How to get the text node of an element?


<div class="title">
   I am text node
   <a class="edit">Edit</a>
</div>

I wish to get the "I am text node", do not wish to remove the "edit" tag, and need a cross browser solution.

var text = $(".title").contents().filter(function() {
  return this.nodeType == Node.TEXT_NODE;
}).text();

This gets the contents of the selected element, and applies a filter function to it. The filter function returns only text nodes (i.e. those nodes with nodeType == Node.TEXT_NODE).


You can get the nodeValue of the first childNode using

$('.title')[0].childNodes[0].nodeValue

http://jsfiddle.net/TU4FB/


If you mean get the value of the first text node in the element, this code will work:

var oDiv = document.getElementById("MyDiv");
var firstText = "";
for (var i = 0; i < oDiv.childNodes.length; i++) {
    var curNode = oDiv.childNodes[i];
    if (curNode.nodeName === "#text") {
        firstText = curNode.nodeValue;
        break;
    }
}

You can see this in action here: http://jsfiddle.net/ZkjZJ/


Another native JS solution that can be useful for "complex" or deeply nested elements is to use NodeIterator. Put NodeFilter.SHOW_TEXT as the second argument ("whatToShow"), and iterate over just the text node children of the element.

var root = document.querySelector('p'),
    iter = document.createNodeIterator(root, NodeFilter.SHOW_TEXT),
    textnode;

// print all text nodes
while (textnode = iter.nextNode()) {
  console.log(textnode.textContent)
}
<p>
<br>some text<br>123
</p>

You can also use TreeWalker. The difference between the two is that NodeIterator is a simple linear iterator, while TreeWalker allows you to navigate via siblings and ancestors as well.


Pure JavaScript: Minimalist

First off, always keep this in mind when looking for text in the DOM.

MDN - Whitespace in the DOM

This issue will make you pay attention to the structure of your XML / HTML.

In this pure JavaScript example, I account for the possibility of multiple text nodes that could be interleaved with other kinds of nodes. However, initially, I do not pass judgment on whitespace, leaving that filtering task to other code.

In this version, I pass a NodeList in from the calling / client code.

/**
* Gets strings from text nodes. Minimalist. Non-robust. Pre-test loop version.
* Generic, cross platform solution. No string filtering or conditioning.
*
* @author Anthony Rutledge
* @param nodeList The child nodes of a Node, as in node.childNodes.
* @param target A positive whole number >= 1
* @return String The text you targeted.
*/
function getText(nodeList, target)
{
    var trueTarget = target - 1,
        length = nodeList.length; // Because you may have many child nodes.

    for (var i = 0; i < length; i++) {
        if ((nodeList[i].nodeType === Node.TEXT_NODE) && (i === trueTarget)) {
            return nodeList[i].nodeValue;  // Done! No need to keep going.
        }
    }

    return null;
}

Of course, by testing node.hasChildNodes() first, there would be no need to use a pre-test for loop.

/**
* Gets strings from text nodes. Minimalist. Non-robust. Post-test loop version.
* Generic, cross platform solution. No string filtering or conditioning.
*
* @author Anthony Rutledge
* @param nodeList The child nodes of a Node, as in node.childNodes.
* @param target A positive whole number >= 1
* @return String The text you targeted.
*/
function getText(nodeList, target)
{
    var trueTarget = target - 1,
        length = nodeList.length,
        i = 0;

    do {
        if ((nodeList[i].nodeType === Node.TEXT_NODE) && (i === trueTarget)) {
            return nodeList[i].nodeValue;  // Done! No need to keep going.
         }

        i++;
    } while (i < length);

    return null;
}

Pure JavaScript: Robust

Here the function getTextById() uses two helper functions: getStringsFromChildren() and filterWhitespaceLines().


getStringsFromChildren()

