Raphaël G. Git Repositories - youtubedl/blob - 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 from ..utils import js_to_json
   8
   9
  10 class C56IE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
  12     IE_NAME = '56.com'
  13     _TESTS = [{
  14         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
  15         'md5': 'e59995ac63d0457783ea05f93f12a866',
  16         'info_dict': {
  17             'id': '93440716',
  18             'ext': 'flv',
  19             'title': '网事知多少 第32期：车怒',
  20             'duration': 283.813,
  21         },
  22     }, {
  23         'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
  24         'md5': '',
  25         'info_dict': {
  26             'id': '82247482',
  27             'title': '爱的诅咒之杜鹃花开',
  28         },
  29         'playlist_count': 7,
  30         'add_ie': ['Sohu'],
  31     }]
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
  35         text_id = mobj.group('textid')
  36
  37         webpage = self._download_webpage(url, text_id)
  38         sohu_video_info_str = self._search_regex(
  39             r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
  40         if sohu_video_info_str:
  41             sohu_video_info = self._parse_json(
  42                 sohu_video_info_str, text_id, transform_source=js_to_json)
  43             return self.url_result(sohu_video_info['url'], 'Sohu')
  44
  45         page = self._download_json(
  46             'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
  47
  48         info = page['info']
  49
  50         formats = [
  51             {
  52                 'format_id': f['type'],
  53                 'filesize': int(f['filesize']),
  54                 'url': f['url']
  55             } for f in info['rfiles']
  56         ]
  57         self._sort_formats(formats)
  58
  59         return {
  60             'id': info['vid'],
  61             'title': info['Subject'],
  62             'duration': int(info['duration']) / 1000.0,
  63             'formats': formats,
  64             'thumbnail': info.get('bimg') or info.get('img'),
  65         }