有验证码的模拟登录获取数据信息

Question

有一个网站，想获取它的数据信息，但需要登录才可以获取到。他们有图片验证码，我现在能否在我这里远程调用他的图片验证码url,手动录入这个验证码，来实现模拟登录获取数据信息的？我目前测试的好像总是提示验证码不正确，不清楚怎么回事？

Answer 1

可以:
1、访问图片的URL，获取 第一次的cookie1，下载图片，识别图片 str。

2、使用 上一次的 cookie1 和 str 加你的用户名和密码等.... 登陆，获取 cookie2

3、访问带上cookie2

在获取验证码时不但要把验证码下载下来，还需要保存当时的参数（百度登录里面是token）和cookie，然后在收入验证码后把验证码和上一次的cookie+参数再加到post参数里面，就OK了，这样验证码就不会变

我用代码说话吧：
语言：Java
第三方jar：httpclient-4.2.1

package cn.gb40;

import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.List;

import org.apache.http.Consts;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.cookie.Cookie;
import org.apache.http.entity.mime.HttpMultipartMode;
import org.apache.http.entity.mime.MultipartEntity;
import org.apache.http.entity.mime.content.FileBody;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.params.CoreConnectionPNames;

import cn.uuwise.CQZDMDLL;


public class Login
{
    public static DefaultHttpClient httpclient = new DefaultHttpClient();
    public static String login_url = "http://www.400gb.com/index.php";
    public static String img_path_url = "http://www.400gb.com/randcodeV2_login.php";
    public static String image_save_path = "c://vcode.png";
    public static String update_url = "http://upload.zhuanmi.net/web/upload.do";
    public static String userid = "1883879";
    public static String modify_file_url = "http://newhome.400gb.com/iajax.php?item=file_act";
    public static String delete_file_url = "http://newhome.400gb.com/iajax.php?item=file_act&action=file_delete&task=file_delete&file_id=";

    public static void main(String[] args) throws Exception
    {

        String cookie = imgCookie();
        System.out.println("img cookie " + cookie);
        String code = identifyImg();

        cookie = loginCookie(code, cookie);

        System.out.println("login cookie " + cookie);

    // <span></span> }

    public static String imgCookie()
    {

        BufferedReader in = null;

        try
        {
            httpclient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 20000);
            HttpGet httpGet = new HttpGet(img_path_url);
            httpGet.getParams().setParameter(CoreConnectionPNames.SO_TIMEOUT, 20000);
            HttpResponse response = httpclient.execute(httpGet); 
            //保存图片
            download(response.getEntity().getContent(), image_save_path);
            List<Cookie> cookies = httpclient.getCookieStore().getCookies();
            httpGet.releaseConnection();
            StringBuilder cookiesSB = new StringBuilder();
            System.out.println("第一次cookie");
            if (cookies.isEmpty())
            {
                System.out.println("None");
            } else
            {
                for (int i = 0; i < cookies.size(); i++)
                {
                    // System.out.println("- " + cookies.get(i).toString());
                    cookiesSB.append(cookies.get(i).getName()).append("=")
                            .append(cookies.get(i).getValue()).append("; ");
                }
            }

            return cookiesSB.toString();
        }  catch (Exception e)
        {
            e.printStackTrace();

            return null;
        } finally{
            if(in != null)
                try
                {
                    in.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
        }
    }


    public static String identifyImg()
    String str = CQZDMDLL.result(image_save_path);
        if(str != null && str.trim().matches("\\d{4,}"))
            return str;

        return null;
    }

    public static String loginCookie(String code, String cookie)
    {
        try
        {
            httpclient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 20000);
            // 2  用户登录
            HttpPost httppost = new HttpPost(login_url); 
            httppost.setHeader("Cookie", cookie);
            List<NameValuePair> nvps = new ArrayList<NameValuePair>();
            nvps.add(new BasicNameValuePair("item", "account"));
            nvps.add(new BasicNameValuePair("action", "login"));
            nvps.add(new BasicNameValuePair("task", "login"));
            nvps.add(new BasicNameValuePair("ref", ""));
            nvps.add(new BasicNameValuePair("formhash", "fba6075a"));
            nvps.add(new BasicNameValuePair("randcodeV2", code));
            nvps.add(new BasicNameValuePair("username", "----"));
            nvps.add(new BasicNameValuePair("password", "-------"));

