webmechanicx/getInnerHTML.php

## getInnerHTML.php
<?php
$html = <<< HTML
<body>
 <h1>Hello,
  <b>world!</b>
 </h1>
</body>
HTML;

$dom = new DOMDocument;
$dom->loadHTML($html);
$xpath = new DOMXPath($dom);
$textNodes = array();
foreach($xpath->query('/html/body//text()') as $i => $textNode) {
    $textNodes[$i] = array(
    	'text' => $textNode->nodeValue,
    	'parents' => array()
    );
    for (
        $currentNode = $textNode->parentNode;
        $currentNode->parentNode;
        $currentNode = $currentNode->parentNode
    ) {
        $textNodes[$i]['parents'][] = $currentNode->nodeName;
    }
}
print_r($textNodes);
	<?php
	$html = <<< HTML
	<body>
	<h1>Hello,
	<b>world!</b>
	</h1>
	</body>
	HTML;

	$dom = new DOMDocument;
	$dom->loadHTML($html);
	$xpath = new DOMXPath($dom);
	$textNodes = array();
	foreach($xpath->query('/html/body//text()') as $i => $textNode) {
	$textNodes[$i] = array(
	'text' => $textNode->nodeValue,
	'parents' => array()
	);
	for (
	$currentNode = $textNode->parentNode;
	$currentNode->parentNode;
	$currentNode = $currentNode->parentNode
	) {
	$textNodes[$i]['parents'][] = $currentNode->nodeName;
	}
	}
	print_r($textNodes);