# encoding: UTF-8

class WpTarget < WebSite
  module Malwares
    # Used as cache :
    #   nil => malwares not checked,
    #   [] => no malwares,
    #   otherwise array of malwares url found
    @malwares = nil

    def has_malwares?(malwares_file_path = nil)
      !malwares(malwares_file_path).empty?
    end

    # return array of string (url of malwares found)
    def malwares(malwares_file_path = nil)
      unless @malwares
        malwares_found = []
        malwares_file = Malwares.malwares_file(malwares_file_path)
        index_page_body = Browser.get(@uri.to_s).body

        File.open(malwares_file, 'r') do |file|
          file.readlines.collect do |url|
            chomped_url = url.chomp

            if chomped_url.length > 0
              malwares_found += index_page_body.scan(Malwares.malware_pattern(chomped_url))
            end
          end
        end

        malwares_found.flatten!
        malwares_found.uniq!

        @malwares = malwares_found
      end
      @malwares
    end

    def self.malwares_file(malwares_file_path)
      malwares_file_path || DATA_DIR + '/malwares.txt'
    end

    def self.malware_pattern(url_regex)
      # no need to escape regex here, because malware.txt contains regex
      %r{<(?:script|iframe).* src=(?:"|')(#{url_regex}[^"']*)(?:"|')[^>]*>}i
    end

  end
end