aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-27 14:53:14 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-08-02 16:53:16 +0200
commit09825cb5c0a5f1d53e66e91efe3db49da7c8ae4a (patch)
treee896150e06c1ea8f4868a6631ac77f3b488ec1d5
parented27d35674b015728f4a9ec9d5d6d5733b597db0 (diff)
Add an extractor for Ooyala (closes #833)
Only works for some sites, it doesn't work for videos that use a f4m manifest
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/ooyala.py52
2 files changed, 53 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index c20172a53..f15caf4b4 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -48,6 +48,7 @@ from .mtv import MTVIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .nba import NBAIE
+from .ooyala import OoyalaIE
from .photobucket import PhotobucketIE
from .pornotube import PornotubeIE
from .rbmaradio import RBMARadioIE
diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py
new file mode 100644
index 000000000..b734722d0
--- /dev/null
+++ b/youtube_dl/extractor/ooyala.py
@@ -0,0 +1,52 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import unescapeHTML
+
+class OoyalaIE(InfoExtractor):
+ _VALID_URL = r'https?://.+?\.ooyala\.com/.*?embedCode=(?P<id>.+?)(&|$)'
+
+ _TEST = {
+ # 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',
+ u'file': u'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8.mp4',
+ u'md5': u'3f5cceb3a7bf461d6c29dc466cf8033c',
+ u'info_dict': {
+ u'title': u'Explaining Data Recovery from Hard Drives and SSDs',
+ u'description': u'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+ },
+ }
+
+ def _extract_result(self, info, more_info):
+ return {'id': info['embedCode'],
+ 'ext': 'mp4',
+ 'title': unescapeHTML(info['title']),
+ 'url': info['url'],
+ 'description': unescapeHTML(more_info['description']),
+ 'thumbnail': more_info['promo'],
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ embedCode = mobj.group('id')
+ player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
+ player = self._download_webpage(player_url, embedCode)
+ mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
+ player, u'mobile player url')
+ mobile_player = self._download_webpage(mobile_url, embedCode)
+ videos_info = self._search_regex(r'eval\("\((\[{.*?stream_redirect.*?}\])\)"\);', mobile_player, u'info').replace('\\"','"')
+ videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"')
+ videos_info = json.loads(videos_info)
+ videos_more_info =json.loads(videos_more_info)
+
+ 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'])]
+ return {'_type': 'playlist',
+ 'id': embedCode,
+ 'title': unescapeHTML(videos_more_info['title']),
+ 'entries': videos,
+ }
+ else:
+ return self._extract_result(videos_info[0], videos_more_info)
+