0xV3NOMx
Linux ip-172-26-7-228 5.4.0-1103-aws #111~18.04.1-Ubuntu SMP Tue May 23 20:04:10 UTC 2023 x86_64

Your IP : 3.140.188.195

Current Path : /proc/thread-self/root/usr/share/doc/libhtml-parser-perl/examples/
Upload File :
Current File : //proc/thread-self/root/usr/share/doc/libhtml-parser-perl/examples/htext

#!/usr/bin/perl -w

# Extract all plain text from an HTML file

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

my %inside;

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

sub text
{
    return if $inside{script} || $inside{style};
    print encode('utf8',$_[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";;