#!/usr/bin/perl

use strict;
use warnings;

use HTML::Parser ();

my $htmltree = [ { tag => 'document', content => [] } ];
my $node = $htmltree->[0]->{content};
my @prevnodes = ($htmltree);

sub start {
  my $tagname = shift;
  my $attr = shift;
  my $newnode = {};

  $newnode->{tag} = $tagname;
  foreach my $key(keys %{$attr}) {
    $newnode->{$key} = $attr->{$key};
  }
  $newnode->{content} = [];
  push @prevnodes, $node;
  push @{$node}, $newnode;
  $node = $newnode->{content};
}

sub end {
  my $tagname = shift;

  $node = pop @prevnodes;
}

sub text {
  my $text = shift;

  chomp $text;
  if($text ne '') {
    push @{$node}, $text;
  }
}

my $p = HTML::Parser->new( api_version => 3,
                           start_h => [\&start, "tagname, attr"],
                           end_h   => [\&end,   "tagname"],
                           text_h  => [\&text,  "dtext"] );

$p->parse_file("test.html");