#!/usr/bin/perl

use strict;
use warnings;
use Carp;

use HTML::TreeBuilder;
use HTML::Scrubber;
use Perl6::Slurp;

my $tidy = HTML::TreeBuilder->new();
my $scrubber = HTML::Scrubber->new(
    allow => [ qw[ p em stong a img ] ],
    rules => [
        img => {
            src => 1,
            alt => 1,
            title => 1,
            width => 1,
            height => 1,
        },
        a => {
            href=>1,
            title=>1,
        },
    ],
);
$scrubber->{_p}->empty_element_tags(1);

my $html = slurp $ARGV[0];

$tidy->no_expand_entities(1);
$tidy->p_strict(1);
print $scrubber->scrub($tidy->parse_content($html)->as_XML);