Server : ApacheSystem : Linux host.digitalbabaji.in 4.18.0-513.11.1.el8_9.x86_64 #1 SMP Wed Jan 17 02:00:40 EST 2024 x86_64 User : addictionfreeind ( 1003) PHP Version : 7.2.34 Disable Function : exec,passthru,shell_exec,system Directory : /usr/share/doc/perl-HTML-Parser/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";;