Cleaning Up Bad HTML in Perl

2008_10_24-cleanup.pl

#
# Here is a short way to cleanup bad HTML input and convert to XML with Perl:
#

use HTML::TreeBuilder;
use XML::LibXML;

$html_code = '';

my $builder = HTML::TreeBuilder->new();
$xml_source = $builder->parse($html_code);
$xml_source->elementify();
$xml_source1 = $xml_source->as_XML();

my $parser = XML::LibXML->new();
$parser->recover(1);    
my $doc = $parser->parse_string($xml_source1);
$xml_source2 = $doc->toString();