码迷,mamicode.com
首页 > Web开发 > 详细

使用Post方法模拟登陆爬取网页(转)

时间:2017-09-05 00:23:59      阅读:190      评论:0      收藏:0      [点我收藏+]

标签:tostring   exception   pre   agent   response   post请求   puts   结果   bash   

最近弄爬虫,遇到的一个问题就是如何使用post方法模拟登陆爬取网页。下面是极简版的代码:

技术分享


import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;

import java.net.HttpURLConnection;
import java.net.URL;

import java.util.HashMap;

public class test {

    //post请求地址
    private static final String POST_URL = "";
    
    //模拟谷歌浏览器请求
    private static final String USER_AGENT = "";
    
    //用账号登录某网站后 请求POST_URL链接获取cookie
    private static final String COOKIE = "";
    
    //用账号登录某网站后 请求POST_URL链接获取数据包
    private static final String REQUEST_DATA =  "";
    
    public static void main(String[] args) throws Exception {
        HashMap<String, String> map = postCapture(REQUEST_DATA);
        String responseCode = map.get("responseCode");
        String value = map.get("value");
        
        while(!responseCode.equals("200")){
            map =  postCapture(REQUEST_DATA);
            responseCode = map.get("responseCode");
            value = map.get("value");
        }
        
        //打印爬取结果
        System.out.println(value);
    }
    
    private static HashMap<String, String> postCapture(String requestData) throws Exception{
        HashMap<String, String> map = new HashMap<>();
        
        URL url = new URL(POST_URL);
        HttpURLConnection httpConn = (HttpURLConnection) url.openConnection();
        httpConn.setDoInput(true); // 设置输入流采用字节流
        httpConn.setDoOutput(true); // 设置输出流采用字节流
        httpConn.setUseCaches(false); //设置缓存
        httpConn.setRequestMethod("POST");//POST请求
        httpConn.setRequestProperty("User-Agent", USER_AGENT);
        httpConn.setRequestProperty("Cookie", COOKIE);
        
        PrintWriter out = new PrintWriter(new OutputStreamWriter(httpConn.getOutputStream(), "UTF-8"));
        out.println(requestData);
        out.close();

        int responseCode = httpConn.getResponseCode();
        StringBuffer buffer = new StringBuffer();
        if (responseCode == 200) {
            BufferedReader reader = new BufferedReader(new InputStreamReader(httpConn.getInputStream(), "UTF-8"));
            String line = null;
            while ((line = reader.readLine()) != null) {
                buffer.append(line);
            }
            reader.close();
            httpConn.disconnect();
        }
        
        map.put("responseCode", new Integer(responseCode).toString());
        map.put("value", buffer.toString());
        return map;
    }

}

原文地址:
http://wangxin123.com/2016/12/19/%E4%BD%BF%E7%94%A8Post%E6%96%B9%E6%B3%95%E6%A8%A1%E6%8B%9F%E7%99%BB%E9%99%86%E7%88%AC%E5%8F%96%E7%BD%91%E9%A1%B5/

使用Post方法模拟登陆爬取网页(转)

标签:tostring   exception   pre   agent   response   post请求   puts   结果   bash   

原文地址:http://www.cnblogs.com/panxuejun/p/7476222.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!