % video_id) |
de7f3446 | 686 | mobj = re.search(r';ytplayer.config = ({.*?});', webpage) |
78caa52a | 687 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
de7f3446 JMF |
688 | if mobj is None: |
689 | self._downloader.report_warning(err_msg) | |
690 | return {} | |
691 | player_config = json.loads(mobj.group(1)) | |
692 | try: | |
0792d563 PH |
693 | args = player_config['args'] |
694 | caption_url = args['ttsurl'] | |
695 | timestamp = args['timestamp'] | |
055e6f36 JMF |
696 | # We get the available subtitles |
697 | list_params = compat_urllib_parse.urlencode({ | |
698 | 'type': 'list', | |
699 | 'tlangs': 1, | |
700 | 'asrs': 1, | |
de7f3446 | 701 | }) |
055e6f36 | 702 | list_url = caption_url + '&' + list_params |
e26f8712 | 703 | caption_list = self._download_xml(list_url, video_id) |
e3dc22ca | 704 | original_lang_node = caption_list.find('track') |
7d900ef1 | 705 | if original_lang_node is None: |
69ea8ca4 | 706 | self._downloader.report_warning('Video doesn\'t have automatic captions') |
e3dc22ca JMF |
707 | return {} |
708 | original_lang = original_lang_node.attrib['lang_code'] | |
7d900ef1 | 709 | caption_kind = original_lang_node.attrib.get('kind', '') |
055e6f36 JMF |
710 | |
711 | sub_lang_list = {} | |
712 | for lang_node in caption_list.findall('target'): | |
713 | sub_lang = lang_node.attrib['lang_code'] | |
360e1ca5 JMF |
714 | sub_formats = [] |
715 | for ext in ['sbv', 'vtt', 'srt']: | |
716 | params = compat_urllib_parse.urlencode({ | |
717 | 'lang': original_lang, | |
718 | 'tlang': sub_lang, | |
719 | 'fmt': ext, | |
720 | 'ts': timestamp, | |
721 | 'kind': caption_kind, | |
722 | }) | |
723 | sub_formats.append({ | |
724 | 'url': caption_url + '&' + params, | |
725 | 'ext': ext, | |
726 | }) | |
727 | sub_lang_list[sub_lang] = sub_formats | |
055e6f36 | 728 | return sub_lang_list |
de7f3446 JMF |
729 | # An extractor error can be raise by the download process if there are |
730 | # no automatic captions but there are subtitles | |
731 | except (KeyError, ExtractorError): | |
732 | self._downloader.report_warning(err_msg) | |
733 | return {} | |
734 | ||
97665381 PH |
735 | @classmethod |
736 | def extract_id(cls, url): | |
737 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 738 | if mobj is None: |
69ea8ca4 | 739 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
740 | video_id = mobj.group(2) |
741 | return video_id | |
742 | ||
1d043b93 JMF |
743 | def _extract_from_m3u8(self, manifest_url, video_id): |
744 | url_map = {} | |
5f6a1245 | 745 | |
1d043b93 JMF |
746 | def _get_urls(_manifest): |
747 | lines = _manifest.split('\n') | |
748 | urls = filter(lambda l: l and not l.startswith('#'), | |
8bcc8756 | 749 | lines) |
1d043b93 | 750 | return urls |
78caa52a | 751 | manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') |
1d043b93 JMF |
752 | formats_urls = _get_urls(manifest) |
753 | for format_url in formats_urls: | |
890f62e8 | 754 | itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag') |
1d043b93 JMF |
755 | url_map[itag] = format_url |
756 | return url_map | |
757 | ||
1fb07d10 JG |
758 | def _extract_annotations(self, video_id): |
759 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
69ea8ca4 | 760 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') |
1fb07d10 | 761 | |
da276600 PH |
762 | def _parse_dash_manifest( |
763 | self, video_id, dash_manifest_url, player_url, age_gate): | |
774e208f PH |
764 | def decrypt_sig(mobj): |
765 | s = mobj.group(1) | |
766 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
767 | return '/signature/%s' % dec_s | |
768 | dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) | |
769 | dash_doc = self._download_xml( | |
770 | dash_manifest_url, video_id, | |
771 | note='Downloading DASH manifest', | |
772 | errnote='Could not download DASH manifest') | |
773 | ||
774 | formats = [] | |
775 | for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): | |
776 | url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') | |
777 | if url_el is None: | |
778 | continue | |
779 | format_id = r.attrib['id'] | |
780 | video_url = url_el.text | |
781 | filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) | |
782 | f = { | |
783 | 'format_id': format_id, | |
784 | 'url': video_url, | |
785 | 'width': int_or_none(r.attrib.get('width')), | |
e65566a9 | 786 | 'height': int_or_none(r.attrib.get('height')), |
774e208f PH |
787 | 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), |
788 | 'asr': int_or_none(r.attrib.get('audioSamplingRate')), | |
789 | 'filesize': filesize, | |
790 | 'fps': int_or_none(r.attrib.get('frameRate')), | |
791 | } | |
792 | try: | |
793 | existing_format = next( | |
794 | fo for fo in formats | |
795 | if fo['format_id'] == format_id) | |
796 | except StopIteration: | |
ba617964 JMF |
797 | full_info = self._formats.get(format_id, {}).copy() |
798 | full_info.update(f) | |
799 | formats.append(full_info) | |
774e208f PH |
800 | else: |
801 | existing_format.update(f) | |
802 | return formats | |
803 | ||
c5e8d7af | 804 | def _real_extract(self, url): |
7e8c0af0 | 805 | proto = ( |
78caa52a PH |
806 | 'http' if self._downloader.params.get('prefer_insecure', False) |
807 | else 'https') | |
7e8c0af0 | 808 | |
c5e8d7af PH |
809 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
810 | mobj = re.search(self._NEXT_URL_RE, url) | |
811 | if mobj: | |
7e8c0af0 | 812 | url = proto + '://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') |
97665381 | 813 | video_id = self.extract_id(url) |
c5e8d7af PH |
814 | |
815 | # Get video webpage | |
aa79ac0c | 816 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 817 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
818 | |
819 | # Attempt to extract SWF player URL | |
e0df6211 | 820 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
821 | if mobj is not None: |
822 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
823 | else: | |
