searx

commit: ee1ffbc87f0b2471e33b14561002c400cd8db861
parent: 2d42208e835105119db3bddce1efdf7b90757985
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Tue,  4 Mar 2014 14:19:59 +0100

[fix] yahoo engine url extraction

Diffstat:
M
searx/engines/yahoo.py
2
+-
M
searx/engines/yahoo_news.py
2
+-

2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/searx/engines/yahoo.py b/searx/engines/yahoo.py
@@ -35,7 +35,7 @@ def response(resp):
 
     for result in dom.xpath(results_xpath):
         url_string = extract_url(result.xpath(url_xpath), search_url)
-        start = url_string.find('/RU=')+4
+        start = url_string.find('http', url_string.find('/RU=')+1)
         end = url_string.rfind('/RS')
         url = unquote(url_string[start:end])
         title = extract_text(result.xpath(title_xpath)[0])
diff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py
@@ -35,7 +35,7 @@ def response(resp):
 
     for result in dom.xpath(results_xpath):
         url_string = extract_url(result.xpath(url_xpath), search_url)
-        start = url_string.find('/RU=')+4
+        start = url_string.find('http', url_string.find('/RU=')+1)
         end = url_string.rfind('/RS')
         url = unquote(url_string[start:end])
         title = extract_text(result.xpath(title_xpath)[0])