feedforall_xmlparser.inc.php

RSS to html

    $XMLString = str_replace("Ê", "Ê", $XMLString);
    $XMLString = str_replace("Ë", "Ë", $XMLString);
    $XMLString = str_replace("Ì", "Ì", $XMLString);
    $XMLString = str_replace("Í", "Í", $XMLString);
    $XMLString = str_replace("Î", "Î", $XMLString);
    $XMLString = str_replace("Ï", "Ï", $XMLString);
    $XMLString = str_replace("Ð", "Ð", $XMLString);
    $XMLString = str_replace("Ñ", "Ñ", $XMLString);
    $XMLString = str_replace("Ò", "Ò", $XMLString);
    $XMLString = str_replace("Ó", "Ó", $XMLString);
    $XMLString = str_replace("Ô", "Ô", $XMLString);
    $XMLString = str_replace("Õ", "Õ", $XMLString);
    $XMLString = str_replace("Ö", "Ö", $XMLString);
    $XMLString = str_replace("×", "×", $XMLString);
    $XMLString = str_replace("Ø", "Ø", $XMLString);
    $XMLString = str_replace("Ù", "Ù", $XMLString);
    $XMLString = str_replace("Ú", "Ú", $XMLString);
    $XMLString = str_replace("Û", "Û", $XMLString);
    $XMLString = str_replace("Ü", "Ü", $XMLString);
    $XMLString = str_replace("Ý", "Ý", $XMLString);
    $XMLString = str_replace("Þ", "Þ", $XMLString);
    $XMLString = str_replace("ß", "ß", $XMLString);
    $XMLString = str_replace("à", "à", $XMLString);
    $XMLString = str_replace("á", "á", $XMLString);
    $XMLString = str_replace("â", "â", $XMLString);
    $XMLString = str_replace("ã", "ã", $XMLString);
    $XMLString = str_replace("ä", "ä", $XMLString);
    $XMLString = str_replace("å", "å", $XMLString);
    $XMLString = str_replace("æ", "æ", $XMLString);
    $XMLString = str_replace("ç", "ç", $XMLString);
    $XMLString = str_replace("è", "è", $XMLString);
    $XMLString = str_replace("é", "é", $XMLString);
    $XMLString = str_replace("ê", "ê", $XMLString);
    $XMLString = str_replace("ë", "ë", $XMLString);
    $XMLString = str_replace("ì", "ì", $XMLString);
    $XMLString = str_replace("í", "í", $XMLString);
    $XMLString = str_replace("î", "î", $XMLString);
    $XMLString = str_replace("ï", "ï", $XMLString);
    $XMLString = str_replace("ð", "ð", $XMLString);
    $XMLString = str_replace("ñ", "ñ", $XMLString);
    $XMLString = str_replace("ò", "ò", $XMLString);
    $XMLString = str_replace("ó", "ó", $XMLString);
    $XMLString = str_replace("ô", "ô", $XMLString);
    $XMLString = str_replace("õ", "õ", $XMLString);
    $XMLString = str_replace("ö", "ö", $XMLString);
    $XMLString = str_replace("÷", "÷", $XMLString);
    $XMLString = str_replace("ø", "ø", $XMLString);
    $XMLString = str_replace("ù", "ù", $XMLString);
    $XMLString = str_replace("ú", "ú", $XMLString);
    $XMLString = str_replace("û", "û", $XMLString);
    $XMLString = str_replace("ü", "ü", $XMLString);
    $XMLString = str_replace("ý", "ý", $XMLString);
    $XMLString = str_replace("þ", "þ", $XMLString);
    $XMLString = str_replace("ÿ", "ÿ", $XMLString);
    $XMLString = str_replace(" ", " ", $XMLString);
    $XMLString = str_replace(" ", " ", $XMLString);
    $XMLString = str_replace(" ", " ", $XMLString);
    $XMLString = str_replace("‌", "‌", $XMLString);
    $XMLString = str_replace("‍", "‍", $XMLString);
    $XMLString = str_replace("‎", "‎", $XMLString);
    $XMLString = str_replace("‏", "‏", $XMLString);
    $XMLString = str_replace("–", "–", $XMLString);
    $XMLString = str_replace("—", "—", $XMLString);
    $XMLString = str_replace("‘", "‘", $XMLString);
    $XMLString = str_replace("’", "’", $XMLString);
    $XMLString = str_replace("‚", "‚", $XMLString);
    $XMLString = str_replace("“", "“", $XMLString);
    $XMLString = str_replace("”", "”", $XMLString);
    $XMLString = str_replace("„", "„", $XMLString);
    $XMLString = str_replace("†", "†", $XMLString);
    $XMLString = str_replace("‡", "‡", $XMLString);
    $XMLString = str_replace("•", "•", $XMLString);
    $XMLString = str_replace("&hellep;", "…", $XMLString);
    $XMLString = str_replace("‰", "‰", $XMLString);
    $XMLString = str_replace("′", "′", $XMLString);
    $XMLString = str_replace("″", "″", $XMLString);
    $XMLString = str_replace("‹", "‹", $XMLString);
    $XMLString = str_replace("›", "›", $XMLString);
    $XMLString = str_replace("‾", "‾", $XMLString);
    $XMLString = str_replace("⁄", "⁄", $XMLString);
    $XMLString = str_replace("€", "⁈", $XMLString);
    return $XMLString;
  }
}

