youtube_dl/extractor/c56.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class C56IE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
  11     IE_NAME = '56.com'
  12     _TEST = {
  13         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
  14         'md5': 'e59995ac63d0457783ea05f93f12a866',
  15         'info_dict': {
  16             'id': '93440716',
  17             'ext': 'flv',
  18             'title': '网事知多少 第32期：车怒',
  19             'duration': 283.813,
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
  25         text_id = mobj.group('textid')
  26
  27         page = self._download_json(
  28             'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
  29
  30         info = page['info']
  31
  32         formats = [
  33             {
  34                 'format_id': f['type'],
  35                 'filesize': int(f['filesize']),
  36                 'url': f['url']
  37             } for f in info['rfiles']
  38         ]
  39         self._sort_formats(formats)
  40
  41         return {
  42             'id': info['vid'],
  43             'title': info['Subject'],
  44             'duration': int(info['duration']) / 1000.0,
  45             'formats': formats,
  46             'thumbnail': info.get('bimg') or info.get('img'),
  47         }