quickNdirty: get a list of all urls with statuscode 404 from apache-format logfiles with the number of occurrence

404grep.rb

#!/usr/bin/ruby

# ruby 404grep.rb /path/to/apache/logfile

require "pp"

LOGFILE = ARGV.join

resH = Hash.new{ |h,k| h[k] = 0 }

all404 = File.readlines(LOGFILE).grep(/404/)

all404.each{ |line|
  url = line.split(" ")[6]
  resH[url] += 1
}

pp resH.sort_by{ |k,v| v }