Question

I am doing it this way :

$dom = new DOMDocument;
$dom->loadHTMLFile("test.html");
//$books = $dom->getElementsByTagName('body');

$i = 0;
while (is_object($finance = $dom->getElementsByTagName("body")->item($i))) {
    foreach ($finance->childNodes as $nodename) {
        if ($nodename->childNodes) {
            foreach ($nodename->childNodes as $subNodes) {
                if ($subNodes->childNodes) {
                    foreach ($subNodes->childNodes as $potha){
                        echo $potha->nodeName . " - " . $potha->nodeValue . "<br>";
                    }
                } else {
                    echo $subNodes->nodeName . " - " . $subNodes->nodeValue . "<br>";
                }
            }
        } else {
            echo $nodename->nodeName . " - " . $nodename->nodeValue . "<br>";
        }
    }
    $i++;
}

But how can i make it recursive so each time when there is subChild , it should loop through each child, sub child and sub child and so on …. else echo Name of the Node and Value.

Also how can i get the position of each node relative to body or html so there is a difference between each segment.

Answer 1

Something like this should work for you:

function treatNode($node)
{
    if ($node->hasChildNodes()) {
        foreach ($node->childNodes as $child){
            treatNode($child);
        }
    } else {
        echo $node->nodeName . " - " . $node->nodeValue . "<br>";
    }
}

$dom = new DOMDocument;
$dom->loadHTMLFile("test.html");
//$books = $dom->getElementsByTagName('body');

$i = 0;
while (is_object($finance = $dom->getElementsByTagName("body")->item($i))) {
    treatNode($finance);
    $i++;
}