this script is used for creating an RSS feed from Typo3 pages, without touching the Typo3 installation

kolabrss.php

<?php


function getContent(&$contents, $startContentStr, $endContentStr)
{ 
  // if we want the content of an html element, we need to count, eg. the div's
  $element = '';
  if ($startContentStr[0] == '<' && substr($endContentStr, 0, 2) == '</')
  {
    $posSpace = strpos($startContentStr, ' ');
    $posClose = strpos($startContentStr, '>');
    if ($posSpace !== false && $posClose !== false)
    {
      $element = substr($startContentStr, 1, $posSpace < $posClose ? $posSpace : $posClose);
    }
    else if ($posSpace !== false)
    {
      $element = substr($startContentStr, 1, $posSpace - 1);
    }
    else if ($posClose !== false)
    {
      $element = substr($startContentStr, 1, $posClose - 1);
    }
    else
    {  
      $element = substr($startContentStr, 1);
    }
    $element = trim($element);
  }

  if ($startContentStr == '^')
  {
    $startContentStr = '';
    $contentPos = 0;
  }
  else
  {
    $contentPos = strpos($contents, $startContentStr);
    //if ($contentPos === false) die('Problem reading page '.$startContentStr);
    if ($contentPos === false) 
    {
      $contents = '';
      return '';
    }
  }
  $start = $contentPos + strlen($startContentStr);
  if ($endContentStr == '^')
  {
    $end = strlen($contents);
  }
  else
  {
    $end = strpos($contents, $endContentStr, $start);
    
    if (strlen($element) > 0)
    {
      // make sure we find the right ending element. count the number of open element tags
      $result = substr($contents, $start, $end - $start);
      
      while (substr_count($result, '<'.$element) <> substr_count($result, '</'.$element.'>') && $end !== false)
      {
        $end = strpos($contents, $endContentStr, $end + 1);
        $result = substr($contents, $start, $end - $start);
      }
      if ($end === false)
      {
        // something went wrong. incorrect number of elements
        $end = strlen($contents);
      }
    }
  }
  $result = substr($contents, $start, $end - $start);
  $contents = substr($contents, $end);
  return $result;
}

// it seems file_get_contents does not return the full page
function curl_get_file_contents($URL)
{
    $c = curl_init();
    curl_setopt($c, CURLOPT_TIMEOUT, 0);
    curl_setopt($c, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($c, CURLOPT_CONNECTTIMEOUT, 0);
    curl_setopt($c, CURLOPT_URL, str_replace('&amp;', '&', $URL));
    $agent = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.0.3705; .NET CLR 1.1.4322)';
    curl_setopt($c, CURLOPT_USERAGENT, $agent);


    $contents = curl_exec($c);
    curl_close($c);
    if ($contents) return $contents;
    else return FALSE;
}

function GetArticleFromTypo3($date_published, $url)
{
    $html = curl_get_file_contents($url);
    $title = getContent($html, '<title>', '</title>');
    $content = getContent($html, '<div id="content">', '</div>');
    $content = preg_replace('%(<!--).*?(-->)%i', '', $content);
    $content = preg_replace('%( javascript:linkTo_UnCryptMailto\().*?(\);)%i', '', $content);
    $content = preg_replace('%( class=").*?(")%i', '', $content);
    $content = preg_replace('%( style=").*?(")%i', '', $content);
    $content = preg_replace('%( id=").*?(")%i', '', $content);
    $content = str_replace('&nbsp;', ' ', $content);
    $content = str_replace('&lt;', '&amp;lt;', $content);
    $content = str_replace('<', '&lt;', $content);
    $content = str_replace('>', '&gt;', $content);
?>
<item>
        <title><?php echo $title; ?></title>
        <link><?php echo $url;?></link>
        <pubDate><?php echo date(DATE_RSS, $date_published); ?></pubDate>
        <dc:creator>Timotheus Pokorra (TBits)</dc:creator>

        <guid isPermaLink="false"><?php echo $url;?></guid>
        <description><?php echo $content; ?></description>
</item>
<?php
}

function PrintRSSHeader()
{
    header('Content-Type: text/xml');
    echo '<?xml version="1.0" encoding="utf-8" ?'.">\n"; 

?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/">

<channel>
    <title>TBits.net Kolab News</title>
    <link>http://www.tbits.net</link>
    <description>TBits.net works with the Kolab project and provides patches and extensions to Kolab on this RSS Feed</description>
    <language>en</language>

<?php
}

function PrintRSSFooter()
{
?>
    </channel>
</rss>
<?php

}


PrintRSSHeader();
GetArticleFromTypo3(mktime(1, 0, 0, 6, 4, 2013), "http://www.tbits.net/tbits-opensource/install-nightly-build-from-gitkolaborg-master.html");
GetArticleFromTypo3(mktime(1, 0, 0, 3, 27, 2013), "http://www.tbits.net/tbits-opensource/kolab3multipledomains.html");
PrintRSSFooter();

?>