Browse Source

Fix detection of the webpage charset if it's declared using ' instead of "

Like in "<meta charset='utf-8'/>"
Jaime Marquínez Ferrándiz 12 years ago
parent
commit
0d75ae2ce3
1 changed files with 1 additions and 1 deletions
  1. 1 1
      youtube_dl/extractor/common.py

+ 1 - 1
youtube_dl/extractor/common.py

@@ -150,7 +150,7 @@ class InfoExtractor(object):
         if m:
         if m:
             encoding = m.group(1)
             encoding = m.group(1)
         else:
         else:
-            m = re.search(br'<meta[^>]+charset="?([^"]+)[ /">]',
+            m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
                           webpage_bytes[:1024])
                           webpage_bytes[:1024])
             if m:
             if m:
                 encoding = m.group(1).decode('ascii')
                 encoding = m.group(1).decode('ascii')