extract-uri.rb

#!/usr/bin/env ruby
#
# Extract URI from an Apache log and generate a
# full URL file (like for exemple load-testing with Siege)
#
# Usage:
# extract-url.rb your.domain.name.com logfile [logfile logfile logfile]
#

targetdomain = ARGV.shift

ARGV.each do |logfile|
  File.foreach(logfile, "rt") do |line|
    matches = /^.*GET\s([^\s]*)\sHTTP\S*\s(\d+)/.match(line)
    unless matches == nil
      puts 'http://'+ targetdomain + matches[1]
    end
  end
end