added Anemone path extractors

lib/anemone/extractors/anchors.rb

@@ -0,0 +1,7 @@
+class Anemone::Extractors::Anchors < Anemone::Extractors::Base
+
+    def run
+        doc.search( '//a[@href]' ).map { |a| a['href'] }
+    end
+
+end

lib/anemone/extractors/dirbuster.rb

@@ -0,0 +1,12 @@
+class Anemone::Extractors::Dirbuster < Anemone::Extractors::Base
+
+	def run
+		return [] if page.code.to_i != 200
+
+		@@dirs ||= nil
+
+		return @@dirs if @@dirs
+		@@dirs = IO.read( File.dirname( __FILE__ ) + '/dirbuster/directories' ).split( "\n" )
+	end
+
+end

lib/anemone/extractors/dirbuster/directories

@@ -0,0 +1,10 @@
+test/
+tmp/
+stuff/
+awstats/
+awstats/awstats/
+basilic/
+cacti/
+docs/text/manual.txt
+docs/CHANGELOG
+docs/html/php_script_server.html

lib/anemone/extractors/forms.rb

@@ -0,0 +1,7 @@
+class Anemone::Extractors::Forms < Anemone::Extractors::Base
+
+    def run
+        doc.search( '//form[@action]' ).map { |a| a['action'] }
+    end
+
+end

lib/anemone/extractors/frames.rb

@@ -0,0 +1,7 @@
+class Anemone::Extractors::Frames < Anemone::Extractors::Base
+
+    def run
+        doc.css( 'frame', 'iframe' ).map { |a| a.attributes['src'].content rescue next }
+    end
+
+end

lib/anemone/extractors/generic.rb

@@ -0,0 +1,50 @@
+require 'uri'
+
+class Anemone::Extractors::Generic < Anemone::Extractors::Base
+
+	def run
+        URI.extract( doc.to_s, %w(http https) ).map do |u|
+            #
+            # This extractor needs to be a tiny bit intelligent because
+            # due to its generic nature it'll inevitably match some garbage.
+            #
+            # For example, if some JS code contains:
+            #
+            #    var = 'http://blah.com?id=1'
+            #
+            # or
+            #
+            #    var = { 'http://blah.com?id=1', 1 }
+            #
+            #
+            # The URI.extract call will match:
+            #
+            #    http://blah.com?id=1'
+            #
+            # and
+            #
+            #    http://blah.com?id=1',
+            #
+            # respectively.
+            #
+            if !includes_quotes?( u )
+                u
+            else
+                if html.include?( "'#{u}" )
+                    u.split( '\'' ).first
+                elsif html.include?( "\"#{u}" )
+                    u.split( '"' ).first
+                else
+                    u
+                end
+            end
+        end
+    rescue
+        []
+    end
+
+    def includes_quotes?( url )
+        url.include?( '\'' ) || url.include?( '"' )
+    end
+
+end

lib/anemone/extractors/links.rb

@@ -0,0 +1,7 @@
+class Anemone::Extractors::Links < Anemone::Extractors::Base
+
+    def run
+        doc.search( "//link[@href]" ).map { |a| a['href'] }
+    end
+
+end

lib/anemone/extractors/meta_refresh.rb

@@ -0,0 +1,24 @@
+class Anemone::Extractors::MetaRefresh < Anemone::Extractors::Base
+
+    def run
+        doc.search( "//meta[@http-equiv='refresh']" ).map do |url|
+            begin
+                _, url = url['content'].split( ';', 2 )
+                next if !url
+                unquote( url.split( '=', 2 ).last )
+            rescue
+                next
+            end
+        end
+    rescue
+        nil
+    end
+
+    def unquote( str )
+        [ '\'', '"' ].each do |q|
+            return str[1...-1] if str.start_with?( q ) && str.end_with?( q )
+        end
+        str
+    end
+
+end

lib/anemone/extractors/scripts.rb

@@ -0,0 +1,7 @@
+class Anemone::Extractors::Scripts < Anemone::Extractors::Base
+
+    def run
+        doc.search( '//script[@src]' ).map { |a| a['src'] }
+    end
+
+end