<?php

$LINKCHECKER_total_str = '';

// +----------------------------------------------------------------------+
// | LinkChecker                                                          |
// | Gets URL header data using cURL                                      |
// +----------------------------------------------------------------------+
// | Copyright (c) 2003 Jaimie Sirovich                                   |
// +----------------------------------------------------------------------+
// | Author: Jaimie Sirovich <jsirovic@gmail.com>                         |
// +----------------------------------------------------------------------+

class LinkChecker
{
  // helper function for the cURL request
  function CURLOPT_WRITEFUNCTION($ch, $str)
  {
    global $LINKCHECKER_total_str;
    $LINKCHECKER_total_str .= $str;
    if (preg_match('/^(.*?)\r\n\r\n/s', $LINKCHECKER_total_str, $matches)) 
    {
      echo $matches[1];
      return -1;
    } 
    else  
    {
      return strlen($str);
    }  
  }  

  // return the header data
  function getHeader($url, $userAgent = "Mozilla/4.0")
  {
    global $LINKCHECKER_total_str;
    $LINKCHECKER_total_str = "";
    ob_start();  
    $ch = curl_init();
    curl_setopt ($ch, CURLOPT_URL, $url);
    curl_setopt ($ch, CURLOPT_USERAGENT, $userAgent);
    curl_setopt ($ch, CURLOPT_HEADER, 1);
    curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt ($ch, CURLOPT_TIMEOUT, 60);
    curl_setopt ($ch, CURLOPT_WRITEFUNCTION, 
                 array("LinkChecker", "CURLOPT_WRITEFUNCTION"));
     
    $result = curl_exec($ch);
    curl_close($ch);
    return ob_get_clean();
  }

  // return response code  
  function parseResponseCode($str) 
  {
    preg_match('/^HTTP\/\d\.\d (.{3})/', $str, $matches);
    return (isset($matches[1]) ? $matches[1] : '(not available)');
  }

  // return the MIME type
  function parseMimeType($str) 
  {
    preg_match('/Content-Type: (.*)/', $str, $matches);
    return (isset($matches[1]) ? $matches[1] : '(not available)');
  }
  
  // return the Content-Length
  function parseContentLength($str) 
  {
    preg_match('/Content-Length: (.*)/', $str, $matches);
    return (isset($matches[1]) ? $matches[1] : '(not available)');
  }
  
  // return the Location
  function parseLocation($str) 
  {
    preg_match('/Location: ?([^\r\n]*)/i', $str, $matches);
    return (isset($matches[1]) ? $matches[1] : '(not available)');
  }

  // return the path to the destination URL
  function getPath($url, &$_response_code, $userAgent = 'Mozilla/4.0')
  {
    $_url = $url;
    $path = array();
    $path[] = 'Initial destination ' . $_url;
    $iterations = 0;

    do 
    {
      $_buffer = LinkChecker::getHeader($_url);
      if (!$_buffer) 
      {
        $path[] = 'ERROR: Maximum number of redirections exceeded; aborting.';
        break;
      }
      $_url = LinkChecker::parseLocation($_buffer) ? 
              LinkChecker::parseLocation($_buffer) : $_url;
      $_response_code = LinkChecker::parseResponseCode($_buffer);
      $path[] = ($_response_code != 200 && $_response_code != 404) ? 
                ('Redirect (' . $_response_code . ') to => ' . $_url) : 
                ('Final destination (' . $_response_code . ') ' . $_url ); 
      $iterations++;
      if ($iterations > 10) 
      {
        $path[] = 'ERROR: Maximum number of redirections exceeded; aborting.';
        break;
      }
    } 
    while ($_response_code != '200' && $_response_code != '404'); 

    return $path;
  }
}
?>