youtube-dl

commit 5301304bf2785888454d41d27c20e743a2501f1a
parent 948bcc60df48415ddbf3d7ea03bc3af53a9d928d
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Tue, 13 May 2014 10:04:29 +0200

[slutload] Simplify (#2898)

Diffstat:
M
youtube_dl/extractor/slutload.py
 | 
57
+++++++++++++++++++++++++++++----------------------------

1 file changed, 29 insertions(+), 28 deletions(-)
diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -5,42 +7,41 @@ from ..utils import (
     ExtractorError,
 )
 
+
 class SlutloadIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<videoid>[^/]+)/?$'
+    _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
     _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,
+        'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
+        'md5': '0cf531ae8006b530bd9df947a6a0df77',
+        'info_dict': {
+            'id': 'TD73btpBqSxc',
+            'ext': 'mp4',
+            "title": "virginie baisee en cam",
+            "age_limit": 18,
+            'thumbnail': 're:https?://.*?\.jpg'
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
 
-        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]
+            webpage, 'title').strip()
+
+        video_url = self._html_search_regex(
+            r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
+            webpage, 'video URL')
+        thumbnail = self._html_search_regex(
+            r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'thumbnail': thumbnail,
+            'age_limit': 18
+        }