HttpURLConnection模拟登录后添加cookie读取网页

该代码示例展示了如何使用HttpURLConnection进行模拟登录百度,并获取cookie来遍历和读取百度贴吧的帖子内容。通过设置请求头的Cookie属性,程序能够读取到每个帖子的标题和内容,并将结果保存到本地文件中,同时记录无法读取的帖子链接。
摘要由CSDN通过智能技术生成
package fileTest;

import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;

public class ConnTest {
    public static void main(String args[]) throws Exception{
        String lianzaiUrl = "http://tieba.baidu.com/p/1243174814?pn=";
        String loginAction = "https://passport.baidu.com/?login?";
        //取cookie
        String cookie =  getCookie("test","test",loginAction);
        if(!cookie.contains("USERID=")){
            System.out.println("登录失败");
            System.exit(1);
        }
        StringBuffer result = new StringBuffer();
        StringBuffer errorList = new StringBuffer();
        for(int i=1;i<=3;i++){
            String allUrl = getUrl(lianzaiUrl+i);
            String all[] = allUrl.split(";");
            for(int x = 0;x < all.length;x++){//拿到每个帖子的地址
                String content = doRead(cookie, all[x]);
                if(null != content && !"".equals(content)){
                    result.append(content);
                }else{
                    errorList.append(all[x] + "\r\n");
                }
            }
        }
        BufferedWriter writer = new BufferedWriter(new FileWriter(new File("F:\\遮天.txt")));
        BufferedWriter errorWriter = new BufferedWriter(new FileWriter(new File("F:\\errorList.txt")));
        writer.write(result.toString());
        writer.flush();
        writer.clo
  • 0
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
package test; import java.io.BufferedReader; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.io.OutputStream; import java.net.HttpURLConnection; import java.net.MalformedURLException; import java.net.URL; import java.util.List; import java.util.Map; public class HttpTest { private HttpURLConnection hc = null; private static final String oneUrlString = "http://xxx.jsp"; private static final String twoUrlString = "http://xxx.action"; public String getSessionId() { String sessionId = ""; try { URL url = new URL(oneUrlString); hc = (HttpURLConnection) url.openConnection();//默认的用GET提交 hc.setDoOutput(true); hc.connect(); Map map = hc.getHeaderFields(); //得到Cookie的所有内容,包括SESSIONID,在进行下次提交的时候 直接把这个Cookie的值设到头里头就行了 //淡然只得到SESSIONID也很简单的 ,但是有时候Set-Cookie的值有几个的 List list = (List) map.get("Set-Cookie"); if(list.size() == 0||list == null) { return null; } StringBuilder builder = new StringBuilder(); for(String str : list) { sessionId = builder.append(str).toString(); } hc.disconnect(); } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } return sessionId; } public String getResponseContext(String parameters) { String responseContext = ""; try { URL url = new URL(twoUrlString); hc = (HttpURLConnection) url.openConnection();//使用POST提交 hc.addRequestProperty("Cookie", getSessionId()); hc.setDoOutput(true); hc.connect(); OutputStream out = hc.getOutputStream(); //参数是a=""&b=""这样拼接的一个串 out.flush(); out.close(); out.write(parameters.getBytes(),0,parameters.getBytes().length); InputStream in = hc.getInputStream(); InputStreamReader reader = new InputStreamReader(in,"gb2312"); BufferedReader read = new BufferedReader(reader); StringBuilder builder = new StringBuilder(); String str = ""; while((str = read.readLine()) != null) { builder = builder.append(str); } read.close(); reader.close(); in.close(); hc.disconnect(); responseContext = builder.toString(); } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } return responseContext; } }
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值