if (function_exists("FeedForAll_fopen") === FALSE) {
  Function FeedForAll_fopen($url) {
    //
    // The internal "hidden function is to do some initialization
    if (function_exists("h_FeedForAll_fopen") === FALSE) {
      Function h_FeedForAll_fopen($url, $RedirectHistory) {
        GLOBAL $connectTimeoutLimit;
        GLOBAL $ReadErrorString;

        //
        // Divide the URL into parts so we can work with it
        $parts = parse_url($url);
        $thepath = $parts["path"];
        if (isset($parts["query"])) {
          $thepath .= "?$parts[query]";
        }
        $domain = $parts["host"];
        if (isset($parts["port"])) {
          $port = $parts["port"];
        } else {
          $port = 80;
        }

        $errno = "";
        $errstr = "";
        if (isset($connectTimeoutLimit) && $connectTimeoutLimit != 0) {
          $fd = fsockopen($domain, $port, $errno, $errstr, $connectTimeoutLimit);
        } else {
          $fd = fsockopen($domain, $port, $errno, $errstr);
        }
        if ($fd !== FALSE) {
          $request = "GET $thepath HTTP/1.0\r\n";
          $request .= "Host: $domain\r\n";
          $request .= "User-Agent: FeedForAll rss2html scripts v3\r\n\r\n";
          fputs($fd, $request);
          
          $headerLine = 0;

          do {
            if (feof($fd) !== FALSE) {
              // End of file
              break;
            }
            $header = fgets($fd, 1024);
            if (($header[0] == "\n") || ($header[0] == "\r")) {
              // End of the headers
              break;
            }
            if ($headerLine == 0) {
              $firstHeaderLine = $header;
            }
            $headerLine++;
            if (substr($header, 0, 9) == "Location:") {
              //
              // We got a location header, try to fetch from the new location
              fclose($fd);
              if (count($RedirectHistory) < 10) {
                $loc = trim(substr($header, 9));
                //
                // Check if the redirect is relative or absolute
                if (substr($loc, 0, 7) != "http://") {
                  if ($loc[0] == "/") {
                    if ($port == 80) {
                      $loc = "http://$domain$loc";
                    } else {
                      $loc = "http://$domain:$port$loc";
                    }
                  } else {
                    //
                    // The path is relative so we need the existing path
                    $path = dirname($parts["path"])."/$loc";
                    if ($port == 80) {
                      $loc = "http://$domain$path";
                    } else {
                      $loc = "http://$domain:$port$path";
                    }
                  }
                }
                for ($x = count($RedirectHistory)-1; $x >= 0; $x--) {
                  if (!strcmp($loc, $RedirectHistory[$x])) {
                    $ReadErrorString = "Redirection loop detected";
                    return FALSE;
                  }
                }
                $RedirectHistory[count($RedirectHistory)] = $loc;
                return h_FeedForAll_fopen($loc, $RedirectHistory);
              } else {
                $ReadErrorString = "Too many redirects";
                return FALSE;
              }
            }
          } while (1);
        } else {
          $ReadErrorString = $errstr($errno);
          return FALSE;
        }
        //
        // Get the result code
        $parts = explode(" ", $firstHeaderLine);
        if (($parts[1] < 200) || (300 <= $parts[1])) {
          $ReadErrorString = "HTTP ERROR: ".$parts[1];
          fclose($fd);
          return FALSE;
        }
        
        $result = "";
        while (($data = fread($fd, 4096)) != "") {
          $result .= $data;
        }
        fclose($fd);
        return $result;
      }
    }

