Perlでスクレイピング Web::Scraper

Web::Scraper - search.cpan.org
use Web::Scraper; - 今日のCPANモジュール（跡地）

Web Scraper Shibuya.pm tech talk #8 from Tatsuhiko Miyagawa

www.slideshare.net

sudo apt-get install libweb-scraper-perl
sudo apt-get install libxml-treepp-perl
sudo apt-get install libxml-feedpp-perl

sudo apt-get install libunicode-japanese-perl

qiita.com

$ sudo apt-get install build-essential cpanminus
$ export PERL5LIB="$HOME/perl5/lib/perl5:$PERL5LIB"
$ export PATH="$HOME/perl5/bin:$PATH"
$ cpanm --installdeps .
$ cpanm Text::Data::Dumper

http://search.cpan.org/~miyagawa/Web-Scraper-0.38/
http://search.cpan.org/~cjm/HTML-Tree-5.909-TRIAL/
http://search.cpan.org/~mirod/HTML-TreeBuilder-XPath-0.14/
http://search.cpan.org/~corion/HTML-Selector-XPath-0.18/
http://search.cpan.org/~mirod/XML-XPathEngine-0.14/
http://search.cpan.org/~neilb/UNIVERSAL-require-0.18/

#!/usr/bin/perl
 
use strict;
use warnings;
use Web::Scraper;
use URI;

my $uri = new URI('http://www.ehime-np.co.jp/news/local/');
 
my $scraper = scraper {
    process '#Contents_L > div > div.news_lists > ul > li > a', 'list[]' => {
        link => '@href',
        title => 'TEXT'
    };
};
 
my $res = $scraper->scrape($uri);


foreach my $list (@{$res->{list}}) {

    print $list->{title},"\n";
    print $list->{link},"\n";

}