]>
Commit | Line | Data |
---|---|---|
1 | import collections | |
2 | import hashlib | |
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from .dailymotion import DailymotionIE | |
7 | from .odnoklassniki import OdnoklassnikiIE | |
8 | from .pladform import PladformIE | |
9 | from .sibnet import SibnetEmbedIE | |
10 | from .vimeo import VimeoIE | |
11 | from .youtube import YoutubeIE | |
12 | from ..utils import ( | |
13 | ExtractorError, | |
14 | UserNotLive, | |
15 | clean_html, | |
16 | get_element_by_class, | |
17 | get_element_html_by_id, | |
18 | int_or_none, | |
19 | join_nonempty, | |
20 | parse_resolution, | |
21 | str_or_none, | |
22 | str_to_int, | |
23 | try_call, | |
24 | unescapeHTML, | |
25 | unified_timestamp, | |
26 | update_url_query, | |
27 | url_or_none, | |
28 | urlencode_postdata, | |
29 | urljoin, | |
30 | traverse_obj, | |
31 | ) | |
32 | ||
33 | ||
34 | class VKBaseIE(InfoExtractor): | |
35 | _NETRC_MACHINE = 'vk' | |
36 | ||
37 | def _download_webpage_handle(self, url_or_request, video_id, *args, fatal=True, **kwargs): | |
38 | response = super()._download_webpage_handle(url_or_request, video_id, *args, fatal=fatal, **kwargs) | |
39 | challenge_url, cookie = response[1].geturl() if response else '', None | |
40 | if challenge_url.startswith('https://vk.com/429.html?'): | |
41 | cookie = self._get_cookies(challenge_url).get('hash429') | |
42 | if not cookie: | |
43 | return response | |
44 | ||
45 | hash429 = hashlib.md5(cookie.value.encode('ascii')).hexdigest() | |
46 | self._request_webpage( | |
47 | update_url_query(challenge_url, {'key': hash429}), video_id, fatal=fatal, | |
48 | note='Resolving WAF challenge', errnote='Failed to bypass WAF challenge') | |
49 | return super()._download_webpage_handle(url_or_request, video_id, *args, fatal=True, **kwargs) | |
50 | ||
51 | def _perform_login(self, username, password): | |
52 | login_page, url_handle = self._download_webpage_handle( | |
53 | 'https://vk.com', None, 'Downloading login page') | |
54 | ||
55 | login_form = self._hidden_inputs(login_page) | |
56 | ||
57 | login_form.update({ | |
58 | 'email': username.encode('cp1251'), | |
59 | 'pass': password.encode('cp1251'), | |
60 | }) | |
61 | ||
62 | # vk serves two same remixlhk cookies in Set-Cookie header and expects | |
63 | # first one to be actually set | |
64 | self._apply_first_set_cookie_header(url_handle, 'remixlhk') | |
65 | ||
66 | login_page = self._download_webpage( | |
67 | 'https://vk.com/login', None, | |
68 | note='Logging in', | |
69 | data=urlencode_postdata(login_form)) | |
70 | ||
71 | if re.search(r'onLoginFailed', login_page): | |
72 | raise ExtractorError( | |
73 | 'Unable to login, incorrect username and/or password', expected=True) | |
74 | ||
75 | def _download_payload(self, path, video_id, data, fatal=True): | |
76 | endpoint = f'https://vk.com/{path}.php' | |
77 | data['al'] = 1 | |
78 | code, payload = self._download_json( | |
79 | endpoint, video_id, data=urlencode_postdata(data), fatal=fatal, | |
80 | headers={ | |
81 | 'Referer': endpoint, | |
82 | 'X-Requested-With': 'XMLHttpRequest', | |
83 | })['payload'] | |
84 | if code == '3': | |
85 | self.raise_login_required() | |
86 | elif code == '8': | |
87 | raise ExtractorError(clean_html(payload[0][1:-1]), expected=True) | |
88 | return payload | |
89 | ||
90 | ||
91 | class VKIE(VKBaseIE): | |
92 | IE_NAME = 'vk' | |
93 | IE_DESC = 'VK' | |
94 | _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1'] | |
95 | _VALID_URL = r'''(?x) | |
96 | https?:// | |
97 | (?: | |
98 | (?: | |
99 | (?:(?:m|new)\.)?vk\.com/video_| | |
100 | (?:www\.)?daxab.com/ | |
101 | ) | |
102 | ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)| | |
103 | (?: | |
104 | (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)| | |
105 | (?:www\.)?daxab.com/embed/ | |
106 | ) | |
107 | (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))? | |
108 | ) | |
109 | ''' | |
110 | ||
111 | _TESTS = [ | |
112 | { | |
113 | 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521', | |
