| Server IP : 101.53.144.229 / Your IP : 216.73.216.104 Web Server : Apache System : Linux host.gdigitalindia.in 3.10.0-1160.119.1.el7.x86_64 #1 SMP Tue Jun 4 14:43:51 UTC 2024 x86_64 User : digitalshiksha ( 1179) PHP Version : 5.6.40 Disable Function : eval,show_source,system,shell_exec,escapeshellarg,escapeshellcmd,proc_close,proc_open,ini_alter,dl,show_source,curl_multi_exechellcmd, ini_restore,apache_get_modules,get_cfg_var,passthru, exec ,proc_get_status,fpassthru,c999_buff_prepare,c999_sess_put,c99_buff_prepare,c99_sess_put,proc_close,ini_alter,dl,symlink,link,proc_close,ini_alter,dl,symlink,link,mail MySQL : ON | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /proc/self/cwd/c1/1/proc/self/root/proc/self/root/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";;