824 | player_url = None | |
825 | ||
826 | # Get video info | |
6449cd80 | 827 | embed_webpage = None |
c108eb73 | 828 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
829 | age_gate = True |
830 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
831 | # this can be viewed without login into Youtube | |
beb95e77 CL |
832 | url = proto + '://www.youtube.com/embed/%s' % video_id |
833 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
2c57c7fa JMF |
834 | data = compat_urllib_parse.urlencode({ |
835 | 'video_id': video_id, | |
836 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 837 | 'sts': self._search_regex( |
beb95e77 | 838 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 839 | }) |
7e8c0af0 | 840 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
841 | video_info_webpage = self._download_webpage( |
842 | video_info_url, video_id, | |
20436c30 | 843 | note='Refetching age-gated info webpage', |
94bd3613 | 844 | errnote='unable to download video info webpage') |
c5e8d7af | 845 | video_info = compat_parse_qs(video_info_webpage) |
c108eb73 JMF |
846 | else: |
847 | age_gate = False | |
4e62ebe2 JMF |
848 | try: |
849 | # Try looking directly into the video webpage | |
850 | mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) | |
851 | if not mobj: | |
852 | raise ValueError('Could not find ytplayer.config') # caught below | |
853 | json_code = uppercase_escape(mobj.group(1)) | |
854 | ytplayer_config = json.loads(json_code) | |
855 | args = ytplayer_config['args'] | |
856 | # Convert to the same format returned by compat_parse_qs | |
857 | video_info = dict((k, [v]) for k, v in args.items()) | |
858 | if 'url_encoded_fmt_stream_map' not in args: | |
859 | raise ValueError('No stream_map present') # caught below | |
860 | except ValueError: | |
861 | # We fallback to the get_video_info pages (used by the embed page) | |
862 | self.report_video_info_webpage_download(video_id) | |
863 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
810fb84d PH |
864 | video_info_url = ( |
865 | '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
866 | % (proto, video_id, el_type)) | |
867 | video_info_webpage = self._download_webpage( | |
868 | video_info_url, | |
4e62ebe2 JMF |
869 | video_id, note=False, |
870 | errnote='unable to download video info webpage') | |
871 | video_info = compat_parse_qs(video_info_webpage) | |
872 | if 'token' in video_info: | |
873 | break | |
c5e8d7af PH |
874 | if 'token' not in video_info: |
875 | if 'reason' in video_info: | |
d11271dd | 876 | raise ExtractorError( |
78caa52a | 877 | 'YouTube said: %s' % video_info['reason'][0], |
d11271dd | 878 | expected=True, video_id=video_id) |
c5e8d7af | 879 | else: |
d11271dd | 880 | raise ExtractorError( |
78caa52a | 881 | '"token" parameter not in video info for unknown reason', |
d11271dd | 882 | video_id=video_id) |
c5e8d7af | 883 | |
1d699755 PH |
884 | if 'view_count' in video_info: |
885 | view_count = int(video_info['view_count'][0]) | |
886 | else: | |
887 | view_count = None | |
888 | ||
c5e8d7af PH |
889 | # Check for "rental" videos |
890 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
69ea8ca4 | 891 | raise ExtractorError('"rental" videos not supported') |
c5e8d7af PH |
892 | |
893 | # Start extracting information | |
894 | self.report_information_extraction(video_id) | |
895 | ||
896 | # uploader | |
897 | if 'author' not in video_info: | |
69ea8ca4 | 898 | raise ExtractorError('Unable to extract uploader name') |
c5e8d7af PH |
899 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) |
900 | ||
901 | # uploader_id | |
902 | video_uploader_id = None | |
903 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) | |
904 | if mobj is not None: | |
905 | video_uploader_id = mobj.group(1) | |
906 | else: | |
69ea8ca4 | 907 | self._downloader.report_warning('unable to extract uploader nickname') |
c5e8d7af PH |
908 | |
909 | # title | |
a8c6b241 | 910 | if 'title' in video_info: |
aa92f063 | 911 | video_title = video_info['title'][0] |
a8c6b241 | 912 | else: |
69ea8ca4 | 913 | self._downloader.report_warning('Unable to extract video title') |
78caa52a | 914 | video_title = '_' |
c5e8d7af PH |
915 | |
916 | # thumbnail image | |
7763b04e JMF |
917 | # We try first to get a high quality image: |
918 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
919 | video_webpage, re.DOTALL) | |
920 | if m_thumb is not None: | |
921 | video_thumbnail = m_thumb.group(1) | |
922 | elif 'thumbnail_url' not in video_info: | |
69ea8ca4 | 923 | self._downloader.report_warning('unable to extract video thumbnail') |
f490e77e | 924 | video_thumbnail = None |
c5e8d7af PH |
925 | else: # don't panic if we can't find it |
926 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
927 | ||
928 | # upload date | |
929 | upload_date = None | |
ad3bc6ac | 930 | mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage) |
beee53de PH |
931 | if mobj is None: |
932 | mobj = re.search( | |
263bd4ec | 933 | r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>', |
beee53de | 934 | video_webpage) |
c5e8d7af PH |
935 | if mobj is not None: |
936 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
937 | upload_date = unified_strdate(upload_date) | |
938 | ||
55f7bd2d PH |
939 | m_cat_container = self._search_regex( |
940 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
624dcebf | 941 | video_webpage, 'categories', default=None) |
ec8deefc | 942 | if m_cat_container: |
ad3bc6ac | 943 | category = self._html_search_regex( |
01ed5c9b | 944 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', |
ad3bc6ac PH |
945 | default=None) |
946 | video_categories = None if category is None else [category] | |
947 | else: | |
948 | video_categories = None | |
ec8deefc | 949 | |
c5e8d7af PH |
950 | # description |
951 | video_description = get_element_by_id("eow-description", video_webpage) | |
952 | if video_description: | |
27dcce19 PH |
