<?
/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
/* Written by Reverend Jim (jim@revjim.net)
*
* http://revjim.net/code/feedParser/
*/
class feedParser {
var $version = "0.5";
var $entities = array(
'nbsp' => " ",
'iexcl' => "¡",
'cent' => "¢",
'pound' => "£",
'curren' => "¤",
'yen' => "¥",
'brvbar' => "¦",
'sect' => "§",
'uml' => "¨",
'copy' => "©",
'ordf' => "ª",
'laquo' => "«",
'not' => "¬",
'shy' => "­",
'reg' => "®",
'macr' => "¯",
'deg' => "°",
'plusmn' => "±",
'sup2' => "²",
'sup3' => "³",
'acute' => "´",
'micro' => "µ",
'para' => "¶",
'middot' => "·",
'cedil' => "¸",
'sup1' => "¹",
'ordm' => "º",
'raquo' => "»",
'frac14' => "¼",
'frac12' => "½",
'frac34' => "¾",
'iquest' => "¿",
'Agrave' => "À",
'Aacute' => "Á",
'Acirc' => "Â",
'Atilde' => "Ã",
'Auml' => "Ä",
'Aring' => "Å",
'AElig' => "Æ",
'Ccedil' => "Ç",
'Egrave' => "È",
'Eacute' => "É",
'Ecirc' => "Ê",
'Euml' => "Ë",
'Igrave' => "Ì",
'Iacute' => "Í",
'Icirc' => "Î",
'Iuml' => "Ï",
'ETH' => "Ð",
'Ntilde' => "Ñ",
'Ograve' => "Ò",
'Oacute' => "Ó",
'Ocirc' => "Ô",
'Otilde' => "Õ",
'Ouml' => "Ö",
'times' => "×",
'Oslash' => "Ø",
'Ugrave' => "Ù",
'Uacute' => "Ú",
'Ucirc' => "Û",
'Uuml' => "Ü",
'Yacute' => "Ý",
'THORN' => "Þ",
'szlig' => "ß",
'agrave' => "à",
'aacute' => "á",
'acirc' => "â",
'atilde' => "ã",
'auml' => "ä",
'aring' => "å",
'aelig' => "æ",
'ccedil' => "ç",
'egrave' => "è",
'eacute' => "é",
'ecirc' => "ê",
'euml' => "ë",
'igrave' => "ì",
'iacute' => "í",
'icirc' => "î",
'iuml' => "ï",
'eth' => "ð",
'ntilde' => "ñ",
'ograve' => "ò",
'oacute' => "ó",
'ocirc' => "ô",
'otilde' => "õ",
'ouml' => "ö",
'divide' => "÷",
'oslash' => "ø",
'ugrave' => "ù",
'uacute' => "ú",
'ucirc' => "û",
'uuml' => "ü",
'yacute' => "ý",
'thorn' => "þ",
'yuml' => "ÿ"
);
var $namespaces = array(
'DC' => 'http://purl.org/dc/elements/1.1/',
'RDF' => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#',
'RSS' => 'http://purl.org/rss/1.0/',
'RSS2'=> 'http://backend.userland.com/rss2',
'RDF2' => 'http://my.netscape.com/rdf/simple/0.9/'
);
function buildStruct($xmldata) {
// Create a parser object
$p = new XMLParser;
// Define our known namespaces
foreach ($this->namespaces as $space => $uri) {
$p->definens($space,$uri);
}
// Define base namespace
$p->definens("UNDEF");
$this->parseEntities($xmldata);
// Tell the parser to get the file.
$p->setXmlData($xmldata);
// Tell the parser to build the tree.
