traceroute.rb

# Ruby script for parsing traceroute stream to JSON

require 'rubygems'
require 'open3'
require 'json'

#Array of top 25 US sites by Alexa rank (daily visits & pageviews)
destinations = %w{ google.com facebook.com yahoo.com youtube.com amazon.com wikipedia.org twitter.com ebay.com craigslist.org blogspot.com live.com msn.com go.com bing.com aol.com linkedin.com espn.go.com myspace.com cnn.com wordpress.com netflix.com paypal.com imdb.com flickr.com microsoft.com }

traceroutes = Hash.new()

destinations.each do |destination|
  puts "\nTracing: #{destination}"
  cmd_string = "traceroute -m 25 -w 1 #{destination}" #25 hops, 1s timeout
  stdin, stdout, stderr = Open3.popen3(cmd_string)
  hop_count = 1
  hop_array = []
  stdout.each_with_index do |line, index|
    line_parse = line.delete(' ')
    
    if line_parse.include?('***') #If we've received * for all three packets
      hop_array[index]=["#{hop_count}","timeout"]
      p hop_array[index]
      hop_count+=1
    else
      line.strip!
      
      hop_num = line[0...line.index(' ')] #1: hop number
      
      #Only the first line has a hop number
      #If we don't find a digit, the hop is returning from a different ip
      if hop_num =~ /\D/
        hop_count-=1
        hop_num = "#{hop_count}"
        line_parse = line
        hop_count+=1
      else
        line_parse = line[hop_num.size,line.size]
        line_parse.strip!
        hop_count+=1
      end
      
      hostname = line_parse[0...line_parse.index(' ')] #2: hostname
      
      #check for up to two asterisk responses at beginning of line (3 = complete timeout)
      if hostname =="*"
        hostname = line_parse[2...line_parse.index(' ', 2)]
        if hostname =="*"
          hostname = line_parse[4...line_parse.index(' ',4)]
        end
      end
      
      #if hostname contains alphabetical characters
      if hostname =~ /[a-z]/
        #if it also contains periods
        if hostname.include?(".") == true      
          hostname_array = hostname.split(".")
        else
          #not an address (device name on local?)
          hostname_array = [hostname]
        end
      #if we don't find alphabetical characters, we just have an ip
      else 
        hostname_array = [hostname]
      end
      #offset for leading asterisks
      line_parse = line_parse[hostname.size+line_parse.index(hostname),line_parse.size]
      line_parse.strip!
      ip = line_parse[0, line_parse.index(' ')]
      line_parse = line_parse[ip.size, line_parse.size]
      line_parse.strip!
      
      if ip #trim parentheses from ip
        ip.delete!('(')
        ip.delete!(')')
      end 

      line_parse.delete!('ms')
      line_parse.strip!
      time_array = line_parse.split(" ")
      hop_array[index]=[hop_num,hostname_array,ip,time_array]
      p hop_array[index]
    end
    traceroutes[destination]=hop_array
  end
end

json_doc = JSON.generate(traceroutes)
puts "\nJSON:"
puts json_doc

time = Time.now.strftime("%y-%m-%d-%H%M%S")
filename = "json/traceroute_#{time}.json"
File.open(filename,"w") do |tracefile|
  tracefile.puts json_doc
end
puts "\nsaved to #{filename}"