114 | 'info_dict': { | |
115 | 'id': '-77521_162222515', | |
116 | 'ext': 'mp4', | |
117 | 'title': 'ProtivoGunz - Хуёвая песня', | |
118 | 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', | |
119 | 'uploader_id': '39545378', | |
120 | 'duration': 195, | |
121 | 'timestamp': 1329049880, | |
122 | 'upload_date': '20120212', | |
123 | 'comment_count': int, | |
124 | 'like_count': int, | |
125 | 'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$', | |
126 | }, | |
127 | 'params': {'skip_download': 'm3u8'}, | |
128 | }, | |
129 | { | |
130 | 'url': 'http://vk.com/video205387401_165548505', | |
131 | 'info_dict': { | |
132 | 'id': '205387401_165548505', | |
133 | 'ext': 'mp4', | |
134 | 'title': 'No name', | |
135 | 'uploader': 'Tom Cruise', | |
136 | 'uploader_id': '205387401', | |
137 | 'duration': 9, | |
138 | 'timestamp': 1374364108, | |
139 | 'upload_date': '20130720', | |
140 | 'comment_count': int, | |
141 | 'like_count': int, | |
142 | 'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$', | |
143 | } | |
144 | }, | |
145 | { | |
146 | 'note': 'Embedded video', | |
147 | 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa', | |
148 | 'info_dict': { | |
149 | 'id': '-77521_162222515', | |
150 | 'ext': 'mp4', | |
151 | 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', | |
152 | 'title': 'ProtivoGunz - Хуёвая песня', | |
153 | 'duration': 195, | |
154 | 'upload_date': '20120212', | |
155 | 'timestamp': 1329049880, | |
156 | 'uploader_id': '39545378', | |
157 | 'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$', | |
158 | }, | |
159 | 'params': {'skip_download': 'm3u8'}, | |
160 | }, | |
161 | { | |
162 | 'url': 'https://vk.com/video-93049196_456239755?list=ln-cBjJ7S4jYYx3ADnmDT', | |
163 | 'info_dict': { | |
164 | 'id': '-93049196_456239755', | |
165 | 'ext': 'mp4', | |
166 | 'title': '8 серия (озвучка)', | |
167 | 'duration': 8383, | |
168 | 'comment_count': int, | |
169 | 'uploader': 'Dizi2021', | |
170 | 'like_count': int, | |
171 | 'timestamp': 1640162189, | |
172 | 'upload_date': '20211222', | |
173 | 'uploader_id': '-93049196', | |
174 | 'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$', | |
175 | }, | |
176 | }, | |
177 | { | |
178 | 'note': 'youtube embed', | |
179 | 'url': 'https://vk.com/video276849682_170681728', | |
180 | 'info_dict': { | |
181 | 'id': 'V3K4mi0SYkc', | |
182 | 'ext': 'mp4', | |
183 | 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", | |
184 | 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a', | |
185 | 'duration': 178, | |
186 | 'upload_date': '20130117', | |
187 | 'uploader': "Children's Joy Foundation Inc.", | |
188 | 'uploader_id': 'thecjf', | |
189 | 'view_count': int, | |
190 | 'channel_id': 'UCgzCNQ11TmR9V97ECnhi3gw', | |
191 | 'availability': 'public', | |
192 | 'like_count': int, | |
193 | 'live_status': 'not_live', | |
194 | 'playable_in_embed': True, | |
195 | 'channel': 'Children\'s Joy Foundation Inc.', | |
196 | 'uploader_url': 'http://www.youtube.com/user/thecjf', | |
197 | 'thumbnail': r're:https?://.+\.jpg$', | |
198 | 'tags': 'count:27', | |
199 | 'start_time': 0.0, | |
200 | 'categories': ['Nonprofits & Activism'], | |
201 | 'channel_url': 'https://www.youtube.com/channel/UCgzCNQ11TmR9V97ECnhi3gw', | |
202 | 'channel_follower_count': int, | |
203 | 'age_limit': 0, | |
204 | }, | |
205 | }, | |
206 | { | |
207 | 'note': 'dailymotion embed', | |
208 | 'url': 'https://vk.com/video-95168827_456239103?list=cca524a0f0d5557e16', | |
209 | 'info_dict': { | |
210 | 'id': 'x8gfli0', | |
211 | 'ext': 'mp4', | |
212 | 'title': 'md5:45410f60ccd4b2760da98cb5fc777d70', | |
213 | 'description': 'md5:2e71c5c9413735cfa06cf1a166f16c84', | |
214 | 'uploader': 'Movies and cinema.', | |
215 | 'upload_date': '20221218', | |
216 | 'uploader_id': 'x1jdavv', | |
217 | 'timestamp': 1671387617, | |
218 | 'age_limit': 0, | |
219 | 'duration': 2918, | |
220 | 'like_count': int, | |
221 | 'view_count': int, | |
222 | 'thumbnail': r're:https?://.+x1080$', | |