$p->buildXmlTree();
// Spit the tree out so we can see it
return $p->getXmlTree();
}
function parseEntities(&$data) {
foreach($this->entities as $entity => $replace) {
$data = preg_replace('/&' . $entity . ';/',$replace,$data);
}
$data = preg_replace('/&[ ]*;/','',$data);
}
function parseFeed($xmldata) {
$data =& $this->buildStruct(&$xmldata);
if(is_array($data)) {
foreach($data as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "RSS:RSS":
case "UNDEF:RSS":
case "RSS2:RSS":
$info = $this->parseRSS(&$child);
break;
case "RDF:RDF":
$info = $this->parseRDF(&$child);
break;
default:
$info["warning"] .= "Unknown document format: " . $child['tag'] . "\n";
break;
}
}
}
}
return $info;
}
function parseRDF(&$data) {
if(is_array($data['children'])) {
foreach($data['children'] as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "RSS:CHANNEL":
case "RDF2:CHANNEL":
$channel = $this->getRDFChannel(&$child);
break;
case "RSS:ITEM":
case "RDF2:ITEM":
$item[] = $this->getRDFItem(&$child);
break;
default:
break;
}
}
}
}
return array('channel' => $channel, 'item' => $item);
}
function parseRSS(&$data) {
if(is_array($data['children'])) {
foreach($data['children'] as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "RSS:CHANNEL":
case "RSS2:CHANNEL":
case "UNDEF:CHANNEL":
$info = $this->getRSSChannel(&$child);
break;
default:
break;
}
}
}
}
return $info;
}
function getRDFChannel($data) {
if(is_array($data['children'])) {
foreach($data['children'] as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "RSS:TITLE":
case "RDF2:TITLE":
$channel['title'] = $child['children'][0];
break;
case "RSS:LINK":
case "RDF2:LINK":
$channel['link'] = $child['children'][0];
break;
case "RSS:DESCRIPTION":
case "RDF2:DESCRIPTION":
$channel['description'] = $child['children'][0];
break;
case "RSS:WEBMASTER":
$channel['creator'] = $child['children'][0];
break;
default:
break;
}
}
}
}
return $channel;
}
function getRSSChannel($data) {
if(is_array($data['children'])) {
foreach($data['children'] as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "UNDEF:TITLE":
case "RSS:TITLE":
case "RSS2:TITLE":
$channel['title'] = $child['children'][0];
break;
case "UNDEF:LINK":
case "RSS:LINK":
case "RSS2:LINK":
$channel['link'] = $child['children'][0];
break;
case "UNDEF:DESCRIPTION":
case "RSS:DESCRIPTION":
case "RSS2:DESCRIPTION":
$channel['description'] = $child['children'][0];
break;
case "UNDEF:ITEM":
case "RSS:ITEM":
case "RSS2:ITEM":
$item[] = $this->getRSSItem(&$child);
break;
case "UNDEF:LASTBUILDDATE":
case "RSS:LASTBUILDDATE":
case "RSS2:LASTBUILDDATE":
$channel['lastbuilddate'] = strtotime($child['children'][0]);
break;
default:
break;
}
}
}
}
return array('channel' => $channel, 'item' => $item);
}
function getRDFItem($data) {
if(is_array($data['children'])) {
foreach($data['children'] as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "RSS:TITLE":
case "RDF2:TITLE":
$item['title'] = $child['children'][0];
break;
case "RSS:LINK":
case "RDF2:LINK":
$item['link'] = $child['children'][0];
break;
case "RSS:DESCRIPTION":
case "RDF2:DESCRIPTION":
$item["description"] = $child['children'][0];
break;
case "DC:DATE":
$item["date"] = $this->dcDateToUnixTime($child['children'][0],0);
$item["locdate"] = $this->dcDateToUnixTime($child['children'][0],1);
break;
default:
break;
}
}
}
}
return $item;
}
function getRSSItem($data) {
if(is_array($data['children'])) {
foreach($data['children'] as $child) {
if(is_array($child)) {
switch($child['tag']) {
case "UNDEF:TITLE":
case "RSS:TITLE":
case "RSS2:TITLE":
$item['title'] = $child['children'][0];
break;
case "UNDEF:LINK":
case "RSS:LINK":
case "RSS2:LINK":
$item['link'] = $child['children'][0];
break;
case "UNDEF:DESCRIPTION":
case "RSS:DESCRIPTION":
case "RSS2:DESCRIPTION":
$item["description"] = $child['children'][0];
break;
case "DC:DATE":
$item["date"] = $this->dcDateToUnixTime($child['children'][0],0);
$item["locdate"] = $this->dcDateToUnixTime($child['children'][0],1);
break;
case "UNDEF:PUBDATE":
case "RSS:PUBDATE":
case "RSS2:PUBDATE":
$item["date"] = strtotime($child['children'][0]);
$item["locdate"] = strtotime($child['children'][0]);
break;
default:
break;
}
}
}
}
return $item;
}
function dcDateToUnixTime($dcdate,$cvttz = 1) {
list($date,$time) = explode("T",$dcdate);
preg_match(
"/([0-9]{2}:[0-9]{2}:[0-9]{2})(\-?\+?)([0-9]{2}):([0-9]{2})/",
$time,
$yo
);
if ($cvttz == 1) {
return strtotime($date . " " . $yo[1] . $yo[2] . $yo[3] . $yo[4]);
} else {
return strtotime($date . " " . $yo[1]);
}
}
}
?>