| Server IP : 49.231.201.246 / Your IP : 216.73.216.149 Web Server : Apache/2.4.18 (Ubuntu) System : Linux 246 4.4.0-210-generic #242-Ubuntu SMP Fri Apr 16 09:57:56 UTC 2021 x86_64 User : root ( 0) PHP Version : 7.0.33-0ubuntu0.16.04.16 Disable Function : exec,passthru,shell_exec,system,proc_open,popen,pcntl_exec MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /usr/share/doc/libhtml-parser-perl/examples/ |
Upload File : |
#!/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";;