【百度OCR 封装篇】SDK调用方式，API调用方式，自定义模版，表格文字识别

淡淡的烟草味﹌ 2023-05-31 10:09 7阅读 0赞

全部代码下载地址：[https://download.csdn.net/download/qq\_33333654/11914449][https_download.csdn.net_download_qq_33333654_11914449]

SDK调用所需单例：

>     package com.jeeplus.ocr;
>     
>     import com.baidu.aip.ocr.AipOcr;
>     
>     /**
>      * @ProjectName: 百度ocr单例 目前是iocr，做文字识别
>      * @Package: com.jeeplus.ocr
>      * @ClassName: AipOcrSingleton
>      * @Author: MC
>      * @Description: ${description}
>      * @Date: 2019/10/23 0023 10:20
>      * @Version: 1.0
>      */
>     public class AipOcrSingleton {
>         public static volatile AipOcr aipOcr = null;
>         //设置APPID/AK/SK
>         public static final String APP_ID = "17593750";
>         public static final String API_KEY = "VExogNuAiDslahMNe2uRn5IB";
>         public static final String SECRET_KEY = "zILi6zsRwgKa1dTmbv2Rw8uG1oPGyI9A";
>         public static final int CONNECTION_TIME_OUT = 2000;//建立连接的超时时间（单位：毫秒）
>         public static final int SOCKET_TIME_OUT = 6000;//通过打开的连接传输数据的超时时间（单位：毫秒）
>         private AipOcrSingleton(){}
>     
>         public static AipOcr getAipOcr(){
>             if(aipOcr == null){
>                 synchronized (AipOcrSingleton.class){
>                     if(aipOcr == null){
>                         aipOcr = new AipOcr(APP_ID, API_KEY, SECRET_KEY);
>                         // 可选：设置网络连接参数
>                         aipOcr.setConnectionTimeoutInMillis(CONNECTION_TIME_OUT);
>                         aipOcr.setSocketTimeoutInMillis(SOCKET_TIME_OUT);
>                         //setHttpProxy 设置http代理服务器
>                         //setSocketProxy 设置socket代理服务器 （http和socket类型代理服务器只能二选一）
>                     }
>                 }
>             }
>             return aipOcr;
>         }
>     }

API调用所需httputil

>     public static String ocrPost(String requestUrl, String accessToken, String params)
>             throws Exception {
>         String contentType = "application/x-www-form-urlencoded";
>         return HttpUtil.ocrPost(requestUrl, accessToken, contentType, params);
>     }
>     
>     public static String ocrPost(String requestUrl, String accessToken, String contentType, String params)
>             throws Exception {
>         String encoding = "UTF-8";
>         if (requestUrl.contains("nlp")) {
>             encoding = "GBK";
>         }
>         return HttpUtil.ocrPost(requestUrl, accessToken, contentType, params, encoding);
>     }
>     
>     public static String ocrPost(String requestUrl, String accessToken, String contentType, String params, String encoding)
>             throws Exception {
>         String url = requestUrl + "?access_token=" + accessToken;
>         return HttpUtil.ocrPostGeneralUrl(url, contentType, params, encoding);
>     }
>     
>     public static String ocrPostGeneralUrl(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<String, List<String>> 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;
>     }

