_ Git - youtube-dl/blob - youtube_dl/extractor/ynet.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import base64
   6 import json
   7
   8 from .common import InfoExtractor
   9 from youtube_dl.utils import compat_urllib_parse_urlparse, compat_urllib_parse
  10
  11 class YnetIE(InfoExtractor):
  12     _VALID_URL = r'http://.*ynet\.co\.il/.*/0,7340,(?P<id>L(-[0-9]+)+),00\.html'
  13     _TEST = {
  14         'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
  15         'info_dict': {
  16             'id': 'L-11659-99244',
  17             'ext': 'flv',
  18             'title': 'md5:3dba12d2837ee2ad9652cc64af652b16',
  19             'thumbnail': 'http://hot.ynet.co.il/PicServer4/2014/09/23/5606015/AMERICAN_COMMUNE1_T.jpg',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25
  26         id = mobj.group('id')
  27
  28         webpage = self._download_webpage(url, id)
  29
  30         content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage).decode('utf-8'))
  31
  32         player_url = re.match('(http.*\.swf)\?' ,content).group(1)
  33
  34         config = json.loads(re.match('.*config\=(.*)' ,content).group(1))
  35
  36         f4m_url = config['clip']['url']
  37
  38         title = re.sub(': Video$', '', self._og_search_title(webpage))
  39
  40         return {
  41             'id': id,
  42             'title': title,
  43             'formats': self._extract_f4m_formats(f4m_url, id),
  44             'thumbnail': self._og_search_thumbnail(webpage),
  45             'player_url': player_url,
  46         }
  47