| Server IP : 35.154.56.2 / Your IP : 216.73.217.116 Web Server : Apache/2.4.58 (Ubuntu) System : Linux ip-172-31-0-189 6.8.0-1029-aws #31-Ubuntu SMP Wed Apr 23 18:20:04 UTC 2025 aarch64 User : ubuntu ( 1000) PHP Version : 8.3.6 Disable Function : NONE MySQL : OFF | cURL : OFF | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : OFF 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";