封装大全：

AipOcrUtil

>     package com.jeeplus.ocr;
>     
>     import com.alibaba.fastjson.JSON;
>     import com.baidu.aip.ocr.AipOcr;
>     import com.baidu.aip.util.Base64Util;
>     import com.jeeplus.common.utils.CacheUtils;
>     import com.jeeplus.common.utils.HttpUtil;
>     import com.jeeplus.common.utils.StringUtils;
>     import com.jeeplus.modules.sys.common.Constants;
>     import com.jeeplus.ocr.bean.AccessTokenResultBean;
>     import com.jeeplus.ocr.bean.AipOcrBasicGeneralResultBean;
>     import com.jeeplus.ocr.bean.AipOcrCustomResultBean;
>     import com.jeeplus.ocr.bean.AipOcrExcleRequestResultBean;
>     import org.json.JSONObject;
>     
>     import java.io.*;
>     import java.net.HttpURLConnection;
>     import java.net.URL;
>     import java.net.URLEncoder;
>     import java.util.*;
>     
>     /**
>      * @ProjectName: Hematopathy
>      * @Package: com.jeeplus.ocr
>      * @ClassName: AipOcrUtil
>      * @Author: MC
>      * @Description: ${description}
>      * @Date: 2019/10/23 0023 10:48
>      * @Version: 1.0
>      */
>     public class AipOcrUtil {
>     
>         /**
>          * @Method 通用文字识别
>          * @Author MC
>          path:本地文件路径
>         options:请求API参数，可为空
>          * @Return
>          * @Date 2019/10/23 0023 11:36
>          */
>         public static AipOcrBasicGeneralResultBean basicGeneralByPath(String path, HashMap<String, String> options){
>             if(checkFileIsImg(path)){
>                 if(options == null || options.isEmpty()){
>                     options = new HashMap<String, String>();
>                 }
>                 options.put("language_type", "CHN_ENG");
>                 options.put("detect_direction", "true");
>                 options.put("detect_language", "true");
>                 options.put("probability", "true");
>                 AipOcr client = AipOcrSingleton.getAipOcr();
>                 JSONObject res = client.basicGeneral(path, options);
>                 String resStr = res.toString();
>                 AipOcrBasicGeneralResultBean bean = JSON.parseObject(resStr, AipOcrBasicGeneralResultBean.class);
>                 return bean;
>             }
>             return null;
>         }
>     
>         /**
>          * @Method 通用文字识别
>          * @Author MC
>         url:网络图片地址
>         options:请求API参数，可为空
>          * @Return
>          * @Date 2019/10/23 0023 11:36
>          */
>         public static AipOcrBasicGeneralResultBean basicGeneralByURL(String url, HashMap<String, String> options){
>             if(!StringUtils.isEmpty(url)){
>                 if(options == null || options.isEmpty()){
>                     options = new HashMap<String, String>();
>                 }
>                 options.put("language_type", "CHN_ENG");
>                 options.put("detect_direction", "true");
>                 options.put("detect_language", "true");
>                 options.put("probability", "true");
>                 AipOcr client = AipOcrSingleton.getAipOcr();
>                 JSONObject res = client.basicGeneralUrl(url, options);
>                 String resStr = res.toString();
>                 AipOcrBasicGeneralResultBean bean = JSON.parseObject(resStr, AipOcrBasicGeneralResultBean.class);
>                 return bean;
>             }
>             return null;
>         }
>     
>     
>         /**
>          * @Method 根据模版ID或者分类器ID识别本地图片
>          * @Author MC
>         path：本地图片路径
>         templateSign：指定模版ID
>         classifierId：指定分类器ID
>         模版ID与分类ID至少一个不为空
>          * @Return
>          * @Date 2019/10/23 0023 13:59
>          */
>         public static AipOcrCustomResultBean customByPath(String path,String templateSign,String classifierId){
>             if(checkFileIsImg(path)){
>                 if(StringUtils.isEmpty(templateSign) && StringUtils.isEmpty(classifierId)){
>                     return null;
>                 }
>                 HashMap<String, String> options = new HashMap<String, String>();
>                 if(!StringUtils.isEmpty(templateSign)){
>                     options.put("templateSign", templateSign);
>                 }
>                 if(!StringUtils.isEmpty(classifierId)){
>                     options.put("classifierId", classifierId);
>                 }
>                 AipOcr client = AipOcrSingleton.getAipOcr();
>                 JSONObject res = client.custom(path, options);
>                 String resStr = res.toString();
>                 AipOcrCustomResultBean bean = JSON.parseObject(resStr, AipOcrCustomResultBean.class);
>                 return bean;
