use HTML::HTML5::Parser;

my $parser = HTML::HTML5::Parser->new;
my $doc    = $parser->parse_string(<<'EOT');
<?xml version="1.0" encoding="UTF-8"?>
<title>Foo</title>
<p><b><i>Foo</b> bar</i>.
<p>Baz</br>Quux.
EOT
print $doc->textContent;