use HTML::Parser;
use Text::Wrap;

sub html2text {
    my $html = shift;
    my %inside;
    my $text = '';
    my $tag = sub { $inside{$_[0]} += $_[1]; $text .= " " };
    my $txt = sub { $text .= $_[0] unless $inside{script} or $inside{style} };
    HTML::Parser->new(  api_version => 3,
                        handlers => [ start => [$tag, "tagname, '+1'"],
                                      end   => [$tag, "tagname, '-1'"],
                                      text  => [$txt, "dtext"] ],
                        marked_sections => 1,
    )->parse($html);
    #$text =~ tr/\11\12\40-\176//cd; # remove wide non ascii chars
    $text = Text::Wrap::fill('', '', $text);
    $text =~ s/^\s+//;
    return $text;
}