#!/usr/bin/perl

    use strict;
    use warnings;

    my %id;
    my $next_id = 10000;

    while (<>) {
        next unless m!^\S+ (\S+) .+ "GET ([^"]+) HTTP/\d\.\d" 200!;
        my ($ip,$path) = ($1,$2);

        study $path;

        # Skip directories
        next if $path =~ /\/$/;  # Directory
        next if $path =~ /\/\?/; # Directory with sort parms

        # Skip certain directories
        next if $path =~ /^\/(icons|misc|ports|src)\//;

        # Skip certain file extensions
        next if $path =~ /\.(rss|html|meta|readme)$/;

        # Skip CPAN & distro maintenance stuff
        next if $path =~ /CHECKSUMS$/;
        next if $path =~ /MIRRORING/;

        # Module list stuff
        next if $path =~ /\Q00whois./;
        next if $path =~ /\Q01mailrc./;
        next if $path =~ /\Q02packages.details/;
        next if $path =~ /\Q03modlist./;

        my $id = ($id{$ip} ||= ++$next_id);

        print "$id $path\n";
    }