953 | video_description = re.sub(r'''(?x) |
954 | <a\s+ | |
955 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
956 | title="([^"]+)"\s+ | |
957 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
958 | class="yt-uix-redirect-link"\s*> | |
959 | [^<]+ | |
960 | </a> | |
961 | ''', r'\1', video_description) | |
c5e8d7af PH |
962 | video_description = clean_html(video_description) |
963 | else: | |
964 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
965 | if fd_mobj: | |
966 | video_description = unescapeHTML(fd_mobj.group(1)) | |
967 | else: | |
78caa52a | 968 | video_description = '' |
c5e8d7af | 969 | |
f30a38be | 970 | def _extract_count(count_name): |
46374a56 | 971 | count = self._search_regex( |
f30a38be JMF |
972 | r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name), |
973 | video_webpage, count_name, default=None) | |
336c3a69 JMF |
974 | if count is not None: |
975 | return int(count.replace(',', '')) | |
976 | return None | |
69ea8ca4 PH |
977 | like_count = _extract_count('like') |
978 | dislike_count = _extract_count('dislike') | |
336c3a69 | 979 | |
c5e8d7af | 980 | # subtitles |
d82134c3 | 981 | video_subtitles = self.extract_subtitles(video_id, video_webpage) |
360e1ca5 | 982 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) |
c5e8d7af PH |
983 | |
984 | if 'length_seconds' not in video_info: | |
69ea8ca4 | 985 | self._downloader.report_warning('unable to extract video duration') |
b466b702 | 986 | video_duration = None |
c5e8d7af | 987 | else: |
b466b702 | 988 | video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])) |
c5e8d7af | 989 | |
1fb07d10 JG |
990 | # annotations |
991 | video_annotations = None | |
992 | if self._downloader.params.get('writeannotations', False): | |
5f6a1245 | 993 | video_annotations = self._extract_annotations(video_id) |
1fb07d10 | 994 | |
dd27fd17 PH |
995 | def _map_to_format_list(urlmap): |
996 | formats = [] | |
997 | for itag, video_real_url in urlmap.items(): | |
998 | dct = { | |
999 | 'format_id': itag, | |
1000 | 'url': video_real_url, | |
1001 | 'player_url': player_url, | |
1002 | } | |
0b65e5d4 PH |
1003 | if itag in self._formats: |
1004 | dct.update(self._formats[itag]) | |
dd27fd17 PH |
1005 | formats.append(dct) |
1006 | return formats | |
1007 | ||
c5e8d7af PH |
1008 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1009 | self.report_rtmp_download() | |
dd27fd17 PH |
1010 | formats = [{ |
1011 | 'format_id': '_rtmp', | |
1012 | 'protocol': 'rtmp', | |
1013 | 'url': video_info['conn'][0], | |
1014 | 'player_url': player_url, | |
1015 | }] | |
24270b03 | 1016 | elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: |
5f6a1245 | 1017 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1018 | if 'rtmpe%3Dyes' in encoded_url_map: |
a7055eb9 | 1019 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) |
c5e8d7af | 1020 | url_map = {} |
00fe14fc | 1021 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1022 | url_data = compat_parse_qs(url_data_str) |
201e9eaa PH |
1023 | if 'itag' not in url_data or 'url' not in url_data: |
1024 | continue | |
1025 | format_id = url_data['itag'][0] | |
1026 | url = url_data['url'][0] | |
1027 | ||
1028 | if 'sig' in url_data: | |
1029 | url += '&signature=' + url_data['sig'][0] | |
1030 | elif 's' in url_data: | |
1031 | encrypted_sig = url_data['s'][0] | |
6449cd80 | 1032 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
201e9eaa | 1033 | |
beb95e77 | 1034 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1035 | ASSETS_RE, |
1036 | embed_webpage if age_gate else video_webpage, | |
1037 | 'JS player URL (1)', default=None) | |
1038 | if not jsplayer_url_json and not age_gate: | |
1039 | # We need the embed website after all | |
1040 | if embed_webpage is None: | |
1041 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1042 | embed_webpage = self._download_webpage( | |
1043 | embed_url, video_id, 'Downloading embed webpage') | |
1044 | jsplayer_url_json = self._search_regex( | |
1045 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1046 | ||
beb95e77 | 1047 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1048 | if player_url is None: |
1049 | player_url_json = self._search_regex( | |
1050 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1051 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1052 | player_url = json.loads(player_url_json) |
1053 | ||
1054 | if self._downloader.params.get('verbose'): | |
cf010131 | 1055 | if player_url is None: |
201e9eaa PH |
1056 | player_version = 'unknown' |
1057 | player_desc = 'unknown' | |
1058 | else: | |
1059 | if player_url.endswith('swf'): | |
1060 | player_version = self._search_regex( | |
1061 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 1062 | 'flash player', fatal=False) |
201e9eaa | 1063 | player_desc = 'flash player %s' % player_version |
cf010131 | 1064 | else: |
201e9eaa PH |
1065 | player_version = self._search_regex( |
1066 | r'html5player-([^/]+?)(?:/html5player)?\.js', | |
1067 | player_url, | |
1068 | 'html5 player', fatal=False) | |
78caa52a | 1069 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 1070 | |
60064c53 | 1071 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 1072 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 1073 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
1074 | |
1075 | signature = self._decrypt_signature( | |
1076 | encrypted_sig, video_id, player_url, age_gate) | |
1077 | url += '&signature=' + signature | |
1078 | if 'ratebypass' not in url: | |
1079 | url += '&ratebypass=yes' | |
1080 | url_map[format_id] = url | |
dd27fd17 | 1081 | formats = _map_to_format_list(url_map) |
1d043b93 JMF |
1082 | elif video_info.get('hlsvp'): |
1083 | manifest_url = video_info['hlsvp'][0] | |
1084 | url_map = self._extract_from_m3u8(manifest_url, video_id) | |
dd27fd17 | 1085 | formats = _map_to_format_list(url_map) |
c5e8d7af | 1086 | else: |
