I have the following:
$node = $doc->getElementsByTagName('img');
if ($node->item(0) == null || $node->item(0) == '') {
// do stuff
} elseif ($node->item(0)->hasAttribute('src')) {
// do other stuff
} else {
// do more other stuff
}
What I want is to only return images from the body tag.
I have tried:
$body = $doc->getElementsByTagName('body');
foreach ($body as $body_node) {
$node = $body_node->getElementsByTagName('img');
}
however if there is an image in header it still seems to get returned by
$node->item(0)->hasAttribute('src')
Personally there should never be an img in the header but I find some url's add them in a noscript tag in the the header.
So how do I return only images from he body tag excluding any found in the head tag?
Do it using DOMXPath:
$xpath = new DOMXpath($doc);
$nodes = $xpath->query('//body//img');
$nodes is now a DOMNodeList that you can iterate over.
If you only want img nodes that have a src attribute:
$nodes = $xpath->query('//body//img[#src]');
Edit: Here is a fully working example:
<?php
$contents = file_get_contents('http://stackoverflow.com/');
$doc = new DOMDocument();
$doc->loadHTML($contents);
$xpath = new DOMXpath($doc);
$nodes = $xpath->query('//body//img');
foreach ($nodes as $node) {
echo $node->getAttribute('src') . "\n";
}
I have the following html
$html = '<body><div style="font-color:#000">Hello</div>
<span style="what">My name is rasid</span><div>new to you
</div><div style="rashid">New here</div></body>';
$dom = new DOMDocument();
$dom->loadHTML($html);
$elements = $dom->getElementsByTagName('body');
I have tried
foreach($elements as $child)
{
echo $child->nodeName;
}
The Ouput is
body
But I need to loop through all the tags under body not the body. How can I do that.
I have also tried in above example to replace
$elements = $dom->getElementsByTagName('body');
with
$elements = $dom->getElementsByTagName('body')->item(0);
But It gives Error. Any Solution??
try this
$elements = $dom->getElementsByTagName('*');
$i = 1; //counter to output from 3rd one, since foreach loop below will output" html body div span div div"
foreach($elements as $child)
{
if ($i > 2) echo $child->nodeName."<br>"; //output "div span div div"
++$i;
}
If you only want child nodes of the body element, you can use:
$body = $dom->getElementsByTagName( 'body' )->item( 0 );
foreach( $body->childNodes as $node )
{
echo $node->nodeName . PHP_EOL;
}
If you want all descending nodes of the body element, you could use DOMXPath:
$xpath = new DOMXPath( $dom );
$bodyDescendants = $xpath->query( '//body//node()' );
foreach( $bodyDescendants as $node )
{
echo $node->nodeName . PHP_EOL;
}
use this code
$elements = $dom->getElementsByTagName('*');
foreach($elements as $child)
{
echo $child->nodeName;
}
I am trying to use the dom object to simplify the implementation of a glossary tooltip. What I need to do is to replace a text element in a paragraph, but NOT in an anchor tag that may be embedded in the paragraph.
$html = '<p>Replace this tag not this tag</p>';
$document = new DOMDocument();
$document->loadHTML($html);
$document->preserveWhiteSpace = false;
$document->validateOnParse = true;
$nodes = $document->getElementByTagName("p");
foreach ($nodes as $node) {
$node->nodeValue = str_replace("tag","element",$node->nodeValue);
}
echo $document->saveHTML();
I get:
'...<p>Replace this element not this element</p>...'
I want:
'...<p>Replace this element not this tag</p>...'
How do I implement this such that only the parent node text is changed and the child node (a tag) is not changed?
Try this:
$html = '<p>Replace this tag not this tag</p>';
$document = new DOMDocument();
$document->loadHTML($html);
$document->preserveWhiteSpace = false;
$document->validateOnParse = true;
$nodes = $document->getElementsByTagName("p");
foreach ($nodes as $node) {
while( $node->hasChildNodes() ) {
$node = $node->childNodes->item(0);
}
$node->nodeValue = str_replace("tag","element",$node->nodeValue);
}
echo $document->saveHTML();
Hope this helps.
