Raphaël G. Git Repositories - youtubedl/blob - 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     @classmethod
  26     def _build_url_result(cls, embed_code):
  27         return cls.url_result(cls._url_for_embed_code(embed_code),
  28             ie=cls.ie_key())
  29
  30     def _extract_result(self, info, more_info):
  31         return {'id': info['embedCode'],
  32                 'ext': 'mp4',
  33                 'title': unescapeHTML(info['title']),
  34                 'url': info.get('ipad_url') or info['url'],
  35                 'description': unescapeHTML(more_info['description']),
  36                 'thumbnail': more_info['promo'],
  37                 }
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41         embedCode = mobj.group('id')
  42         player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
  43         player = self._download_webpage(player_url, embedCode)
  44         mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
  45                                         player, u'mobile player url')
  46         mobile_player = self._download_webpage(mobile_url, embedCode)
  47         videos_info = self._search_regex(
  48             r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
  49             mobile_player, u'info').replace('\\"','"')
  50         videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"')
  51         videos_info = json.loads(videos_info)
  52         videos_more_info =json.loads(videos_more_info)
  53
  54         if videos_more_info.get('lineup'):
  55             videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
  56             return {'_type': 'playlist',
  57                     'id': embedCode,
  58                     'title': unescapeHTML(videos_more_info['title']),
  59                     'entries': videos,
  60                     }
  61         else:
  62             return self._extract_result(videos_info[0], videos_more_info)
  63