yt_dlp/extractor/c56.py

   1 from .common import InfoExtractor
   2 from ..utils import js_to_json
   3
   4
   5 class C56IE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
   7     IE_NAME = '56.com'
   8     _TESTS = [{
   9         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
  10         'md5': 'e59995ac63d0457783ea05f93f12a866',
  11         'info_dict': {
  12             'id': '93440716',
  13             'ext': 'flv',
  14             'title': '网事知多少 第32期：车怒',
  15             'duration': 283.813,
  16         },
  17     }, {
  18         'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
  19         'md5': '',
  20         'info_dict': {
  21             'id': '82247482',
  22             'title': '爱的诅咒之杜鹃花开',
  23         },
  24         'playlist_count': 7,
  25         'add_ie': ['Sohu'],
  26     }]
  27
  28     def _real_extract(self, url):
  29         mobj = self._match_valid_url(url)
  30         text_id = mobj.group('textid')
  31
  32         webpage = self._download_webpage(url, text_id)
  33         sohu_video_info_str = self._search_regex(
  34             r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
  35         if sohu_video_info_str:
  36             sohu_video_info = self._parse_json(
  37                 sohu_video_info_str, text_id, transform_source=js_to_json)
  38             return self.url_result(sohu_video_info['url'], 'Sohu')
  39
  40         page = self._download_json(
  41             'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
  42
  43         info = page['info']
  44
  45         formats = [
  46             {
  47                 'format_id': f['type'],
  48                 'filesize': int(f['filesize']),
  49                 'url': f['url']
  50             } for f in info['rfiles']
  51         ]
  52
  53         return {
  54             'id': info['vid'],
  55             'title': info['Subject'],
  56             'duration': int(info['duration']) / 1000.0,
  57             'formats': formats,
  58             'thumbnail': info.get('bimg') or info.get('img'),
  59         }