阿里云 OCR 图片文字识别接口使用案例（java）

阿里云 OCR 图片文字识别接口使用案例（java）

阿里云官方接口文档

前期需要完成

购买阿里云服务

购买服务

可以购买测试服务。每个阿里云用户可以购买1次免费的500次接口请求进行测试
购买完成之后在代码中使用appCode

代码集成

pom依赖添加

 <dependencies>   
    <dependency>
        <groupId>com.alibaba</groupId>
        <artifactId>fastjson</artifactId>
        <version>1.2.15</version>
    </dependency>
    <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpclient</artifactId>
        <version>4.2.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpcore</artifactId>
        <version>4.2.1</version>
    </dependency>
    <dependency>
        <groupId>commons-lang</groupId>
        <artifactId>commons-lang</artifactId>
        <version>2.6</version>
    </dependency>
    <dependency>
        <groupId>org.eclipse.jetty</groupId>
        <artifactId>jetty-util</artifactId>
        <version>9.3.7.v20160115</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.5</version>
        <scope>test</scope>
    </dependency>
</dependencies>


<build>
    <pluginManagement>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <configuration>
                    <archive>
                        <manifest>
                            <mainClass>com.example.ocr.StartOcr</mainClass>
                            <addClasspath>true</addClasspath>
                            <classpathPrefix>lib/</classpathPrefix>
                        </manifest>
                    </archive>
                    <classesDirectory>
                    </classesDirectory>
                </configuration>
            </plugin>
        </plugins>
    </pluginManagement>
</build>

代码实现-接口调用

我自己的测试用项目为 SpringBoot+swagger2。其中用到swagger的一些注解 如@Api@ApiOperation等，如果没有集成直接删去即可

测试的代码中直接读取本地的图片ocrtest.jpg进行简单的测试
图片要求：
	要求base64编码后大小不超过4M，最短边至少15px，最长边最大4096px，支持jpg/png/bmp格式，和url参数只能同时存在一个
其他请参考阿里云官方文档：
	

@Controller
@RequestMapping("/ocr")
@Api(value="OCR Service Controller", description = "阿里云OCR测试")
public class OCRController {

    @ApiOperation(value = "OCR图片文字识别", notes = "OCR图片文字识别", httpMethod = "POST")
    @RequestMapping(value = "/test", method = RequestMethod.POST)
    @ResponseBody
    public String test() throws Exception {
        String host = "https://ocrapi-document.taobao.com";
        String path = "/ocrservice/document";
        String method = "POST";
        String appcode = "xxxxxxxxxxxx";
        Map<String, String> headers = new HashMap<String, String>();
        //最后在header中的格式(中间是英文空格)为Authorization:APPCODE 83359fd73fe94948385f570e3c139105
        headers.put("Authorization", "APPCODE " + appcode);
        //根据API的要求，定义相对应的Content-Type
        headers.put("Content-Type", "application/json; charset=UTF-8");
        Map<String, String> querys = new HashMap<String, String>();
        /*
        {
          //图像数据：base64编码，要求base64编码后大小不超过4M，最短边至少15px，最长边最大4096px，支持jpg/png/bmp格式，和url参数只能同时存在一个
          "img": "",
          //图像url地址：图片完整URL，URL长度不超过1024字节，URL对应的图片base64编码后大小不超过4M，最短边至少15px，最长边最大4096px，支持jpg/png/bmp格式，和img参数只能同时存在一个
          "url": "",
          //是否需要识别结果中每一行的置信度，默认不需要。 true：需要 false：不需要
          "prob": false
        }
        */
        String bodys =  "{\"img\":\""+ changeToBase64("D:\\ocrtest.jpg")+"\",\"prob\":false}";


        try {
            /**
             * 重要提示如下:
             * HttpUtils请从
             * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/src/main/java/com/aliyun/api/gateway/demo/util/HttpUtils.java
             * 下载
             *
             * 相应的依赖请参照
             * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/pom.xml
             */
            HttpResponse response = HttpUtils.doPost(host, path, method, headers, querys, bodys);
            System.out.println(response.toString());
            //获取response的body
            prase(EntityUtils.toString(response.getEntity()));
        } catch (Exception e) {
            e.printStackTrace();
        }

