fix issue #265 - remove base64 images before passive detection

lib/common/collections/wp_items/detectable.rb

@@ -73,6 +73,8 @@ class WpItems < Array
     def passive_detection(wp_target, options = {})
       results  = new(wp_target)
       body     = Browser.get(wp_target.url).body
+      # improves speed
+      body     = remove_base64_images_from_html(body)
       names    = body.scan(passive_detection_pattern(wp_target))
 
       names.flatten.uniq.each { |name| results.add(name) }

lib/common/common_helper.rb

@@ -149,3 +149,10 @@ def get_equal_string_end(stringarray = [''])
   end
   already_found
 end
+
+def remove_base64_images_from_html(html)
+  # remove data:image/png;base64, images
+  base64regex = %r{(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?}
+  imageregex = %r{data\s*:\s*image/[^\s;]+\s*;\s*base64\s*,\s*}
+  html.gsub(/["']\s*#{imageregex}#{base64regex}\s*["']/, '""')
+end