#!/usr/bin/perl
use strict;
use warnings;
# Apache logs robots filter-outer
# Author: Gary C. Wang
# Contact: gary@quartertone.net
# Website: www.quartertone.net
# Filename: norobotlog
#
# Usage: norobotlog [logfile_name]
#
# This script parses Apache log files and 
#   filters out entries from IP addresses 
#   that request "robots.txt" file, commonly
#   associated with webcrawlers and site indexers.
# Prior to usage, check regexp to make sure it matches your log format.
# My log format is something like:
#  192.168.0.xx - - [11/Jul/2004:22:25:22 -0400] "GET /robots.txt HTTP/1.0" 200 78

my %robots;
my $ip_ptn = '((\d{1,3}\.){3}\d{1,3})'; # this regexp matches IP addresses
my @file = <>; #file from stdin

# First, find out which IPs are associated with crawlers
foreach (@file) {
	# ----- Adjust this pattern to match your log file -----
	$robots{$1} ++ if m/^$ip_ptn .+?robots\.txt/;
}

# Then weed those out, printing only the ones that do not request robots.txt
foreach (@file) {
	if (m/$ip_ptn /) {
		print if ! defined $robots{$1};
	}
}