UPDATE
To answer #paul's question in the comments below, you can create
$html = '<p>Replace this tag not this tag</p>';
$document = new DOMDocument();
$document->loadHTML($html);
$document->preserveWhiteSpace = false;
$document->validateOnParse = true;
$nodes = $document->getElementsByTagName("p");
//create the element which should replace the text in the original string
$elem = $document->createElement( 'dfn', 'tag' );
$attr = $document->createAttribute('title');
$attr->value = 'element';
$elem->appendChild( $attr );
foreach ($nodes as $node) {
while( $node->hasChildNodes() ) {
$node = $node->childNodes->item(0);
}
//dump the new string here, which replaces the source string
$node->nodeValue = str_replace("tag",$document->saveHTML($elem),$node->nodeValue);
}
echo $document->saveHTML();
Question
How can I remove empty xml tags in PHP?
Example:
$value1 = "2";
$value2 = "4";
$value3 = "";
xml = '<parentnode>
<tag1> ' .$value1. '</tag1>
<tag2> ' .$value2. '</tag2>
<tag3> ' .$value3. '</tag3>
</parentnode>';
XML Result:
<parentnode>
<tag1>2</tag1>
<tag2>4</tag2>
<tag3></tag3> // <- Empty tag
</parentnode>
What I want!
<parentnode>
<tag1>2</tag1>
<tag2>4</tag2>
</parentnode>
The XML without the empty tags like "tag3"
Thanks!
You can use XPath with the predicate not(node()) to select all elements that do not have child nodes.
<?php
$doc = new DOMDocument;
$doc->preserveWhiteSpace = false;
$doc->loadxml('<parentnode>
<tag1>2</tag1>
<tag2>4</tag2>
<tag3></tag3>
<tag2>4</tag2>
<tag3></tag3>
<tag2>4</tag2>
<tag3></tag3>
</parentnode>');
$xpath = new DOMXPath($doc);
foreach( $xpath->query('//*[not(node())]') as $node ) {
$node->parentNode->removeChild($node);
}
$doc->formatOutput = true;
echo $doc->savexml();
prints
<?xml version="1.0"?>
<parentnode>
<tag1>2</tag1>
<tag2>4</tag2>
<tag2>4</tag2>
<tag2>4</tag2>
</parentnode>
This works recursively and removes nodes that:
contain only spaces
do not have attributes
do not have child notes
// not(*) does not have children elements
// not(#*) does not have attributes
// text()[normalize-space()] nodes that include whitespace text
while (($node_list = $xpath->query('//*[not(*) and not(#*) and not(text()[normalize-space()])]')) && $node_list->length) {
foreach ($node_list as $node) {
$node->parentNode->removeChild($node);
}
}
$dom = new DOMDocument;
$dom->loadXML($xml);
$elements = $dom->getElementsByTagName('*');
foreach($elements as $element) {
if ( ! $element->hasChildNodes() OR $element->nodeValue == '') {
$element->parentNode->removeChild($element);
}
}
echo $dom->saveXML();
CodePad.
The solution that worked with my production PHP SimpleXMLElement object code, by using Xpath, was:
/*
* Remove empty (no children) and blank (no text) XML element nodes, but not an empty root element (/child::*).
* This does not work recursively; meaning after empty child elements are removed, parents are not reexamined.
*/
foreach( $this->xml->xpath('/child::*//*[not(*) and not(text()[normalize-space()])]') as $emptyElement ) {
unset( $emptyElement[0] );
}
Note that it is not required to use PHP DOM, DOMDocument, DOMXPath, or dom_import_simplexml().
