weekly_hits2.pl

#!/usr/bin/env perl

use strict;
use warnings;
use Syntax::Construct qw<
  operator-double-diamond
  regex-named-capture-group
>;
use Regexp::Log::Common;
use Date::WeekNumber 'iso_week_number';
use List::Util 1.33 'any';
use Number::Format 'format_number';

my $parser = Regexp::Log::Common->new(
    format  => ':extended',
    capture => [qw<req ts status>],
);
my @fields      = $parser->capture;
my $compiled_re = $parser->regexp;

my @skip_uri_patterns = qw<
  ^/+robots\.txt
  [-\w]*sitemap[-\w]*\.xml
  ^/+wp-
  /feed/?$
  ^/+\?rest_route=
>;

my %month = (
    Jan => '01', Feb => '02', Mar => '03', Apr => '04',
    May => '05', Jun => '06', Jul => '07', Aug => '08',
    Sep => '09', Oct => '10', Nov => '11', Dec => '12',
);

my ( %count, %week_of );
while (<<>>) {
    my %log;
    @log{@fields} = /$compiled_re/;

    # only interested in successful or cached requests
    next unless $log{status} =~ /^2/ or $log{status} == 304;

    my ( $method, $uri, $protocol ) = split ' ', $log{req};
    next unless $method eq 'GET';
    next if any { $uri =~ $_ } @skip_uri_patterns;

    # convert log timestamp to YYYY-MM-DD for Date::WeekNumber
    $log{ts} =~ m!^ (?<day>\d\d) / (?<month>...) / (?<year>\d{4}) : !x;
    my $date = "$+{year}-$month{ $+{month} }-$+{day}";

    my $week = iso_week_number($date);
    $week_of{$week} ||= $date;
    $count{$week}++;
}

printf "Week of %s: % 10s\n", $week_of{$_}, format_number( $count{$_} )
  for sort keys %count;