| Server IP : 104.21.4.30 / Your IP : 104.23.197.86 Web Server : Apache System : Linux keen-cori.18-142-40-148.plesk.page 5.15.0-1084-aws #91~20.04.1-Ubuntu SMP Fri May 2 06:59:36 UTC 2025 x86_64 User : simottodesign.com_2tntp341vs7 ( 10011) PHP Version : 8.3.31 Disable Function : opcache_get_status 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";;