use strict;
use HTML::TokeParser::Simple;

if($#ARGV < 0){
    die "You did not specify any files to process! : $@\n";
}

foreach my $infname (@ARGV)
{
    my $outfname = $infname.".txt";
    
    my $inputtxt = HTML::TokeParser::Simple->new($infname);
    my $outputtxt = "";

    #this section removes the code   
    while(my $token = $inputtxt->get_token){
        next unless $token->is_text;
        $outputtxt.= $token->as_is;
    }
    
    #this section removes whitespace
    $outputtxt =~ s/&nbsp;/ /g;  #HTML special space char
    $outputtxt =~ s/\s\s\s//mg;  #tabs (mostly) and newlines
    
    open (OUTPUT, ">>$outfname") or die "$outfname could not be opened
+.: $@ *_* $!\n";
 
    print OUTPUT $outputtxt;

    close $infname;
    close $outfname;
}
[download]