Sitemap XML De-duplicator

parser.php

<?php

$xml=simplexml_load_file("sitemap.xml") or die("Error: Cannot create object");
$storage = [];
$xmltxt = fopen("xml.txt", "w");
$count = $skipped = 0;
// Normalize and remove duplicates.
foreach ($xml as $sxe) {
  $count++;
  $loc = strtolower($sxe->loc);
  $parse = parse_url($loc);
  $path = base64_encode($parse['path']);
  print "Processing $count: " . $parse['path'] . PHP_EOL;
  if (empty($storage[$path])) {
    $storage[$path] = $path;
    fwrite($xmltxt, $sxe->asXML() . PHP_EOL);
  } else {
  	$skipped++;
  }
}

fclose($xmltxt);
$total = round($skipped / $count) * 100;
print "Skipped $skipped ($total%)";

Removes any duplicate entries from a sitemap.xml file.