Java 百度API识别图片文字，根据图片提取文字

Java 百度API识别图片文字，根据图片提取文字

图片（例）

提取之后的字

代码附上

ImgToWords.java

import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.mddb.util.photoscan.util.Base64Util;
import com.mddb.util.photoscan.util.HttpUtil;
import org.apache.http.entity.ContentType;
import org.springframework.mock.web.MockMultipartFile;
import org.springframework.web.multipart.MultipartFile;

import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

/**
 * @description: 百度云提取图片上的文字
 * @author: LCHYUE
 * @time: 2021/6/24 15:28
 */
public class ImgToWords {
    /**
     * 根据图片获取图片中信息
     *
     * @param file
     * @return
     */
    public static String convertPicToStr(MultipartFile[] file) {
        String strTwo = "";
        //百度图片验证接口
        String url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic";
        try {
            String apiKey = "xxxxxxxxxxxxxxx";//使用自己申请的apiKey
            String secretKey = "xxxxxxxxxxxxx";//使用自己申请的secretKey
            String tocken = "";
            //请求百度tocken接口，获取tocken信息，存到数据库中
            String tockens = getAuth(apiKey, secretKey);
            tocken = tockens;
            //去请求加载百度
            for (int i = 0; i < file.length; i++) {
                byte[] imgData = file[i].getBytes();
                String imgStr = Base64Util.encode(imgData);
                String imgParam = URLEncoder.encode(imgStr, "UTF-8");
                String param = "image=" + imgParam;
                // 注意这里仅为了简化编码每一次请求都去获取access_token，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 = "24.f75c3ee94c663b3ac2097f16ae1099cd.2592000.1622122152.282335-24066719";
                String str = HttpUtil.post(url, tocken, param);

                JSONObject parse = JSONObject.parseObject(str);
                JSONArray jsonArray = parse.getJSONArray("words_result");
                for (int j = 0; j < jsonArray.size(); j++) {
                    JSONObject parses = JSONObject.parseObject(jsonArray.get(j).toString());
                    strTwo += parses.get("words").toString();
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
        }

        return strTwo;
    }

    /**
     * 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 String getAuth(String ak, String sk) {
        // 获取token地址
        String authHost = "https://aip.baidubce.com/oauth/2.0/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);
//            JSONObject jsonObject = new JSONObject(Boolean.parseBoolean(result));
            JSONObject jsonObject = JSONObject.parseObject(result);
            String access_token = jsonObject.getString("access_token");
            return access_token;
        } catch (Exception e) {
            System.err.printf("获取token失败！");
            e.printStackTrace(System.err);
        }
        return null;
    }

    /**
     * @Description: 根据路径装化成 MultipartFile
     * @Param: imgUrlList 文件路径
     * @return: MultipartFile
     * @Author: LCHYUE
     * @Date: 2021/6/24
     */
    public static MultipartFile[] fileToMultipartFile(List<String> imgUrlList) {

        FileInputStream fileInputStream = null;
        int fileSize = imgUrlList.size();//图片的页数
        MultipartFile[] multipartFiles = new MultipartFile[fileSize];
        try {
            for (int i = 0; i < fileSize; i++) {
                String fileUrl = imgUrlList.get(i);
                //linux---start---
//                String result = fileUrl.replaceAll("\\\\", File.separator);
//                File file = new java.io.File(result);
                //linux--end----
                //windows--start
                File file = new java.io.File(fileUrl);
                //windows--end
                fileInputStream = new FileInputStream(file);
                MultipartFile multipartFile = new MockMultipartFile(file.getName(), file.getName(),
                        ContentType.APPLICATION_OCTET_STREAM.toString(), fileInputStream);
                multipartFiles[i] = multipartFile;
            }
            return multipartFiles;
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    public static void main(String[] args) {
        List<String> imgUrlList = new ArrayList<>();
        imgUrlList.add("D:\\Desktop\\书\\诗.png");
        MultipartFile[] multipartFiles = fileToMultipartFile(imgUrlList);
        String strTwo = convertPicToStr(multipartFiles);
        System.out.println(strTwo);
    }
}