One Hat Cyber Team

Your IP: 216.73.216.74
Server IP: 104.21.64.1
Server: Linux vmi2315822.contaboserver.net 5.15.0-134-generic #145-Ubuntu SMP Wed Feb 12 20:08:39 UTC 2025 x86_64
Server Software: LiteSpeed
PHP Version: 8.3.21
Buat File | Buat Folder

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

View File Name : htext

#!/usr/bin/perl

# Extract all plain text from an HTML file

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

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";