xpath java html_Java根据XPath提取HTML

有这样一段HTML：

希望通过这个XPath提取出Hello：

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

先导入maven依赖：

net.sourceforge.htmlcleaner

htmlcleaner

2.21

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 = "

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：