youtube_dl/extractor/ooyala.py

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5 from ..utils import unescapeHTML
   6
   7 class OoyalaIE(InfoExtractor):
   8     _VALID_URL = r'https?://.+?\.ooyala\.com/.*?embedCode=(?P<id>.+?)(&|$)'
   9
  10     _TEST = {
  11         # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
  12         u'url': u'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
  13         u'file': u'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8.mp4',
  14         u'md5': u'3f5cceb3a7bf461d6c29dc466cf8033c',
  15         u'info_dict': {
  16             u'title': u'Explaining Data Recovery from Hard Drives and SSDs',
  17             u'description': u'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
  18         },
  19     }
  20
  21     @staticmethod
  22     def _url_for_embed_code(embed_code):
  23         return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
  24
  25     def _extract_result(self, info, more_info):
  26         return {'id': info['embedCode'],
  27                 'ext': 'mp4',
  28                 'title': unescapeHTML(info['title']),
  29                 'url': info.get('ipad_url') or info['url'],
  30                 'description': unescapeHTML(more_info['description']),
  31                 'thumbnail': more_info['promo'],
  32                 }
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         embedCode = mobj.group('id')
  37         player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
  38         player = self._download_webpage(player_url, embedCode)
  39         mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
  40                                         player, u'mobile player url')
  41         mobile_player = self._download_webpage(mobile_url, embedCode)
  42         videos_info = self._search_regex(
  43             r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
  44             mobile_player, u'info').replace('\\"','"')
  45         videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"')
  46         videos_info = json.loads(videos_info)
  47         videos_more_info =json.loads(videos_more_info)
  48
  49         if videos_more_info.get('lineup'):
  50             videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
  51             return {'_type': 'playlist',
  52                     'id': embedCode,
  53                     'title': unescapeHTML(videos_more_info['title']),
  54                     'entries': videos,
  55                     }
  56         else:
  57             return self._extract_result(videos_info[0], videos_more_info)
  58