+ info = self._get_common_fields(webpage)
+ info.update({
+ 'id': video_id,
+ 'formats': formats,
+ 'view_count': view_count,
+ 'subtitles': subtitles,
+ })
+ return info
+
+ def _download_init_page(self, video_id):
+ return self._download_webpage(
+ 'https://www.vlive.tv/video/init/view',
+ video_id, note='Downloading live webpage',
+ data=urlencode_postdata({'videoSeq': video_id}),
+ headers={
+ 'Referer': 'https://www.vlive.tv/video/%s' % video_id,
+ 'Content-Type': 'application/x-www-form-urlencoded'
+ })
+
+
+class VLiveChannelIE(InfoExtractor):
+ IE_NAME = 'vlive:channel'
+ _VALID_URL = r'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)'
+ _TEST = {
+ 'url': 'http://channels.vlive.tv/FCD4B',
+ 'info_dict': {
+ 'id': 'FCD4B',
+ 'title': 'MAMAMOO',
+ },
+ 'playlist_mincount': 110
+ }
+ _APP_ID = '8c6cc7b45d2568fb668be6e05b6e5a3b'
+
+ def _real_extract(self, url):
+ channel_code = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'http://channels.vlive.tv/%s/video' % channel_code, channel_code)
+
+ app_id = None
+
+ app_js_url = self._search_regex(
+ r'<script[^>]+src=(["\'])(?P<url>http.+?/app\.js.*?)\1',
+ webpage, 'app js', default=None, group='url')
+
+ if app_js_url:
+ app_js = self._download_webpage(
+ app_js_url, channel_code, 'Downloading app JS', fatal=False)
+ if app_js:
+ app_id = self._search_regex(
+ r'Global\.VFAN_APP_ID\s*=\s*[\'"]([^\'"]+)[\'"]',
+ app_js, 'app id', default=None)
+
+ app_id = app_id or self._APP_ID
+
+ channel_info = self._download_json(
+ 'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode',
+ channel_code, note='Downloading decode channel code',
+ query={
+ 'app_id': app_id,
+ 'channelCode': channel_code,
+ '_': int(time.time())
+ })
+
+ channel_seq = channel_info['result']['channelSeq']
+ channel_name = None
+ entries = []
+
+ for page_num in itertools.count(1):
+ video_list = self._download_json(
+ 'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList',
+ channel_code, note='Downloading channel list page #%d' % page_num,
+ query={
+ 'app_id': app_id,
+ 'channelSeq': channel_seq,
+ # Large values of maxNumOfRows (~300 or above) may cause
+ # empty responses (see [1]), e.g. this happens for [2] that
+ # has more than 300 videos.
+ # 1. https://github.com/ytdl-org/youtube-dl/issues/13830
+ # 2. http://channels.vlive.tv/EDBF.
+ 'maxNumOfRows': 100,
+ '_': int(time.time()),
+ 'pageNo': page_num
+ }
+ )
+
+ if not channel_name:
+ channel_name = try_get(
+ video_list,
+ lambda x: x['result']['channelInfo']['channelName'],
+ compat_str)
+
+ videos = try_get(
+ video_list, lambda x: x['result']['videoList'], list)
+ if not videos:
+ break
+
+ for video in videos:
+ video_id = video.get('videoSeq')
+ if not video_id:
+ continue
+ video_id = compat_str(video_id)
+ entries.append(
+ self.url_result(
+ 'http://www.vlive.tv/video/%s' % video_id,
+ ie=VLiveIE.ie_key(), video_id=video_id))
+
+ return self.playlist_result(
+ entries, channel_code, channel_name)
+
+
+class VLivePlaylistIE(InfoExtractor):
+ IE_NAME = 'vlive:playlist'
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)'
+ _VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
+ _TESTS = [{
+ # regular working playlist
+ 'url': 'https://www.vlive.tv/video/117956/playlist/117963',
+ 'info_dict': {
+ 'id': '117963',
+ 'title': '아이돌룸(IDOL ROOM) 41회 - (여자)아이들'
+ },
+ 'playlist_mincount': 10
+ }, {
+ # playlist with no playlistVideoSeqs
+ 'url': 'http://www.vlive.tv/video/22867/playlist/22912',
+ 'info_dict': {
+ 'id': '22867',
+ 'ext': 'mp4',
+ 'title': '[V LIVE] Valentine Day Message from MINA',
+ 'creator': 'TWICE',
+ 'view_count': int
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }]
+
+ def _build_video_result(self, video_id, message):
+ self.to_screen(message)
+ return self.url_result(
+ self._VIDEO_URL_TEMPLATE % video_id,
+ ie=VLiveIE.ie_key(), video_id=video_id)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id, playlist_id = mobj.group('video_id', 'id')
+
+ if self._downloader.params.get('noplaylist'):
+ return self._build_video_result(
+ video_id,
+ 'Downloading just video %s because of --no-playlist'
+ % video_id)
+
+ self.to_screen(
+ 'Downloading playlist %s - add --no-playlist to just download video'
+ % playlist_id)
+
+ webpage = self._download_webpage(
+ 'http://www.vlive.tv/video/%s/playlist/%s'
+ % (video_id, playlist_id), playlist_id)
+
+ raw_item_ids = self._search_regex(
+ r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
+ 'playlist video seqs', default=None, fatal=False)
+
+ if not raw_item_ids:
+ return self._build_video_result(
+ video_id,
+ 'Downloading just video %s because no playlist was found'
+ % video_id)
+
+ item_ids = self._parse_json(raw_item_ids, playlist_id)
+
+ entries = [
+ self.url_result(
+ self._VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
+ video_id=compat_str(item_id))
+ for item_id in item_ids]
+
+ playlist_name = self._html_search_regex(
+ r'<div[^>]+class="[^"]*multicam_playlist[^>]*>\s*<h3[^>]+>([^<]+)',
+ webpage, 'playlist title', fatal=False)
+
+ return self.playlist_result(entries, playlist_id, playlist_name)
Rapsys Git / youtubedl / blobdiff