gistfile1.txt

sub parse_log_line {
    my $log_line = shift;

    my $monthname_numbers = {
        Jan => "01", Feb => "02", Mar => "03", Apr => "04",
        May => "05", Jun => "06", Jul => "07", Aug => "08",
        Sep => "09", Oct => "10", Nov => "11", Dec => "12"
    };

    if ($log_line =~ /^(.*?) - - \[(.*)\]  "(.*)" (\d+) \d+ "(.*)" "(.*)" hostname ".*?"/) {
        my $ip_address   = $1;
        my $date         = $2;
        my $query_string = $3;
        my $status       = $4;
        my $referer      = $5;
        my $useragent    = $6;

        # $date is like "19/Apr/2011:06:54:51 +0000"
        my ($dmy, $hh, $mm) = split /:/, $date;
        my ($dd, $month_name, $yyyy) = split m[/], $dmy;

        my $ymd = join "", ( $yyyy, $monthname_numbers->{ $month_name }, $dd );

        return ( $ip_address, $ymd, $query_string, $status, $referer, $useragent, $hh, $mm );
    }

    return;
}