searx

commit: 525e5d275c195d26cb9302ceb03f46ffffa6e730
parent: 3d8c9bab9618b4d0cceadfac888af4560f7d3c9b
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Mon,  2 Jan 2017 12:36:50 +0100

Merge pull request #801 from dalf/extract_text

[fix] extract_text: use html.tostring instead html_to_text.
Diffstat:
M
searx/engines/xpath.py
4
+++-

1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
@@ -42,7 +42,9 @@ def extract_text(xpath_results):
         return ''.join(xpath_results)
     else:
         # it's a element
-        return html_to_text(xpath_results.text_content()).strip()
+        text = html.tostring(xpath_results, encoding='unicode', method='text', with_tail=False)
+        text = text.strip().replace('\n', ' ')
+        return ' '.join(text.split())
 
 
 def extract_url(xpath_results, search_url):