        return "成功";
    }


    /**
     * 输出获取的Json返回值，并把它输出到控制台和文件
     * @param content 获取的Json返回值
     */
    public static void output(String content) {
        System.out.println(content);
        File file = new File("D:\\result.txt");  //这里选择输出文件的地址
        try {
            FileWriter writer = new FileWriter(file, true);
            writer.write(content);
            writer.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    /**
     * 解析Json
     * @param string 获取response中的Json
     */
    public static void prase(String string){
        JSONObject jsonObject=JSONObject.parseObject(string);
        JSONArray jsonArray=jsonObject.getJSONArray("prism_wordsInfo");
        for (int i=0;i<jsonArray.size();i++){
            JSONObject newjsonObject=(JSONObject) jsonArray.get(i);
            output(newjsonObject.getString("word"));
        }
    }

    /**
     * 将文件读取并转化为Base64字符串
     * @param fileName 文件名
     * @return  Base64字符串
     * @throws Exception
     */
    public static String changeToBase64(String fileName) throws Exception{
        File file = new File(fileName);
        FileInputStream inputFile = new FileInputStream(file);
        byte[] buffer = new byte[(int)file.length()];
        inputFile.read(buffer);
        inputFile.close();
        String base64Code=new BASE64Encoder().encode(buffer);
        return base64Code;
    }

}

官方github实例

/**
 * 重要提示如下:
 * HttpUtils请从
 * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/src/main/java/com/aliyun/api/gateway/demo/util/HttpUtils.java
 * 下载
 *
 * 相应的依赖请参照
 * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/pom.xml
 */

工具类

package com.learning.ssm_swagger.util;

/**
 * @Author Qizy
 * @Date 2019/12/11 10:26
 * @Version 1.0
 **/
import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.X509Certificate;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;

import org.apache.commons.lang.StringUtils;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.client.HttpClient;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpDelete;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpPut;
import org.apache.http.conn.ClientConnectionManager;
import org.apache.http.conn.scheme.Scheme;
import org.apache.http.conn.scheme.SchemeRegistry;
import org.apache.http.conn.ssl.SSLSocketFactory;
import org.apache.http.entity.ByteArrayEntity;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;

public class HttpUtils {

    /**
     * get
     *
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @return
     * @throws Exception
     */
    public static HttpResponse doGet(String host, String path, String method,
                                     Map<String, String> headers,
                                     Map<String, String> querys)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpGet request = new HttpGet(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        return httpClient.execute(request);
    }

    /**
     * post form
     *
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @param bodys
     * @return
     * @throws Exception
     */
    public static HttpResponse doPost(String host, String path, String method,
                                      Map<String, String> headers,
                                      Map<String, String> querys,
                                      Map<String, String> bodys)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpPost request = new HttpPost(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        if (bodys != null) {
            List<NameValuePair> nameValuePairList = new ArrayList<NameValuePair>();

            for (String key : bodys.keySet()) {
                nameValuePairList.add(new BasicNameValuePair(key, bodys.get(key)));
            }
            UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(nameValuePairList, "utf-8");
            formEntity.setContentType("application/x-www-form-urlencoded; charset=UTF-8");
            request.setEntity(formEntity);
        }

        return httpClient.execute(request);
    }

    /**
     * Post String
     *
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @param body
     * @return
     * @throws Exception
     */
    public static HttpResponse doPost(String host, String path, String method,
                                      Map<String, String> headers,
                                      Map<String, String> querys,
                                      String body)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpPost request = new HttpPost(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        if (StringUtils.isNotBlank(body)) {
            request.setEntity(new StringEntity(body, "utf-8"));
        }

        return httpClient.execute(request);
    }

    /**
     * Post stream
     *
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @param body
     * @return
     * @throws Exception
     */
    public static HttpResponse doPost(String host, String path, String method,
                                      Map<String, String> headers,
                                      Map<String, String> querys,
                                      byte[] body)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpPost request = new HttpPost(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        if (body != null) {
            request.setEntity(new ByteArrayEntity(body));
        }

        return httpClient.execute(request);
    }

    /**
     * Put String
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @param body
     * @return
     * @throws Exception
     */
    public static HttpResponse doPut(String host, String path, String method,
                                     Map<String, String> headers,
                                     Map<String, String> querys,
                                     String body)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpPut request = new HttpPut(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        if (StringUtils.isNotBlank(body)) {
            request.setEntity(new StringEntity(body, "utf-8"));
        }

