简体   繁体   中英

Javascript get XPath of a node

Is there anyway to return an XPath string of a DOM element in Javascript?

I refactored this from another example. It will attempt to check or there is for sure a unique id and if so use that case to shorten the expression.

function createXPathFromElement(elm) { 
    var allNodes = document.getElementsByTagName('*'); 
    for (var segs = []; elm && elm.nodeType == 1; elm = elm.parentNode) 
    { 
        if (elm.hasAttribute('id')) { 
                var uniqueIdCount = 0; 
                for (var n=0;n < allNodes.length;n++) { 
                    if (allNodes[n].hasAttribute('id') && allNodes[n].id == elm.id) uniqueIdCount++; 
                    if (uniqueIdCount > 1) break; 
                }; 
                if ( uniqueIdCount == 1) { 
                    segs.unshift('id("' + elm.getAttribute('id') + '")'); 
                    return segs.join('/'); 
                } else { 
                    segs.unshift(elm.localName.toLowerCase() + '[@id="' + elm.getAttribute('id') + '"]'); 
                } 
        } else if (elm.hasAttribute('class')) { 
            segs.unshift(elm.localName.toLowerCase() + '[@class="' + elm.getAttribute('class') + '"]'); 
        } else { 
            for (i = 1, sib = elm.previousSibling; sib; sib = sib.previousSibling) { 
                if (sib.localName == elm.localName)  i++; }; 
                segs.unshift(elm.localName.toLowerCase() + '[' + i + ']'); 
        }; 
    }; 
    return segs.length ? '/' + segs.join('/') : null; 
}; 

function lookupElementByXPath(path) { 
    var evaluator = new XPathEvaluator(); 
    var result = evaluator.evaluate(path, document.documentElement, null,XPathResult.FIRST_ORDERED_NODE_TYPE, null); 
    return  result.singleNodeValue; 
} 

There's not a unique XPath to a node, so you'll have to decide what's the most appropriate way of constructing a path. Use IDs where available? Numeral position in the document? Position relative to other elements?

See getPathTo() in this answer for one possible approach.

Here is a functional programming style ES6 function for the job:

 function getXPathForElement(element) { const idx = (sib, name) => sib ? idx(sib.previousElementSibling, name||sib.localName) + (sib.localName == name) : 1; const segs = elm => !elm || elm.nodeType !== 1 ? [''] : elm.id && document.getElementById(elm.id) === elm ? [`id("${elm.id}")`] : [...segs(elm.parentNode), `${elm.localName.toLowerCase()}[${idx(elm)}]`]; return segs(element).join('/'); } function getElementByXPath(path) { return (new XPathEvaluator()) .evaluate(path, document.documentElement, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null) .singleNodeValue; } // Demo: const li = document.querySelector('li:nth-child(2)'); const path = getXPathForElement(li); console.log(path); console.log(li === getElementByXPath(path)); // true
 <div> <table id="start"></table> <div> <ul><li>option</ul></ul> <span>title</span> <ul> <li>abc</li> <li>select this</li> </ul> </div> </div>

It will use an id selector, unless the element is not the first one with that id. Class selectors are not used, because in interactive web pages classes may change often.

I've adapted the algorithm Chromium uses to calculate the XPath from devtools below.

To use this as-written you'd call Elements.DOMPath.xPath(<some DOM node>, false) . The last parameter controls whether you get the shorter "Copy XPath" (if true ) or "Copy full XPath".

// Copyright 2018 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

Elements = {};
Elements.DOMPath = {};

/**
 * @param {!Node} node
 * @param {boolean=} optimized
 * @return {string}
 */
Elements.DOMPath.xPath = function (node, optimized) {
    if (node.nodeType === Node.DOCUMENT_NODE) {
        return '/';
    }

    const steps = [];
    let contextNode = node;
    while (contextNode) {
        const step = Elements.DOMPath._xPathValue(contextNode, optimized);
        if (!step) {
            break;
        }  // Error - bail out early.
        steps.push(step);
        if (step.optimized) {
            break;
        }
        contextNode = contextNode.parentNode;
    }

    steps.reverse();
    return (steps.length && steps[0].optimized ? '' : '/') + steps.join('/');
};

