百度OCR文字识别接口对接

import java.awt.image.BufferedImage;
import java.io.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLEncoder;
import java.util.List;
import java.util.Map;

import javax.imageio.ImageIO;

import nc.bs.logging.Logger;
import nc.bs.os.outside.TGOutsideUtils;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.springframework.web.multipart.MultipartFile;

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONObject;
import com.baidu.ai.aip.utils.Base64Util;
import com.baidu.ai.aip.utils.FileUtil;
import com.baidu.ai.aip.utils.HttpUtil;

public class BaiduOCRTest {
	public static void main(String[] args) {
		File imagfile = null;
		String result = null;
		try {
			String filepath = "f:/111.pdf";
			String url = "https://aip.baidubce.com/rest/2.0/solution/v1/iocr/recognise/finance";

			// 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 =
			// "24.11e2f516b3dd260b2427251fa610cb83.2592000.1629255151.282335-24426393";
			String accessToken = getAuth();

			int begin = filepath.indexOf(".");
			int last = filepath.length();
			String fileType = filepath.substring(begin, last);
			if (fileType.endsWith(".pdf")) {// PDF格式文件
				try {
					File file = new File(filepath);
					PDDocument doc = PDDocument.load(file);
					PDFRenderer renderer = new PDFRenderer(doc);
					int pageCount = doc.getNumberOfPages();
					for (int i = 0; i < pageCount; i++) {
						// 方式1,第二个参数是设置缩放比(即像素)
						// BufferedImage image = renderer.renderImageWithDPI(i,
						// 296);
						// 方式2,第二个参数是设置缩放比(即像素)
						BufferedImage images = renderer.renderImage(i, 1.25f); // 第二个参数越大生成图片分辨率越高，转换时间也就越长
						imagfile = new File("d:/icepdf_a" + i + ".jpg");
						ImageIO.write(images, "PNG", imagfile);
					}
					doc.close(); // 关闭文件,不然该pdf文件会一直被占用。
					MultipartFile newFile = FileUtil.getUtils()
							.fileToMultipartFile(imagfile);
					byte[] imgData1 = newFile.getBytes();
					String imgStr1 = Base64Util.encode(imgData1);
					String imgParam = URLEncoder.encode(imgStr1, "UTF-8");

					String param = "image=" + imgParam
							+ "&templateSign=mixed_receipt";

					result = HttpUtil.post(url, accessToken, param);
				} catch (IOException e) {
					e.printStackTrace();
				}

			} else if (fileType.endsWith(".jpg") || fileType.endsWith(".jpeg")
					|| fileType.endsWith("png") || fileType.endsWith(".bmp")) {// 图片格式
				imagfile = new File(filepath);
				MultipartFile newFile = FileUtil.getUtils()
						.fileToMultipartFile(imagfile);
				byte[] imgData1 = newFile.getBytes();
				String imgStr1 = Base64Util.encode(imgData1);
				String imgParam = URLEncoder.encode(imgStr1, "UTF-8");

				String param = "image=" + imgParam
						+ "&templateSign=mixed_receipt";

				result = HttpUtil.post(url, accessToken, param);
			}
		} catch (Exception e) {
			// TODO 自动生成的 catch 块
			e.printStackTrace();
		} finally {
			if (imagfile != null) {
				imagfile.delete();
			}
		}
	}

	private static String getAuth() throws Exception {
		// 官网获取的 API Key 更新为你注册的
		String clientId = "API Key";
		// 官网获取的 Secret Key 更新为你注册的
		String clientSecret = "Secret Key";
		return getAuth(clientId, clientSecret);
	}

	/**
	 * 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"
	 * @throws Exception
	 */
	private static String getAuth(String ak, String sk) throws Exception {
		// 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> 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);
			org.json.JSONObject jsonObject = new org.json.JSONObject(result);
			String access_token = jsonObject.getString("access_token");
			return access_token;
		} catch (Exception e) {
			Logger.error("调用百度OCR获取token失败！" + e.getMessage(), e);
			throw new Exception("调用百度OCR获取token失败！" + e.getMessage(), e);
		}
	}
}

注：百度OCR文字识别接口，涉及将PDF文件转为图片；主类中使用到的工具类，都是百度提供的，如：Base64Util，FileUtil，HttpUtil，具体代码如下

FileUtil:

package com.baidu.ai.aip.utils;

import java.io.*;

import org.apache.commons.fileupload.FileItem;
import org.apache.commons.fileupload.FileItemFactory;
import org.apache.commons.fileupload.disk.DiskFileItemFactory;
import org.springframework.web.multipart.MultipartFile;
import org.springframework.web.multipart.commons.CommonsMultipartFile;

/**
 * 文件读取工具类
 */
public class FileUtil {

	static FileUtil utils;

	public static FileUtil getUtils() {
		if (utils == null) {
			utils = new FileUtil();
		}
		return utils;
	}

	public MultipartFile fileToMultipartFile(File file) {
		FileItem fileItem = createFileItem(file);
		MultipartFile multipartFile = new CommonsMultipartFile(fileItem);
		return multipartFile;
	}

	private static FileItem createFileItem(File file) {
		FileItemFactory factory = new DiskFileItemFactory(16, null);
		FileItem item = factory.createItem("textField", "text/plain", true,
				file.getName());
		int bytesRead = 0;
		byte[] buffer = new byte[8192];
		try {
			FileInputStream fis = new FileInputStream(file);
			OutputStream os = item.getOutputStream();
			while ((bytesRead = fis.read(buffer, 0, 8192)) != -1) {
				os.write(buffer, 0, bytesRead);
			}
			os.close();
			fis.close();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return item;
	}

	/**
	 * 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();
			}
		}
	}
}

Base65Util:

package com.baidu.ai.aip.utils;

/**
 * Base64 工具类
 */
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:

package com.baidu.ai.aip.utils;

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;

/**
 * http 工具类
 */
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;
    }
}