strip_subdomains.php

<?php
$filename = 'master_no_duplicates.csv';
$contents = file($filename);

function get_domain($url)
{
  $pieces = parse_url($url);
  $domain = isset($pieces['host']) ? $pieces['host'] : '';
  if (preg_match('/(?P<domain>[a-z0-9][a-z0-9\-]{1,63}\.[a-z\.]{2,6})$/i', $domain, $regs)) {
      return $regs['domain'];
    }
  return false;
}
echo "starting";
foreach($contents as $line) {
  echo "adding: ".$line;
  $line_to_write = get_domain($line) . ",";
  file_put_contents("results.txt", $line_to_write, FILE_APPEND);
}
?>