/**
* Collects strings from child text nodes.
* Generic, cross platform solution. No string filtering or conditioning.
*
* @author Anthony Rutledge
* @version 7.0
* @param parentNode An instance of the Node interface, such as an Element. object.
* @return Array of strings, or null.
* @throws TypeError if the parentNode is not a Node object.
*/
function getStringsFromChildren(parentNode)
{
    var strings = [],
        nodeList,
        length,
        i = 0;

    if (!parentNode instanceof Node) {
        throw new TypeError("The parentNode parameter expects an instance of a Node.");
    }

    if (!parentNode.hasChildNodes()) {
        return null; // We are done. Node may resemble <element></element>
    }

    nodeList = parentNode.childNodes;
    length = nodeList.length;

    do {
        if ((nodeList[i].nodeType === Node.TEXT_NODE)) {
            strings.push(nodeList[i].nodeValue);
         }

        i++;
    } while (i < length);

    if (strings.length > 0) {
        return strings;
    }

    return null;
}

filterWhitespaceLines()

/**
* Filters an array of strings to remove whitespace lines.
* Generic, cross platform solution.
*
* @author Anthony Rutledge
* @version 6.0
* @param textArray a String associated with the id attribute of an Element.
* @return Array of strings that are not lines of whitespace, or null.
* @throws TypeError if the textArray param is not of type Array.
*/
function filterWhitespaceLines(textArray) 
{
    var filteredArray = [],
        whitespaceLine = /(?:^\s+$)/; // Non-capturing Regular Expression.

    if (!textArray instanceof Array) {
        throw new TypeError("The textArray parameter expects an instance of a Array.");
    }

    for (var i = 0; i < textArray.length; i++) {
        if (!whitespaceLine.test(textArray[i])) {  // If it is not a line of whitespace.
            filteredArray.push(textArray[i].trim());  // Trimming here is fine. 
        }
    }

    if (filteredArray.length > 0) {
        return filteredArray ; // Leave selecting and joining strings for a specific implementation. 
    }

    return null; // No text to return.
}

getTextById()

/**
* Gets strings from text nodes. Robust.
* Generic, cross platform solution.
*
* @author Anthony Rutledge
* @version 6.0
* @param id A String associated with the id property of an Element.
* @return Array of strings, or null.
* @throws TypeError if the id param is not of type String.
* @throws TypeError if the id param cannot be used to find a node by id.
*/
function getTextById(id) 
{
    var textArray = null;             // The hopeful output.
    var idDatatype = typeof id;       // Only used in an TypeError message.
    var node;                         // The parent node being examined.

    try {
        if (idDatatype !== "string") {
            throw new TypeError("The id argument must be of type String! Got " + idDatatype);
        }

        node = document.getElementById(id);

        if (node === null) {
            throw new TypeError("No element found with the id: " + id);
        }

        textArray = getStringsFromChildren(node);

        if (textArray === null) {
            return null; // No text nodes found. Example: <element></element>
        }

        textArray = filterWhitespaceLines(textArray);

        if (textArray.length > 0) {
            return textArray; // Leave selecting and joining strings for a specific implementation. 
        }
    } catch (e) {
        console.log(e.message);
    }

    return null; // No text to return.
}

Next, the return value (Array, or null) is sent to the client code where it should be handled. Hopefully, the array should have string elements of real text, not lines of whitespace.

Empty strings ("") are not returned because you need a text node to properly indicate the presence of valid text. Returning ("") may give the false impression that a text node exists, leading someone to assume that they can alter the text by changing the value of .nodeValue. This is false, because a text node does not exist in the case of an empty string.

Example 1:

<p id="bio"></p> <!-- There is no text node here. Return null. -->

Example 2:

<p id="bio">

</p> <!-- There are at least two text nodes ("\n"), here. -->

The problem comes in when you want to make your HTML easy to read by spacing it out. Now, even though there is no human readable valid text, there are still text nodes with newline ("\n") characters in their .nodeValue properties.

Humans see examples one and two as functionally equivalent--empty elements waiting to be filled. The DOM is different than human reasoning. This is why the getStringsFromChildren() function must determine if text nodes exist and gather the .nodeValue values into an array.

for (var i = 0; i < length; i++) {
    if (nodeList[i].nodeType === Node.TEXT_NODE) {
            textNodes.push(nodeList[i].nodeValue);
    }
}

In example two, two text nodes do exist and getStringFromChildren() will return the .nodeValue of both of them ("\n"). However, filterWhitespaceLines() uses a regular expression to filter out lines of pure whitespace characters.