>             }
>             return null;
>         }
>     
>         /**
>          * @Method 使用API调用方式进行自定义模版或者分类器的文字识别
>          * @Author MC
>          ak:app_key 必传
>         sk:secret_key 必传
>         filePath:本地文件路径 要求为图片格式 必传
>         templateSign：自定义模版ID
>         classifierParams：自定义分类器ID
>         templateSign和classifierParams至少传递一个
>          * @Return
>          * @Date 2019/10/24 0024 11:34
>          */
>         public static AipOcrCustomResultBean customByApiUrl(String ak, String sk,String filePath,String templateSign,String classifierParams) throws Exception {
>             if(StringUtils.isEmpty(ak) || StringUtils.isEmpty(sk) || StringUtils.isEmpty(filePath)){
>                 return null;
>             }
>             if(StringUtils.isEmpty(templateSign) && StringUtils.isEmpty(classifierParams)){
>                 return null;
>             }
>             if(checkFileIsImg(filePath)){
>                 String imgStr = imgFile2Bytes2Encode(filePath);
>                 String param = "";
>                 if(!StringUtils.isEmpty(classifierParams)){
>                     param = "classifierId="+classifierParams+"&image=" + URLEncoder.encode(imgStr, "UTF-8");
>                 }else{
>                     param = "templateSign="+templateSign+"&image=" + URLEncoder.encode(imgStr, "UTF-8");
>                 }
>                 AccessTokenResultBean auth = getAuth(ak, sk);
>                 if(auth == null || !StringUtils.isEmpty(auth.getError())){
>                     return null;
>                 }
>     
>                 String accessToken = auth.getAccess_token();
>                 // 请求模板识别
>                 String result = HttpUtil.ocrPost(Constants.OCR_API_URL_GET_RECOGNISE, accessToken, param);
>                 AipOcrCustomResultBean bean = JSON.parseObject(result, AipOcrCustomResultBean.class);
>                 return bean;
>             }
>             return null;
>         }
>     
>         /**
>          * @Method 同步表格文字识别，获取excle下载地址
>          * @Author MC
>     
>          * @Return
>          * @Date 2019/10/24 0024 14:38
>          */
>         public static AipOcrExcleRequestResultBean ocrExcle(String filePath,String accessToken) throws Exception {
>             String s = ocrExcle(filePath, true, "", accessToken);
>             return JSON.parseObject(s, AipOcrExcleRequestResultBean.class);
>         }
>     
>         /**
>          * @Method ocr表格识别
>          * @Author MC
>         filePath：要识别的图片地址 必传
>         isSync：是否同步识别 默认false
>         requestType：传递json或者excel或者空 默认使用excel
>         传递json时返回的是解析结果的json字符串，传递excel或者空时返回的是识别结果的下载地址
>         accessToken:token必传
>          * @Return
>          * @Date 2019/10/24 0024 13:49
>          */
>         public static String ocrExcle (String filePath,boolean isSync,String requestType,String accessToken) throws Exception {
>             if(StringUtils.isEmpty(accessToken)){
>                 return null;
>             }
>             if(checkFileIsImg(filePath)){
>                 if(!StringUtils.isEmpty(requestType) && !"excel".equals(requestType)&& !"json".equals(requestType)){
>                     return null;
>                 }
>                 if(isSync){//同步
>                     String params;
>                     if(StringUtils.isEmpty(requestType) || "excel".equals(requestType)){
>                         params = URLEncoder.encode("image", "UTF-8") + "=" + URLEncoder.encode(filePath, "UTF-8")
>                                 +"&is_sync=true";
>                     }else{
>                         params = URLEncoder.encode("image", "UTF-8") + "=" + URLEncoder.encode(filePath, "UTF-8")
>                                 +"&is_sync=true&request_type=json";
>                     }
>                     return HttpUtil.ocrPost(Constants.OCR_API_URL_GET_EXCL, accessToken, params);
>                 }else{//异步
>                     String requestId ="";
>                     if(StringUtils.isEmpty(requestType) || "excel".equals(requestType)){//异步 excle下载
>                         requestId = getOcrExcleRequestId(filePath, accessToken,"");
>                     }else{
>                         String params = URLEncoder.encode("image", "UTF-8") + "=" + URLEncoder.encode(filePath, "UTF-8")
>                                 +"&is_sync=false&request_type=json";
>                         requestId = getOcrExcleRequestId(filePath, accessToken,params);
>                     }
>                     if(!StringUtils.isEmpty(requestId)){
>                         String reslut = "";
>                         do{