69ea8ca4 | 1087 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') |
c5e8d7af | 1088 | |
dd27fd17 | 1089 | # Look for the DASH manifest |
203fb43f | 1090 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
774e208f | 1091 | dash_mpd = video_info.get('dashmpd') |
75111274 | 1092 | if dash_mpd: |
774e208f PH |
1093 | dash_manifest_url = dash_mpd[0] |
1094 | try: | |
1095 | dash_formats = self._parse_dash_manifest( | |
da276600 | 1096 | video_id, dash_manifest_url, player_url, age_gate) |
774e208f PH |
1097 | except (ExtractorError, KeyError) as e: |
1098 | self.report_warning( | |
1099 | 'Skipping DASH manifest: %r' % e, video_id) | |
1100 | else: | |
e65566a9 PH |
1101 | # Hide the formats we found through non-DASH |
1102 | dash_keys = set(df['format_id'] for df in dash_formats) | |
1103 | for f in formats: | |
1104 | if f['format_id'] in dash_keys: | |
1105 | f['format_id'] = 'nondash-%s' % f['format_id'] | |
ee61f6f3 | 1106 | f['preference'] = f.get('preference', 0) - 10000 |
774e208f | 1107 | formats.extend(dash_formats) |
d80044c2 | 1108 | |
6271f1ca PH |
1109 | # Check for malformed aspect ratio |
1110 | stretched_m = re.search( | |
1111 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
1112 | video_webpage) | |
1113 | if stretched_m: | |
1114 | ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) | |
1115 | for f in formats: | |
1116 | if f.get('vcodec') != 'none': | |
1117 | f['stretched_ratio'] = ratio | |
1118 | ||
4bcc7bd1 | 1119 | self._sort_formats(formats) |
4ea3be0a | 1120 | |
1121 | return { | |
8bcc8756 JW |
1122 | 'id': video_id, |
1123 | 'uploader': video_uploader, | |
1124 | 'uploader_id': video_uploader_id, | |
1125 | 'upload_date': upload_date, | |
1126 | 'title': video_title, | |
1127 | 'thumbnail': video_thumbnail, | |
1128 | 'description': video_description, | |
1129 | 'categories': video_categories, | |
1130 | 'subtitles': video_subtitles, | |
360e1ca5 | 1131 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
1132 | 'duration': video_duration, |
1133 | 'age_limit': 18 if age_gate else 0, | |
1134 | 'annotations': video_annotations, | |
7e8c0af0 | 1135 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 1136 | 'view_count': view_count, |
4ea3be0a | 1137 | 'like_count': like_count, |
1138 | 'dislike_count': dislike_count, | |
2d30521a | 1139 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), |
8bcc8756 | 1140 | 'formats': formats, |
4ea3be0a | 1141 | } |
c5e8d7af | 1142 | |
5f6a1245 | 1143 | |
880e1c52 | 1144 | class YoutubePlaylistIE(YoutubeBaseInfoExtractor): |
78caa52a | 1145 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 1146 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
1147 | (?:https?://)? |
1148 | (?:\w+\.)? | |
1149 | youtube\.com/ | |
1150 | (?: | |
ac7553d0 | 1151 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) |
c5e8d7af PH |
1152 | \? (?:.*?&)*? (?:p|a|list)= |
1153 | | p/ | |
1154 | ) | |
d67cc9fa | 1155 | ( |
99209c29 | 1156 | (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 1157 | # Top tracks, they can also include dots |
d67cc9fa JMF |
1158 | |(?:MC)[\w\.]* |
1159 | ) | |
c5e8d7af PH |
1160 | .* |
1161 | | | |
99209c29 | 1162 | ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) |
c5e8d7af | 1163 | )""" |
dbb94fb0 | 1164 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
dbb94fb0 | 1165 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' |
78caa52a | 1166 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
1167 | _TESTS = [{ |
1168 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
1169 | 'info_dict': { | |
1170 | 'title': 'ytdl test PL', | |
a1cf99d0 | 1171 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
1172 | }, |
1173 | 'playlist_count': 3, | |
9291475f PH |
1174 | }, { |
1175 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
1176 | 'info_dict': { | |
acf757f4 | 1177 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
1178 | 'title': 'YDL_Empty_List', |
1179 | }, | |
1180 | 'playlist_count': 0, | |
1181 | }, { | |
1182 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
1183 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
1184 | 'info_dict': { | |
1185 | 'title': '29C3: Not my department', | |
acf757f4 | 1186 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
9291475f PH |
1187 | }, |
1188 | 'playlist_count': 95, | |
1189 | }, { | |
1190 | 'note': 'issue #673', | |
1191 | 'url': 'PLBB231211A4F62143', | |
1192 | 'info_dict': { | |
f46a8702 | 1193 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 1194 | 'id': 'PLBB231211A4F62143', |
9291475f PH |
1195 | }, |
1196 | 'playlist_mincount': 26, | |
1197 | }, { | |
1198 | 'note': 'Large playlist', | |
1199 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
1200 | 'info_dict': { | |
1201 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 1202 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
9291475f PH |
1203 | }, |
1204 | 'playlist_mincount': 799, | |
1205 | }, { | |
1206 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
1207 | 'info_dict': { | |
1208 | 'title': 'YDL_safe_search', | |
acf757f4 | 1209 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
1210 | }, |
1211 | 'playlist_count': 2, | |
ac7553d0 PH |
1212 | }, { |
1213 | 'note': 'embedded', | |
1214 | 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
1215 | 'playlist_count': 4, | |
1216 | 'info_dict': { | |
1217 | 'title': 'JODA15', | |
acf757f4 | 1218 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 | 1219 | } |
6b08cdf6 PH |
1220 | }, { |
1221 | 'note': 'Embedded SWF player', | |
1222 | 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', | |
1223 | 'playlist_count': 4, | |
1224 | 'info_dict': { | |
1225 | 'title': 'JODA7', | |
acf757f4 | 1226 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
6b08cdf6 | 1227 | } |
4b7df0d3 JMF |
1228 | }, { |
1229 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
1230 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
