这种方法包括使用html结构来检索DOMXPath所需的元素.正则表达式第二次用于从文本节点或属性中提取信息:
$classRel = ['sect2' => 'section-ref',
'figure' => 'fig-ref'];
libxml_use_internal_errors(true);
$dom = new DOMDocument;
$dom->loadHTML($html); // or $dom->loadHTMLFile($url);
$xp = new DOMXPath($dom);
// make a custom php function available for the XPath query
// (it isn't really necessary, but it is more rigorous than writing
// "contains(@class, 'myClass')" )
$xp->registerNamespace("php", "http://php.net/xpath");
function hasClass($classNode, $className) {
if (!empty($classNode))
return in_array($className, preg_split('~\s+~', $classNode[0]->value, -1, PREG_SPLIT_NO_EMPTY));
return false;
}
$xp->registerPHPFunctions('hasClass');
// The XPath query will find the first ancestor of a text node with '[label*'
// that is a div tag with an id and a class attribute,
// if the class attribute doesn't contain the "metadata" class.
$labelQuery = <<
//text()[contains(., 'label*')]
/ancestor::div
[@id and @class and not(php:function('hasClass', @class, 'metadata'))][1]
EOD;
$idNodeList = $xp->query($labelQuery);
$links = [];
// For each div node, a new link node is created in the associative array $links.
// The keys are labels.
foreach($idNodeList as $divNode) {
// The pattern extract the first text part in group 1 and the label in group 2
if (preg_match('~(\S+) .*? \[label\* ([^]]+) ]~x', $divNode->textContent, $m)) {
$links[$m[2]] = $dom->createElement('a');
$links[$m[2]]->setAttribute('href', $divNode->getAttribute('id'));
$links[$m[2]]->setAttribute('class', $classRel[$divNode->getAttribute('class')]);
$links[$m[2]]->nodeValue = $m[1];
}
}
if ($links) { // if $links is empty no need to do anything
$refNodeList = $xp->query("//text()[contains(., '[ref*')]");
foreach ($refNodeList as $refNode) {
// split the text with square brackets parts, the reference name is preserved in a capture
$parts = preg_split('~\[ref\*([^]]+)]~', $refNode->nodeValue, -1, PREG_SPLIT_DELIM_CAPTURE);
// create a fragment to receive text parts and links
$frag = $dom->createDocumentFragment();
foreach ($parts as $k=>$part) {
if ($k%2 && isset($links[$part])) { // delimiters are always odd items
$clone = $links[$part]->cloneNode(true);
$frag->appendChild($clone);
} elseif ($part !== '') {
$frag->appendChild($dom->createTextNode($part));
}
}
$refNode->parentNode->replaceChild($frag, $refNode);
}
}
$result = '';
$childNodes = $dom->getElementsByTagName('body')->item(0)->childNodes;
foreach ($childNodes as $childNode) {
$result .= $dom->saveXML($childNode);
}
echo $result;