yt_dlp/extractor/mnet.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_duration,
   5     parse_iso8601,
   6 )
   7
   8
   9 class MnetIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?mnet\.(?:com|interest\.me)/tv/vod/(?:.*?\bclip_id=)?(?P<id>[0-9]+)'
  11     _TESTS = [{
  12         'url': 'http://www.mnet.com/tv/vod/171008',
  13         'info_dict': {
  14             'id': '171008',
  15             'title': 'SS_이해인@히든박스',
  16             'description': 'md5:b9efa592c3918b615ba69fe9f8a05c55',
  17             'duration': 88,
  18             'upload_date': '20151231',
  19             'timestamp': 1451564040,
  20             'age_limit': 0,
  21             'thumbnails': 'mincount:5',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'ext': 'flv',
  24         },
  25         'params': {
  26             # rtmp download
  27             'skip_download': True,
  28         },
  29     }, {
  30         'url': 'http://mnet.interest.me/tv/vod/172790',
  31         'only_matching': True,
  32     }, {
  33         'url': 'http://www.mnet.com/tv/vod/vod_view.asp?clip_id=172790&tabMenu=',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         # TODO: extract rtmp formats
  41         # no stype -> rtmp url
  42         # stype=H -> m3u8 url
  43         # stype=M -> mpd url
  44         info = self._download_json(
  45             'http://content.api.mnet.com/player/vodConfig',
  46             video_id, 'Downloading vod config JSON', query={
  47                 'id': video_id,
  48                 'ctype': 'CLIP',
  49                 'stype': 'H',
  50             })['data']['info']
  51
  52         title = info['title']
  53
  54         cdn_data = self._download_json(
  55             info['cdn'], video_id, 'Downloading vod cdn JSON')['data'][0]
  56         m3u8_url = cdn_data['url']
  57         token = cdn_data.get('token')
  58         if token and token != '-':
  59             m3u8_url += '?' + token
  60         formats = self._extract_wowza_formats(
  61             m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp', 'f4m'])
  62
  63         description = info.get('ment')
  64         duration = parse_duration(info.get('time'))
  65         timestamp = parse_iso8601(info.get('date'), delimiter=' ')
  66         age_limit = info.get('adult')
  67         if age_limit is not None:
  68             age_limit = 0 if age_limit == 'N' else 18
  69         thumbnails = [{
  70             'id': thumb_format,
  71             'url': thumb['url'],
  72             'width': int_or_none(thumb.get('width')),
  73             'height': int_or_none(thumb.get('height')),
  74         } for thumb_format, thumb in info.get('cover', {}).items() if thumb.get('url')]
  75
  76         return {
  77             'id': video_id,
  78             'title': title,
  79             'description': description,
  80             'duration': duration,
  81             'timestamp': timestamp,
  82             'age_limit': age_limit,
  83             'thumbnails': thumbnails,
  84             'formats': formats,
  85         }