223 | 'tags': list | |
224 | }, | |
225 | }, | |
226 | { | |
227 | 'url': 'https://vk.com/clips-74006511?z=clip-74006511_456247211', | |
228 | 'info_dict': { | |
229 | 'id': '-74006511_456247211', | |
230 | 'ext': 'mp4', | |
231 | 'comment_count': int, | |
232 | 'duration': 9, | |
233 | 'like_count': int, | |
234 | 'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$', | |
235 | 'timestamp': 1664995597, | |
236 | 'title': 'Clip by @madempress', | |
237 | 'upload_date': '20221005', | |
238 | 'uploader': 'Шальная императрица', | |
239 | 'uploader_id': '-74006511', | |
240 | }, | |
241 | }, | |
242 | { | |
243 | # video key is extra_data not url\d+ | |
244 | 'url': 'http://vk.com/video-110305615_171782105', | |
245 | 'md5': 'e13fcda136f99764872e739d13fac1d1', | |
246 | 'info_dict': { | |
247 | 'id': '-110305615_171782105', | |
248 | 'ext': 'mp4', | |
249 | 'title': 'S-Dance, репетиции к The way show', | |
250 | 'uploader': 'THE WAY SHOW | 17 апреля', | |
251 | 'uploader_id': '-110305615', | |
252 | 'timestamp': 1454859345, | |
253 | 'upload_date': '20160207', | |
254 | }, | |
255 | 'skip': 'Removed', | |
256 | }, | |
257 | { | |
258 | 'note': 'finished live stream, postlive_mp4', | |
259 | 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2', | |
260 | 'info_dict': { | |
261 | 'id': '-387766_456242764', | |
262 | 'ext': 'mp4', | |
263 | 'title': 'ИгроМир 2016 День 1 — Игромания Утром', | |
264 | 'uploader': 'Игромания', | |
265 | 'duration': 5239, | |
266 | 'upload_date': '20160929', | |
267 | 'uploader_id': '-387766', | |
268 | 'timestamp': 1475137527, | |
269 | 'thumbnail': r're:https?://.+\.jpg$', | |
270 | 'comment_count': int, | |
271 | 'like_count': int, | |
272 | }, | |
273 | 'params': { | |
274 | 'skip_download': True, | |
275 | }, | |
276 | }, | |
277 | { | |
278 | # live stream, hls and rtmp links, most likely already finished live | |
279 | # stream by the time you are reading this comment | |
280 | 'url': 'https://vk.com/video-140332_456239111', | |
281 | 'only_matching': True, | |
282 | }, | |
283 | { | |
284 | # removed video, just testing that we match the pattern | |
285 | 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', | |
286 | 'only_matching': True, | |
287 | }, | |
288 | { | |
289 | # age restricted video, requires vk account credentials | |
290 | 'url': 'https://vk.com/video205387401_164765225', | |
291 | 'only_matching': True, | |
292 | }, | |
293 | { | |
294 | # pladform embed | |
295 | 'url': 'https://vk.com/video-76116461_171554880', | |
296 | 'only_matching': True, | |
297 | }, | |
298 | { | |
299 | 'url': 'http://new.vk.com/video205387401_165548505', | |
300 | 'only_matching': True, | |
301 | }, | |
302 | { | |
303 | # This video is no longer available, because its author has been blocked. | |
304 | 'url': 'https://vk.com/video-10639516_456240611', | |
305 | 'only_matching': True, | |
306 | }, | |
307 | { | |
308 | # The video is not available in your region. | |
309 | 'url': 'https://vk.com/video-51812607_171445436', | |
310 | 'only_matching': True, | |
311 | }, | |
312 | { | |
313 | 'url': 'https://vk.com/clip30014565_456240946', | |
314 | 'only_matching': True, | |
315 | }] | |
316 | ||
317 | def _real_extract(self, url): | |
318 | mobj = self._match_valid_url(url) | |
319 | video_id = mobj.group('videoid') | |
320 | ||
321 | mv_data = {} | |
322 | if video_id: | |
323 | data = { | |
324 | 'act': 'show', | |
325 | 'video': video_id, | |
326 | } | |
327 | # Some videos (removed?) can only be downloaded with list id specified | |
328 | list_id = mobj.group('list_id') | |
329 | if list_id: | |
330 | data['list'] = list_id | |
331 | ||
332 | payload = self._download_payload('al_video', video_id, data) | |
333 | info_page = payload[1] | |
334 | opts = payload[-1] | |
335 | mv_data = opts.get('mvData') or {} | |
336 | player = opts.get('player') or {} | |
337 | else: | |
338 | video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) | |
339 | ||
340 | info_page = self._download_webpage( | |
