| Server IP : 80.241.246.6 / Your IP : 216.73.216.129 Web Server : Apache/2.4.25 (Debian) System : Linux kharagauli 4.9.0-19-amd64 #1 SMP Debian 4.9.320-2 (2022-06-30) x86_64 User : www-data ( 33) PHP Version : 7.0.33-0+deb9u12 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority, MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /proc/thread-self/root/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";;