[generic] Do not fetch XML URLs (Fixes #2162)
authorPhilipp Hagemeister <phihag@phihag.de>
Fri, 17 Jan 2014 01:13:00 +0000 (02:13 +0100)
committerPhilipp Hagemeister <phihag@phihag.de>
Fri, 17 Jan 2014 01:13:00 +0000 (02:13 +0100)
youtube_dl/extractor/generic.py

index a9023f38d3b1ecd04aff4032fa6ceade7e7575b5..839530982e7db4704ece2a589420ab4ecfc31c66 100644 (file)
@@ -328,7 +328,7 @@ class GenericIE(InfoExtractor):
             mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
         if mobj is None:
             # Broaden the search a little bit: JWPlayer JS loader
-            mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"]*)', webpage)
+            mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
         if mobj is None:
             # Try to find twitter cards info
             mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)