[Java] JAVA使用HtmlUnit爬虫工具模拟登陆CSDN案例

<dependencies>
<!-- https://mvnrepository.com/artifact/net.sourceforge.htmlunit/htmlunit -->
<dependency>
<groupid>net.sourceforge.htmlunit</groupid>
<artifactid>htmlunit</artifactid>
<version>2.18</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
<dependency>
<groupid>org.jsoup</groupid>
<artifactid>jsoup</artifactid>
<version>1.9.2</version>
</dependency>
</dependencies>

package com.test;
import java.io.ioexception;
import java.net.malformedurlexception;
import java.util.hashmap;
import java.util.map;
import java.util.set;
import com.gargoylesoftware.htmlunit.browserversion;
import com.gargoylesoftware.htmlunit.failinghttpstatuscodeexception;
import com.gargoylesoftware.htmlunit.nicelyresynchronizingajaxcontroller;
import com.gargoylesoftware.htmlunit.silentcsserrorhandler;
import com.gargoylesoftware.htmlunit.webclient;
import com.gargoylesoftware.htmlunit.html.htmlbuttoninput;
import com.gargoylesoftware.htmlunit.html.htmlform;
import com.gargoylesoftware.htmlunit.html.htmlpage;
import com.gargoylesoftware.htmlunit.html.htmlpasswordinput;
import com.gargoylesoftware.htmlunit.html.htmltextinput;
import com.gargoylesoftware.htmlunit.util.cookie;
public class simulatelogin
{
 //访问的目标网址（csdn）
 private static string target_url = "https://passport.csdn.net/account/login?from=http://www.csdn.net";
 public static void main(string[] args) throws failinghttpstatuscodeexception, malformedurlexception, ioexception
 {
  // 模拟一个浏览器
  webclient webclient = new webclient(browserversion.chrome);
  // 设置webclient的相关参数
  webclient.setcsserrorhandler(new silentcsserrorhandler()); 
  //设置ajax
  webclient.setajaxcontroller(new nicelyresynchronizingajaxcontroller());
  //设置支持js
  webclient.getoptions().setjavascriptenabled(true);
  //css渲染禁止
  webclient.getoptions().setcssenabled(false);
  //超时时间
  webclient.getoptions().settimeout(50000);
  //设置js抛出异常:false
  webclient.getoptions().setthrowexceptiononscripterror(false);
  //允许重定向
  webclient.getoptions().setredirectenabled(true); 
  //允许cookie
  webclient.getcookiemanager().setcookiesenabled(true); 
  // 模拟浏览器打开一个目标网址
  htmlpage page = webclient.getpage(target_url);
  /**等待js加载完全，csdn这点 特别坑，js加载时间超长！！！！！！！ 后人切记不要用csdn模拟登陆！！！！！！！**/
  webclient.waitforbackgroundjavascript(10000*3);
  // 根据form的名字获取页面表单，也可以通过索引来获取：page.getforms().get(0)  
  htmlform form = (htmlform) page.getelementbyid("fm1");   
  htmltextinput username = (htmltextinput) form.getinputbyname("username"); 
  htmlpasswordinput password = (htmlpasswordinput) form.getinputbyname("password"); 
  username.setvalueattribute("********"); //用户名
  password.setvalueattribute("********"); //密码
  htmlbuttoninput button = (htmlbuttoninput) page.getbyxpath("//input[contains(@class, 'logging')]").get(0);
//  scriptresult result = page.executejavascript("javascript:document.getelementsbyclassname('logging')[0].click()");
//  htmlpage retpage = (htmlpage) result.getnewpage();
  htmlpage retpage = button.click();
  // 等待js驱动dom完成获得还原后的网页 
  webclient.waitforbackgroundjavascript(1000); 
  //输出跳转网页的地址
  system.out.println(retpage.geturl().tostring()); 
  //输出跳转网页的内容
  system.out.println(retpage.asxml());
  //获取cookie 
  set<cookie> cookies = webclient.getcookiemanager().getcookies();
  map<string, string> responsecookies = new hashmap<string, string>(); 
  for (cookie c : cookies) { 
   responsecookies.put(c.getname(), c.getvalue()); 
   system.out.print(c.getname()+":"+c.getvalue()); 
  } 
  webclient.close();
  system.out.println("success!");
 }
}

//设置日志级别，原页面js异常不打印
logfactory.getfactory().setattribute("org.apache.commons.logging.log", "org.apache.commons.logging.impl.nooplog"); 
 
java.util.logging.logger.getlogger("com.gargoylesoftware.htmlunit") 
 .setlevel(level.off); 
 
java.util.logging.logger.getlogger("org.apache.commons.httpclient") 
 .setlevel(level.off);