fix issue with url encoding anchors

efrat-safanov · May 30, 2012 · 28b8a6a · 28b8a6a
1 parent 531d771
commit 28b8a6a
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/lib/anemone/page.rb b/lib/anemone/page.rb
@@ -62,7 +62,7 @@ def links
       doc.search("//a[@href]").each do |a|
         u = a['href']
         next if u.nil? or u.empty?
-        abs = to_absolute(URI(URI.escape(u))) rescue next
+        abs = to_absolute(u) rescue next
         @links << abs if in_domain?(abs)
       end
       @links.uniq!

diff --git a/spec/page_spec.rb b/spec/page_spec.rb
@@ -126,6 +126,14 @@ module Anemone
       end
     end
 
+    describe "#links" do
+      it "should not convert anchors to %23" do
+        page = @http.fetch_page(FakePage.new('', :body => '<a href="#top">Top</a>').url)
+        page.links.should have(1).link
+        page.links.first.to_s.should == SPEC_DOMAIN
+      end
+    end
+
     it "should detect, store and expose the base url for the page head" do
       base = "#{SPEC_DOMAIN}path/to/base_url/"
       page = @http.fetch_page(FakePage.new('body_test', {:base => base}).url)