OCR图片转文字功能实现

前言：由于本人技术过于菜，在实现这个功能的时候，遇到很多问题，其实主要原因还是因为看不太习惯API接口，所以我建议大家多看看API文档，经常看以后遇到需要看API文档的时候也就会了；

软硬件环境：百度云文字识别接口，MyEclipse;

步骤：1.注册或者登录百度云官网，进入控制台选择文字识别

步骤 ：2.创建应用，填入相关信息后点击创建

步骤：3.创建成功后进入管理应用界面，可以看到我们刚刚创建的应用的AppID，APIKey，SercretKey等信息（实现OCR功能时，需要这几个参数）

步骤：4.编写代码

      主要有以下几个类

        Main.java,主函数；                                                             TokenUtil.java 获取token的工具类 ；

        FileUtil.java  获取图片地址并转化为Byte的工具类              HttpUtil.java 发送http的工具类；

        Base64Util.java 把图片转为base64格式的工具类

      Main.java:

package com.edu.fjnu.demo;
import java.net.URLEncoder;
/**
 * @author XXX
 * 1.获取token 
 * 2.获取字符串文件图片
 * 3.图片转Base64
 * 4.发送http请求
 */
public class Main {
	 public static void main(String[] args) {
	        // 通用识别url
	        String otherHost = "https://aip.baidubce.com/rest/2.0/ocr/v1/general";
	        // 本地图片路径
	        String filePath = "D:\\ImageTest\\test2.jpg";
	        String token = TokenUtil.getToken();
	        try {
	            byte[] imgData = FileUtil.readFileByBytes(filePath);
	            String imgStr = Base64Util.encode(imgData);
	            String params = URLEncoder.encode("image", "UTF-8") + "=" + URLEncoder.encode(imgStr, "UTF-8");
	            /**
	             * 线上环境access_token有过期时间， 客户端可自行缓存，过期后重新获取。
	             */
	            String accessToken = token;
	            String result = HttpUtil.post(otherHost, accessToken, params);
	            System.out.println(result);
	        } catch (Exception e) {
	            e.printStackTrace();
	        }
	    }

}

    TokenUtil.java:

package com.edu.fjnu.demo;
import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import net.sf.json.JSONObject;

/**
 * @author XXX
 *
 */
public class TokenUtil {
	public static final String APP_ID = "***";  //你创建应用中的APP_ID               
	public static final String API_KEY = "***"; //你创建应用中的API_KEY
	public static final String SECRET_KEY = "***";//你创建应用中的SECRET_KEY

	public static String getToken() {
		String token_url = "https://aip.baidubce.com/oauth/2.0/token?";   
         //百度API中可以找到这个路径
		String path = token_url + "grant_type=client_credentials&" + "client_id=" + API_KEY + "&client_secret="
				+ SECRET_KEY;
		StringBuffer sbf = new StringBuffer();
		try {
			URL url = new URL(path);
			HttpURLConnection connection = (HttpURLConnection) url.openConnection();
			connection.connect();
			InputStream is = connection.getInputStream();	
			BufferedReader reader = new BufferedReader(new InputStreamReader(is, "UTF-8"));
			String strRead = null;
			if ((strRead = reader.readLine()) != null) {
				sbf.append(strRead);
			}
			reader.close();
			String json = sbf.toString();
			JSONObject jsStr = JSONObject.fromObject(json);
			String token = jsStr.get("access_token").toString();
			return token;
		} catch (Exception e) {
			e.printStackTrace();
		}
		return null;
	}
}

    File.java:

package com.edu.fjnu.demo;
import java.io.BufferedInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;

/**
 * @author XXX
 *
 */
public class FileUtil {
	 /**
     * 读取文件内容，作为字符串返回
     */
    public static String readFileAsString(String filePath) throws IOException {
        File file = new File(filePath);
        if (!file.exists()) {
            throw new FileNotFoundException(filePath);
        } 

        if (file.length() > 1024 * 1024 * 1024) {
            throw new IOException("File is too large");
        } 

        StringBuilder sb = new StringBuilder((int) (file.length()));
        // 创建字节输入流  
        FileInputStream fis = new FileInputStream(filePath);  
        // 创建一个长度为10240的Buffer
        byte[] bbuf = new byte[10240];  
        // 用于保存实际读取的字节数  
        int hasRead = 0;  
        while ( (hasRead = fis.read(bbuf)) > 0 ) {  
            sb.append(new String(bbuf, 0, hasRead));  
        }  
        fis.close();  
        return sb.toString();
    }

    /**
     * 根据文件路径读取byte[] 数组
     */
    public static byte[] readFileByBytes(String filePath) throws IOException {
        File file = new File(filePath);
        if (!file.exists()) {
            throw new FileNotFoundException(filePath);
        } else {
            ByteArrayOutputStream bos = new ByteArrayOutputStream((int) file.length());
            BufferedInputStream in = null;

            try {
                in = new BufferedInputStream(new FileInputStream(file));
                short bufSize = 1024;
                byte[] buffer = new byte[bufSize];
                int len1;
                while (-1 != (len1 = in.read(buffer, 0, bufSize))) {
                    bos.write(buffer, 0, len1);
                }

                byte[] var7 = bos.toByteArray();
                return var7;
            } finally {
                try {
                    if (in != null) {
                        in.close();
                    }
                } catch (IOException var14) {
                    var14.printStackTrace();
                }

                bos.close();
            }
        }
    }
}

    Base64Util.java：

/**
 * 
 */
package com.edu.fjnu.demo;

