htmlunit 点击复选框进行选择和模拟点击

最新推荐文章于 2022-10-25 11:17:53 发布

原创最新推荐文章于 2022-10-25 11:17:53 发布 · 2k 阅读

1 ·

CC 4.0 BY-SA版权

本文展示了如何使用HtmlUnit库在Java中模拟点击网页上的复选框和进行其他交互操作，例如输入内容和点击查询按钮。通过这些步骤，可以获取并打印出页面上特定元素的文本信息。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package a.test;

import java.io.IOException;
import java.net.MalformedURLException;
import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlElement;
import com.gargoylesoftware.htmlunit.html.HtmlInput;
import com.gargoylesoftware.htmlunit.html.HtmlOption;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
import com.gargoylesoftware.htmlunit.html.HtmlSelect;
import com.gargoylesoftware.htmlunit.html.HtmlSubmitInput;

/**
*
* @author Administrator
*
*/
public class HkltCrawlerImpl{

public static void main(String[] args) {
   try {
           start("350582199001122011");//身份证id
       } 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();
       }
   }


   public static String start(String id) throws FailingHttpStatusCodeException, MalformedURLException, IOException { final WebClient webClient = new WebClient();

HtmlPage page1 = webClient.getPage("http://218.85.65.43:28000/FJWeb/Web/Studytimeselect.aspx");//获取要爬的页面地址
HtmlSelect select = (HtmlSelect) page1.getElementByName("drop_cx");//获取复选框
HtmlOption option = select.getOptionByValue("B1");//选择复选框里的选项
HtmlPage page3 = option.click();//模拟点击

HtmlInput input1 = page1.getElementByName("txt_sfzh_search");//获取一个输入框
input1.setValueAttribute(id);//输入框里输入内容

HtmlSubmitInput submit1 = page1.getElementByName("btn_search");//获取查询按钮
page1=submit1.click();//模拟点击

System.out.println(page1.asXml()); //输出xml代码页面的形式
HtmlElement pxdw = page1.getHtmlElementById("lbl_yhmc");//获取xml代码页面中培训单位
HtmlElement xm = page1.getHtmlElementById("lbl_xm");//获取xml代码页面中学员姓名
HtmlElement time = page1.getHtmlElementById("lbl_bmrq");//获取xml代码页面报名时间
String a = pxdw.getTextContent();//获取中培训单位
String b = xm.getTextContent();//获取学员姓名
String c = time.getTextContent();//获取报名时间
String html=a+" "+b+" "+c;
System.out.println(html);
webClient.closeAllWindows();//关掉
return html;
}