java 使用HtmlUnit来爬取该网页动态加载的正文部分

1.在maven项目中的配置

<!-- https://mvnrepository.com/artifact/net.sourceforge.htmlunit/htmlunit -->
<dependency>
    <groupId>net.sourceforge.htmlunit</groupId>
    <artifactId>htmlunit</artifactId>
    <version>2.27</version>
</dependency>
 

2.代码部分（按照参考的博客进行编写的）

import java.io.IOException;
import java.net.MalformedURLException;
 
import com.gargoylesoftware.htmlunit.BrowserVersion;
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) {
        String url ="http://www.qidian.com";
        url = "http://news.cqcoal.com/blank/nc.jsp?mid=98212";
        // 1创建WebClien