Add parsers

git-svn-id: file:///home/svn/framework3/trunk@9441 4d416f70-5f16-0410-b530-b9f4589650da

data/msfcrawler/frames.rb

@@ -0,0 +1,41 @@
+
+##
+# This file is part of the Metasploit Framework and may be subject to
+# redistribution and commercial restrictions. Please see the Metasploit
+# Framework web site for more information on licensing and terms of use.
+# http://metasploit.com/framework/
+##
+
+
+require 'rubygems'
+require 'pathname'
+require 'hpricot'
+require 'uri'
+
+class CrawlerFrames < BaseParser
+
+	def parse(request,result)
+
+		if !result['Content-Type'].include? "text/html"
+			return
+		end
+
+		doc = Hpricot(result.body.to_s)
+		doc.search('iframe').each do |ifra|
+
+		ir = ifra.attributes['src']
+
+		if ir and !ir.match(/^(\#|javascript\:)/)
+			begin
+				hreq = urltohash('GET',ir,request['uri'],nil)
+
+				insertnewpath(hreq)
+
+			rescue URI::InvalidURIError
+				#puts "Error"
+			end
+		end
+		end
+	end
+end
+

data/msfcrawler/image.rb

@@ -0,0 +1,43 @@
+
+##
+# This file is part of the Metasploit Framework and may be subject to
+# redistribution and commercial restrictions. Please see the Metasploit
+# Framework web site for more information on licensing and terms of use.
+# http://metasploit.com/framework/
+##
+
+# $Revision: 9212 $
+
+require 'rubygems'
+require 'pathname'
+require 'hpricot'
+require 'uri'
+
+class CrawlerImage < BaseParser
+
+	def parse(request,result)
+
+		if !result['Content-Type'].include? "text/html"
+			return
+		end
+
+		doc = Hpricot(result.body.to_s)
+		doc.search('img').each do |i|
+
+		im = i.attributes['src']
+
+		if im and !im.match(/^(\#|javascript\:)/)
+			begin
+				hreq = urltohash('GET',im,request['uri'],nil)
+
+				insertnewpath(hreq)
+
+			rescue URI::InvalidURIError
+				#puts "Parse error"
+				#puts "Error: #{i[0]}"
+			end
+		end
+		end
+	end
+end
+

data/msfcrawler/link.rb

@@ -0,0 +1,43 @@
+
+##
+# This file is part of the Metasploit Framework and may be subject to
+# redistribution and commercial restrictions. Please see the Metasploit
+# Framework web site for more information on licensing and terms of use.
+# http://metasploit.com/framework/
+##
+
+# $Revision: 9212 $
+
+require 'rubygems'
+require 'pathname'
+require 'hpricot'
+require 'uri'
+
+class CrawlerLink < BaseParser
+
+	def parse(request,result)
+
+		if !result['Content-Type'].include? "text/html"
+			return
+		end
+
+		doc = Hpricot(result.body.to_s)
+		doc.search('link').each do |link|
+
+		hr = link.attributes['href']
+
+		if hr and !hr.match(/^(\#|javascript\:)/)
+			begin
+				hreq = urltohash('GET',hr,request['uri'],nil)
+
+				insertnewpath(hreq)
+
+			rescue URI::InvalidURIError
+				#puts "Parse error"
+				#puts "Error: #{link[0]}"
+			end
+		end
+		end
+	end
+end
+