341 | 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) | |
342 | ||
343 | error_message = self._html_search_regex( | |
344 | [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', | |
345 | r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], | |
346 | info_page, 'error message', default=None) | |
347 | if error_message: | |
348 | raise ExtractorError(error_message, expected=True) | |
349 | ||
350 | if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): | |
351 | raise ExtractorError( | |
352 | 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', | |
353 | expected=True) | |
354 | ||
355 | ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' | |
356 | ||
357 | ERRORS = { | |
358 | r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': | |
359 | ERROR_COPYRIGHT, | |
360 | ||
361 | r'>The video .*? was removed from public access by request of the copyright holder.<': | |
362 | ERROR_COPYRIGHT, | |
363 | ||
364 | r'<!>Please log in or <': | |
365 | 'Video %s is only available for registered users, ' | |
366 | 'use --username and --password options to provide account credentials.', | |
367 | ||
368 | r'<!>Unknown error': | |
369 | 'Video %s does not exist.', | |
370 | ||
371 | r'<!>Видео временно недоступно': | |
372 | 'Video %s is temporarily unavailable.', | |
373 | ||
374 | r'<!>Access denied': | |
375 | 'Access denied to video %s.', | |
376 | ||
377 | r'<!>Видеозапись недоступна, так как её автор был заблокирован.': | |
378 | 'Video %s is no longer available, because its author has been blocked.', | |
379 | ||
380 | r'<!>This video is no longer available, because its author has been blocked.': | |
381 | 'Video %s is no longer available, because its author has been blocked.', | |
382 | ||
383 | r'<!>This video is no longer available, because it has been deleted.': | |
384 | 'Video %s is no longer available, because it has been deleted.', | |
385 | ||
386 | r'<!>The video .+? is not available in your region.': | |
387 | 'Video %s is not available in your region.', | |
388 | } | |
389 | ||
390 | for error_re, error_msg in ERRORS.items(): | |
391 | if re.search(error_re, info_page): | |
392 | raise ExtractorError(error_msg % video_id, expected=True) | |
393 | ||
394 | player = self._parse_json(self._search_regex( | |
395 | r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', | |
396 | info_page, 'player params'), video_id) | |
397 | ||
398 | youtube_url = YoutubeIE._extract_url(info_page) | |
399 | if youtube_url: | |
400 | return self.url_result(youtube_url, YoutubeIE.ie_key()) | |
401 | ||
402 | vimeo_url = VimeoIE._extract_url(url, info_page) | |
403 | if vimeo_url is not None: | |
404 | return self.url_result(vimeo_url, VimeoIE.ie_key()) | |
405 | ||
406 | pladform_url = PladformIE._extract_url(info_page) | |
407 | if pladform_url: | |
408 | return self.url_result(pladform_url, PladformIE.ie_key()) | |
409 | ||
410 | m_rutube = re.search( | |
411 | r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page) | |
412 | if m_rutube is not None: | |
413 | rutube_url = self._proto_relative_url( | |
414 | m_rutube.group(1).replace('\\', '')) | |
415 | return self.url_result(rutube_url) | |
416 | ||
417 | dailymotion_url = next(DailymotionIE._extract_embed_urls(url, info_page), None) | |
418 | if dailymotion_url: | |
419 | return self.url_result(dailymotion_url, DailymotionIE.ie_key()) | |
420 | ||
421 | odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page) | |
422 | if odnoklassniki_url: | |
423 | return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) | |
424 | ||
425 | sibnet_url = next(SibnetEmbedIE._extract_embed_urls(url, info_page), None) | |
426 | if sibnet_url: | |
427 | return self.url_result(sibnet_url) | |
428 | ||
429 | m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) | |
430 | if m_opts: | |
431 | m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) | |
432 | if m_opts_url: | |
433 | opts_url = m_opts_url.group(1) | |
434 | if opts_url.startswith('//'): | |
435 | opts_url = 'http:' + opts_url | |
