| Server IP : 104.21.38.3 / Your IP : 172.69.176.32 Web Server : Apache System : Linux krdc-ubuntu-s-2vcpu-4gb-amd-blr1-01.localdomain 5.15.0-142-generic #152-Ubuntu SMP Mon May 19 10:54:31 UTC 2025 x86_64 User : www ( 1000) PHP Version : 7.4.33 Disable Function : passthru,exec,system,putenv,chroot,chgrp,chown,shell_exec,popen,proc_open,pcntl_exec,ini_alter,ini_restore,dl,openlog,syslog,readlink,symlink,popepassthru,pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,imap_open,apache_setenv MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : ON Directory : /usr/share/doc/libhtml-parser-perl/examples/ |
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";