summary refs log tree commit diff
diff options
context:
space:
mode:
authorhojel <hojelei@gmail.com>2014-05-12 01:28:56 -0700
committerhojel <hojelei@gmail.com>2014-05-12 01:28:56 -0700
commit1476b497ebda9155d442065bb2a987d86c29026f (patch)
treee264fba8855ffa14fdbf7a53e3b34bb1c774732f
parente399853d0c5784257ffcb6fba147d0b47d3f9bb6 (diff)
downloadyoutube-dl-1476b497ebda9155d442065bb2a987d86c29026f.tar.gz
youtube-dl-1476b497ebda9155d442065bb2a987d86c29026f.tar.xz
youtube-dl-1476b497ebda9155d442065bb2a987d86c29026f.zip
[slutload] Add new extractor
-rw-r--r--youtube_dl/extractor/slutload.py46
1 files changed, 46 insertions, 0 deletions
diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py
new file mode 100644
index 000000000..095adfc15
--- /dev/null
+++ 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]