<dependency>

    <groupId>net.sourceforge.htmlunit</groupId>

    <artifactId>htmlunit</artifactId>

    <version>2.26</version>

</dependency>

package com.demo;

import com.gargoylesoftware.htmlunit.BrowserVersion;

import java.io.IOException;

import java.net.MalformedURLException;

import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;

import com.gargoylesoftware.htmlunit.WebClient;

import com.gargoylesoftware.htmlunit.html.HtmlPage;

public class HtmlUnitTest {

    public static void main(String[] args) {

       //模拟指定浏览器   使用代理

        WebClient webClient=new WebClient(BrowserVersion.FIREFOX_52,"202.106.16.36",3128); // 实例化Web客户端

 webClient.getOptions().setCssEnabled(false); // 取消css支持

        webClient.getOptions().setJavaScriptEnabled(false); // 取消javascript支持

        try {

            HtmlPage page=webClient.getPage("http://www.baidu.com"); // 解析获取页面

         Thread.sleep(10000); // 休息10秒钟 等待htmlunit执行js

          HtmlForm form=page.getFormByName("myform"); // 得到搜索Form

            HtmlTextInput textField=form.getInputByName("q"); // 获取查询文本框

            HtmlSubmitInput button=form.getInputByName("submitButton"); // 获取提交按钮

            textField.setValueAttribute("java"); // 文本框“填入”数据

            HtmlPage page2=button.click(); // 模拟点击

            HtmlTable table=page.getHtmlElementById("table1");

            for(HtmlTableRow row:table.getRows()){ // 遍历所有行

                for(HtmlTableCell cell:row.getCells()){  // 遍历所有列

                    System.out.print(cell.asText()+" ");

                }

                System.out.println();

            }

            HtmlDivision div=page.getHtmlElementById("navMenu");  // 查找指定id的html dom元素

            System.out.println(div.asXml());

            System.out.println("======================");

            DomNodeList<DomElement> aList=page.getElementsByTagName("a"); // 根据tag名称查询所有tag

            for(int i=0;i<aList.getLength();i++){

                DomElement a=aList.get(i);

                System.out.println(a.asXml());

            }

            System.out.println("======================");

            HtmlListItem item =(HtmlListItem) page.getByXPath("//div[@id='navMenu'][1]/ul/li").get(0); // xpath方式

            System.out.println(item.asXml());

            System.out.println("网页html:"+page.asXml()); // 获取Html

            System.out.println("====================");

            System.out.println("网页文本："+page.asText()); // 获取文本

        } catch (FailingHttpStatusCodeException e) {

            // TODO Auto-generated catch block

            e.printStackTrace();

        } catch (MalformedURLException e) {

            // TODO Auto-generated catch block

            e.printStackTrace();

        } catch (IOException e) {

            // TODO Auto-generated catch block

            e.printStackTrace();

        }finally{

            webClient.close(); // 关闭客户端，释放内存

        }

    }

}