Is returning null instead of newline ("\n") characters a form of lying to the client / calling code? In human terms, no. In DOM terms, yes. However, the issue here is getting text, not editing it. There is no human text to return to the calling code.

One can never know how many newline characters might appear in someone's HTML. Creating a counter that looks for the "second" newline character is unreliable. It might not exist.

Of course, further down the line, the issue of editing text in an empty <p></p> element with extra whitespace (example 2) might mean destroying (maybe, skipping) all but one text node between a paragraph's tags to ensure the element contains precisely what it is supposed to display.

Regardless, except for cases where you are doing something extraordinary, you will need a way to determine which text node's .nodeValue property has the true, human readable text that you want to edit. filterWhitespaceLines gets us half way there.

var whitespaceLine = /(?:^\s+$)/; // Non-capturing Regular Expression.

for (var i = 0; i < filteredTextArray.length; i++) {
    if (!whitespaceLine.test(textArray[i])) {  // If it is not a line of whitespace.
        filteredTextArray.push(textArray[i].trim());  // Trimming here is fine. 
    }
}

At this point you may have output that looks like this:

["Dealing with text nodes is fun.", "Some people just use jQuery."]

There is no guarantee that these two strings are adjacent to each other in the DOM, so joining them with .join() might make an unnatural composite. Instead, in the code that calls getTextById(), you need to chose which string you want to work with.

Test the output.

try {
    var strings = getTextById("bio");

    if (strings === null) {
        // Do something.
    } else if (strings.length === 1) {
        // Do something with strings[0]
    } else { // Could be another else if
        // Do something. It all depends on the context.
    }
} catch (e) {
    console.log(e.message);
}

One could add .trim() inside of getStringsFromChildren() to get rid of leading and trailing whitespace (or to turn a bunch of spaces into a zero length string (""), but how can you know a priori what every application may need to have happen to the text (string) once it is found? You don't, so leave that to a specific implementation, and let getStringsFromChildren() be generic.

There may be times when this level of specificity (the target and such) is not required. That is great. Use a simple solution in those cases. However, a generalized algorithm enables you to accommodate simple and complex situations.


ES6 version that return the first #text node content

const extract = (node) => {
  const text = Array.from(node.childNodes).find(child => child.NodeType === Node.TEXT_NODE);
  return text && text.textContent.trim();
}

.text() - for jquery

$('.title').clone()    //clone the element
.children() //select all the children
.remove()   //remove all the children
.end()  //again go back to selected element
.text();    //get the text of element

This will ignore the whitespace as well so, your never got the Blank textNodes..code using core Javascript.

var oDiv = document.getElementById("MyDiv");
var firstText = "";
for (var i = 0; i < oDiv.childNodes.length; i++) {
    var curNode = oDiv.childNodes[i];
    whitespace = /^\s*$/;
    if (curNode.nodeName === "#text" && !(whitespace.test(curNode.nodeValue))) {
        firstText = curNode.nodeValue;
        break;
    }
}

Check it on jsfiddle : - http://jsfiddle.net/webx/ZhLep/


You can also use XPath's text() node test to get the text nodes only. For example

var target = document.querySelector('div.title');
var iter = document.evaluate('text()', target, null, XPathResult.ORDERED_NODE_ITERATOR_TYPE);
var node;
var want = '';

while (node = iter.iterateNext()) {
    want += node.data;
}

This is my solution in ES6 to create a string contraining the concatenated text of all childnodes (recursive). Note that is also visit the shdowroot of childnodes.

function text_from(node) {
    const extract = (node) => [...node.childNodes].reduce(
        (acc, childnode) => [
            ...acc,
            childnode.nodeType === Node.TEXT_NODE ? childnode.textContent.trim() : '',
            ...extract(childnode),
            ...(childnode.shadowRoot ? extract(childnode.shadowRoot) : [])],
        []);

    return extract(node).filter(text => text.length).join('\n');
}

This solution was inspired by the solution of https://stackoverflow.com/a/41051238./1300775.