//this is a recursively option
do {
$removed = false;
foreach( $this->xml->xpath('/child::*//*[not(*) and not(text()[normalize-space()])]') as $emptyElement ) {
unset( $emptyElement[0] );
$removed = true;
}
} while ($removed) ;
If you're going to be a lot of this, just do something like:
$value[] = "2";
$value[] = "4";
$value[] = "";
$xml = '<parentnode>';
for($i=1,$m=count($value); $i<$m+1; $i++)
$xml .= !empty($value[$i-1]) ? "<tag{$i}>{$value[$i-1]}</tag{$i}>" : null;
$xml .= '</parentnode>';
echo $xml;
Ideally though, you should probably use domdocument.
This question already has answers here:
How to get innerHTML of DOMNode?
(9 answers)
Closed 5 years ago.
How to Change innerHTML of a php DOMElement ?
Another solution:
1) create new DOMDocumentFragment from the HTML string to be inserted;
2) remove old content of our element by deleting its child nodes;
3) append DOMDocumentFragment to our element.
function setInnerHTML($element, $html)
{
$fragment = $element->ownerDocument->createDocumentFragment();
$fragment->appendXML($html);
while ($element->hasChildNodes())
$element->removeChild($element->firstChild);
$element->appendChild($fragment);
}
Alternatively, we can replace our element with its clean copy and then append DOMDocumentFragment to this clone.
function setInnerHTML($element, $html)
{
$fragment = $element->ownerDocument->createDocumentFragment();
$fragment->appendXML($html);
$clone = $element->cloneNode(); // Get element copy without children
$clone->appendChild($fragment);
$element->parentNode->replaceChild($clone, $element);
}
Test:
$doc = new DOMDocument();
$doc->loadXML('<div><span style="color: green">Old HTML</span></div>');
$div = $doc->getElementsByTagName('div')->item(0);
echo $doc->saveHTML();
setInnerHTML($div, '<p style="color: red">New HTML</p>');
echo $doc->saveHTML();
// Output:
// <div><span style="color: green">Old HTML</span></div>
// <div><p style="color: red">New HTML</p></div>
I needed to do this for a project recently and ended up with an extension to DOMElement: http://www.keyvan.net/2010/07/javascript-like-innerhtml-access-in-php/
Here's an example showing how it's used:
<?php
require_once 'JSLikeHTMLElement.php';
$doc = new DOMDocument();
$doc->registerNodeClass('DOMElement', 'JSLikeHTMLElement');
$doc->loadHTML('<div><p>Para 1</p><p>Para 2</p></div>');
$elem = $doc->getElementsByTagName('div')->item(0);
// print innerHTML
echo $elem->innerHTML; // prints '<p>Para 1</p><p>Para 2</p>'
// set innerHTML
$elem->innerHTML = 'FF';
// print document (with our changes)
echo $doc->saveXML();
?>
I think the best thing you can do is come up with a function that will take the DOMElement that you want to change the InnerHTML of, copy it, and replace it.
In very rough PHP:
function replaceElement($el, $newInnerHTML) {
$newElement = $myDomDocument->createElement($el->nodeName, $newInnerHTML);
$el->parentNode->insertBefore($newElement, $el);
$el->parentNode->removeChild($el);
return $newElement;
}
This doesn't take into account attributes and nested structures, but I think this will get you on your way.
I ended up making this function using a few functions from other people on this page. I changed the one from Joanna Goch the way that Peter Brand says mostly, and also added some code from Guest and from other places.
This function does not use an extension, and does not use appendXML (which is very picky and breaks even if it sees one BR tag that is not closed) and seems to be working good.
