naver-cafe-atom-generator.pl

use strict;
use warnings;
use LWP::UserAgent;
use Config::Pit;
use WWW::Mechanize;
use Web::Scraper;
use URI;
use Data::Dumper;
use XML::Feed;
use DateTime;
use DateTime::Format::MySQL;

my $config = pit_get("www.naver.com", require => {
    id => "your id on example",
    pw => "your pw on example",
});

my $url = "http://nid.naver.com/nidlogin.login";                           
my $mech = WWW::Mechanize->new();                                         
$mech->get($url);                                          
my $res = $mech->submit_form(                              
        form_name => 'frmNIDLogin',
        fields    => { id  => $config->{id}, pw => $config->{pw} },                   
);                                    

my $feed = XML::Feed->new('Atom');
$feed->title("IIJ");
$feed->link("http://cafe.naver.com/itcareer");
$feed->description("");
$feed->author("IIJ Members");
$feed->id("tag:cafe.naver.com:itcareer");
$feed->modified(DateTime::Format::W3CDTF->parse_datetime(DateTime->now( time_zone => 'Asia/Tokyo' ) . '+09:00'));
my $article_id = 18735;
while($article_id++ >= 0) {
  $mech->get(sprintf("http://cafe.naver.com/ArticleRead.nhn?articleid=%s&clubid=11192577", $article_id));
  my $c = scraper {
    process "div[id=\"post_${article_id}\"]>div.inbox>div[class=\"tit-box\"]>div.fl>table>tr>td", title => 'TEXT';
    process "div[id=\"post_${article_id}\"]>div.inbox>div[class=\"tit-box\"]>div.fl>table>tr>td+td+td>a", category => 'TEXT';
    process "div[id=\"post_${article_id}\"]>div.inbox>div[class=\"tit-box\"]>div.fl>table>tr>td+td+td>a", category_link => '@href';
    process "div[id=\"post_${article_id}\"]>div.inbox>div[class=\"tit-box\"]>div.fr", registered_at => 'TEXT';
    process "table>tr>td[class=\"p-nick\"]", author => "TEXT";
    process "div[id=\"tbody\"]", content => "HTML";
  }->scrape($mech->content);
  last unless $c->{title};
  my $row = {
     articleId => $article_id,
     title     => $c->{title},
     category  => $c->{category},
     author    => $c->{author},
     category_link => $c->{category_link},
     registered_at => $c->{registered_at},
     content => $c->{content},
  };
  $row->{registered_at} =~ s/^.\///;
  $row->{registered_at} =~ s/\s+$//;
  my $entry = XML::Feed::Entry->new('Atom');
  my $content = XML::Feed::Content->new({ body => $row->{content} });
  $entry->title($row->{title});
  $entry->link("http://cafe.naver.com/itcareer/$article_id");
  $entry->summary("..");
  $entry->author($row->{author});
  my $date = $row->{registered_at};
  my ($yy, $mm, $dd, $hh, $ii) = $date =~ /^(....)\.(.{1,2})\.(.{1,2}) (..):(..)$/;
  $entry->issued(DateTime::Format::W3CDTF->parse_datetime(DateTime::Format::MySQL->parse_datetime(sprintf("%04d-%02d-%02d %02d:%02d:00", $yy, $mm, $dd, $hh, $ii)) . '+09:00'));
  $entry->content($content);
  $feed->add_entry($entry);
}

open my $fh, ">", "feed.xml";
print $fh $feed->as_xml;
close $fh;