有这样一段HTML： 

<div><table><td id='1234 foo 5678'>Hello</td>

希望通过这个XPath提取出Hello：

//div//td[contains(@id, 'foo')]/text()

先导入maven依赖：

<!-- https://mvnrepository.com/artifact/net.sourceforge.htmlcleaner/htmlcleaner -->
<dependency>
    <groupId>net.sourceforge.htmlcleaner</groupId>
    <artifactId>htmlcleaner</artifactId>
    <version>2.21</version>
</dependency>

main函数：

package com.my.demo;

import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;

import org.htmlcleaner.CleanerProperties;
import org.htmlcleaner.DomSerializer;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.TagNode;
import org.w3c.dom.Document;

public class HtmlXpathJava {
    public static void main(String[] args) {
        String sampleHtml = "<div><table><td id='1234 foo 5678'>Hello</td>";
        String sampleXpath = "//div//td[contains(@id, 'foo')]/text()";
        System.out.println(getValueByXpath(sampleXpath, sampleHtml));
    }
    
    /**
     * Extract value by xPath from HTML.
     */
    private static String getValueByXpath(String xPath, String html) {
        TagNode tagNode = new HtmlCleaner().clean(html);
        String value = null;
        try {
            Document doc = new DomSerializer(new CleanerProperties()).createDOM(tagNode);
            XPath xpath = XPathFactory.newInstance().newXPath();
            value = (String) xpath.evaluate(xPath, doc, XPathConstants.STRING);
        } catch (Exception e) {
            System.out.println("Extract value error. " + e.getMessage());
            e.printStackTrace();
        }
        return value;
    }
}

输出：

Hello

参考：

https://stackoverflow.com/questions/9022140/using-xpath-contains-against-html-in-java