436 | return self.url_result(opts_url) | |
437 | ||
438 | data = player['params'][0] | |
439 | title = unescapeHTML(data['md_title']) | |
440 | ||
441 | # 2 = live | |
442 | # 3 = post live (finished live) | |
443 | is_live = data.get('live') == 2 | |
444 | ||
445 | timestamp = unified_timestamp(self._html_search_regex( | |
446 | r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page, | |
447 | 'upload date', default=None)) or int_or_none(data.get('date')) | |
448 | ||
449 | view_count = str_to_int(self._search_regex( | |
450 | r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)', | |
451 | info_page, 'view count', default=None)) | |
452 | ||
453 | formats = [] | |
454 | for format_id, format_url in data.items(): | |
455 | format_url = url_or_none(format_url) | |
456 | if not format_url or not format_url.startswith(('http', '//', 'rtmp')): | |
457 | continue | |
458 | if (format_id.startswith(('url', 'cache')) | |
459 | or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')): | |
460 | height = int_or_none(self._search_regex( | |
461 | r'^(?:url|cache)(\d+)', format_id, 'height', default=None)) | |
462 | formats.append({ | |
463 | 'format_id': format_id, | |
464 | 'url': format_url, | |
465 | 'height': height, | |
466 | }) | |
467 | elif format_id == 'hls': | |
468 | formats.extend(self._extract_m3u8_formats( | |
469 | format_url, video_id, 'mp4', 'm3u8_native', | |
470 | m3u8_id=format_id, fatal=False, live=is_live)) | |
471 | elif format_id == 'rtmp': | |
472 | formats.append({ | |
473 | 'format_id': format_id, | |
474 | 'url': format_url, | |
475 | 'ext': 'flv', | |
476 | }) | |
477 | ||
478 | subtitles = {} | |
479 | for sub in data.get('subs') or {}: | |
480 | subtitles.setdefault(sub.get('lang', 'en'), []).append({ | |
481 | 'ext': sub.get('title', '.srt').split('.')[-1], | |
482 | 'url': url_or_none(sub.get('url')), | |
483 | }) | |
484 | ||
485 | return { | |
486 | 'id': video_id, | |
487 | 'formats': formats, | |
488 | 'title': title, | |
489 | 'thumbnail': data.get('jpg'), | |
490 | 'uploader': data.get('md_author'), | |
491 | 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')), | |
492 | 'duration': int_or_none(data.get('duration') or mv_data.get('duration')), | |
493 | 'timestamp': timestamp, | |
494 | 'view_count': view_count, | |
495 | 'like_count': int_or_none(mv_data.get('likes')), | |
496 | 'comment_count': int_or_none(mv_data.get('commcount')), | |
497 | 'is_live': is_live, | |
498 | 'subtitles': subtitles, | |
499 | } | |
500 | ||
501 | ||
502 | class VKUserVideosIE(VKBaseIE): | |
503 | IE_NAME = 'vk:uservideos' | |
504 | IE_DESC = "VK - User's Videos" | |
505 | _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/(?:playlist/)?(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)' | |
506 | _TEMPLATE_URL = 'https://vk.com/videos' | |
507 | _TESTS = [{ | |
508 | 'url': 'https://vk.com/video/@mobidevices', | |
509 | 'info_dict': { | |
510 | 'id': '-17892518_all', | |
511 | }, | |
512 | 'playlist_mincount': 1355, | |
513 | }, { | |
514 | 'url': 'https://vk.com/video/@mobidevices?section=uploaded', | |
515 | 'info_dict': { | |
516 | 'id': '-17892518_uploaded', | |
517 | }, | |
518 | 'playlist_mincount': 182, | |
519 | }, { | |
520 | 'url': 'https://vk.com/video/playlist/-174476437_2', | |
521 | 'info_dict': { | |
522 | 'id': '-174476437_playlist_2', | |
523 | 'title': 'Анонсы' | |
524 | }, | |
525 | 'playlist_mincount': 108, | |
526 | }] | |
527 | _VIDEO = collections.namedtuple('Video', ['owner_id', 'id']) | |
528 | ||
529 | def _entries(self, page_id, section): | |
530 | video_list_json = self._download_payload('al_video', page_id, { | |
531 | 'act': 'load_videos_silent', | |
532 | 'offset': 0, | |
533 | 'oid': page_id, | |
534 | 'section': section, | |
535 | })[0][section] | |
536 | count = video_list_json['count'] | |
537 | total = video_list_json['total'] | |
538 | video_list = video_list_json['list'] | |
539 | ||
540 | while True: | |
541 | for video in video_list: | |