>                             reslut = getExclResultUrl(requestId, accessToken);
>                         }while (!StringUtils.isEmpty(reslut));
>                         return reslut;
>                     }
>                 }
>             }
>             return null;
>         }
>     
>     
>         /**
>          * @Method 获取OCR表格文字识别的requestId
>          * @Author MC
>         filePath:要识别的图片路径
>         accessToken：token
>         注意：默认使用异步获取，以excle识别结果下载excle的方式
>          * @Return
>          * @Date 2019/10/24 0024 13:32
>          */
>         public static String getOcrExcleRequestId(String filePath,String accessToken,String param) throws Exception {
>             String params;
>             if(!StringUtils.isEmpty(param)){
>                 params = param;
>             }else{
>                 String imgStr = imgFile2Bytes2Encode(filePath);
>                 params = URLEncoder.encode("image", "UTF-8") + "=" + URLEncoder.encode(imgStr, "UTF-8");
>             }
>             String result = HttpUtil.ocrPost(Constants.OCR_API_URL_GET_EXCL, accessToken, params);
>             //结果例：{"result":[{"request_id":"17593750_1197891"}],"log_id":1571894645836523}
>             com.alibaba.fastjson.JSONObject jsonObject = com.alibaba.fastjson.JSONObject.parseObject(result);
>             List<com.alibaba.fastjson.JSONObject> list = (List<com.alibaba.fastjson.JSONObject>) jsonObject.get("result");
>             com.alibaba.fastjson.JSONObject jsonObject1 = list.get(0);
>             String request_id = jsonObject1.getString("request_id");
>             return request_id;
>         }
>     
>         /**
>          * @Method 获取表格文字识别结果的excle下载地址
>          * @Author MC
>         request_id：表格文字识别接口返回的ID
>         accessToken：token
>          * @Return
>          * @Date 2019/10/24 0024 13:03
>          */
>         public static String getExclResultUrl(String request_id,String accessToken) throws Exception {
>             String params = URLEncoder.encode("request_id", "UTF-8") + "=" + URLEncoder.encode(request_id, "UTF-8");
>             String result = HttpUtil.ocrPost(Constants.OCR_API_URL_GET_EXCL_RESULT, accessToken, params);
>             AipOcrExcleRequestResultBean aipOcrExcleRequestResultBean = JSON.parseObject(result, AipOcrExcleRequestResultBean.class);
>             String ret_code = aipOcrExcleRequestResultBean.getResult().getRet_code();
>             if("3".equals(ret_code)){
>                 return aipOcrExcleRequestResultBean.getResult().getResult_data();
>             }
>             return "";
>         }
>     
>         /**
>          * 获取API访问token
>          * 该token有一定的有效期，需要自行管理，当失效时需重新获取.
>          * @param ak - 百度云官网获取的 API Key
>          * @param sk - 百度云官网获取的 Securet Key
>          * @return assess_token 示例：
>          * "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567"
>          */
>         public static AccessTokenResultBean getAuth(String ak, String sk) {
>             AccessTokenResultBean bean = (AccessTokenResultBean) CacheUtils.get(Constants.OCR_CACHE_NAME,Constants.OCR_CACHE_ACCESS_TOKEN);
>             if(bean != null){
>                 //检查缓存中的token是否过期
>                 long expires_in = bean.getMyTimeOut().getTime();
>                 Date nowDate = new Date();
>                 long nowDateTime = nowDate.getTime();
>                 if(expires_in > nowDateTime){
>                     return bean;
>                 }else{
>                     CacheUtils.remove(Constants.OCR_CACHE_NAME,Constants.OCR_CACHE_ACCESS_TOKEN);
>                 }
>             }
>     
>             // 获取token地址
>             String authHost = Constants.OCR_API_URL_GET_ACCESS_TOKEN + "?";
>             String getAccessTokenUrl = authHost
>                     // 1. grant_type为固定参数
>                     + "grant_type=client_credentials"
>                     // 2. 官网获取的 API Key
>                     + "&client_id=" + ak
>                     // 3. 官网获取的 Secret Key
>                     + "&client_secret=" + sk;
>             try {
>                 URL realUrl = new URL(getAccessTokenUrl);
>                 // 打开和URL之间的连接
>                 HttpURLConnection connection = (HttpURLConnection) realUrl.openConnection();
>                 connection.setRequestMethod("GET");
>                 connection.connect();
>                 // 获取所有响应头字段
>                 Map<String, List<String>> map = connection.getHeaderFields();
>                 // 遍历所有的响应头字段
>     //            for (String key : map.keySet()) {
>     //                System.err.println(key + "--->" + map.get(key));
>     //            }
