| Server IP : 88.99.149.37 / Your IP : 216.73.216.141 Web Server : nginx/1.31.2 System : Linux server-88-99-149-37 6.12.0-124.56.5.el10_1.x86_64 #1 SMP PREEMPT_DYNAMIC Fri May 15 06:12:08 EDT 2026 x86_64 User : muralimurth ( 1015) PHP Version : 8.4.23 Disable Function : exec,system,passthru,shell_exec,proc_close,proc_open,dl,popen,show_source,posix_kill,posix_mkfifo,posix_getpwuid,posix_setpgid,posix_setsid,posix_setuid,posix_setgid,posix_seteuid,posix_setegid,posix_uname MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : ON Directory : /proc/1/root/usr/share/doc/perl-HTML-Parser/eg/ |
Upload File : |
#!/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";