542 | v = self._VIDEO._make(video[:2]) | |
543 | video_id = '%d_%d' % (v.owner_id, v.id) | |
544 | yield self.url_result( | |
545 | 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id) | |
546 | if count >= total: | |
547 | break | |
548 | video_list_json = self._download_payload('al_video', page_id, { | |
549 | 'act': 'load_videos_silent', | |
550 | 'offset': count, | |
551 | 'oid': page_id, | |
552 | 'section': section, | |
553 | })[0][section] | |
554 | count += video_list_json['count'] | |
555 | video_list = video_list_json['list'] | |
556 | ||
557 | def _real_extract(self, url): | |
558 | u_id, section = self._match_valid_url(url).groups() | |
559 | webpage = self._download_webpage(url, u_id) | |
560 | ||
561 | if u_id.startswith('@'): | |
562 | page_id = self._search_regex(r'data-owner-id\s?=\s?"([^"]+)"', webpage, 'page_id') | |
563 | elif '_' in u_id: | |
564 | page_id, section = u_id.split('_', 1) | |
565 | section = f'playlist_{section}' | |
566 | else: | |
567 | raise ExtractorError('Invalid URL', expected=True) | |
568 | ||
569 | if not section: | |
570 | section = 'all' | |
571 | ||
572 | playlist_title = clean_html(get_element_by_class('VideoInfoPanel__title', webpage)) | |
573 | return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section), playlist_title) | |
574 | ||
575 | ||
576 | class VKWallPostIE(VKBaseIE): | |
577 | IE_NAME = 'vk:wallpost' | |
578 | _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))' | |
579 | _TESTS = [{ | |
580 | # public page URL, audio playlist | |
581 | 'url': 'https://vk.com/bs.official?w=wall-23538238_35', | |
582 | 'info_dict': { | |
583 | 'id': '-23538238_35', | |
584 | 'title': 'Black Shadow - Wall post -23538238_35', | |
585 | 'description': 'md5:190c78f905a53e0de793d83933c6e67f', | |
586 | }, | |
587 | 'playlist': [{ | |
588 | 'md5': '5ba93864ec5b85f7ce19a9af4af080f6', | |
589 | 'info_dict': { | |
590 | 'id': '135220665_111806521', | |
591 | 'ext': 'm4a', | |
592 | 'title': 'Black Shadow - Слепое Верование', | |
593 | 'duration': 370, | |
594 | 'uploader': 'Black Shadow', | |
595 | 'artist': 'Black Shadow', | |
596 | 'track': 'Слепое Верование', | |
597 | }, | |
598 | }, { | |
599 | 'md5': '4cc7e804579122b17ea95af7834c9233', | |
600 | 'info_dict': { | |
601 | 'id': '135220665_111802303', | |
602 | 'ext': 'm4a', | |
603 | 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!', | |
604 | 'duration': 423, | |
605 | 'uploader': 'Black Shadow', | |
606 | 'artist': 'Black Shadow', | |
607 | 'track': 'Война - Негасимое Бездны Пламя!', | |
608 | }, | |
609 | }], | |
610 | 'params': { | |
611 | 'skip_download': True, | |
612 | }, | |
613 | }, { | |
614 | # single YouTube embed with irrelevant reaction videos | |
615 | 'url': 'https://vk.com/wall-32370614_7173954', | |
616 | 'info_dict': { | |
617 | 'id': '-32370614_7173954', | |
618 | 'title': 'md5:9f93c405bbc00061d34007d78c75e3bc', | |
619 | 'description': 'md5:953b811f26fa9f21ee5856e2ea8e68fc', | |
620 | }, | |
621 | 'playlist_count': 1, | |
622 | }, { | |
623 | # wall page URL | |
624 | 'url': 'https://vk.com/wall-23538238_35', | |
625 | 'only_matching': True, | |
626 | }, { | |
627 | # mobile wall page URL | |
628 | 'url': 'https://m.vk.com/wall-23538238_35', | |
629 | 'only_matching': True, | |
630 | }] | |
631 | _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/=' | |
632 | _AUDIO = collections.namedtuple('Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads']) | |
633 | ||
634 | def _decode(self, enc): | |
635 | dec = '' | |
636 | e = n = 0 | |
637 | for c in enc: | |
638 | r = self._BASE64_CHARS.index(c) | |
639 | cond = n % 4 | |
640 | e = 64 * e + r if cond else r | |
641 | n += 1 | |
642 | if cond: | |
643 | dec += chr(255 & e >> (-2 * n & 6)) | |
644 | return dec | |
645 | ||
646 | def _unmask_url(self, mask_url, vk_id): | |
647 | if 'audio_api_unavailable' in mask_url: | |
648 | extra = mask_url.split('?extra=')[1].split('#') | |
649 | func, base = self._decode(extra[1]).split(chr(11)) | |
650 | mask_url = list(self._decode(extra[0])) | |
