One Hat Cyber Team

Your IP: 216.73.216.93
Server IP: 65.108.141.171
Server: Linux server.heloix.com 5.4.0-214-generic #234-Ubuntu SMP Fri Mar 14 23:50:27 UTC 2025 x86_64
Server Software: Apache
PHP Version: 7.4.33
Buat File | Buat Folder

Dir : ~/usr/share/doc/libhtml-parser-perl/examples/

View File Name : 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";;