    $RedirectHistory = Array();

    return h_FeedForAll_fopen($url, $RedirectHistory);
  }
}

if (function_exists("FeedForAll_scripts_readFile") === FALSE) {
  Function FeedForAll_scripts_readFile($filename, $useFopenURL, $useCaching = 0) {
    GLOBAL $connectTimeoutLimit;
    GLOBAL $ReadErrorString;
    GLOBAL $debugLevel;

    if ($useCaching);

    if (isset($debugLevel) && ($debugLevel >= 1)) {
      echo "DIAG: FeedForAll_scripts_readFile($filename, $useFopenURL, $useCaching <= 0)<br>\n";
    }
    
    $ReadErrorString = "";
    $result = "";
    if (stristr($filename, "://")) {
      if ($useFopenURL == 1) {
        if (($fd = @fopen($filename, "rb")) === FALSE) {
          if (isset($debugLevel) && ($debugLevel >= 1)) {
            echo "DIAG: FeedForAll_scripts_readFile(): fopen() failed<br>\n";
          }
          return FALSE;
        }
        while (($data = fread($fd, 4096)) != "") {
          $result .= $data;
        }
        fclose($fd);
      }
      elseif ($useFopenURL == -1) {
        $result = FeedForAll_fopen($filename);
      } else {
        FeedForAll_fopen($filename);
        // This is a URL so use CURL
        $curlHandle = curl_init();
        curl_setopt($curlHandle, CURLOPT_URL, $filename);
        curl_setopt($curlHandle, CURLOPT_HEADER, 0);
        curl_setopt($curlHandle, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt($curlHandle, CURLOPT_USERAGENT, "FeedForAll rss2html scripts v3");
        //    curl_setopt($curlHandle, CURLOPT_AUTOREFERER, 1);
        curl_setopt($curlHandle, CURLOPT_REFERER, $filename);
        if (!(ini_get("safe_mode") || ini_get("open_basedir"))) {
          curl_setopt($curlHandle, CURLOPT_FOLLOWLOCATION, 1);
        }
        if (isset($connectTimeoutLimit) && $connectTimeoutLimit != 0) {
          curl_setopt($curlHandle, CURLOPT_CONNECTTIMEOUT, $connectTimeoutLimit);
        }
        curl_setopt($curlHandle, CURLOPT_MAXREDIRS, 10);
        $result = curl_exec($curlHandle);
        if (curl_errno($curlHandle)) {
          $ReadErrorString = curl_error($curlHandle);
          curl_close($curlHandle);
          return FALSE;
        }
        $http_response = curl_getinfo($curlHandle, CURLINFO_HTTP_CODE);
        if (($http_response < 200) || (300 <= $http_response)) {
          $ReadErrorString = "HTTP ERROR: $http_response";
          curl_close($curlHandle);
          return FALSE;
        }
        curl_close($curlHandle);
      }
    } else {
      // This is a local file, so use fopen
      if (($fd = @fopen($filename, "rb")) === FALSE) {
        if (isset($debugLevel) && ($debugLevel >= 1)) {
          echo "DIAG: FeedForAll_scripts_readFile(): fopen(): failed<br>\n";
        }
        return FALSE;
      }
      while (($data = fread($fd, 4096)) != "") {
        $result .= $data;
      }
      fclose($fd);
      if (isset($debugLevel) && ($debugLevel >= 1)) {
        echo "DIAG: FeedForAll_scripts_readFile(): flock() successeded<br>\n";
      }
    }
    return $result;
  }
}

class rootItemClass {
  var $operateAs;
  var $title;
  var $description;
  var $contentEncoded;
  var $link;
  var $pubDate;
  var $pubDate_t;
  var $pubDateDC;
  var $enclosureURL;
  var $enclosureLength;
  var $enclosureType;
  var $categoryArray;
  var $category;
  var $categoryDomain;
  var $guid;
  var $guidIsPermaLink;
  var $author;
  var $comments;
  var $source;
  var $sourceURL;
  var $creativeCommons;
  var $rssMeshExtra;
  var $rssMeshExtra1;
  var $rssMeshExtra2;
  var $rssMeshExtra3;
  var $rssMeshFeedImageTitle;
  var $rssMeshFeedImageUrl;
  var $rssMeshFeedImageLink;
  var $rssMeshFeedImageDescription;
  var $rssMeshFeedImageHeight;
  var $rssMeshFeedImageWidth;
  var $atomID;
  var $atomUpdated;
  var $atomContent;
  var $atomContentStartPos;
  var $atomAuthorEmail;
  
  var $contentEncodedUsed;

  var $itemStartPos;
  var $itemFullText;

  // Constructor
  Function rootItemClass($operateAs) {
    $this->operateAs = $operateAs;
    $this->title = "";
    $this->description = "";
    $this->contentEncoded = "";
    $this->link = "";
    $this->pubDate = "";