Contents

require 'timeout'
require 'net/http'
require 'nokogiri'

module Impressionist
  module Bots
    LIST_URL = "http://www.user-agents.org/allagents.xml"
    def self.consume
      Timeout.timeout(4) do
        response = Net::HTTP.get(URI.parse(LIST_URL))
        doc = Nokogiri::XML(response)
        list = []
        doc.xpath('//user-agent').each do |agent|
          type = agent.xpath("Type").text
          list << agent.xpath("String").text.gsub("&lt;","<") if ["R","S"].include?(type) #gsub hack for badly formatted data
        end
        list
      end
    end
  end
end

Version data entries

9 entries across 9 versions & 3 rubygems

Version	Path
impressionist-cody-2.0.0	lib/impressionist/bots.rb
impressionist-2.0.0	lib/impressionist/bots.rb
impressionist-1.6.1	lib/impressionist/bots.rb
impressionist-1.6.0	lib/impressionist/bots.rb
impressionist-1.5.2	lib/impressionist/bots.rb
impressionist2-1.5.5	lib/impressionist/bots.rb
impressionist2-1.5.4	lib/impressionist/bots.rb
impressionist2-1.5.3	lib/impressionist/bots.rb
impressionist2-1.5.1	lib/impressionist/bots.rb