w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[ooyala] Modernize

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-03-21 21:55:51 +01:00
parent 750f9020ae
commit e24b5a8610
1 changed files with 26 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
youtube_dl/extractor/ooyala.py
View file

@ -1,20 +1,23 @@
from __future__ import unicode_literals
import re import re
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import unescapeHTML from ..utils import unescapeHTML
class OoyalaIE(InfoExtractor): class OoyalaIE(InfoExtractor):
_VALID_URL = r'https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=(?P<id>.+?)(&|$)' _VALID_URL = r'https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=(?P<id>.+?)(&|$)'
_TEST = { _TEST = {
# From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
u'url': u'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
u'file': u'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8.mp4', 'md5': '3f5cceb3a7bf461d6c29dc466cf8033c',
u'md5': u'3f5cceb3a7bf461d6c29dc466cf8033c', 'info_dict': {
u'info_dict': { 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
u'title': u'Explaining Data Recovery from Hard Drives and SSDs', 'ext': 'mp4',
u'description': u'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', 'title': 'Explaining Data Recovery from Hard Drives and SSDs',
'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
}, },
} }
@ -28,13 +31,14 @@ class OoyalaIE(InfoExtractor):
ie=cls.ie_key()) ie=cls.ie_key())
def _extract_result(self, info, more_info): def _extract_result(self, info, more_info):
return {'id': info['embedCode'], return {
'ext': 'mp4', 'id': info['embedCode'],
'title': unescapeHTML(info['title']), 'ext': 'mp4',
'url': info.get('ipad_url') or info['url'], 'title': unescapeHTML(info['title']),
'description': unescapeHTML(more_info['description']), 'url': info.get('ipad_url') or info['url'],
'thumbnail': more_info['promo'], 'description': unescapeHTML(more_info['description']),
} 'thumbnail': more_info['promo'],
}
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -42,22 +46,23 @@ class OoyalaIE(InfoExtractor):
player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
player = self._download_webpage(player_url, embedCode) player = self._download_webpage(player_url, embedCode)
mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
player, u'mobile player url') player, 'mobile player url')
mobile_player = self._download_webpage(mobile_url, embedCode) mobile_player = self._download_webpage(mobile_url, embedCode)
videos_info = self._search_regex( videos_info = self._search_regex(
r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
mobile_player, u'info').replace('\\"','"') mobile_player, 'info').replace('\\"','"')
videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"') videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"')
videos_info = json.loads(videos_info) videos_info = json.loads(videos_info)
videos_more_info =json.loads(videos_more_info) videos_more_info =json.loads(videos_more_info)
if videos_more_info.get('lineup'): if videos_more_info.get('lineup'):
videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
return {'_type': 'playlist', return {
'id': embedCode, '_type': 'playlist',
'title': unescapeHTML(videos_more_info['title']), 'id': embedCode,
'entries': videos, 'title': unescapeHTML(videos_more_info['title']),
} 'entries': videos,
}
else: else:
return self._extract_result(videos_info[0], videos_more_info) return self._extract_result(videos_info[0], videos_more_info)