gihyo_newbooks_rss.pl

#!/usr/bin/env perl
use strict;
use warnings;
use utf8;
use URI;
use LWP::Simple ();
use XML::Simple;
use Web::Scraper;
use Encode qw/ encode_utf8 /;

my $url = URI->new('http://gihyo.jp/book/feed/rss2');
my $rss = LWP::Simple::get($url);
die "FAIL!!" unless $rss;

my $scraper = scraper {
    process '#publishedDetail div.cover img', 'source' => '@src';
};

my $xml = XML::Simple->new->XMLin($rss);
for my $item (@{ $xml->{channel}->{item} }) {
	warn encode_utf8($item->{title});
	warn encode_utf8($item->{link});
	warn encode_utf8($item->{author});
	warn encode_utf8($item->{pubDate});
	warn encode_utf8($item->{description});

	if ($item->{link}) {
		my $result = eval { $scraper->scrape(URI->new($item->{link})) };
		warn($@) && next if $@;
		if ($result->{source}) {
			warn $result->{source};
			my $thumbnail = LWP::Simple::get(URI->new($result->{source}));
			warn "FAIL!! GETTING THUMBNAIL!!" unless $thumbnail;
			(my $file = $result->{source}) =~ s{^.*/([^/]+)$}{$1};
			warn $file;
			open my $fh, '>', $file or warn($@) && next;
			print $fh $thumbnail;
			close $fh;
		}
	}
}