1231 | 'info_dict': { | |
acf757f4 PH |
1232 | 'title': 'Uploads from Interstellar Movie', |
1233 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4b7df0d3 JMF |
1234 | }, |
1235 | 'playlist_mincout': 21, | |
81127aa5 | 1236 | }] |
c5e8d7af | 1237 | |
880e1c52 JMF |
1238 | def _real_initialize(self): |
1239 | self._login() | |
1240 | ||
652cdaa2 | 1241 | def _ids_to_results(self, ids): |
c9cc0bf5 PH |
1242 | return [ |
1243 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
1244 | for vid_id in ids] | |
652cdaa2 JMF |
1245 | |
1246 | def _extract_mix(self, playlist_id): | |
99209c29 | 1247 | # The mixes are generated from a single video |
652cdaa2 | 1248 | # the id of the playlist is just 'RD' + video_id |
7d4afc55 | 1249 | url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) |
c9cc0bf5 | 1250 | webpage = self._download_webpage( |
78caa52a | 1251 | url, playlist_id, 'Downloading Youtube mix') |
bc2f773b | 1252 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 PH |
1253 | title_span = ( |
1254 | search_title('playlist-title') or | |
1255 | search_title('title long-title') or | |
1256 | search_title('title')) | |
76d1700b | 1257 | title = clean_html(title_span) |
c9cc0bf5 PH |
1258 | ids = orderedSet(re.findall( |
1259 | r'''(?xs)data-video-username=".*?".*? | |
1260 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
1261 | webpage)) | |
652cdaa2 JMF |
1262 | url_results = self._ids_to_results(ids) |
1263 | ||
1264 | return self.playlist_result(url_results, playlist_id, title) | |
1265 | ||
c5e8d7af PH |
1266 | def _real_extract(self, url): |
1267 | # Extract playlist id | |
d67cc9fa | 1268 | mobj = re.match(self._VALID_URL, url) |
c5e8d7af | 1269 | if mobj is None: |
69ea8ca4 | 1270 | raise ExtractorError('Invalid URL: %s' % url) |
47192f92 FV |
1271 | playlist_id = mobj.group(1) or mobj.group(2) |
1272 | ||
1273 | # Check if it's a video-specific URL | |
7c61bd36 | 1274 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) |
47192f92 FV |
1275 | if 'v' in query_dict: |
1276 | video_id = query_dict['v'][0] | |
1277 | if self._downloader.params.get('noplaylist'): | |
69ea8ca4 | 1278 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) |
7012b23c | 1279 | return self.url_result(video_id, 'Youtube', video_id=video_id) |
47192f92 | 1280 | else: |
69ea8ca4 | 1281 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) |
c5e8d7af | 1282 | |
99209c29 | 1283 | if playlist_id.startswith('RD') or playlist_id.startswith('UL'): |
652cdaa2 JMF |
1284 | # Mixes require a custom extraction process |
1285 | return self._extract_mix(playlist_id) | |
1286 | ||
dbb94fb0 S |
1287 | url = self._TEMPLATE_URL % playlist_id |
1288 | page = self._download_webpage(url, playlist_id) | |
1289 | more_widget_html = content_html = page | |
1290 | ||
10c0e2d8 | 1291 | # Check if the playlist exists or is private |
e399853d | 1292 | if re.search(r'<div class="yt-alert-message">[^<]*?(The|This) playlist (does not exist|is private)[^<]*?</div>', page) is not None: |
10c0e2d8 | 1293 | raise ExtractorError( |
78caa52a | 1294 | 'The playlist doesn\'t exist or is private, use --username or ' |
10c0e2d8 JMF |
1295 | '--netrc to access it.', |
1296 | expected=True) | |
1297 | ||
dcbb4580 JMF |
1298 | # Extract the video ids from the playlist pages |
1299 | ids = [] | |
c5e8d7af | 1300 | |
755eb032 | 1301 | for page_num in itertools.count(1): |
dbb94fb0 | 1302 | matches = re.finditer(self._VIDEO_RE, content_html) |
6e47b51e JMF |
1303 | # We remove the duplicates and the link with index 0 |
1304 | # (it's not the first video of the playlist) | |
1305 | new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0') | |
dcbb4580 | 1306 | ids.extend(new_ids) |
c5e8d7af | 1307 | |
dbb94fb0 S |
1308 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) |
1309 | if not mobj: | |
c5e8d7af PH |
1310 | break |
1311 | ||
dbb94fb0 | 1312 | more = self._download_json( |
5912c639 PH |
1313 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, |
1314 | 'Downloading page #%s' % page_num, | |
1315 | transform_source=uppercase_escape) | |
dbb94fb0 | 1316 | content_html = more['content_html'] |
4b7df0d3 JMF |
1317 | if not content_html.strip(): |
1318 | # Some webpages show a "Load more" button but they don't | |
1319 | # have more videos | |
1320 | break | |
dbb94fb0 S |
1321 | more_widget_html = more['load_more_widget_html'] |
1322 | ||
1323 | playlist_title = self._html_search_regex( | |
68eb8e90 | 1324 | r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', |
78caa52a | 1325 | page, 'title') |
c5e8d7af | 1326 | |
652cdaa2 | 1327 | url_results = self._ids_to_results(ids) |
dcbb4580 | 1328 | return self.playlist_result(url_results, playlist_id, playlist_title) |
c5e8d7af PH |
1329 | |
1330 | ||
1331 | class YoutubeChannelIE(InfoExtractor): | |
78caa52a | 1332 | IE_DESC = 'YouTube.com channels' |
9ff67727 | 1333 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' |
78caa52a | 1334 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
1335 | _TESTS = [{ |
1336 | 'note': 'paginated channel', | |
1337 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
1338 | 'playlist_mincount': 91, | |
acf757f4 PH |
1339 | 'info_dict': { |
1340 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
1341 | } | |
cdc628a4 | 1342 | }] |
c5e8d7af PH |
1343 | |
1344 | def extract_videos_from_page(self, page): | |
1345 | ids_in_page = [] | |
1346 | for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page): | |
1347 | if mobj.group(1) not in ids_in_page: | |
1348 | ids_in_page.append(mobj.group(1)) | |
1349 | return ids_in_page | |
1350 | ||
1351 | def _real_extract(self, url): | |
9ff67727 | 1352 | channel_id = self._match_id(url) |
c5e8d7af | 1353 | |
c5e8d7af | 1354 | video_ids = [] |
b9643eed JMF |
1355 | url = 'https://www.youtube.com/channel/%s/videos' % channel_id |
1356 | channel_page = self._download_webpage(url, channel_id) | |
31812a9e PH |
