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