htmlunit设置只采集html，取消对css,javascript支持

 

引入htmlunit依赖

 <!-- https://mvnrepository.com/artifact/net.sourceforge.htmlunit/htmlunit -->
        <dependency>
            <groupId>net.sourceforge.htmlunit</groupId>
            <artifactId>htmlunit</artifactId>
            <version>2.15</version>
        </dependency>

 

 

使用

package com.test.htmlunit;

import com.gargoylesoftware.htmlunit.BrowserVersion;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlPage;

import java.io.IOException;

public class Test {

    public static void main(String[] args) {

        try {
            String url="http://www";
            WebClient webClient=new WebClient(BrowserVersion.CHROME);
            webClient.getOptions().setCssEnabled(false );         // 取消css支持
            webClient.getOptions().setJavaScriptEnabled(false );  // 取消javascript支持
            HtmlPage html=webClient.getPage(url);
            System.out.println(html.asXml());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }



}