| Server IP : 77.68.64.21 / Your IP : 216.73.217.59 Web Server : Apache System : Linux hp3-wp-1011352.hostingp3.local 3.10.0-1160.144.1.el7.tuxcare.els9.x86_64 #1 SMP Fri Jul 10 17:06:31 UTC 2026 x86_64 User : csh2516497 ( 2094697) PHP Version : 8.3.30 Disable Function : shell_exec,exec,system,popen,set_time_limit MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /usr/share/doc/perl-HTML-Parser-3.71/eg/ |
Upload File : |
#!/usr/bin/perl -w
# Extract all plain text from an HTML file
use strict;
use HTML::Parser 3.00 ();
my %inside;
sub tag
{
my($tag, $num) = @_;
$inside{$tag} += $num;
print " "; # not for all tags
}
sub text
{
return if $inside{script} || $inside{style};
print $_[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";;