java爬虫模拟登陆的实例详解

import java.io.BufferedWriter;

import java.io.FileOutputStream;

import java.io.IOException;

import java.io.OutputStreamWriter;

import java.util.Map.Entry;

import java.util.Set;

import org.jsoup.Connection;

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
public class SplitTable {
  public static void main(String[] args) throws IOException {
    //想要爬取的url
    String url = "http://jwcnew.nefu.edu.cn/dblydx_jsxsd/xskb/xskb_list.do?
Ves632DSdyV=NEW_XSD_PYGL";
    String username = "";
    String password = "";
    String sessionId = getSessionInfo(username,password);
    spiderWebSite(sessionId,url);
  }

private static String getSessionInfo(String username,String password)
throws IOException{

Connection.Response res = Jsoup.connect(http://jwcnew.nefu.edu.cn/dblydx_jsxsd/xk/LoginToXk)

 String sessionId = res.cookie("JSESSIONID");
    System.out.println(sessionId);
    return sessionId;
  }

private static void spiderWebSite(String sessionId,String url) throws IOException{
    //爬取
    Document doc = Jsoup.connect(url).cookie("JSESSIONID", sessionId).timeout(10000).get();
    Element table = doc.getElementById("kbtable");
    //System.out.println(table);
    BufferedWriter bw = new BufferedWriter
(new OutputStreamWriter(new FileOutputStream("F:/table.html")));
    bw.write(new String(table.toString().getBytes()));
    bw.flush();
    bw.close();
  }
}

import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.jsoup.Connection.Method;
import org.jsoup.Connection.Response;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;

public class LoginDemo {
  public static void main(String[] args) throws Exception {
    LoginDemo loginDemo = new LoginDemo();
    loginDemo.login("16xxx20xxx", "16xxx20xxx");// 用户名，和密码
  }
  /**
   * 模拟登陆座位系统
   * @param userName
   *      用户名
   * @param pwd
   *      密码
   *
   * **/
  public void login(String userName, String pwd) throws Exception {
    // 第一次请求
    Connection con = Jsoup
        .connect("http://lib???.?????????.aspx");// 获取连接
    con.header("User-Agent",
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:29.0) Gecko/20100101 Firefox/29.0");// 配置模拟浏览器
    Response rs = con.execute();// 获取响应
    Document d1 = Jsoup.parse(rs.body());// 转换为Dom树
    List et = d1.select("#form1");// 获取form表单，可以通过查看页面源码代码得知
    // 获取，cooking和表单属性，下面map存放post时的数据
    Map datas = new HashMap<>();
    for (Element e : et.get(0).getAllElements()) {
      //System.out.println(e.attr("name")+"----Little\n");
      if (e.attr("name").equals("tbUserName")) {
        e.attr("value", userName);// 设置用户名
      }

      if (e.attr("name").equals("tbPassWord")) {
        e.attr("value", pwd); // 设置用户密码
      }
      if (e.attr("name").length() > 0) {// 排除空值表单属性
        datas.put(e.attr("name"), e.attr("value"));
      }
    }


    /**
     * 第二次请求，post表单数据，以及cookie信息
     *
     * **/
    Connection con2 = Jsoup
        .connect("http://lib???.?????????.aspx");
    con2.header("User-Agent",
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:29.0) Gecko/20100101 Firefox/29.0");
    // 设置cookie和post上面的map数据
    Response login = con2.ignoreContentType(true).method(Method.POST)
        .data(datas).cookies(rs.cookies()).execute();

    // 登陆成功后的cookie信息，可以保存到本地，以后登陆时，只需一次登陆即可
    Map map = login.cookies();
    //下面输出的是cookie 的内容
    for (String s : map.keySet()) {
      System.out.println(s + "=====-----" + map.get(s));
    }

    System.out.println(login.body());
    /**
     * 登录之后模拟获取预约记录
     *
     * */
    Connection con_record = Jsoup
        .connect("http://lib???.?????????.aspx");// 获取连接
    con_record.header("User-Agent",
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:29.0) Gecko/20100101 Firefox/29.0");// 配置模拟浏览器
    con_record.cookies(datas);

    Response record = con_record.ignoreContentType(true)
        .method(Method.GET)
        .cookies(rs.cookies())
        .execute();
    System.out.println(record.body());
  }
}