Автор.*?onmouseover="popup_user_info[^"]+">(.*?)', video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL) video_uploader_id = self._html_search_regex( '

Автор.*?onmouseover="popup_user_info\$.*?\'([^\']+)\'\$;">', video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL) video_view_count = self._html_search_regex( 'Общее количество просмотров.*?(\\d+)', video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL) return { 'id': video_id, 'url': video_url, 'title': video_title, 'thumbnail': video_thumbnail, 'description': video_description, 'uploader': video_uploader, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'duration': video_duration, 'view_count': video_view_count, 'age_limit': 18 if adult_content else 0, 'video_page_url': video_page_url } class SmotriCommunityIE(InfoExtractor): IE_DESC = 'Smotri.com community videos' IE_NAME = 'smotri:community' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P[0-9A-Za-z_\'-]+)' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) community_id = mobj.group('communityid') url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id rss = self._download_xml(url, community_id, 'Downloading community RSS') entries = [self.url_result(video_url.text, 'Smotri') for video_url in rss.findall('./channel/item/link')] description_text = rss.find('./channel/description').text community_title = self._html_search_regex( '^Видео сообщества "([^"]+)"$', description_text, 'community title') return self.playlist_result(entries, community_id, community_title) class SmotriUserIE(InfoExtractor): IE_DESC = 'Smotri.com user videos' IE_NAME = 'smotri:user' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P[0-9A-Za-z_\'-]+)' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user_id = mobj.group('userid') url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id rss = self._download_xml(url, user_id, 'Downloading user RSS') entries = [self.url_result(video_url.text, 'Smotri') for video_url in rss.findall('./channel/item/link')] description_text = rss.find('./channel/description').text user_nickname = self._html_search_regex( '^Видео режиссера (.*)$', description_text, 'user nickname') return self.playlist_result(entries, user_id, user_nickname) class SmotriBroadcastIE(InfoExtractor): IE_DESC = 'Smotri.com broadcasts' IE_NAME = 'smotri:broadcast' _VALID_URL = r'^https?://(?:www\.)?(?Psmotri\.com/live/(?P[^/]+))/?.*' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) broadcast_id = mobj.group('broadcastid') broadcast_url = 'http://' + mobj.group('url') broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page') if re.search('>Режиссер с логином
"%s"
не существует<' % broadcast_id, broadcast_page) is not None: raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True) # Adult content if re.search('EroConfirmText">', broadcast_page) is not None: (username, password) = self._get_login_info() if username is None: raise ExtractorError('Erotic broadcasts allowed only for registered users, ' 'use --username and --password options to provide account credentials.', expected=True) login_form = { 'login-hint53': '1', 'confirm_erotic': '1', 'login': username, 'password': password, } request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age') if re.search('>Неверный логин или пароль<', broadcast_page) is not None: raise ExtractorError('Unable to log in: bad username or password', expected=True) adult_content = True else: adult_content = False ticket = self._html_search_regex( 'window\.broadcast_control\.addFlashVar\$\'file\', \'([^\']+)\'\$;', broadcast_page, 'broadcast ticket') url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket broadcast_password = self._downloader.params.get('videopassword', None) if broadcast_password: url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest() broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON') try: broadcast_json = json.loads(broadcast_json_page) protected_broadcast = broadcast_json['_pass_protected'] == 1 if protected_broadcast and not broadcast_password: raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True) broadcast_offline = broadcast_json['is_play'] == 0 if broadcast_offline: raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True) rtmp_url = broadcast_json['_server'] if not rtmp_url.startswith('rtmp://'): raise ExtractorError('Unexpected broadcast rtmp URL') broadcast_playpath = broadcast_json['_streamName'] broadcast_thumbnail = broadcast_json['_imgURL'] broadcast_title = broadcast_json['title'] broadcast_description = broadcast_json['description'] broadcaster_nick = broadcast_json['nick'] broadcaster_login = broadcast_json['login'] rtmp_conn = 'S:%s' % uuid.uuid4().hex except KeyError: if protected_broadcast: raise ExtractorError('Bad broadcast password', expected=True) raise ExtractorError('Unexpected broadcast JSON') return { 'id': broadcast_id, 'url': rtmp_url, 'title': broadcast_title, 'thumbnail': broadcast_thumbnail, 'description': broadcast_description, 'uploader': broadcaster_nick, 'uploader_id': broadcaster_login, 'age_limit': 18 if adult_content else 0, 'ext': 'flv', 'play_path': broadcast_playpath, 'rtmp_live': True, 'rtmp_conn': rtmp_conn }