1357 | autogenerated = re.search(r'''(?x) |
1358 | class="[^"]*?(?: | |
1359 | channel-header-autogenerated-label| | |
1360 | yt-channel-title-autogenerated | |
1361 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 1362 | |
b9643eed JMF |
1363 | if autogenerated: |
1364 | # The videos are contained in a single page | |
1365 | # the ajax pages can't be used, they are empty | |
1366 | video_ids = self.extract_videos_from_page(channel_page) | |
b82f815f PH |
1367 | entries = [ |
1368 | self.url_result(video_id, 'Youtube', video_id=video_id) | |
1369 | for video_id in video_ids] | |
1370 | return self.playlist_result(entries, channel_id) | |
1371 | ||
1372 | def _entries(): | |
23d3608c | 1373 | more_widget_html = content_html = channel_page |
b9643eed | 1374 | for pagenum in itertools.count(1): |
81c2f20b | 1375 | |
23d3608c | 1376 | ids_in_page = self.extract_videos_from_page(content_html) |
b82f815f PH |
1377 | for video_id in ids_in_page: |
1378 | yield self.url_result( | |
1379 | video_id, 'Youtube', video_id=video_id) | |
5f6a1245 | 1380 | |
23d3608c JMF |
1381 | mobj = re.search( |
1382 | r'data-uix-load-more-href="/?(?P<more>[^"]+)"', | |
1383 | more_widget_html) | |
1384 | if not mobj: | |
b9643eed | 1385 | break |
c5e8d7af | 1386 | |
23d3608c JMF |
1387 | more = self._download_json( |
1388 | 'https://youtube.com/%s' % mobj.group('more'), channel_id, | |
1389 | 'Downloading page #%s' % (pagenum + 1), | |
1390 | transform_source=uppercase_escape) | |
1391 | content_html = more['content_html'] | |
1392 | more_widget_html = more['load_more_widget_html'] | |
1393 | ||
b82f815f | 1394 | return self.playlist_result(_entries(), channel_id) |
c5e8d7af PH |
1395 | |
1396 | ||
1397 | class YoutubeUserIE(InfoExtractor): | |
78caa52a | 1398 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
9ff67727 | 1399 | _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_-]+)' |
38c2e5b8 | 1400 | _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/users/%s' |
c5e8d7af | 1401 | _GDATA_PAGE_SIZE = 50 |
38c2e5b8 | 1402 | _GDATA_URL = 'https://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json' |
78caa52a | 1403 | IE_NAME = 'youtube:user' |
c5e8d7af | 1404 | |
cdc628a4 PH |
1405 | _TESTS = [{ |
1406 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
1407 | 'playlist_mincount': 320, | |
1408 | 'info_dict': { | |
1409 | 'title': 'TheLinuxFoundation', | |
1410 | } | |
1411 | }, { | |
1412 | 'url': 'ytuser:phihag', | |
1413 | 'only_matching': True, | |
1414 | }] | |
1415 | ||
e3ea4790 | 1416 | @classmethod |
f4b05232 | 1417 | def suitable(cls, url): |
e3ea4790 JMF |
1418 | # Don't return True if the url can be extracted with other youtube |
1419 | # extractor, the regex would is too permissive and it would match. | |
1420 | other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) | |
5f6a1245 JW |
1421 | if any(ie.suitable(url) for ie in other_ies): |
1422 | return False | |
1423 | else: | |
1424 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 1425 | |
c5e8d7af | 1426 | def _real_extract(self, url): |
9ff67727 | 1427 | username = self._match_id(url) |
c5e8d7af PH |
1428 | |
1429 | # Download video ids using YouTube Data API. Result size per | |
1430 | # query is limited (currently to 50 videos) so we need to query | |
1431 | # page by page until there are no video ids - it means we got | |
1432 | # all of them. | |
1433 | ||
b7ab0590 | 1434 | def download_page(pagenum): |
c5e8d7af PH |
1435 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 |
1436 | ||
1437 | gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index) | |
b7ab0590 PH |
1438 | page = self._download_webpage( |
1439 | gdata_url, username, | |
78caa52a | 1440 | 'Downloading video ids from %d to %d' % ( |
b7ab0590 | 1441 | start_index, start_index + self._GDATA_PAGE_SIZE)) |
c5e8d7af | 1442 | |
fd9cf738 JMF |
1443 | try: |
1444 | response = json.loads(page) | |
1445 | except ValueError as err: | |
69ea8ca4 | 1446 | raise ExtractorError('Invalid JSON in API response: ' + compat_str(err)) |
71c82637 | 1447 | if 'entry' not in response['feed']: |
b7ab0590 | 1448 | return |
fd9cf738 | 1449 | |
c5e8d7af | 1450 | # Extract video identifiers |
e302f9ce PH |
1451 | entries = response['feed']['entry'] |
1452 | for entry in entries: | |
1453 | title = entry['title']['$t'] | |
1454 | video_id = entry['id']['$t'].split('/')[-1] | |
b7ab0590 | 1455 | yield { |
e302f9ce PH |
1456 | '_type': 'url', |
1457 | 'url': video_id, | |
1458 | 'ie_key': 'Youtube', | |
b11cec41 | 1459 | 'id': video_id, |
e302f9ce | 1460 | 'title': title, |
b7ab0590 | 1461 | } |
9c44d242 | 1462 | url_results = OnDemandPagedList(download_page, self._GDATA_PAGE_SIZE) |
c5e8d7af | 1463 | |
7012b23c PH |
1464 | return self.playlist_result(url_results, playlist_title=username) |
1465 | ||
b05654f0 PH |
1466 | |
1467 | class YoutubeSearchIE(SearchInfoExtractor): | |
78caa52a PH |
1468 | IE_DESC = 'YouTube.com searches' |
1469 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' | |
b05654f0 | 1470 | _MAX_RESULTS = 1000 |
78caa52a | 1471 | IE_NAME = 'youtube:search' |
b05654f0 PH |
1472 | _SEARCH_KEY = 'ytsearch' |
1473 | ||
b05654f0 PH |
1474 | def _get_n_results(self, query, n): |
1475 | """Get a specified number of results for a query""" | |
1476 | ||
1477 | video_ids = [] | |
1478 | pagenum = 0 | |
1479 | limit = n | |
83d548ef | 1480 | PAGE_SIZE = 50 |
b05654f0 | 1481 | |
83d548ef PH |
1482 | while (PAGE_SIZE * pagenum) < limit: |
1483 | result_url = self._API_URL % ( | |
1484 | compat_urllib_parse.quote_plus(query.encode('utf-8')), | |
1485 | (PAGE_SIZE * pagenum) + 1) | |
7cc3570e | 1486 | data_json = self._download_webpage( |
69ea8ca4 PH |
1487 | result_url, video_id='query "%s"' % query, |
1488 | note='Downloading page %s' % (pagenum + 1), | |
1489 | errnote='Unable to download API page') | |
7cc3570e PH |
1490 | data = json.loads(data_json) |
1491 | api_response = data['data'] | |
