Replace every bunch of whitespaces with only one space in HTML text

2015-01-30 21:00:49 +01:00 · 2015-01-30 21:00:49 +01:00 · 52a57ee045
commit 52a57ee045
parent a3d444ab85
1 changed files with 2 additions and 0 deletions
--- a/searx/utils.py
+++ b/searx/utils.py
@ -119,6 +119,8 @@ class HTMLTextExtractor(HTMLParser):


 def html_to_text(html):
+    html = html.replace('\n', ' ')
+    html = ' '.join(html.split())
    s = HTMLTextExtractor()
    s.feed(html)
    return s.get_text()