Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mnet.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_duration,
   8     parse_iso8601,
   9 )
  10
  11
  12 class MnetIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?mnet\.(?:com|interest\.me)/tv/vod/(?:.*?\bclip_id=)?(?P<id>[0-9]+)'
  14     _TESTS = [{
  15         'url': 'http://www.mnet.com/tv/vod/171008',
  16         'info_dict': {
  17             'id': '171008',
  18             'title': 'SS_이해인@히든박스',
  19             'description': 'md5:b9efa592c3918b615ba69fe9f8a05c55',
  20             'duration': 88,
  21             'upload_date': '20151231',
  22             'timestamp': 1451564040,
  23             'age_limit': 0,
  24             'thumbnails': 'mincount:5',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'ext': 'flv',
  27         },
  28         'params': {
  29             # rtmp download
  30             'skip_download': True,
  31         },
  32     }, {
  33         'url': 'http://mnet.interest.me/tv/vod/172790',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://www.mnet.com/tv/vod/vod_view.asp?clip_id=172790&tabMenu=',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         # TODO: extract rtmp formats
  44         # no stype -> rtmp url
  45         # stype=H -> m3u8 url
  46         # stype=M -> mpd url
  47         info = self._download_json(
  48             'http://content.api.mnet.com/player/vodConfig',
  49             video_id, 'Downloading vod config JSON', query={
  50                 'id': video_id,
  51                 'ctype': 'CLIP',
  52                 'stype': 'H',
  53             })['data']['info']
  54
  55         title = info['title']
  56
  57         cdn_data = self._download_json(
  58             info['cdn'], video_id, 'Downloading vod cdn JSON')['data'][0]
  59         m3u8_url = cdn_data['url']
  60         token = cdn_data.get('token')
  61         if token and token != '-':
  62             m3u8_url += '?' + token
  63         formats = self._extract_wowza_formats(
  64             m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp', 'f4m'])
  65         self._sort_formats(formats)
  66
  67         description = info.get('ment')
  68         duration = parse_duration(info.get('time'))
  69         timestamp = parse_iso8601(info.get('date'), delimiter=' ')
  70         age_limit = info.get('adult')
  71         if age_limit is not None:
  72             age_limit = 0 if age_limit == 'N' else 18
  73         thumbnails = [{
  74             'id': thumb_format,
  75             'url': thumb['url'],
  76             'width': int_or_none(thumb.get('width')),
  77             'height': int_or_none(thumb.get('height')),
  78         } for thumb_format, thumb in info.get('cover', {}).items() if thumb.get('url')]
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'description': description,
  84             'duration': duration,
  85             'timestamp': timestamp,
  86             'age_limit': age_limit,
  87             'thumbnails': thumbnails,
  88             'formats': formats,
  89         }