AspriseOCR破解用Java实现网络图片解析

AspriseOCR破解用Java实现网络图片解析

             

 

             

前段时间做网络爬虫需要用到图片解析功能，个人从网络苦心搜索研究了一下，由此产生了以下的文档，博客一下，给有同样需要的人分享，呵呵

 

一、开发环境配置

 

l         开发环境：jdk6.0

l         硬件环境：Windows XP 32bit

l         开发工具：eclipse3.4

l         开发用到外部java组件包：Asprise OCR v4.0 for Java

下载Asprise OCR v4.0 for Java到http://asprise.com/product/ocr/download.php?lang=java

l         破解Asprise OCR v4.0 for Java工具：CloseWin.exe

（破解Asprise OCR v4.0 for Java的原因：由于利用Asprise OCR v4.0 for Java进行开发时，总是弹出提示购买的窗口，只有当点击该窗口后才会得到图片的解析结果，所以破解工具的作用就是实现销毁这个窗口，从而实现利用Asprise OCR v4.0 for Java进行图片的批量解析）

破解工具是C++写的工程源码等我已经上传了，有需要的下载了，得给点辛苦分哦，呵呵

l         配置Asprise OCR v4.0 for Java

解压Asprise-OCR-Java-Windows_XP_32bit-4.0.rar，到解压后的文件内把AspriseOCR.dll、DevIL.dll、ILU.dll这三个dll库文件放到 windows/system32，开发中会用到开发用到aspriseOCR.jar组件

下面

 

二、代码开发

 

1、流程如下：

 

2、详细代码如下：

 

l         图片下载类

package net.crawler.common;

 

/**

 * 本程序的功能实现网络下载

 * 把指定url的文件下载到本地硬盘

 *

 */

import java.io.*;

import java.net.*;

 

/**

 * @todo 将网上获取的图像,mp3等文件存储到本地

 *

 * @version 1.0

 */

 

public class DownLoadWithUrl {

 

       public static File downLoadFile(String fromUrl) {

              URL url;

              File file = null;

              try {

                     // url = new

                     // URL("http://count.koubei.com/showphone/showphone.php?f=jpg&w=96&h=10&bc=255,255,255&fc=0,0,0&fs=10&fn=arial&phone=NzMwNzIyNTE1%236aWCXtTNZYkxASrj");

                     url = new URL(fromUrl);

                     URLConnection uc = url.openConnection();

                     InputStream is = uc.getInputStream();

 

                     // 根据下载文件类型的不同，进行相应的文件命名

                     file = new File("D://showphone.jpg");

                     FileOutputStream out = new FileOutputStream(file);

 

                     /*

                      * 该注释内的也是一种写入文件的方法，不过通常下载mp3或者比mp3更小图片

                      * 等这些文件用这种带缓冲的方法写文件比较慢，所以说小文件下载通常用下面 的写文件方法就可以了 // byte[] b = new

                      * byte[102400*3]; // int size = 0; // // while ((size = is.read(b)) !=

                      * -1) { // out.write(b, 1, size); // // }

                      */

 

                     int i = 0;

                     while ((i = is.read()) != -1) {

                            out.write(i);

                     }

                     out.flush();

 

                     is.close();

              } catch (Exception e) {

                     System.out.println("图片下载或存盘失败！");

              }

 

              return file;

 

       }

 

       /**

        * 删除本地磁盘指定路径的文件 create date:2009-5-13 author:Administrator

        *

        * @param file

        */

       public static void delFile(File file) {

             

              if (file.exists())

                     file.delete();

       }

 

       public static void main(String[] args) {

              // delFile("D://forever.mp3");

              downLoadFile("http://count.koubei.com/showphone/showphone.php?f=jpg&w=96&h=10&bc=255,255,255&fc=0,0,0&fs=10&fn=arial&phone=NzMwNzIyNTE1%236aWCXtTNZYkxASrj");

       }

}

 

l         图片文字解析类

package net.crawler.common;

 

/**

 * 本程序实现了图片文字解析(识别图片中的文字信息）

 */

import java.awt.image.BufferedImage;

import java.io.File;

import java.io.IOException;

 

import javax.imageio.ImageIO;

 

import com.asprise.util.ocr.OCR;

 

public class ParseJPEG_withOCR {

 

       public static void main(String[] args) {

 

       }

 

       /**

        * 返回图片文字的识别结果 create date:2009-5-22 author:Administrator

        *

        * @param imageFile

        * @return

        */

       public static String getRecogniseStr(File imageFile) {

 

              String s = "";

              try {

 

                     BufferedImage image = ImageIO.read(imageFile);

                     int width = image.getTileWidth();

                     int height = image.getTileHeight();

                     image = image.getSubimage(0, 0, width, height);

                     s = new OCR().recognizeEverything(image);

 

              } catch (IOException e) {

                     e.printStackTrace();

                     System.out.println("图片识别失败！");

              }

              return s;

       }

}

 

l         网络图片解析类

package net.crawler.common;

 

/**

 * 本程序实现功能：给出一个图片的具体网络地址，把该图片的进行解析，解析后把图片内容以字符串形式进行返回

 */

import java.io.File;

 

public class RecognisePicture {

 

    /**

     * create date:2009-5-22 author:Administrator

     *

     * @param args

     */

    public static void main(String[] args) {

       // TODO Auto-generated method stub

 

        recognise("http://count.koubei.com/showphone/showphone.php?f=jpg&w=96&h=10&bc=255,255,255&fc=0,0,0&fs=10&fn=arial&phone=NzMwNzIyNTE1%236aWCXtTNZYkxASrj");

    }

 

    /**

     * 解析指定网络地址的图片信息 create date:2009-5-22 author:Administrator

     *

     * @param fromUrl

     * @return

     */

    public static String recognise(String fromUrl) {

 

       String result = "";

       // 下载图片文件到本地磁盘

       File file = DownLoadWithUrl.downLoadFile(fromUrl);

       if (file != null) {

           // 解析下载到本地磁盘文件

           result = ParseJPEG_withOCR.getRecogniseStr(file);

           // 删除下载到本地磁盘的文件

           DownLoadWithUrl.delFile(file);

       }

       return result;

    }

}