searx

commit: c43476229b58f20dba62c0f623ae2dad96bc8525
parent: 3a8eafcc6b19b4b47b10534fbc683e4e3fbc064d
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Mon, 24 Aug 2015 13:23:13 +0200

Merge pull request #405 from pointhi/bug_fixes

some Bug fixes
Diffstat:
M
searx/__init__.py
2
+-
M
searx/engines/startpage.py
10
+++++++++-
M
searx/search.py
4
++++

3 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/searx/__init__.py b/searx/__init__.py
@@ -40,7 +40,7 @@ else:
 with open(settings_path) as settings_yaml:
     settings = load(settings_yaml)
 
-if settings.get('server', {}).get('debug'):
+if settings.get('general', {}).get('debug'):
     logging.basicConfig(level=logging.DEBUG)
 else:
     logging.basicConfig(level=logging.WARNING)
diff --git a/searx/engines/startpage.py b/searx/engines/startpage.py
@@ -66,7 +66,15 @@ def response(resp):
         url = link.attrib.get('href')
 
         # block google-ad url's
-        if re.match("^http(s|)://www.google.[a-z]+/aclk.*$", url):
+        if re.match("^http(s|)://(www\.)?google\.[a-z]+/aclk.*$", url):
+            continue
+
+        # block startpage search url's
+        if re.match("^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):
+            continue
+
+        # block ixquick search url's
+        if re.match("^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):
             continue
 
         title = escape(extract_text(link))
diff --git a/searx/search.py b/searx/search.py
@@ -206,6 +206,10 @@ 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)
 
     results = sorted(results, key=itemgetter('score'), reverse=True)