        return httpClient.execute(request);
    }

    /**
     * Put stream
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @param body
     * @return
     * @throws Exception
     */
    public static HttpResponse doPut(String host, String path, String method,
                                     Map<String, String> headers,
                                     Map<String, String> querys,
                                     byte[] body)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpPut request = new HttpPut(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        if (body != null) {
            request.setEntity(new ByteArrayEntity(body));
        }

        return httpClient.execute(request);
    }

    /**
     * Delete
     *
     * @param host
     * @param path
     * @param method
     * @param headers
     * @param querys
     * @return
     * @throws Exception
     */
    public static HttpResponse doDelete(String host, String path, String method,
                                        Map<String, String> headers,
                                        Map<String, String> querys)
            throws Exception {
        HttpClient httpClient = wrapClient(host);

        HttpDelete request = new HttpDelete(buildUrl(host, path, querys));
        for (Map.Entry<String, String> e : headers.entrySet()) {
            request.addHeader(e.getKey(), e.getValue());
        }

        return httpClient.execute(request);
    }

    private static String buildUrl(String host, String path, Map<String, String> querys) throws UnsupportedEncodingException {
        StringBuilder sbUrl = new StringBuilder();
        sbUrl.append(host);
        if (!StringUtils.isBlank(path)) {
            sbUrl.append(path);
        }
        if (null != querys) {
            StringBuilder sbQuery = new StringBuilder();
            for (Map.Entry<String, String> query : querys.entrySet()) {
                if (0 < sbQuery.length()) {
                    sbQuery.append("&");
                }
                if (StringUtils.isBlank(query.getKey()) && !StringUtils.isBlank(query.getValue())) {
                    sbQuery.append(query.getValue());
                }
                if (!StringUtils.isBlank(query.getKey())) {
                    sbQuery.append(query.getKey());
                    if (!StringUtils.isBlank(query.getValue())) {
                        sbQuery.append("=");
                        sbQuery.append(URLEncoder.encode(query.getValue(), "utf-8"));
                    }
                }
            }
            if (0 < sbQuery.length()) {
                sbUrl.append("?").append(sbQuery);
            }
        }

        return sbUrl.toString();
    }

    private static HttpClient wrapClient(String host) {
        HttpClient httpClient = new DefaultHttpClient();
        if (host.startsWith("https://")) {
            sslClient(httpClient);
        }

        return httpClient;
    }

    private static void sslClient(HttpClient httpClient) {
        try {
            SSLContext ctx = SSLContext.getInstance("TLS");
            X509TrustManager tm = new X509TrustManager() {
                @Override
                public X509Certificate[] getAcceptedIssuers() {
                    return null;
                }
                @Override
                public void checkClientTrusted(X509Certificate[] xcs, String str) {

                }
                @Override
                public void checkServerTrusted(X509Certificate[] xcs, String str) {

                }
            };
            ctx.init(null, new TrustManager[] { tm }, null);
            SSLSocketFactory ssf = new SSLSocketFactory(ctx);
            ssf.setHostnameVerifier(SSLSocketFactory.ALLOW_ALL_HOSTNAME_VERIFIER);
            ClientConnectionManager ccm = httpClient.getConnectionManager();
            SchemeRegistry registry = ccm.getSchemeRegistry();
            registry.register(new Scheme("https", 443, ssf));
        } catch (KeyManagementException ex) {
            throw new RuntimeException(ex);
        } catch (NoSuchAlgorithmException ex) {
            throw new RuntimeException(ex);
        }
    }
}

测试图片：

测试结果：

荐深入理解HashMap什么是HashMap?HashMap是基于哈希表的Map接口是实现的。此实现提供所有可选操作， 并允许使用null...Woo_home115◎8666_疊26Java面试题大全(2020版)发现网上很多Java面试题都没有答案， 所以花了很长时间搜集整理出来了这套Java面试题大全， 希望对大家有帮...QJava程序员-张凯山148◎4703四14反转!BAT编程吸金榜来了， A I程序员刷爆了......2019年BAT等大厂积极布局A I领域， 程序员转行学A I的门槛是什么?怎么转?荐Python十大装B语法Python是一种代表简单思想的语言， 其语法相对简单， 很容易上手。不过， 如果就此小视Python语法的精妙和...天元浪子山1345◎88216四100