/**
 * @param {!Node} node
 * @param {boolean=} optimized
 * @return {?Elements.DOMPath.Step}
 */
Elements.DOMPath._xPathValue = function (node, optimized) {
    let ownValue;
    const ownIndex = Elements.DOMPath._xPathIndex(node);
    if (ownIndex === -1) {
        return null;
    }  // Error.

    switch (node.nodeType) {
        case Node.ELEMENT_NODE:
            if (optimized && node.getAttribute('id')) {
                return new Elements.DOMPath.Step('//*[@id="' + node.getAttribute('id') + '"]', true);
            }
            ownValue = node.localName;
            break;
        case Node.ATTRIBUTE_NODE:
            ownValue = '@' + node.nodeName;
            break;
        case Node.TEXT_NODE:
        case Node.CDATA_SECTION_NODE:
            ownValue = 'text()';
            break;
        case Node.PROCESSING_INSTRUCTION_NODE:
            ownValue = 'processing-instruction()';
            break;
        case Node.COMMENT_NODE:
            ownValue = 'comment()';
            break;
        case Node.DOCUMENT_NODE:
            ownValue = '';
            break;
        default:
            ownValue = '';
            break;
    }

    if (ownIndex > 0) {
        ownValue += '[' + ownIndex + ']';
    }

    return new Elements.DOMPath.Step(ownValue, node.nodeType === Node.DOCUMENT_NODE);
};

/**
 * @param {!Node} node
 * @return {number}
 */
Elements.DOMPath._xPathIndex = function (node) {
    // Returns -1 in case of error, 0 if no siblings matching the same expression,
    // <XPath index among the same expression-matching sibling nodes> otherwise.
    function areNodesSimilar(left, right) {
        if (left === right) {
            return true;
        }

        if (left.nodeType === Node.ELEMENT_NODE && right.nodeType === Node.ELEMENT_NODE) {
            return left.localName === right.localName;
        }

        if (left.nodeType === right.nodeType) {
            return true;
        }

        // XPath treats CDATA as text nodes.
        const leftType = left.nodeType === Node.CDATA_SECTION_NODE ? Node.TEXT_NODE : left.nodeType;
        const rightType = right.nodeType === Node.CDATA_SECTION_NODE ? Node.TEXT_NODE : right.nodeType;
        return leftType === rightType;
    }

    const siblings = node.parentNode ? node.parentNode.children : null;
    if (!siblings) {
        return 0;
    }  // Root node - no siblings.
    let hasSameNamedElements;
    for (let i = 0; i < siblings.length; ++i) {
        if (areNodesSimilar(node, siblings[i]) && siblings[i] !== node) {
            hasSameNamedElements = true;
            break;
        }
    }
    if (!hasSameNamedElements) {
        return 0;
    }
    let ownIndex = 1;  // XPath indices start with 1.
    for (let i = 0; i < siblings.length; ++i) {
        if (areNodesSimilar(node, siblings[i])) {
            if (siblings[i] === node) {
                return ownIndex;
            }
            ++ownIndex;
        }
    }
    return -1;  // An error occurred: |node| not found in parent's children.
};

/**
 * @unrestricted
 */
Elements.DOMPath.Step = class {
    /**
     * @param {string} value
     * @param {boolean} optimized
     */
    constructor(value, optimized) {
        this.value = value;
        this.optimized = optimized || false;
    }

    /**
     * @override
     * @return {string}
     */
    toString() {
        return this.value;
    }
};

 function getElementXPath (element) { if (!element) return null if (element.id) { return `//*[@id=${element.id}]` } else if (element.tagName === 'BODY') { return '/html/body' } else { const sameTagSiblings = Array.from(element.parentNode.childNodes) .filter(e => e.nodeName === element.nodeName) const idx = sameTagSiblings.indexOf(element) return getElementXPath(element.parentNode) + '/' + element.tagName.toLowerCase() + (sameTagSiblings.length > 1 ? `[${idx + 1}]` : '') } } console.log(getElementXPath(document.querySelector('#a div')))
 <div id="a"> <div>def</div> </div>