1492 | ||
1493 | if 'items' not in api_response: | |
07ad22b8 | 1494 | raise ExtractorError( |
78caa52a | 1495 | '[youtube] No video results', expected=True) |
b05654f0 PH |
1496 | |
1497 | new_ids = list(video['id'] for video in api_response['items']) | |
1498 | video_ids += new_ids | |
1499 | ||
1500 | limit = min(n, api_response['totalItems']) | |
1501 | pagenum += 1 | |
1502 | ||
1503 | if len(video_ids) > n: | |
1504 | video_ids = video_ids[:n] | |
7012b23c PH |
1505 | videos = [self.url_result(video_id, 'Youtube', video_id=video_id) |
1506 | for video_id in video_ids] | |
b05654f0 | 1507 | return self.playlist_result(videos, query) |
75dff0ee | 1508 | |
c9ae7b95 | 1509 | |
a3dd9248 | 1510 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 1511 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 CM |
1512 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc&orderby=published' |
1513 | _SEARCH_KEY = 'ytsearchdate' | |
78caa52a | 1514 | IE_DESC = 'YouTube.com searches, newest videos first' |
75dff0ee | 1515 | |
c9ae7b95 PH |
1516 | |
1517 | class YoutubeSearchURLIE(InfoExtractor): | |
78caa52a PH |
1518 | IE_DESC = 'YouTube.com search URLs' |
1519 | IE_NAME = 'youtube:search_url' | |
c9ae7b95 | 1520 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
1521 | _TESTS = [{ |
1522 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
1523 | 'playlist_mincount': 5, | |
1524 | 'info_dict': { | |
1525 | 'title': 'youtube-dl test video', | |
1526 | } | |
1527 | }] | |
c9ae7b95 PH |
1528 | |
1529 | def _real_extract(self, url): | |
1530 | mobj = re.match(self._VALID_URL, url) | |
1531 | query = compat_urllib_parse.unquote_plus(mobj.group('query')) | |
1532 | ||
1533 | webpage = self._download_webpage(url, query) | |
1534 | result_code = self._search_regex( | |
78caa52a | 1535 | r'(?s)<ol class="item-section"(.*?)</ol>', webpage, 'result HTML') |
c9ae7b95 PH |
1536 | |
1537 | part_codes = re.findall( | |
1538 | r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) | |
1539 | entries = [] | |
1540 | for part_code in part_codes: | |
1541 | part_title = self._html_search_regex( | |
6feb2d5e | 1542 | [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) |
c9ae7b95 PH |
1543 | part_url_snippet = self._html_search_regex( |
1544 | r'(?s)href="([^"]+)"', part_code, 'item URL') | |
1545 | part_url = compat_urlparse.urljoin( | |
1546 | 'https://www.youtube.com/', part_url_snippet) | |
1547 | entries.append({ | |
1548 | '_type': 'url', | |
1549 | 'url': part_url, | |
1550 | 'title': part_title, | |
1551 | }) | |
1552 | ||
1553 | return { | |
1554 | '_type': 'playlist', | |
1555 | 'entries': entries, | |
1556 | 'title': query, | |
1557 | } | |
1558 | ||
1559 | ||
75dff0ee | 1560 | class YoutubeShowIE(InfoExtractor): |
78caa52a | 1561 | IE_DESC = 'YouTube.com (multi-season) shows' |
cdc628a4 | 1562 | _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 1563 | IE_NAME = 'youtube:show' |
cdc628a4 PH |
1564 | _TESTS = [{ |
1565 | 'url': 'http://www.youtube.com/show/airdisasters', | |
1566 | 'playlist_mincount': 3, | |
1567 | 'info_dict': { | |
1568 | 'id': 'airdisasters', | |
1569 | 'title': 'Air Disasters', | |
1570 | } | |
1571 | }] | |
75dff0ee JMF |
1572 | |
1573 | def _real_extract(self, url): | |
1574 | mobj = re.match(self._VALID_URL, url) | |
cdc628a4 PH |
1575 | playlist_id = mobj.group('id') |
1576 | webpage = self._download_webpage( | |
1577 | url, playlist_id, 'Downloading show webpage') | |
75dff0ee JMF |
1578 | # There's one playlist for each season of the show |
1579 | m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) | |
cdc628a4 PH |
1580 | self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) |
1581 | entries = [ | |
1582 | self.url_result( | |
1583 | 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') | |
1584 | for season in m_seasons | |
1585 | ] | |
1586 | title = self._og_search_title(webpage, fatal=False) | |
1587 | ||
1588 | return { | |
1589 | '_type': 'playlist', | |
1590 | 'id': playlist_id, | |
1591 | 'title': title, | |
1592 | 'entries': entries, | |
1593 | } | |
04cc9617 JMF |
1594 | |
1595 | ||
b2e8bc1b | 1596 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 JMF |
1597 | """ |
1598 | Base class for extractors that fetch info from | |
1599 | http://www.youtube.com/feed_ajax | |
1600 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. | |
1601 | """ | |
b2e8bc1b | 1602 | _LOGIN_REQUIRED = True |
43ba5456 JMF |
1603 | # use action_load_personal_feed instead of action_load_system_feed |
1604 | _PERSONAL_FEED = False | |
04cc9617 | 1605 | |
d7ae0639 JMF |
1606 | @property |
1607 | def _FEED_TEMPLATE(self): | |
43ba5456 JMF |
1608 | action = 'action_load_system_feed' |
1609 | if self._PERSONAL_FEED: | |
1610 | action = 'action_load_personal_feed' | |
38c2e5b8 | 1611 | return 'https://www.youtube.com/feed_ajax?%s=1&feed_name=%s&paging=%%s' % (action, self._FEED_NAME) |
d7ae0639 JMF |
1612 | |
1613 | @property | |
1614 | def IE_NAME(self): | |
78caa52a | 1615 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 1616 | |
81f0259b | 1617 | def _real_initialize(self): |
b2e8bc1b | 1618 | self._login() |
81f0259b | 1619 | |
04cc9617 JMF |
1620 | def _real_extract(self, url): |
1621 | feed_entries = [] | |
0e44d838 JMF |
1622 | paging = 0 |
1623 | for i in itertools.count(1): | |
84d84211 PH |
1624 | info = self._download_json( |
1625 | self._FEED_TEMPLATE % paging, | |
1626 | '%s feed' % self._FEED_NAME, | |
1627 | 'Downloading page %s' % i, | |
1628 | transform_source=uppercase_escape) | |
f6177462 | 1629 | feed_html = info.get('feed_html') or info.get('content_html') |
1a9b9649 | 1630 | load_more_widget_html = info.get('load_more_widget_html') or feed_html |
43ba5456 | 1631 | m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) |
04cc9617 | 1632 | ids = orderedSet(m.group(1) for m in m_ids) |
7012b23c PH |
1633 | feed_entries.extend( |
