searx

commit: e061c6e059ab8055f5b95f162d791fa9c9c422d6
parent: c61ea820d2db9bebe82c8e442b0d3558d014e2cc
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Sat, 23 Jan 2016 15:20:36 +0100

[fix] swisscow and yandex escaping - fixes #499

Diffstat:
M
searx/engines/swisscows.py
9
+++++----
M
searx/engines/yandex.py
5
+++--

2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/searx/engines/swisscows.py b/searx/engines/swisscows.py
@@ -10,6 +10,7 @@
  @parse       url, title, content
 """
 
+from cgi import escape
 from json import loads
 from urllib import urlencode, unquote
 import re
@@ -77,7 +78,7 @@ def response(resp):
 
             # append result
             results.append({'url': result['SourceUrl'],
-                            'title': result['Title'],
+                            'title': escape(result['Title']),
                             'content': '',
                             'img_src': img_url,
                             'template': 'images.html'})
@@ -89,8 +90,8 @@ def response(resp):
 
             # append result
             results.append({'url': result_url,
-                            'title': result_title,
-                            'content': result_content})
+                            'title': escape(result_title),
+                            'content': escape(result_content)})
 
     # parse images
     for result in json.get('Images', []):
@@ -99,7 +100,7 @@ def response(resp):
 
         # append result
         results.append({'url': result['SourceUrl'],
-                        'title': result['Title'],
+                        'title': escape(result['Title']),
                         'content': '',
                         'img_src': img_url,
                         'template': 'images.html'})
diff --git a/searx/engines/yandex.py b/searx/engines/yandex.py
@@ -9,6 +9,7 @@
  @parse       url, title, content
 """
 
+from cgi import escape
 from urllib import urlencode
 from lxml import html
 from searx.search import logger
@@ -51,8 +52,8 @@ def response(resp):
     for result in dom.xpath(results_xpath):
         try:
             res = {'url': result.xpath(url_xpath)[0],
-                   'title': ''.join(result.xpath(title_xpath)),
-                   'content': ''.join(result.xpath(content_xpath))}
+                   'title': escape(''.join(result.xpath(title_xpath))),
+                   'content': escape(''.join(result.xpath(content_xpath)))}
         except:
             logger.exception('yandex parse crash')
             continue