[fix] yahoo engine url extraction

10 years ago · ee1ffbc87f
parent 2d42208e83
commit ee1ffbc87f
2 changed files with 2 additions and 2 deletions
--- 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])
--- 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])