Sitemap generator

<?php
// Inculde the phpcrawl-mainclass
include("libs/PHPCrawler.class.php");

class SitemapGenerator extends PHPCrawler
{
  protected $sitemap_output_file;

  public function setSitemapOutputFile($file)
  {
    $this->sitemap_output_file = $file;

    if (file_exists($this->sitemap_output_file)) unlink($this->sitemap_output_file);

    file_put_contents($this->sitemap_output_file,
                      "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\r\n".
                      "<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">\r\n",
                      FILE_APPEND);
  }

  public function handleDocumentInfo($DocInfo)
  {
    // Just detect linebreak for output ("\n" in CLI-mode, otherwise "<br>").
    if (PHP_SAPI == "cli") $lb = "\n";
    else $lb = "<br />";

    echo "Adding ".$DocInfo->url." to sitemap file".$lb;

    file_put_contents($this->sitemap_output_file, " <url>\r\n".
                                                  "  <loc>".$DocInfo->url."</loc>\r\n".
                                                  " </url>\r\n", FILE_APPEND);

    flush();
  }

  public function closeFile()
  {
    file_put_contents($this->sitemap_output_file, '</urlset>', FILE_APPEND);
  }
}

$crawler = new SitemapGenerator();
$crawler->setSitemapOutputFile("sitemap.xml"); // Set output-file
$crawler->setURL("www.php.net");
$crawler->addContentTypeReceiveRule("#text/html#");
$crawler->addURLFilterRule("#\.(jpg|jpeg|gif|png)$# i");

// ... apply all other options and rules to the crawler

$crawler->setPageLimit(10); // Just for testing
$crawler->goMultiProcessed(5); // Or use go() if you don't want multiple processes
$crawler->closeFile();
?>