1634 | self.url_result(video_id, 'Youtube', video_id=video_id) | |
1635 | for video_id in ids) | |
05ee2b6d JMF |
1636 | mobj = re.search( |
1637 | r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)', | |
1a9b9649 | 1638 | load_more_widget_html) |
05ee2b6d | 1639 | if mobj is None: |
04cc9617 | 1640 | break |
05ee2b6d | 1641 | paging = mobj.group('paging') |
d7ae0639 JMF |
1642 | return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) |
1643 | ||
5f6a1245 | 1644 | |
d7ae0639 | 1645 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
f3a34072 | 1646 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' |
d7ae0639 JMF |
1647 | _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' |
1648 | _FEED_NAME = 'recommended' | |
78caa52a | 1649 | _PLAYLIST_TITLE = 'Youtube Recommended videos' |
c626a3d9 | 1650 | |
5f6a1245 | 1651 | |
43ba5456 | 1652 | class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor): |
f3a34072 | 1653 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' |
43ba5456 JMF |
1654 | _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater' |
1655 | _FEED_NAME = 'watch_later' | |
78caa52a | 1656 | _PLAYLIST_TITLE = 'Youtube Watch Later' |
43ba5456 | 1657 | _PERSONAL_FEED = True |
c626a3d9 | 1658 | |
5f6a1245 | 1659 | |
f459d170 | 1660 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
f3a34072 | 1661 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' |
78caa52a | 1662 | _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' |
f459d170 JMF |
1663 | _FEED_NAME = 'history' |
1664 | _PERSONAL_FEED = True | |
78caa52a | 1665 | _PLAYLIST_TITLE = 'Youtube Watch History' |
f459d170 | 1666 | |
5f6a1245 | 1667 | |
c626a3d9 | 1668 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 1669 | IE_NAME = 'youtube:favorites' |
f3a34072 | 1670 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
c7a7750d | 1671 | _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
1672 | _LOGIN_REQUIRED = True |
1673 | ||
1674 | def _real_extract(self, url): | |
1675 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 1676 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 1677 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
1678 | |
1679 | ||
1ed5b5c9 | 1680 | class YoutubeSubscriptionsIE(YoutubePlaylistIE): |
78caa52a PH |
1681 | IE_NAME = 'youtube:subscriptions' |
1682 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
1ed5b5c9 | 1683 | _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' |
81127aa5 | 1684 | _TESTS = [] |
1ed5b5c9 JMF |
1685 | |
1686 | def _real_extract(self, url): | |
78caa52a | 1687 | title = 'Youtube Subscriptions' |
1ed5b5c9 JMF |
1688 | page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) |
1689 | ||
1690 | # The extraction process is the same as for playlists, but the regex | |
1691 | # for the video ids doesn't contain an index | |
1692 | ids = [] | |
1693 | more_widget_html = content_html = page | |
1694 | ||
1695 | for page_num in itertools.count(1): | |
1696 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
1697 | new_ids = orderedSet(matches) | |
1698 | ids.extend(new_ids) | |
1699 | ||
1700 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
1701 | if not mobj: | |
1702 | break | |
1703 | ||
1704 | more = self._download_json( | |
1705 | 'https://youtube.com/%s' % mobj.group('more'), title, | |
1706 | 'Downloading page #%s' % page_num, | |
1707 | transform_source=uppercase_escape) | |
1708 | content_html = more['content_html'] | |
1709 | more_widget_html = more['load_more_widget_html'] | |
1710 | ||
1711 | return { | |
1712 | '_type': 'playlist', | |
1713 | 'title': title, | |
1714 | 'entries': self._ids_to_results(ids), | |
1715 | } | |
1716 | ||
1717 | ||
15870e90 PH |
1718 | class YoutubeTruncatedURLIE(InfoExtractor): |
1719 | IE_NAME = 'youtube:truncated_url' | |
1720 | IE_DESC = False # Do not list | |
975d35db | 1721 | _VALID_URL = r'''(?x) |
b95aab84 PH |
1722 | (?:https?://)? |
1723 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
1724 | (?:watch\?(?: | |
c4808c60 | 1725 | feature=[a-z_]+| |
b95aab84 PH |
1726 | annotation_id=annotation_[^&]+| |
1727 | x-yt-cl=[0-9]+| | |
c1708b89 | 1728 | hl=[^&]*| |
b95aab84 PH |
1729 | )? |
1730 | | | |
1731 | attribution_link\?a=[^&]+ | |
1732 | ) | |
1733 | $ | |
975d35db | 1734 | ''' |
15870e90 | 1735 | |
c4808c60 PH |
1736 | _TESTS = [{ |
1737 | 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
1738 | 'only_matching': True, | |
dc2fc736 PH |
1739 | }, { |
1740 | 'url': 'http://www.youtube.com/watch?', | |
1741 | 'only_matching': True, | |
b95aab84 PH |
1742 | }, { |
1743 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
1744 | 'only_matching': True, | |
1745 | }, { | |
1746 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
1747 | 'only_matching': True, | |
c1708b89 PH |
1748 | }, { |
1749 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
1750 | 'only_matching': True, | |
c4808c60 PH |
1751 | }] |
1752 | ||
15870e90 PH |
1753 | def _real_extract(self, url): |
1754 | raise ExtractorError( | |
78caa52a PH |
1755 | 'Did you forget to quote the URL? Remember that & is a meta ' |
1756 | 'character in most shells, so you want to put the URL in quotes, ' | |
1757 | 'like youtube-dl ' | |
1758 | '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
1759 | ' or simply youtube-dl BaW_jenozKc .', | |
15870e90 | 1760 | expected=True) |
772fd5cc PH |
1761 | |
1762 | ||
1763 | class YoutubeTruncatedIDIE(InfoExtractor): | |
1764 | IE_NAME = 'youtube:truncated_id' | |
1765 | IE_DESC = False # Do not list | |
b95aab84 | 1766 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
1767 | |
1768 | _TESTS = [{ | |
1769 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
1770 | 'only_matching': True, | |
1771 | }] | |
1772 | ||
1773 | def _real_extract(self, url): | |
1774 | video_id = self._match_id(url) | |
1775 | raise ExtractorError( | |
1776 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
1777 | expected=True) |