From 37c3ace3096d9568f8dbdc3728659f4c77377b33 Mon Sep 17 00:00:00 2001 From: Adam Tauber Date: Fri, 11 Sep 2015 18:33:06 +0200 Subject: [PATCH] [fix] add missing scheme to duplicated results too ++ revert gigablasts handling --- searx/engines/gigablast.py | 2 -- searx/search.py | 7 ++++--- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/searx/engines/gigablast.py b/searx/engines/gigablast.py index 04513cc9..b852de9b 100644 --- a/searx/engines/gigablast.py +++ b/searx/engines/gigablast.py @@ -53,8 +53,6 @@ def response(resp): # parse results for result in dom.xpath(results_xpath): url = result.xpath(url_xpath)[0].text - if not url.startswith('http://') and not url.startswith('https://'): - url = 'http://' + url title = result.xpath(title_xpath)[0].text content = escape(result.xpath(content_xpath)[0].text) diff --git a/searx/search.py b/searx/search.py index 89917124..f2b5235b 100644 --- a/searx/search.py +++ b/searx/search.py @@ -143,6 +143,10 @@ def score_results(results): res['parsed_url'] = urlparse(res['url']) + # if the result has no scheme, use http as default + if not res['parsed_url'].scheme: + res['parsed_url'] = res['parsed_url']._replace(scheme="http") + res['host'] = res['parsed_url'].netloc if res['host'].startswith('www.'): @@ -206,9 +210,6 @@ def score_results(results): # if there is no duplicate found, append result else: res['score'] = score - # if the result has no scheme, use http as default - if res['parsed_url'].scheme == '': - res['parsed_url'] = res['parsed_url']._replace(scheme="http") results.append(res)