function set_inner_html( $element, $content ) {
$DOM_inner_HTML = new DOMDocument();
$internal_errors = libxml_use_internal_errors( true );
$DOM_inner_HTML->loadHTML( mb_convert_encoding( $content, 'HTML-ENTITIES', 'UTF-8' ) );
libxml_use_internal_errors( $internal_errors );
$content_node = $DOM_inner_HTML->getElementsByTagName('body')->item(0);
$content_node = $element->ownerDocument->importNode( $content_node, true );
while ( $element->hasChildNodes() ) {
$element->removeChild( $element->firstChild );
}
$element->appendChild( $content_node );
}
It seems that appendXML doesn't work always - for example if you try to append XML with 3 levels. Here is the function I wrote that always work (you want to set $content as innerHTML to $element):
function setInnerHTML($DOM, $element, $content) {
$DOMInnerHTML = new DOMDocument();
$DOMInnerHTML->loadHTML($content);
$contentNode = $DOMInnerHTML->getElementsByTagName('body')->item(0)->firstChild;
$contentNode = $DOM->importNode($contentNode, true);
$element->appendChild($contentNode);
return $elementNode;
}
Have a look at this library PHP Simple HTML DOM Parser http://simplehtmldom.sourceforge.net/
It looks pretty straightforward. You can change innertextproperty of your elements. It might help.
Here is a replace by class function I just wrote:
It will replace the innerHtml of a class. You can also specify the node type eg. div/p/a etc.
function replaceInnerHtmlByClass($html, $replace=null, $class=null, $nodeType=null){
if(!$nodeType){ $nodeType = '*'; }
$dom = new DOMDocument();
$dom->loadHTML($html);
$xpath = new DOMXPath($dom);
$nodes = $xpath->query("//{$nodeType}[contains(concat(' ', normalize-space(#class), ' '), '$class')]");
foreach($nodes as $node) {
while($node->childNodes->length){
$node->removeChild($node->firstChild);
}
$fragment = $dom->createDocumentFragment();
$fragment->appendXML($replace);
$node->appendChild($fragment);
}
return $dom->saveHTML($dom->documentElement);
}
Here is another function I wrote to remove nodes with a specific class but preserving the inner html.
Setting replace to true will discard the inner html.
Setting replace to any other content will replace the inner html with the provided content.
function stripTagsByClass($html, $class=null, $nodeType=null, $replace=false){
if(!$nodeType){ $nodeType = '*'; }
$dom = new DOMDocument();
$dom->loadHTML($html);
$xpath = new DOMXPath($dom);
$nodes = $xpath->query("//{$nodeType}[contains(concat(' ', normalize-space(#class), ' '), '$class')]");
foreach($nodes as $node) {
$innerHTML = '';
$children = $node->childNodes;
foreach($children as $child) {
$tmp = new DOMDocument();
$tmp->appendChild($tmp->importNode($child,true));
$innerHTML .= $tmp->saveHTML();
}
$fragment = $dom->createDocumentFragment();
if($replace !== null && $replace !== false){
if($replace === true){ $replace = ''; }
$innerHTML = $replace;
}
$fragment->appendXML($innerHTML);
$node->parentNode->replaceChild($fragment, $node);
}
return $dom->saveHTML($dom->documentElement);
}
Theses functions can easily be adapted to use other attributes as the selector.
I only needed it to evaluate the class attribute.
Developing on from Joanna Goch's answer, this function will insert either a text node or an HTML fragment:
function nodeFromContent($node, $content) {
//creates a text node, or dom node if content contains html
$lt = strpos($content, '<');
$gt = strrpos($content, '>');
if (!($lt === false || $gt === false) && $gt > $lt) {
//< followed by > means potentially contains HTML
$DOMInnerHTML = new DOMDocument();
$DOMInnerHTML->loadHTML($content);
$contentNode = $DOMInnerHTML->getElementsByTagName('body')->item(0);
$newNode = $node->ownerDocument->importNode($contentNode, true);
} else {
$newNode = $node->ownerDocument->createTextNode($content);
}
return $newNode;
}
usage
$newNode = nodeFromContent($node, $content);
$node->parentNode->insertBefore($newNode, $node);
//or $node->appendChild($newNode) depending on what you require
here is how you do it:
$doc = new DOMDocument('');
$label = $doc->createElement('label');
$label->appendChild($doc->createTextNode('test'));
$li->appendChild($label);
echo $doc->saveHTML();
function setInnerHTML($DOM, $element, $innerHTML) {
$node = $DOM->createTextNode($innerHTML);
$element->appendChild($node);
}