web-scraper-blahblah.pl

use LWP::UserAgent;
use Web::Scraper;

my $ua = LWP::UserAgent->new( agent => 'Dummy Lee Jongs' );
my $res = $ua->get('http://....');
die "WTF?" unless $res->is_success;

my $scraper = scraper {
   process 'div[id="blahblah"]>table+table>tr>td>table', 'item' => scraper {
     process 'tr>td>table>tr>td+td', 'title' => [ 'TEXT', sub { s/yongbinize/saillinuxize/; $_ } ];
     process 'tr:nth-child(3)>td>table>tr>td+td', 'qty' => 'TEXT';
     process 'tr:nth-child(5)>td>table>tr+tr>td+td', 'detail' => [ 'HTML', 'STRIP' ];
     process 'tr:nth-child(5)>td>table>tr:nth-child(3)>td+td', 'comment' => [ 'HTML', 'STRIP' ];
     process 'tr:nth-child(5)>td>table>tr:nth-child(4)>td+td', 'question' => [ 'HTML', 'STRIP' ];
     process 'tr:nth-child(5)>td>table>tr:nth-child(5)>td+td', 'address' => 'TEXT';
     process 'tr:nth-child(5)>td>table>tr:nth-child(6)>td+td', 'limit_date' => 'TEXT';
     process 'tr:nth-child(5)>td>table>tr:nth-child(6)>td:nth-child(4)', 'deliv_date' => 'TEXT';
     process 'tr:nth-child(5)>td>table>tr:nth-child(7)>td+td', 'budget' => 'TEXT';
     process 'tr:nth-child(7)>td>table>tr+tr>td+td', 'company_detail' => [ 'HTML', 'STRIP' ];
   };
   result 'item';
}->scrape($res->content);

do_something($scraper);

sub do_something { ...; }

package Web::Scraper::Filter::STRIP;
use base qw( Web::Scraper::Filter );

sub filter {
  my ($self, $val) = @_;
  ...;
}