            httppost.setHeader("Host", "www.400gb.com");
            httppost.setHeader("Origin", "http://www.400gb.com");
            httppost.setHeader("Referer", "http://www.400gb.com/index.php");
            httppost.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.110 Safari/537.36 CoolNovo/2.0.9.19");

            httppost.setEntity(new UrlEncodedFormEntity(nvps, Consts.UTF_8));
            httppost.getParams().setParameter(CoreConnectionPNames.SO_TIMEOUT, 20000);
            HttpResponse response = httpclient.execute(httppost);

            System.out.println("Login form get: " + response.getStatusLine().getStatusCode());


        //  System.out.println(sb.toString());

            List<Cookie> cookies = httpclient.getCookieStore().getCookies();
            httppost.releaseConnection();
            StringBuilder cookiesSB = new StringBuilder();
            System.out.println("第一次cookie");
            if (cookies.isEmpty())
            {
                System.out.println("None");
            } else
            {
                for (int i = 0; i < cookies.size(); i++)
                {
                    // System.out.println("- " + cookies.get(i).toString());
                    cookiesSB.append(cookies.get(i).getName()).append("=")
                            .append(cookies.get(i).getValue()).append("; ");
                }
            }

            httppost.releaseConnection();

            return cookiesSB.toString();

        } catch (Exception e)
        {
            e.printStackTrace();
        }

        return null;
    }

    public static String rend(String cookie)
    {
        BufferedReader in = null;

        try
        {
            // 1 获取 _tb_token_
            httpclient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 20000);
            HttpGet httpGet = new HttpGet("http://www.400gb.com/index.php");
            httpGet.setHeader("Cookie", cookie);
            httpGet.setHeader("Host", "www.400gb.com");
            httpGet.setHeader("Referer", "http://www.400gb.com/index.php");
            httpGet.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.110 Safari/537.36 CoolNovo/2.0.9.19");

            httpGet.getParams().setParameter(CoreConnectionPNames.SO_TIMEOUT, 20000);
            HttpResponse response = httpclient.execute(httpGet); 


            in = new BufferedReader(new InputStreamReader(response.getEntity().getContent(), "utf-8"));
            StringBuilder sb = new StringBuilder();
            String s = "";
            while ((s = in.readLine()) != null)
            {
                sb.append(s.trim()).append("\n");
            }

            System.out.println(sb.toString());

            return sb.toString();
        }  catch (Exception e)
        {
            e.printStackTrace();

            return null;
        } finally{
            if(in != null)
                try
                {
                    in.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
        }
    }

    public static long upload(String cookie, String path) throws Exception
    {
        BufferedReader in = null;
        String newurl = update_url + "?userid=" + userid + "&folderid=0&key=key.....................&maxsize=2147483648";
        HttpPost post = new HttpPost(newurl);

        post.setHeader("Cookie", cookie);
        post.setHeader("Referer", "http://newhome.400gb.com/?item=files&action=index");
    //  post.setHeader("Content-Type", "multipart/form-data; boundary=----------ei4Ef1Ef1Ef1cH2KM7ei4gL6gL6ei4");
        post.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17");
        //对请求的表单域进行填充  
    //  MultipartEntity reqEntity = new MultipartEntity(HttpMultipartMode.BROWSER_COMPATIBLE , null, Charset.forName("UTF-8")); 
        MultipartEntity reqEntity = new MultipartEntity(HttpMultipartMode.BROWSER_COMPATIBLE); 


        reqEntity.addPart( "fileData", new FileBody( new File(path), "text/plain" ));
        post.setEntity(reqEntity);  

