Javascript获取节点的XPath

时间:2021-01-29 22:17:56

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

反正有没有在Javascript中返回DOM元素的XPath字符串?

5 个解决方案

#1


28  

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?

节点没有唯一的XPath,因此您必须决定构建路径的最合适方式。在可用的地方使用ID?文件中的数字位置?相对于其他元素的位置?

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

有关一种可能的方法,请参阅此答案中的getPathTo()。

#2


64  

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.

我从另一个例子重构了这个。它将尝试检查或确定一个唯一的id,如果是这样,则使用该情况缩短表达式。

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; 
} 

#3


7  

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

这是一个函数编程风格的ES6函数:

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.querySelector(`#${elm.id}`) === elm
            ? [`id("${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.

它将使用id选择器,除非该元素不是具有该id的第一个元素。不使用类选择器,因为在交互式网页中,类可能经常更改。

#4


3  

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

MDN上的函数getXPathForElement给出了类似的解决方案:

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.

此外,XMLSerializer可能值得一试。

#5


0  

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>

#1


28  

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?

节点没有唯一的XPath,因此您必须决定构建路径的最合适方式。在可用的地方使用ID?文件中的数字位置?相对于其他元素的位置?

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

有关一种可能的方法,请参阅此答案中的getPathTo()。

#2


64  

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.

我从另一个例子重构了这个。它将尝试检查或确定一个唯一的id,如果是这样,则使用该情况缩短表达式。

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; 
} 

#3


7  

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

这是一个函数编程风格的ES6函数:

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.querySelector(`#${elm.id}`) === elm
            ? [`id("${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.

它将使用id选择器,除非该元素不是具有该id的第一个元素。不使用类选择器,因为在交互式网页中,类可能经常更改。

#4


3  

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

MDN上的函数getXPathForElement给出了类似的解决方案:

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.

此外,XMLSerializer可能值得一试。

#5


0  

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>