use HTML::Parser 3;
use LWP::Simple;
my $html = get("http://perlmonks.org");
print body_text($html);


sub body_text {
    my $content = $_[0] || return 'EMPTY BODY';

    # HTML::Parser is broken on Javascript and styles 
    # (well it leaves it in the text) so we 'fix' it....

    my $p = HTML::Parser->new( 
        start_h => [ sub{ $_[0]->{text}.=' '; $_[0]->{skip}++ if $_[1] eq 'script' or $_[1] eq 'style'; } , 'self,tag' ],
        end_h   => [ sub{ $_[0]->{skip}-- if $_[1] eq '/script' or $_[1] eq '/style'; } , 'self,tag' ], 
        text_h  => [ sub{ $_[0]->{text}.=$_[1] unless $_[0]->{skip}}, 'self,dtext' ]
        )->parse($content);
    
    $p->eof();
    my $text = $p->{text};
    
    # remove escapes
    $text =~ s/ / /gi;
    $text =~ s/&[^;]+;/ /g;

    # remove non ASCII printable chars, leaves punctuation stuff
    $text =~ s/[^\040-\177]+/ /g;

    # remove any < or > in case parser choked - rare but happens
    $text =~ s/[<>]/ /g;

    # crunch whitespace
    $text =~ s/\s{2,}/ /g;
    $text =~ s/^\s+//g;

  return $text;
}