#!/usr/bin/perl

use strict;
use warnings;
use Data::Dumper;
use HTML::TokeParser::Simple;

my $html;
{
  local $/;
  $html = <DATA>
}

my $p = HTML::TokeParser::Simple->new(\$html);
$p->unbroken_text(1);

my ($in_li, @record, @db);

while (my $t = $p->get_token){
  
  $in_li++, next if $t->is_start_tag('li');
  next unless $in_li;
  
  if ($t->is_end_tag('li')){
    push @db, [@record];
    $in_li = 0;
    next;
  }
  
  if ($t->is_start_tag('a')){
    push @record, $t->get_attr('href');
    my $text = $p->get_trimmed_text('/a');
    push @record, $text;
  }
  
}

#die Dumper \@db;

# the text inside the first link's text, the 2nd link's URL, the 2nd link's text.

for my $record (@db){
  my @field = @{$record};
  print $field[1], "::", $field[2], "::", $field[3], "\n";
}


__DATA__
<li>
  <a class="style5" href="http://www.site.com/page.html">
    some words here
  </a>
    - 
  <a class="style3" href="http://www.site.com/page2.html">
    "some words here"
  </a> 
</li>