/**
 * @author XXX
 *
 */
public class Base64Util {
	 private static final char last2byte = (char) Integer.parseInt("00000011", 2);
	    private static final char last4byte = (char) Integer.parseInt("00001111", 2);
	    private static final char last6byte = (char) Integer.parseInt("00111111", 2);
	    private static final char lead6byte = (char) Integer.parseInt("11111100", 2);
	    private static final char lead4byte = (char) Integer.parseInt("11110000", 2);
	    private static final char lead2byte = (char) Integer.parseInt("11000000", 2);
	    private static final char[] encodeTable = new char[]{'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '+', '/'};

	    public Base64Util() {
	    }

	    public static String encode(byte[] from) {
	        StringBuilder to = new StringBuilder((int) ((double) from.length * 1.34D) + 3);
	        int num = 0;
	        char currentByte = 0;

	        int i;
	        for (i = 0; i < from.length; ++i) {
	            for (num %= 8; num < 8; num += 6) {
	                switch (num) {
	                    case 0:
	                        currentByte = (char) (from[i] & lead6byte);
	                        currentByte = (char) (currentByte >>> 2);
	                    case 1:
	                    case 3:
	                    case 5:
	                    default:
	                        break;
	                    case 2:
	                        currentByte = (char) (from[i] & last6byte);
	                        break;
	                    case 4:
	                        currentByte = (char) (from[i] & last4byte);
	                        currentByte = (char) (currentByte << 2);
	                        if (i + 1 < from.length) {
	                            currentByte = (char) (currentByte | (from[i + 1] & lead2byte) >>> 6);
	                        }
	                        break;
	                    case 6:
	                        currentByte = (char) (from[i] & last2byte);
	                        currentByte = (char) (currentByte << 4);
	                        if (i + 1 < from.length) {
	                            currentByte = (char) (currentByte | (from[i + 1] & lead4byte) >>> 4);
	                        }
	                }

	                to.append(encodeTable[currentByte]);
	            }
	        }

	        if (to.length() % 4 != 0) {
	            for (i = 4 - to.length() % 4; i > 0; --i) {
	                to.append("=");
	            }
	        }

	        return to.toString();
	    }
}

  HttpUtil.java：

package com.edu.fjnu.OCR.util;

import java.io.BufferedReader;
import java.io.DataOutputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.List;
import java.util.Map;

/**
 * @author XXX
 *
 */
public class HttpUtil {
	public static String post(String requestUrl, String accessToken, String params)
            throws Exception {
        String contentType = "application/x-www-form-urlencoded";
        return HttpUtil.post(requestUrl, accessToken, contentType, params);
    }

    public static String post(String requestUrl, String accessToken, String contentType, String params)
            throws Exception {
        String encoding = "UTF-8";
        if (requestUrl.contains("nlp")) {
            encoding = "GBK";
        }
        return HttpUtil.post(requestUrl, accessToken, contentType, params, encoding);
    }

    public static String post(String requestUrl, String accessToken, String contentType, String params, String encoding)
            throws Exception {
        String url = requestUrl + "?access_token=" + accessToken;
        return HttpUtil.postGeneralUrl(url, contentType, params, encoding);
    }

    public static String postGeneralUrl(String generalUrl, String contentType, String params, String encoding)
            throws Exception {
        URL url = new URL(generalUrl);
        // 打开和URL之间的连接
        HttpURLConnection connection = (HttpURLConnection) url.openConnection();
        connection.setRequestMethod("POST");
        // 设置通用的请求属性
        connection.setRequestProperty("Content-Type", contentType);
        connection.setRequestProperty("Connection", "Keep-Alive");
        connection.setUseCaches(false);
        connection.setDoOutput(true);
        connection.setDoInput(true);

        // 得到请求的输出流对象
        DataOutputStream out = new DataOutputStream(connection.getOutputStream());
        out.write(params.getBytes(encoding));
        out.flush();
        out.close();

        // 建立实际的连接
        connection.connect();
        // 获取所有响应头字段
        Map> headers = connection.getHeaderFields();
        // 遍历所有的响应头字段
        for (String key : headers.keySet()) {
            System.err.println(key + "--->" + headers.get(key));
        }
        // 定义 BufferedReader输入流来读取URL的响应
        BufferedReader in = null;
        in = new BufferedReader(
                new InputStreamReader(connection.getInputStream(), encoding));
        String result = "";
        String getLine;
        while ((getLine = in.readLine()) != null) {
            result += getLine;
        }
        in.close();
        System.err.println("result:" + result);
        return result;
    }
}

步骤：5.完成这些代码的编写后，就是测试

 我的测试结果如下：

最后最后：还是要多看API文档，以上这些代码信息就是API文档中的，贴出来，给那些需要用到的又看不太懂API文档的，也给自己看看，以后要用到直接复制粘贴也不需要在去看API了。