X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fliveleak.py;h=a571fa742e32433c3a5ba0591958d4d87237d0c7;hb=975fa541c204860e25ba5eff330ff85a77eee777;hp=d4b142ea09766b96bf38d35d21e36371b748718e;hpb=825e0984e27f0c626c4d072066e0c9cae9069704;p=youtube-dl

diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py
index d4b142ea0..a571fa742 100644
--- a/youtube_dl/extractor/liveleak.py
+++ b/youtube_dl/extractor/liveleak.py
@@ -1,3 +1,6 @@
+from __future__ import unicode_literals
+
+import json
 import re
 
 from .common import InfoExtractor
@@ -7,38 +10,43 @@ from ..utils import (
 
 
 class LiveLeakIE(InfoExtractor):
-
-    _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
-    IE_NAME = u'liveleak'
+    _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+    _TEST = {
+        'url': 'http://www.liveleak.com/view?i=757_1364311680',
+        'file': '757_1364311680.mp4',
+        'md5': '0813c2430bea7a46bf13acf3406992f4',
+        'info_dict': {
+            'description': 'extremely bad day for this guy..!',
+            'uploader': 'ljfriel2',
+            'title': 'Most unlucky car accident'
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
 
         video_id = mobj.group('video_id')
-
         webpage = self._download_webpage(url, video_id)
-
-        video_url = self._search_regex(r'file: "(.*?)",',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title').replace('LiveLeak.com -', '').strip()
-
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
-            webpage, u'description', fatal=False)
-
-        video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
-            webpage, u'uploader', fatal=False)
-
-        info = {
-            'id':  video_id,
-            'url': video_url,
-            'ext': 'mp4',
+        sources_raw = self._search_regex(
+            r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs')
+        sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
+        sources = json.loads(sources_json)
+
+        formats = [{
+            'format_note': s.get('label'),
+            'url': s['file'],
+        } for s in sources]
+        self._sort_formats(formats)
+
+        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
+        video_description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
+
+        return {
+            'id': video_id,
             'title': video_title,
             'description': video_description,
-            'uploader': video_uploader
+            'uploader': video_uploader,
+            'formats': formats,
         }
-
-        return [info]