diff options
| author | Cqoicebordel <Cqoicebordel@users.noreply.github.com> | 2015-01-25 20:04:44 +0100 |
|---|---|---|
| committer | Cqoicebordel <Cqoicebordel@users.noreply.github.com> | 2015-01-25 20:04:44 +0100 |
| commit | 44c9216c497862293318a48ad5c39f373cee95e6 (patch) | |
| tree | cbd6d639cb4f8c7f209e4c05da0e8dda0d0e74cf /searx | |
| parent | 516ea9b76901532337d1171c6c72bb98dc6d4431 (diff) | |
Sanitize extract_text
Diffstat (limited to 'searx')
| -rw-r--r-- | searx/engines/xpath.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py index 72120304e..1a599dc0a 100644 --- 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): |