>                 // 定义 BufferedReader输入流来读取URL的响应
>                 BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
>                 String result = "";
>                 String line;
>                 while ((line = in.readLine()) != null) {
>                     result += line;
>                 }
>                 /**
>                  * 返回结果示例
>                  */
>                 System.err.println("result:" + result);
>                 AccessTokenResultBean accessTokenResultBean = JSON.parseObject(result, AccessTokenResultBean.class);
>                 if(StringUtils.isEmpty(accessTokenResultBean.getError())){//获取成功 进行缓存
>                     Integer expires_in = accessTokenResultBean.getExpires_in();
>                     if(expires_in > 0){
>                         int days = expires_in / ( 60 * 60 * 24);
>                         Date date=new Date();
>                         Calendar calendar = new GregorianCalendar();
>                         calendar.setTime(date);
>                         calendar.add(Calendar.DATE,days);//把日期往后增加一天.整数往后推,负数往前移动
>                         date=calendar.getTime();
>                         accessTokenResultBean.setMyTimeOut(date);//设置有效期
>                     }else{
>                         CacheUtils.remove(Constants.OCR_CACHE_NAME,Constants.OCR_CACHE_ACCESS_TOKEN);
>                         return null;
>                     }
>                     CacheUtils.put(Constants.OCR_CACHE_NAME,Constants.OCR_CACHE_ACCESS_TOKEN,accessTokenResultBean);
>                 }else{
>                     CacheUtils.remove(Constants.OCR_CACHE_NAME,Constants.OCR_CACHE_ACCESS_TOKEN);
>                 }
>                 return accessTokenResultBean;
>                /* JSONObject jsonObject = new JSONObject(result);
>                 String access_token = jsonObject.getString("access_token");
>                 return access_token;*/
>             } catch (Exception e) {
>                 System.err.printf("获取token失败！");
>                 CacheUtils.remove(Constants.OCR_CACHE_NAME,Constants.OCR_CACHE_ACCESS_TOKEN);
>                 e.printStackTrace(System.err);
>             }
>             return null;
>         }
>     
>         private static boolean checkFileIsImg(String path){
>             if(StringUtils.isEmpty(path)){
>                 return false;
>             }
>             File srcFile = new File(path);
>             // 判断源文件是否存在
>             if (!srcFile.exists()) {
>                 return false;
>             }
>             if(path.indexOf(".") == -1){
>                 return false;
>             }
>             String suffix= path.substring(path.indexOf("."), path.length());
>             if(
>                     suffix.equalsIgnoreCase("jpg") ||
>                             suffix.equalsIgnoreCase("PNG ") ||
>                             suffix.equalsIgnoreCase("GIF") ||
>                             suffix.equalsIgnoreCase("tif") ||
>                             suffix.equalsIgnoreCase("bmp")
>             ){
>                 return false;
>             }
>     
>             return true;
>         }
>     
>     
>         /**
>          * @Method 图片文件转换为字节在进行base64转码
>          * @Author MC
>     
>          * @Return
>          * @Date 2019/10/24 0024 10:19
>          */
>         public static String imgFile2Bytes2Encode(String filePath) throws IOException {
>             if(!checkFileIsImg(filePath)){
>                 return null;
>             }
>             byte[] imgData = readFileByBytes(filePath);
>             String imgStr = Base64Util.encode(imgData);
>             return imgStr;
>         }
>     
>         /**
>          * @Method 文件转换为字节在进行base64转码
>          * @Author MC
>     
>          * @Return
>          * @Date 2019/10/24 0024 10:19
>          */
>         public static String file2Bytes2Encode(String filePath) throws IOException {
>             if(StringUtils.isEmpty(filePath)){
>                 return null;
>             }
>             File srcFile = new File(filePath);
>             // 判断源文件是否存在
>             if (!srcFile.exists()) {
>                 return null;
>             }
>             byte[] imgData = readFileByBytes(filePath);
>             String imgStr = Base64Util.encode(imgData);
>             return imgStr;
>         }
>     
>         /**
>          * 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();
>                 }
>             }
>         }
>     
>     
>     
>     
>     }

[https_download.csdn.net_download_qq_33333654_11914449]: https://download.csdn.net/download/qq_33333654/11914449