youtube-dl

commit 948bcc60df48415ddbf3d7ea03bc3af53a9d928d
parent 25dfe0eb10aedb1ac22a5c9624fc0e35d9e0b926
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Tue, 13 May 2014 10:00:49 +0200

Merge remote-tracking branch 'hojel/slutload'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/slutload.py
 | 
46
++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 47 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -231,6 +231,7 @@ from .scivee import SciVeeIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
+from .slutload import SlutloadIE
 from .smotri import (
     SmotriIE,
     SmotriCommunityIE,
diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py
@@ -0,0 +1,46 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+class SlutloadIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<videoid>[^/]+)/?$'
+    _TEST = {
+        u'url': u'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
+        u'file': u'TD73btpBqSxc.mp4',
+        u'md5': u'0cf531ae8006b530bd9df947a6a0df77',
+        u'info_dict': {
+            u"title": u"virginie baisee en cam",
+            u"age_limit": 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('videoid')
+
+        # Get webpage content
+        webpage = self._download_webpage(url, video_id)
+
+        # Get the video title
+        video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
+            webpage, u'title').strip()
+
+        # Get the video url
+        result = re.compile(r'<div id="vidPlayer"\s+data-url="([^"]+)"\s+previewer-file="([^"]+)"', re.S).search(webpage)
+        if result is None:
+            raise ExtractorError(u'ERROR: unable to extract video_url')
+
+        video_url, video_thumb = result.group(1,2)
+
+        info = {'id': video_id,
+                'url': video_url,
+                'title': video_title,
+                'thumbnail': video_thumb,
+                'ext': 'mp4',
+                'age_limit': 18}
+
+        return [info]