+ page_id, section = re.match(self._VALID_URL, url).groups()
+ if not section:
+ section = 'all'
+
+ entries = OnDemandPagedList(
+ functools.partial(self._fetch_page, page_id, section),
+ self._PAGE_SIZE)
+
+ return self.playlist_result(entries, '%s_%s' % (page_id, section))
+
+
+class VKWallPostIE(VKBaseIE):
+ IE_NAME = 'vk:wallpost'
+ _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
+ _TESTS = [{
+ # public page URL, audio playlist
+ 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
+ 'info_dict': {
+ 'id': '-23538238_35',
+ 'title': 'Black Shadow - Wall post -23538238_35',
+ 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
+ },
+ 'playlist': [{
+ 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
+ 'info_dict': {
+ 'id': '135220665_111806521',
+ 'ext': 'mp4',
+ 'title': 'Black Shadow - Слепое Верование',
+ 'duration': 370,
+ 'uploader': 'Black Shadow',
+ 'artist': 'Black Shadow',
+ 'track': 'Слепое Верование',
+ },
+ }, {
+ 'md5': '4cc7e804579122b17ea95af7834c9233',
+ 'info_dict': {
+ 'id': '135220665_111802303',
+ 'ext': 'mp4',
+ 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
+ 'duration': 423,
+ 'uploader': 'Black Shadow',
+ 'artist': 'Black Shadow',
+ 'track': 'Война - Негасимое Бездны Пламя!',
+ },
+ }],
+ 'params': {
+ 'skip_download': True,
+ 'usenetrc': True,
+ },
+ 'skip': 'Requires vk account credentials',
+ }, {
+ # single YouTube embed, no leading -
+ 'url': 'https://vk.com/wall85155021_6319',
+ 'info_dict': {
+ 'id': '85155021_6319',
+ 'title': 'Сергей Горбунов - Wall post 85155021_6319',
+ },
+ 'playlist_count': 1,
+ 'params': {
+ 'usenetrc': True,
+ },
+ 'skip': 'Requires vk account credentials',
+ }, {
+ # wall page URL
+ 'url': 'https://vk.com/wall-23538238_35',
+ 'only_matching': True,
+ }, {
+ # mobile wall page URL
+ 'url': 'https://m.vk.com/wall-23538238_35',
+ 'only_matching': True,
+ }]
+ _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/='
+ _AUDIO = collections.namedtuple('Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads'])
+
+ def _decode(self, enc):
+ dec = ''
+ e = n = 0
+ for c in enc:
+ r = self._BASE64_CHARS.index(c)
+ cond = n % 4
+ e = 64 * e + r if cond else r
+ n += 1
+ if cond:
+ dec += chr(255 & e >> (-2 * n & 6))
+ return dec
+
+ def _unmask_url(self, mask_url, vk_id):
+ if 'audio_api_unavailable' in mask_url:
+ extra = mask_url.split('?extra=')[1].split('#')
+ func, base = self._decode(extra[1]).split(chr(11))
+ mask_url = list(self._decode(extra[0]))
+ url_len = len(mask_url)
+ indexes = [None] * url_len
+ index = int(base) ^ vk_id
+ for n in range(url_len - 1, -1, -1):
+ index = (url_len * (n + 1) ^ index + n) % url_len
+ indexes[n] = index
+ for n in range(1, url_len):
+ c = mask_url[n]
+ index = indexes[url_len - 1 - n]
+ mask_url[n] = mask_url[index]
+ mask_url[index] = c
+ mask_url = ''.join(mask_url)
+ return mask_url
+
+ def _real_extract(self, url):
+ post_id = self._match_id(url)
+
+ webpage = self._download_payload('wkview', post_id, {
+ 'act': 'show',
+ 'w': 'wall' + post_id,
+ })[1]
+
+ description = clean_html(get_element_by_class('wall_post_text', webpage))
+ uploader = clean_html(get_element_by_class('author', webpage))
+
+ entries = []
+
+ for audio in re.findall(r'data-audio="([^"]+)', webpage):
+ audio = self._parse_json(unescapeHTML(audio), post_id)
+ a = self._AUDIO._make(audio[:16])
+ if not a.url:
+ continue
+ title = unescapeHTML(a.title)
+ performer = unescapeHTML(a.performer)
+ entries.append({
+ 'id': '%s_%s' % (a.owner_id, a.id),
+ 'url': self._unmask_url(a.url, a.ads['vk_id']),
+ 'title': '%s - %s' % (performer, title) if performer else title,
+ 'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None,
+ 'duration': int_or_none(a.duration),
+ 'uploader': uploader,
+ 'artist': performer,
+ 'track': title,
+ 'ext': 'mp4',
+ 'protocol': 'm3u8',
+ })
+
+ for video in re.finditer(
+ r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
+ entries.append(self.url_result(
+ compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
+
+ title = 'Wall post %s' % post_id
+
+ return self.playlist_result(
+ orderedSet(entries), post_id,
+ '%s - %s' % (uploader, title) if uploader else title,
+ description)
Rapsys Git / youtubedl / blobdiff