Java根据XPath提取HTML

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：

1<!-- https://mvnrepository.com/artifact/net.sourceforge.htmlcleaner/htmlcleaner -->
2<dependency>
3    <groupId>net.sourceforge.htmlcleaner</groupId>
4    <artifactId>htmlcleaner</artifactId>
5    <version>2.21</version>
6</dependency>

main函数：

1package com.my.demo;
2
3import javax.xml.xpath.XPath;
4import javax.xml.xpath.XPathConstants;
5import javax.xml.xpath.XPathFactory;
6
7import org.htmlcleaner.CleanerProperties;
8import org.htmlcleaner.DomSerializer;
9import org.htmlcleaner.HtmlCleaner;
10import org.htmlcleaner.TagNode;
11import org.w3c.dom.Document;
12
13public class HtmlXpathJava {
14	public static void main(String[] args) {
15		String sampleHtml = "<div><table><td id='1234 foo 5678'>Hello</td>";
16		String sampleXpath = "//div//td[contains(@id, 'foo')]/text()";
17		System.out.println(getValueByXpath(sampleXpath, sampleHtml));
18	}
19	
20	/**
21	 * Extract value by xPath from HTML.
22	 */
23	private static String getValueByXpath(String xPath, String html) {
24		TagNode tagNode = new HtmlCleaner().clean(html);
25		String value = null;
26		try {
27			Document doc = new DomSerializer(new CleanerProperties()).createDOM(tagNode);
28			XPath xpath = XPathFactory.newInstance().newXPath();
29			value = (String) xpath.evaluate(xPath, doc, XPathConstants.STRING);
30		} catch (Exception e) {
31			System.out.println("Extract value error. " + e.getMessage());
32			e.printStackTrace();
33		}
34		return value;
35	}
36}

输出：

Hello

参考：

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