        // Here we go!
        try
        {
            HttpResponse response = httpclient.execute(post);

            System.out.println("upload code " + response.getStatusLine().getStatusCode());
            if(200 == response.getStatusLine().getStatusCode())
            {

            }

            in = new BufferedReader(new InputStreamReader(response.getEntity().getContent(), "utf-8"));
            StringBuilder sb = new StringBuilder();
            String s = "";
            while ((s = in.readLine()) != null)
            {
                sb.append(s.trim()).append("\n");
            }

            //{"filename":"head","updatetime":"2013-06-10 13:00","filetype":"jpg","istype":1,"username":"safetys","filesize":"10.47 KB","uid":"841690","parentid":null,"ip":"125.39.35.21","sid":8859860,"filethumb":"jpg"}
            String str = sb.toString();

            if(str == null || !str.trim().matches("\\d+"))
                return 0;

            else
                return Long.parseLong(str.trim());

        } catch (ClientProtocolException e)
        {
            System.err.println(e);
        } catch (IOException e)
        {
            System.err.println(e);
        } 

        post.releaseConnection();


        return 0l;
    }

    public static void addDesc(String cookie, long fileid, String desc)
    {
        BufferedReader in = null;
        try
        {
            httpclient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 20000);
            // 2  用户登录
            HttpPost httppost = new HttpPost(modify_file_url); 
            httppost.setHeader("Cookie", cookie);
            List<NameValuePair> nvps = new ArrayList<NameValuePair>();
            nvps.add(new BasicNameValuePair("action", "file_modify"));
            nvps.add(new BasicNameValuePair("task", "file_modify"));
            nvps.add(new BasicNameValuePair("formhash", "a410f69a"));
            nvps.add(new BasicNameValuePair("file_id", String.valueOf(fileid)));
            nvps.add(new BasicNameValuePair("file_name", "vcro3de.png"));
            nvps.add(new BasicNameValuePair("file_description", desc));

            httppost.setHeader("Host", "newhome.400gb.com");
            httppost.setHeader("Origin", "http://newhome.400gb.com");
            httppost.setHeader("Referer", "http://newhome.400gb.com/?item=files&action=index");
            httppost.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.110 Safari/537.36 CoolNovo/2.0.9.19");

            httppost.setEntity(new UrlEncodedFormEntity(nvps, Consts.UTF_8));
            httppost.getParams().setParameter(CoreConnectionPNames.SO_TIMEOUT, 20000);
            HttpResponse response = httpclient.execute(httppost);

            System.out.println("add description code: " + response.getStatusLine().getStatusCode());


             in = new BufferedReader(new InputStreamReader(response.getEntity().getContent(), "utf-8"));
                StringBuilder sb = new StringBuilder();
                String s = "";
                while ((s = in.readLine()) != null)
                {
                    sb.append(s.trim()).append("\n");
                }


            httppost.releaseConnection();
            // 返回OK 就证明修改成功，否则有可能文件重名了
            System.out.println("update desc html " + sb.toString());

        } catch (Exception e)
        {
            e.printStackTrace();
        } finally {
            if(in != null)
                try
                {
                    in.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
        }


    }

    public static void deleteFile(String cookie, long fileid)
    {
        try
        {
            httpclient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT, 20000);
            HttpGet httpGet = new HttpGet(delete_file_url + fileid);
            httpGet.setHeader("Cookie", cookie);
            httpGet.setHeader("Host", "newhome.400gb.com");
            httpGet.setHeader("Referer", "http://newhome.400gb.com/?item=files&action=index");
            httpGet.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.110 Safari/537.36 CoolNovo/2.0.9.19");

            httpGet.getParams().setParameter(CoreConnectionPNames.SO_TIMEOUT, 20000);
            HttpResponse response = httpclient.execute(httpGet); 
            System.out.println("delete file code " + response.getStatusLine().getStatusCode());
            httpGet.releaseConnection();


        }  catch (Exception e)
        {
            e.printStackTrace();

