java分別通過httpclient和HttpURLConnection獲取圖片驗證碼內容

前面的文章，介紹了如何通過selenium+Tesseract-OCR來識別圖片驗證碼，如果用接口來訪問的話，再用selenium就閑的笨重，下面就介紹一下分別通過httpclient和HttpURLConnection，用流的方式獲取圖片驗證碼內容。

1.通過HttpURLConnection

package com.imgyzm;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;

import org.openqa.selenium.io.FileHandler;

/** 
 * @author QiaoJiafei 
 * @version 創建時間：2015年11月9日 上午11:31:14 
 * 類說明 
 */
public class GetYZMByURL {
    public static void main(String[] args) throws Exception {
        getYzm();
    }
    
    public static String getYzm() {
        //new一個URL對象
        URL url;
        String s="";
        try {
            url = new URL("http://172.16.30.226:8099/bms/checkcode.do?0.9858807739801705");
            HttpURLConnection conn = (HttpURLConnection)url.openConnection();
            //設置請求方式為"GET"
            conn.setRequestMethod("GET");
            //超時響應時間為5秒
            conn.setConnectTimeout(5 * 1000);
            //通過輸入流獲取圖片數據
            InputStream inStream = conn.getInputStream();
            //得到圖片的二進制數據，以二進制封裝得到數據，具有通用性
            byte[] data = readInputStream(inStream);
            //new一個文件對象用來保存圖片，默認保存當前工程根目錄
            File imageFile = new File("D:/BeautyGirl.jpg");
            //創建輸出流
            FileOutputStream outStream = new FileOutputStream(imageFile);
            //寫入數據
            outStream.write(data);
            //關閉輸出流
            outStream.close();
            
            Runtime rt = Runtime.getRuntime();
            rt.exec("cmd.exe /C  tesseract.exe D:\\BeautyGirl.jpg  D:\\ddd\\yzm -1 ");
            Thread.sleep(1000);
            File file = new File("D:\\ddd\\yzm.txt");
            if(file.exists()) {
                FileHandler fh = new FileHandler();
                s = fh.readAsString(file).trim();
                System.out.println("========="+s);
            } else {
                System.out.print("yzm.txt不存在");
            }
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        return s;
        //打開鏈接
        
    }
    public static byte[] readInputStream(InputStream inStream) throws Exception{
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        //創建一個Buffer字符串
        byte[] buffer = new byte[1024];
        //每次讀取的字符串長度，如果為-1，代表全部讀取完畢
        int len = 0;
        //使用一個輸入流從buffer里把數據讀取出來
        while( (len=inStream.read(buffer)) != -1 ){
            //用輸出流往buffer里寫入數據，中間參數代表從哪個位置開始讀，len代表讀取的長度
            outStream.write(buffer, 0, len);
        }
        //關閉輸入流
        inStream.close();
        //把outStream里的數據寫入內存
        return outStream.toByteArray();
    }
}

2.通過HttpClient

package com.imgyzm;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.impl.conn.PoolingClientConnectionManager;
import org.apache.http.util.EntityUtils;
import org.openqa.selenium.io.FileHandler;

/** 
 * @author QiaoJiafei 
 * @version 創建時間：2015年11月9日 上午10:53:11 
 * 類說明 
 */
public class GetYZMByHttpClient {
    public static void main(String args[]) throws Exception {
        
        String s="";
        HttpClient httpclient = new DefaultHttpClient(new PoolingClientConnectionManager());
        String imgurl = "http://172.16.30.226:8099/bms/checkcode.do?0.9858807739801705";
        HttpGet ht = new HttpGet(imgurl);
        HttpResponse response = null;
        response = httpclient.execute(ht);
        HttpEntity entity = response.getEntity();
        InputStream inStream = entity.getContent();
        byte[] data = readInputStream(inStream);
        //new一個文件對象用來保存圖片，默認保存當前工程根目錄
        File imageFile = new File("D:/yzm.jpg");
        //創建輸出流
        FileOutputStream outStream = new FileOutputStream(imageFile);
        //寫入數據
        outStream.write(data);
        //關閉輸出流
        outStream.close();
        
        Runtime rt = Runtime.getRuntime();
        rt.exec("cmd.exe /C  tesseract.exe D:\\yzm.jpg  D:\\ddd\\yzm -1 ");
        Thread.sleep(1000);
        File file = new File("D:\\ddd\\yzm.txt");
        if(file.exists()) {
            FileHandler fh = new FileHandler();
            s = fh.readAsString(file).trim();
            System.out.println("========="+s);
        } else {
            System.out.print("yzm.txt不存在");
        }
        
        
        /*===========下面是登錄接口==========*/
        String url = "http://172.16.30.226:8099/bms/staff/login.do?account=admin123&checkcode="+s+"&pwd=aaaaaa1";
        System.out.println("url=========="+url);
        HttpPost httppost = new HttpPost(url);
        response = httpclient.execute(httppost);
        entity = response.getEntity();
        s = EntityUtils.toString(entity, "UTF-8");
        System.out.println(s);
        
    //打開鏈接
    }
    public static byte[] readInputStream(InputStream inStream) throws Exception{
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        //創建一個Buffer字符串
        byte[] buffer = new byte[1024];
        //每次讀取的字符串長度，如果為-1，代表全部讀取完畢
        int len = 0;
        //使用一個輸入流從buffer里把數據讀取出來
        while( (len=inStream.read(buffer)) != -1 ){
            //用輸出流往buffer里寫入數據，中間參數代表從哪個位置開始讀，len代表讀取的長度
            outStream.write(buffer, 0, len);
        }
        //關閉輸入流
        inStream.close();
        //把outStream里的數據寫入內存
        return outStream.toByteArray();
    }
}

那么這兩種方式有什么區別呢，通過測試，使用HttpURLConnection獲取驗證碼，再被其它接口調用的時候，該驗證碼已經失效了。而httpclient，只要保證程序接口調用和獲取驗證碼用的是同一個httpclient，獲取到的驗證碼，再被其它接口調用，該驗證碼仍生效。

保存圖片也可以用下面的方法，更簡便一些

response = client.execute(httpget);
            entity = response.getEntity();
            InputStream  in = entity.getContent();
            BufferedImage input = ImageIO.read(in);
            ImageIO.write(input, "jpg", new File("D:/11.jpg"));   

 

 

HTPPCLIENT API:http://hc.apache.org/httpcomponents-client-ga/httpclient/apidocs/