A similar solution is given by the function getXPathForElement on the MDN:

function getXPathForElement(el, xml) {
    var xpath = '';
    var pos, tempitem2;

    while(el !== xml.documentElement) {     
        pos = 0;
        tempitem2 = el;
        while(tempitem2) {
            if (tempitem2.nodeType === 1 && tempitem2.nodeName === el.nodeName) { // If it is ELEMENT_NODE of the same name
                pos += 1;
            }
            tempitem2 = tempitem2.previousSibling;
        }

        xpath = "*[name()='"+el.nodeName+"' and namespace-uri()='"+(el.namespaceURI===null?'':el.namespaceURI)+"']["+pos+']'+'/'+xpath;

        el = el.parentNode;
    }
    xpath = '/*'+"[name()='"+xml.documentElement.nodeName+"' and namespace-uri()='"+(el.namespaceURI===null?'':el.namespaceURI)+"']"+'/'+xpath;
    xpath = xpath.replace(/\/$/, '');
    return xpath;
}

Also XMLSerializer might be worth a try.

I checked every solution provided here but none of them works with svg elements (code getElementByXPath(getXPathForElement(elm)) === elm returns false for svg or path elements)

So I added the Touko's svg fix to the trincot's solution and got this code:

function getXPathForElement(element) {
    const idx = (sib, name) => sib 
        ? idx(sib.previousElementSibling, name||sib.localName) + (sib.localName == name)
        : 1;
    const segs = elm => !elm || elm.nodeType !== 1 
        ? ['']
        : elm.id && document.getElementById(elm.id) === elm
            ? [`id("${elm.id}")`]
            : [...segs(elm.parentNode), elm instanceof HTMLElement
                ? `${elm.localName}[${idx(elm)}]`
                : `*[local-name() = "${elm.localName}"][${idx(elm)}]`];
    return segs(element).join('/');
}

The difference is it returns *[local-name() = "tag"][n] instead of tag[n] if element is not an instance of HTMLElement (svgs are SVGElement but I decided not to stick with checking only svg).

Example:

Before:
.../div[2]/div[2]/span[1]/svg[1]/path[1]

After:
.../div[2]/div[2]/span[1]/*[local-name() = "svg"][1]/*[local-name() = "path"][1]

Just pass the element in function getXPathOfElement and you will get the Xpath .

function getXPathOfElement(elt)
{
     var path = "";
     for (; elt && elt.nodeType == 1; elt = elt.parentNode)
     {
    idx = getElementIdx(elt);
    xname = elt.tagName;
    if (idx > 1) xname += "[" + idx + "]";
    path = "/" + xname + path;
     }

     return path;   
}
function getElementIdx(elt)
{
    var count = 1;
    for (var sib = elt.previousSibling; sib ; sib = sib.previousSibling)
    {
        if(sib.nodeType == 1 && sib.tagName == elt.tagName) count++
    }

    return count;
}

Get xPath by giving a dom element

This function returns full xPath selector (without any id or class). This type of selector is helpful when an site generate random id or class

function getXPath(element) {
    // Selector
    let selector = '';
    // Loop handler
    let foundRoot;
    // Element handler
    let currentElement = element;

    // Do action until we reach html element
    do {
        // Get element tag name 
        const tagName = currentElement.tagName.toLowerCase();
        // Get parent element
        const parentElement = currentElement.parentElement;

        // Count children
        if (parentElement.childElementCount > 1) {
            // Get children of parent element
            const parentsChildren = [...parentElement.children];
            // Count current tag 
            let tag = [];
            parentsChildren.forEach(child => {
                if (child.tagName.toLowerCase() === tagName) tag.push(child) // Append to tag
            })

            // Is only of type
            if (tag.length === 1) {
                // Append tag to selector
                selector = `/${tagName}${selector}`;
            } else {
                // Get position of current element in tag
                const position = tag.indexOf(currentElement) + 1;
                // Append tag to selector
                selector = `/${tagName}[${position}]${selector}`;
            }

        } else {
            //* Current element has no siblings
            // Append tag to selector
            selector = `/${tagName}${selector}`;
        }

        // Set parent element to current element
        currentElement = parentElement;
        // Is root  
        foundRoot = parentElement.tagName.toLowerCase() === 'html';
        // Finish selector if found root element
        if(foundRoot) selector = `/html${selector}`;
    }
    while (foundRoot === false);

    // Return selector
    return selector;
}

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM