|
Server IP : 184.107.3.203 / Your IP : 216.73.216.51 Web Server : Apache System : Linux dedicated2.avenfashion.com.ph 4.18.0-553.40.1.el8_10.x86_64 #1 SMP Mon Feb 10 12:11:18 EST 2025 x86_64 User : adminteladeoro ( 1015) PHP Version : 8.2.28 Disable Function : exec,passthru,shell_exec,system MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON Directory (0755) : /usr/share/doc/perl-HTML-Parser/eg/ |
| [ Home ] | [ C0mmand ] | [ 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";;