# ... snippet ...
# tags to ignore
my @ignore_tags = qw(font big small body dir html);

# teags to drop with content
@ignore_elements = qw(script style head);


##########################################################
sub clean_up_htmltree {
##########################################################

  my $input = shift;
  my $warn = 0; 
  my $htmlex; 
  use HTML::TreeBuilder;

  my $h = HTML::TreeBuilder->new;
  $h->ignore_unknown(0);
  $h->warn($warn);
  $h->parse($input);

  foreach (@ignore_tags) {
    $htmlex = 1, next if lc($_) eq "html"; # remove <html>...</html>?
    while (my $ok = $h->look_down('_tag', "$_")) { 
      $ok->replace_with_content; 
    }
  }
  foreach (@ignore_elements) {
    while (my $ok = $h->look_down('_tag', "$_")) { 
      $ok->detach; 
    }
  }

  my $output = $h->as_HTML(undef, " ", {}); # entities to encode, indent, optional endtags
  $h = $h->delete(); # nuke it!
  if ($htmlex) {
    $output =~ s:^\s*<html>::m;
    $output =~ s:</html>\s*$::m;
  }
  return $output;
}