Presidium Podium

Right here:

#!/usr/bin/perl

##
# Simple Apache access log parser that yields useful statistics.
# Designed to serve basic web analysis needs.
#
# Alex Balashov 

use strict;
use warnings;

## GLOBALS ##
my      @hits = ();
#############

# Preload.

while() {
        chomp;

        if(/^([0-9.]+)\s+\-\s+\-\s+\[(.[^]]*)\]\s+\”(.[^”]*)\”\s+[0-9]+\s+[0-9]+
\s+\”(.[^”]+)\”/o) {
                push(@hits,
                        {
                                ‘ip_addr’ => $1,
                                ‘date’ => $2,
                                ‘request’ => $3,
                                ‘referrer’ => $4
                        });
        }
}

# Generate reports.

print “Access log report: \n\n”;

print “Top 20 IP addresses:\n” .
      “——————-\n\n”;

&sorted_report(’ip_addr’, 20);

print “\nTop 50 requests: \n” .
      “—————\n\n”;

&sorted_report(’request’, 50);

print “\nTop 50 referrers: \n” .
      “——————\n\n”;

&sorted_report(’referrer’, 50);

# Generate function to hash out unique requests and sort by a certain
# hashed criterion.

sub     sorted_report {
        my      ($key, $limit) = @_;
        my      %unique_tokens = ();

        foreach(@hits) {
                $unique_tokens{$_->{$key}} = 0 unless
                        exists ($unique_tokens{$_->{$key}});

                $unique_tokens{$_->{$key}} ++;
        }

        foreach(sort { $unique_tokens{$b} <=>
                        $unique_tokens{$a}
                     } keys %unique_tokens) {
                $limit — unless $limit == 0;

                printf ”  %-50s %d\n”, $_, $unique_tokens{$_};

                last if $limit == 0;
        }
}

Tells me everything I need to know. Try it yourself:

   cat access.log | perl analyse.pl

This entry was posted on Friday, April 11th, 2008 at 6:16 pm and is filed under Development, Perl, Tips. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.