searx

commit: 90e1db3e5c628ae73800d51b53032064aadbfb44
parent eaa0fb8102825fa4ccdb348429fdbf39837921be
Author: Alexandre Flament <alex@al-f.net>
Date:   Sat, 31 Dec 2016 13:56:09 +0100

[fix] extract_text: use html.tostring instead html_to_text. Fix #711

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):