club-citta-info.pl

#!/usr/bin/perl

use strict;
use warnings;
use Web::Scraper;
use URI;
use YAML;
use DateTime;
use DateTime::Format::W3CDTF;
use Encode;

my $uri = URI->new('http://www.clubcitta.co.jp/information.html');

my $s = scraper {
    process 'div.information', 'entry[]' => scraper {
        process '.information', id    => '@id';
        process '.date',        date  => 'TEXT';
        process '.title',       title => 'TEXT';
        process '.comment',     body  => 'TEXT';
    };
};

my $feed = $s->scrape($uri);

my $w3c = DateTime::Format::W3CDTF->new;

my $prev_month    = 0;
my $subtract_year = 0;
for my $entry ( @{ $feed->{entry} } ) {
    my ( $month, $day ) = ( $entry->{date} =~ m!(\d+)/(\d+)! );

    my $dt = DateTime->now;
    $dt->set_month($month);
    $dt->set_day($day);
    $dt->set_hour(0);
    $dt->set_minute(0);
    $dt->set_second(0);

    if ( $prev_month > $month or $subtract_year) {
        $subtract_year = 1;
        $dt->subtract( years => 1 );
    }

    $entry->{date} = $w3c->format_datetime($dt);

    $entry->{link} = $uri->as_string . "#$entry->{id}";
}

$feed->{link}  = $uri->as_string;
$feed->{title} = Encode::decode('utf8', 'クラブチッタ 最新情報');

print Dump $feed;