        } finally{

        }
    }

    public static boolean download(InputStream in, String path)
    {
        FileOutputStream out = null;
        try
        {
            out = new FileOutputStream(path);
            byte b[] = new byte[1024];
            int j = 0;
            while ((j = in.read(b)) != -1)
            {
                out.write(b, 0, j);
            }
            out.flush();
            File file = new File(path);
            if(file.exists() && file.length() == 0)
                return false;
            return true;
        } catch (MalformedURLException e)
        {
            e.printStackTrace();
        } catch (IOException e)
        {
            if("FileNotFoundException".equals(e.getClass().getSimpleName()))
                System.err.println("download FileNotFoundException");
            if("SocketTimeoutException".equals(e.getClass().getSimpleName()))
                System.err.println("download SocketTimeoutException");
            else
                e.printStackTrace();
        } finally{

            if(out != null)
                try
                {
                    out.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
            if(in != null)
                try
                {
                    in.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
        }
        return false;
    }

    /**
     * 采集
     * @param url：指定URL
     * @param times：如果采集失败，采集最少次数（2次）
     * @return
     */
    public static boolean download(String urlstr, String path)
    {
        if(urlstr == null || "".equals(urlstr.trim()))
            return false;


        InputStream in = null;
        FileOutputStream out = null;
        try
        {
            System.out.println("download url " + urlstr);
            URL url = new URL(urlstr);
            URLConnection connection = url.openConnection();
            connection.setConnectTimeout(5000);//jdk 1.5换成这个,连接超时
            //connection.setReadTimeout(5000);//jdk 1.5换成这个,读操作超时
            connection.setDoOutput(true);

            out = new FileOutputStream(path);
            in = connection.getInputStream();
            byte b[] = new byte[1024];
            int j = 0;
            while ((j = in.read(b)) != -1)
            {
                out.write(b, 0, j);
            }
            out.flush();
            File file = new File(path);
            if(file.exists() && file.length() == 0)
                return false;
            return true;
        } catch (MalformedURLException e)
        {
            e.printStackTrace();
        } catch (IOException e)
        {
            if("FileNotFoundException".equals(e.getClass().getSimpleName()))
                System.err.println("download FileNotFoundException");
            if("SocketTimeoutException".equals(e.getClass().getSimpleName()))
                System.err.println("download SocketTimeoutException");
            else
                e.printStackTrace();
        } finally{

            if(out != null)
                try
                {
                    out.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
            if(in != null)
                try
                {
                    in.close();
                } catch (IOException e)
                {
                    e.printStackTrace();
                }
        }
        return false;
    }

    public static InputStream getUrlImg(String URLName) throws Exception
    {
        ByteArrayOutputStream os = new ByteArrayOutputStream();
        int HttpResult = 0; // 服务器返回的状态
        URL url = new URL(URLName); // 创建URL
        URLConnection urlconn = url.openConnection(); // 试图连接并取得返回状态码urlconn.connect();
        HttpURLConnection httpconn = (HttpURLConnection) urlconn;
        HttpResult = httpconn.getResponseCode();
        System.out.println(HttpResult);
        if (HttpResult != HttpURLConnection.HTTP_OK)
        { // 不等于HTTP_OK说明连接不成功
            System.out.print("连接失败！");
        } else
        {
            int filesize = urlconn.getContentLength(); // 取数据长度
            System.out.println(filesize);
            BufferedInputStream bis = new BufferedInputStream(
                    urlconn.getInputStream());
            BufferedOutputStream bos = new BufferedOutputStream(os);
            byte[] buffer = new byte[1024]; // 创建存放输入流的缓冲
            int num = -1; // 读入的字节数
            while (true)
            {
                num = bis.read(buffer); // 读入到缓冲区
                if (num == -1)
                {
                    bos.flush();
                    break; // 已经读完
                }
                bos.flush();
                bos.write(buffer, 0, num);
            }
            bos.close();
            bis.close();
        }
        ByteArrayInputStream bis = new ByteArrayInputStream(os.toByteArray());
        return bis;
    }
}