Sorry no explanation, but it should be easy to follow with a little work.:

#!/usr/bin/perl -w

use strict;
use HTML::TokeParser;

my @list;
my $level = -1;
my $file = "c:/test.htm";

my $p = HTML::TokeParser->new($file) || die "Can't open $file: $!";

LOOP:
while (my $token = $p->get_token ) {
    my $se  = (@$token)[0]; # an opening tag will eq 'S' a closing tag
+ 'E'
    my $tag = (@$token)[1];
  next LOOP unless $tag eq 'ul' or $tag eq 'li';
    if ( $tag eq 'ul' ) {
        # this will be either a <ul> or a </ul>
        if ( $se eq 'S' ) {
            $level++; # increase level in response to <ul>
        } else {
            $level--; # decrease level in response to </ul>
        }
      next LOOP;
    }
    my $text  = $p->get_trimmed_text();
    push @{$list[$level]}, $text;
}

# data is now in a 2D data structure. you will need to read
# up on these to understand the syntax
# @{$list[0]} is level 1
# @{$list[1]} contains level 2
for my $i (0.. $#list) {
   my @array = @{$list[$i]};
   @array = sort @array;
   print "Level $i\n";
   print "  $_\n" for @array;
}
[download]

cheers

tachyon

s&&rsenoyhcatreve&&&s&n.+t&"$'$`$\"$\&"&ee&&y&srve&&d&&print