| Server IP : 188.40.95.74 / Your IP : 216.73.216.205 Web Server : Apache System : Linux cp01.striminghost.net 3.10.0-1160.119.1.el7.tuxcare.els13.x86_64 #1 SMP Fri Nov 22 06:29:45 UTC 2024 x86_64 User : vlasotin ( 1054) PHP Version : 5.6.40 Disable Function : NONE MySQL : ON | 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";;