youtube-dl

commit: 78fb87b2837e15124b5855734a951598dfe025fe
parent ab2d524780736249c8988313db021e83642c24d1
Author: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date:   Fri, 15 Nov 2013 12:54:13 +0100

Don't accept '>' inside the content attribute in OpenGraph regexes

Diffstat:
M
youtube_dl/extractor/common.py
8
+++++---

1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -316,10 +316,12 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        esc_prop = re.escape(prop)
+        content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+        property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop)
+        template = r'<meta[^>]+?%s[^>]+?%s'
         return [
-            r'<meta[^>]+?property=[\'"]og:%s[\'"][^>]+?content=(?:"(.+?)"|\'(.+?)\')' % esc_prop,
-            r'<meta[^>]+?content=(?:"(.+?)"|\'(.+?)\')[^>]+?property=[\'"]og:%s[\'"]' % esc_prop,
+            template % (property_re, content_re),
+            template % (content_re, property_re),
         ]
 
     def _og_search_property(self, prop, html, name=None, **kargs):