http://qs321.pair.com?node_id=170090
Category: HTML Utilities
Author/Contact Info moxliukas <moxliukas AT delfi DOT lt>
Description: Well, I'm only a beginner in Perl, but I have whacked up a script that extracts headlines from Slashdot. Yes, it is very probably buggy and definately one can come up with a more elegant solution. It uses standard modules from CPAN, such as LWP::UserAgent, HTTP::Request and HTML::TreeBuilder.
use HTTP::Request;
use LWP::UserAgent;
use HTML::TreeBuilder;

$ua = LWP::UserAgent->new;
$request = HTTP::Request->new(GET => 'http://slashdot.org/');
$resp = $ua->request($request);

$tree = HTML::TreeBuilder->new;
$tree->parse($resp->content);

my @titles;
my @authors;
my @dept;

foreach my $h ($tree->look_down('_tag', 'font', 
    sub {
      return unless ($_[0]->attr('face') and $_[0]->attr('size') and $
+_[0]->attr('color'));
      my @c = $_[0]->content_list;
      return unless ref $c[0];
      my @d = $c[0]->content_list;
      return 1 if not ref $d[0];
      $#c == 0 and $c[0]->tag eq 'b' and $d[0]->tag ne 'map';
    }
  )) {
  push @titles, $h->as_text;
}
foreach my $h ($tree->look_down('_tag', 'b', 
    sub {
      my @c = $_[0]->content_list;
      @c == 3 and ref $c[1] and $c[1]->tag eq 'a' and $c[0] =~ /^Poste
+d by/;
    }
  )) {
  push @authors, $h->as_text;
}
foreach my $h ($tree->look_down('_tag', 'b', 
    sub {
      my @c = $_[0]->content_list;
      @c == 1 and $c[0] =~ /^from the .* dept\.$/;
    }
  )) {
  push @dept, $h->as_text;
}

for($i=0; $i<10; $i++) {
  print "$titles[$i]\n";
  print "$authors[$i]\n";
  print "$dept[$i]\n\n";
}

$tree = $tree->delete;