system: Linux mars.sprixweb.com 3.10.0-1160.119.1.el7.x86_64 #1 SMP Tue Jun 4 14:43:51 UTC 2024 x86_64

cmd: 

#!/usr/bin/perl -w

# Extract all plain text from an HTML file

use strict;
use HTML::Parser 3.00 ();

my %inside;

sub tag
{
   my($tag, $num) = @_;
   $inside{$tag} += $num;
   print " ";  # not for all tags
}

sub text
{
    return if $inside{script} || $inside{style};
    print $_[0];
}

HTML::Parser->new(api_version => 3,
		  handlers    => [start => [\&tag, "tagname, '+1'"],
				  end   => [\&tag, "tagname, '-1'"],
				  text  => [\&text, "dtext"],
				 ],
		  marked_sections => 1,
	)->parse_file(shift) || die "Can't open file: $!\n";;