Merge pull request #97 from pointhi/https

Implementing https rewrite support

1 files changed, 78 insertions, 0 deletions

diff --git a/searx/https_rules/GoogleMainSearch.xml b/searx/https_rules/GoogleMainSearch.xml
new file mode 100644
index 000000000..df504d90c
--- /dev/null
+++ b/searx/https_rules/GoogleMainSearch.xml
@@ -0,0 +1,78 @@
+<ruleset name="Search www.google.com">
+
+<!-- 
+Enabling this ruleset should cause searches to go to
+https://www.google.com rather than https://encrypted.google.com.  Note that
+the filename is important; it must be before GoogleSearch.xml in a bash
+expansion of src/chrome/content/rules/*.xml in order to take precedence. 
+-->
+
+  <target host="*.google.com" />
+  <target host="google.com" />
+  <target host="www.google.com.*" />
+  <target host="google.com.*" />
+  <target host="www.google.co.*" />
+  <target host="google.co.*" />
+  <target host="www.google.*" />
+  <target host="google.*" />
+  <!-- beyond clients1 these do not currently exist in the ccTLDs,
+       but just in case... -->
+  <target host="clients1.google.com.*" />
+  <target host="clients2.google.com.*" />
+  <target host="clients3.google.com.*" />
+  <target host="clients4.google.com.*" />
+  <target host="clients5.google.com.*" />
+  <target host="clients6.google.com.*" />
+  <target host="clients1.google.co.*" />
+  <target host="clients2.google.co.*" />
+  <target host="clients3.google.co.*" />
+  <target host="clients4.google.co.*" />
+  <target host="clients5.google.co.*" />
+  <target host="clients6.google.co.*" />
+  <target host="clients1.google.*" />
+  <target host="clients2.google.*" />
+  <target host="clients3.google.*" />
+  <target host="clients4.google.*" />
+  <target host="clients5.google.*" />
+  <target host="clients6.google.*" />
+
+  <rule from="^http://www\.google\.com/$"
+          to="https://www.google.com/"/>
+
+  <!-- The most basic case. -->
+
+  <rule from="^http://(?:www\.)?google\.com/search"
+          to="https://www.google.com/search"/>
+
+  <!-- A very annoying exception that we seem to need for the basic case -->
+
+  <exclusion pattern="^http://(?:www\.)?google\.com/search.*tbs=shop" />
+  <exclusion pattern="^http://clients[0-9]\.google\.com/.*client=products.*" />
+  <exclusion pattern="^http://suggestqueries\.google\.com/.*client=.*" />
+
+  <!-- https://trac.torproject.org/projects/tor/ticket/9713 -->
+
+  <exclusion pattern="^http://clients[0-9]\.google\.com/ocsp" />
+
+  <!-- This is necessary for image results links from web search results -->
+
+  <exclusion pattern="^http://(?:www\.)?google\.com/search.*tbm=isch.*" />
+
+  <rule from="^http://(?:www\.)?google\.com/webhp"
+          to="https://www.google.com/webhp"/>
+
+  <rule from="^http://(?:www\.)?google\.com/#"
+          to="https://www.google.com/#"/>
+
+  <rule from="^http://(?:www\.)?google\.com/$"
+          to="https://www.google.com/"/>
+
+   <!-- Completion urls look like this:
+
+http://clients2.google.co.jp/complete/search?hl=ja&client=hp&expIds=17259,24660,24729,24745&q=m&cp=1 HTTP/1.1\r\n
+
+   -->
+  <rule from="^http://clients[0-9]\.google\.com/complete/search"
+          to="https://clients1.google.com/complete/search"/>
+
+</ruleset>