detect robots.txt

lib/wpscan/modules/web_site.rb

@@ -126,4 +126,16 @@ module WebSite
     homepage_body = Browser.instance.get(@uri.to_s).body
     homepage_body[%r{<link .* type="application/rss\+xml" .* href="([^"]+)" />}, 1]
   end
+
+  # Checks if a robots.txt file exists
+  def has_robots?
+    Browser.instance.get(robots_url).code == 200
+  end
+
+  # Gets a robots.txt URL
+  def robots_url
+    robots = @uri.clone
+    robots.path = '/robots.txt'
+    robots.to_s
+  end
 end

spec/lib/wpscan/modules/web_site_spec.rb

@@ -178,4 +178,22 @@ shared_examples_for 'WebSite' do
       web_site.rss_url.should === 'http://lamp-wp/wordpress-3.5/?feed=rss2'
     end
   end
-end
+
+  describe '#robots_url' do
+    it 'should return the correct url' do
+      web_site.robots_url.should === 'http://example.localhost/robots.txt'
+    end
+  end
+
+  describe '#has_robots?' do
+    it 'should return true' do
+      stub_request(:get, web_site.robots_url).to_return(status: 200)
+      web_site.has_robots?.should be_true
+    end
+
+    it 'should return false' do
+      stub_request(:get, web_site.robots_url).to_return(status: 404)
+      web_site.has_robots?.should be_false
+    end
+  end
+end

wpscan.rb

@@ -151,6 +151,10 @@ begin
     puts
   end
 
+  if wp_target.has_robots?
+    puts green('[+]') + " robots.txt available under '#{wp_target.robots_url}'"
+  end
+
   if wp_target.has_readme?
     puts red('[!]') + " The WordPress '#{wp_target.readme_url}' file exists"
   end