651 | url_len = len(mask_url) | |
652 | indexes = [None] * url_len | |
653 | index = int(base) ^ vk_id | |
654 | for n in range(url_len - 1, -1, -1): | |
655 | index = (url_len * (n + 1) ^ index + n) % url_len | |
656 | indexes[n] = index | |
657 | for n in range(1, url_len): | |
658 | c = mask_url[n] | |
659 | index = indexes[url_len - 1 - n] | |
660 | mask_url[n] = mask_url[index] | |
661 | mask_url[index] = c | |
662 | mask_url = ''.join(mask_url) | |
663 | return mask_url | |
664 | ||
665 | def _real_extract(self, url): | |
666 | post_id = self._match_id(url) | |
667 | ||
668 | webpage = self._download_payload('wkview', post_id, { | |
669 | 'act': 'show', | |
670 | 'w': 'wall' + post_id, | |
671 | })[1] | |
672 | ||
673 | uploader = clean_html(get_element_by_class('PostHeaderTitle__authorName', webpage)) | |
674 | ||
675 | entries = [] | |
676 | ||
677 | for audio in re.findall(r'data-audio="([^"]+)', webpage): | |
678 | audio = self._parse_json(unescapeHTML(audio), post_id) | |
679 | if not audio['url']: | |
680 | continue | |
681 | title = unescapeHTML(audio.get('title')) | |
682 | artist = unescapeHTML(audio.get('artist')) | |
683 | entries.append({ | |
684 | 'id': f'{audio["owner_id"]}_{audio["id"]}', | |
685 | 'title': join_nonempty(artist, title, delim=' - '), | |
686 | 'thumbnails': try_call(lambda: [{'url': u} for u in audio['coverUrl'].split(',')]), | |
687 | 'duration': int_or_none(audio.get('duration')), | |
688 | 'uploader': uploader, | |
689 | 'artist': artist, | |
690 | 'track': title, | |
691 | 'formats': [{ | |
692 | 'url': audio['url'], | |
693 | 'ext': 'm4a', | |
694 | 'vcodec': 'none', | |
695 | 'acodec': 'mp3', | |
696 | 'container': 'm4a_dash', | |
697 | }], | |
698 | }) | |
699 | ||
700 | entries.extend(self.url_result(urljoin(url, entry), VKIE) for entry in set(re.findall( | |
701 | r'<a[^>]+href=(?:["\'])(/video(?:-?[\d_]+)[^"\']*)', | |
702 | get_element_html_by_id('wl_post_body', webpage)))) | |
703 | ||
704 | return self.playlist_result( | |
705 | entries, post_id, join_nonempty(uploader, f'Wall post {post_id}', delim=' - '), | |
706 | clean_html(get_element_by_class('wall_post_text', webpage))) | |
707 | ||
708 | ||
709 | class VKPlayBaseIE(InfoExtractor): | |
710 | _RESOLUTIONS = { | |
711 | 'tiny': '256x144', | |
712 | 'lowest': '426x240', | |
713 | 'low': '640x360', | |
714 | 'medium': '852x480', | |
715 | 'high': '1280x720', | |
716 | 'full_hd': '1920x1080', | |
717 | 'quad_hd': '2560x1440', | |
718 | } | |
719 | ||
720 | def _extract_from_initial_state(self, url, video_id, path): | |
721 | webpage = self._download_webpage(url, video_id) | |
722 | video_info = traverse_obj(self._search_json( | |
723 | r'<script[^>]+\bid="initial-state"[^>]*>', webpage, 'initial state', video_id), | |
724 | path, expected_type=dict) | |
725 | if not video_info: | |
726 | raise ExtractorError('Unable to extract video info from html inline initial state') | |
727 | return video_info | |
728 | ||
729 | def _extract_formats(self, stream_info, video_id): | |
730 | formats = [] | |
731 | for stream in traverse_obj(stream_info, ( | |
732 | 'data', 0, 'playerUrls', lambda _, v: url_or_none(v['url']) and v['type'])): | |
733 | url = stream['url'] | |
734 | format_id = str_or_none(stream['type']) | |
735 | if format_id in ('hls', 'live_hls', 'live_playback_hls') or '.m3u8' in url: | |
736 | formats.extend(self._extract_m3u8_formats(url, video_id, m3u8_id=format_id, fatal=False)) | |
737 | elif format_id == 'dash': | |
738 | formats.extend(self._extract_mpd_formats(url, video_id, mpd_id=format_id, fatal=False)) | |
739 | elif format_id in ('live_dash', 'live_playback_dash'): | |
740 | self.write_debug(f'Not extracting unsupported format "{format_id}"') | |
741 | else: | |
742 | formats.append({ | |
743 | 'url': url, | |
744 | 'ext': 'mp4', | |
745 | 'format_id': format_id, | |
746 | **parse_resolution(self._RESOLUTIONS.get(format_id)), | |
747 | }) | |
748 | return formats | |
749 | ||
