searx

commit: 44c9216c497862293318a48ad5c39f373cee95e6
parent 516ea9b76901532337d1171c6c72bb98dc6d4431
Author: Cqoicebordel <Cqoicebordel@users.noreply.github.com>
Date:   Sun, 25 Jan 2015 20:04:44 +0100

Sanitize extract_text

Diffstat:
M
searx/engines/xpath.py
4
++--

1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
@@ -28,13 +28,13 @@ def extract_text(xpath_results):
         result = ''
         for e in xpath_results:
             result = result + extract_text(e)
-        return result
+        return result.strip()
     elif type(xpath_results) in [_ElementStringResult, _ElementUnicodeResult]:
         # it's a string
         return ''.join(xpath_results)
     else:
         # it's a element
-        return html_to_text(xpath_results.text_content())
+        return html_to_text(xpath_results.text_content()).strip()
 
 
 def extract_url(xpath_results, search_url):