750 | def _extract_common_meta(self, stream_info): | |
751 | return traverse_obj(stream_info, { | |
752 | 'id': ('id', {str_or_none}), | |
753 | 'title': ('title', {str}), | |
754 | 'release_timestamp': ('startTime', {int_or_none}), | |
755 | 'thumbnail': ('previewUrl', {url_or_none}), | |
756 | 'view_count': ('count', 'views', {int_or_none}), | |
757 | 'like_count': ('count', 'likes', {int_or_none}), | |
758 | 'categories': ('category', 'title', {str}, {lambda x: [x] if x else None}), | |
759 | 'uploader': (('user', ('blog', 'owner')), 'nick', {str}), | |
760 | 'uploader_id': (('user', ('blog', 'owner')), 'id', {str_or_none}), | |
761 | 'duration': ('duration', {int_or_none}), | |
762 | 'is_live': ('isOnline', {bool}), | |
763 | 'concurrent_view_count': ('count', 'viewers', {int_or_none}), | |
764 | }, get_all=False) | |
765 | ||
766 | ||
767 | class VKPlayIE(VKPlayBaseIE): | |
768 | _VALID_URL = r'https?://vkplay\.live/(?P<username>[^/]+)/record/(?P<id>[a-f0-9\-]+)' | |
769 | _TESTS = [{ | |
770 | 'url': 'https://vkplay.live/zitsmann/record/f5e6e3b5-dc52-4d14-965d-0680dd2882da', | |
771 | 'info_dict': { | |
772 | 'id': 'f5e6e3b5-dc52-4d14-965d-0680dd2882da', | |
773 | 'ext': 'mp4', | |
774 | 'title': 'Atomic Heart (пробуем!) спасибо подписчику EKZO!', | |
775 | 'uploader': 'ZitsmanN', | |
776 | 'uploader_id': '13159830', | |
777 | 'release_timestamp': 1683461378, | |
778 | 'release_date': '20230507', | |
779 | 'thumbnail': r're:https://images.vkplay.live/public_video_stream/record/f5e6e3b5-dc52-4d14-965d-0680dd2882da/preview\?change_time=\d+', | |
780 | 'duration': 10608, | |
781 | 'view_count': int, | |
782 | 'like_count': int, | |
783 | 'categories': ['Atomic Heart'], | |
784 | }, | |
785 | 'params': {'skip_download': 'm3u8'}, | |
786 | }] | |
787 | ||
788 | def _real_extract(self, url): | |
789 | username, video_id = self._match_valid_url(url).groups() | |
790 | ||
791 | record_info = traverse_obj(self._download_json( | |
792 | f'https://api.vkplay.live/v1/blog/{username}/public_video_stream/record/{video_id}', video_id, fatal=False), | |
793 | ('data', 'record', {dict})) | |
794 | if not record_info: | |
795 | record_info = self._extract_from_initial_state(url, video_id, ('record', 'currentRecord', 'data')) | |
796 | ||
797 | return { | |
798 | **self._extract_common_meta(record_info), | |
799 | 'id': video_id, | |
800 | 'formats': self._extract_formats(record_info, video_id), | |
801 | } | |
802 | ||
803 | ||
804 | class VKPlayLiveIE(VKPlayBaseIE): | |
805 | _VALID_URL = r'https?://vkplay\.live/(?P<id>[^/]+)/?(?:[#?]|$)' | |
806 | _TESTS = [{ | |
807 | 'url': 'https://vkplay.live/bayda', | |
808 | 'info_dict': { | |
809 | 'id': 'f02c321e-427b-408d-b12f-ae34e53e0ea2', | |
810 | 'ext': 'mp4', | |
811 | 'title': r're:эскапизм крута .*', | |
812 | 'uploader': 'Bayda', | |
813 | 'uploader_id': 12279401, | |
814 | 'release_timestamp': 1687209962, | |
815 | 'release_date': '20230619', | |
816 | 'thumbnail': r're:https://images.vkplay.live/public_video_stream/12279401/preview\?change_time=\d+', | |
817 | 'view_count': int, | |
818 | 'concurrent_view_count': int, | |
819 | 'like_count': int, | |
820 | 'categories': ['EVE Online'], | |
821 | 'live_status': 'is_live', | |
822 | }, | |
823 | 'skip': 'livestream', | |
824 | 'params': {'skip_download': True}, | |
825 | }] | |
826 | ||
827 | def _real_extract(self, url): | |
828 | username = self._match_id(url) | |
829 | ||
830 | stream_info = self._download_json( | |
831 | f'https://api.vkplay.live/v1/blog/{username}/public_video_stream', username, fatal=False) | |
832 | if not stream_info: | |
833 | stream_info = self._extract_from_initial_state(url, username, ('stream', 'stream', 'data', 'stream')) | |
834 | ||
835 | formats = self._extract_formats(stream_info, username) | |
836 | if not formats and not traverse_obj(stream_info, ('isOnline', {bool})): | |
837 | raise UserNotLive(video_id=username) | |
838 | ||
839 | return { | |
840 | **self._extract_common_meta(stream_info), | |
841 | 'formats': formats, | |
842 | } |