Java 工具篇（百度文字识别）

背景：

公司项目需要上传省份证，营业执照等图片，需要获取里面的信息。所以使用了百度文字识别，方便快捷 主要是免费的，虽然一天是有限数的；本来百度上的API文档很清楚了，但是现在还是稍微了的整理下。

首先添加一个百度的jar包

<!-- https://mvnrepository.com/artifact/com.baidu.aip/java-sdk -->
        <dependency>
            <groupId>com.baidu.aip</groupId>
            <artifactId>java-sdk</artifactId>
            <version>4.11.3</version>
        </dependency>

其次随便创建一个类，然后配置必要的数据

上面的都是开通百度识别可以看到的配置数据，所以现在就不做描述了。

public static AipOcr aipOcr(){
        AipOcr client = new AipOcr(APP_ID, API_KEY, SECRET_KEY);
        return client;
    }

为了方便所以我写了一个方法来实例化AipOcr类，下面就是具体的方法体了。

/**
     * 身份证验证
     *
     * @param client
     * @param url
     * @param idCarSide front - 身份证含照片的一面  back - 身份证带国徽的一面
     * @return
     */
    public static Dict idCard(AipOcr client, String url, String idCarSide) {
        // 传入可选参数调用接口
        HashMap<String, String> options = new HashMap<String, String>();
        options.put("detect_direction", "true");
        options.put("detect_risk", "false");
        String idCardSide = idCarSide;
        byte[] bytes = GetImage(url);
        JSONObject res = client.idcard(bytes, idCardSide, options);
        JSONObject words_result = (JSONObject) res.get("words_result");
        try {
            if(idCarSide.equals("front")){//正面
                JSONObject name = (JSONObject) words_result.get("姓名");
                dict.set("name", name.get("words"));
                JSONObject nation = (JSONObject) words_result.get("民族");
                dict.set("nation", nation.get("words"));
                JSONObject address = (JSONObject) words_result.get("住址");
                dict.set("address", address.get("words"));
                JSONObject idCard = (JSONObject) words_result.get("公民身份号码");
                dict.set("idCard", idCard.get("words"));
                JSONObject birthTime = (JSONObject) words_result.get("出生");
                dict.set("birthTime", birthTime.get("words"));
                JSONObject gender = (JSONObject) words_result.get("性别");
                dict.set("gender", String.valueOf(gender.get("words")).equals("女")?0:1);
            }else {
                JSONObject endTime = (JSONObject) words_result.get("失效日期");
                dict.set("endTime", endTime.get("words"));
                JSONObject issuingOrgan = (JSONObject) words_result.get("签发机关");
                dict.set("issuingOrgan", issuingOrgan.get("words"));
                JSONObject stateTime = (JSONObject) words_result.get("签发日期");
                dict.set("stateTime", stateTime.get("words"));
            }
        } catch (Exception e) {
            e.getMessage();
        }
        System.out.println(res.toString(2));
        return dict;
    }


    /**
     * 驾驶证
     *
     * @param client
     */
    public static Dict drivingLicense(AipOcr client, String url) {
        // 传入可选参数调用接口
        HashMap<String, String> options = new HashMap<String, String>();
        options.put("detect_direction", "true");
        // 参数为路径
        byte[] bytes = GetImage(url);
        try {
            JSONObject res = client.drivingLicense(bytes, options);
            JSONObject words_result = (JSONObject) res.get("words_result");
            JSONObject name = (JSONObject) words_result.get("姓名");
            dict.set("name", name.get("words"));
            JSONObject idNum = (JSONObject) words_result.get("证号");
            dict.set("idNum", idNum.get("words"));
            JSONObject dataBirth = (JSONObject) words_result.get("出生日期");
            dict.set("dataBirth", dataBirth.get("words"));
            JSONObject address = (JSONObject) words_result.get("住址");
            dict.set("address", address.get("words"));
            JSONObject nationality = (JSONObject) words_result.get("国籍");
            dict.set("nationality", nationality.get("words"));
            JSONObject vehicleType = (JSONObject) words_result.get("准驾车型");
            dict.set("vehicleType", vehicleType.get("words"));
            JSONObject gender = (JSONObject) words_result.get("性别");
            dict.set("gender", gender.get("words").equals("女")?0:1);
            JSONObject startTime = (JSONObject) words_result.get("有效期限");
            dict.set("startTime", startTime.get("words"));
            JSONObject endTime = (JSONObject) words_result.get("至");
            dict.set("endTime", endTime.get("words"));
            System.out.println(dict);
        } catch (Exception e) {
            System.out.println(e.getMessage());
        }
        return dict;
    }


    /**
     * 行驶证
     *
     * @param client
     */
    public static Dict vehicleLicense(AipOcr client, String url) {
        // 传入可选参数调用接口
        HashMap<String, String> options = new HashMap<String, String>();
        options.put("detect_direction", "true");
        options.put("accuracy", "normal");
        byte[] file = GetImage(url);
        try {
            JSONObject res = client.vehicleLicense(file, options);
            System.out.println(res);
            JSONObject words_result = (JSONObject) res.get("words_result");
            JSONObject vehicleIdentificationNumber = (JSONObject) words_result.get("车辆识别代号");
            dict.set("vehicleIdentificationNumber", vehicleIdentificationNumber.get("words"));
            JSONObject dateOfRegistration = (JSONObject) words_result.get("注册登记日期");
            dict.set("dateOfRegistration", dateOfRegistration.get("words"));
            JSONObject address = (JSONObject) words_result.get("住址");
            dict.set("address", address.get("words"));
            JSONObject brandModel = (JSONObject) words_result.get("品牌型号");
            dict.set("brandModel", brandModel.get("words"));
            JSONObject issueTime = (JSONObject) words_result.get("发证日期");
            dict.set("issueTime", issueTime.get("words"));
            JSONObject carType = (JSONObject) words_result.get("车辆类型");
            dict.set("carType", carType.get("words"));
            JSONObject natureOfUsage = (JSONObject) words_result.get("使用性质");
            dict.set("natureOfUsage", String.valueOf(natureOfUsage.get("words")).equals("非运营")?0:1);
            JSONObject licenseNumber = (JSONObject) words_result.get("号牌号码");
            dict.set("licenseNumber", licenseNumber.get("words"));
        } catch (Exception e) {
            e.getMessage();
        }
        return dict;

    }


    /**
     * 营业执照
     *
     * @param client
     */
    public static Dict businessLicense(AipOcr client, String url) {
        try {
            // 传入可选参数调用接口
            HashMap<String, String> options = new HashMap<String, String>();
            // 参数为本地路径
            byte[] bytes = GetImage(url);
            JSONObject res = client.businessLicense(bytes, options);
            JSONObject words_result = (JSONObject) res.get("words_result");
            JSONObject socialCreditCode = (JSONObject) words_result.get("社会信用代码");
            dict.set("socialCreditCode", socialCreditCode.get("words"));
            JSONObject compositionForm = (JSONObject) words_result.get("组成形式");
            dict.set("compositionForm", compositionForm.get("words"));
            JSONObject businessScope = (JSONObject) words_result.get("经营范围");
            dict.set("businessScope", businessScope.get("words"));
            JSONObject legalPerson = (JSONObject) words_result.get("法人");
            dict.set("legalPerson", legalPerson.get("words"));
            JSONObject createTime = (JSONObject) words_result.get("成立日期");
            dict.set("createTime", createTime.get("words"));
            JSONObject registeredCapital = (JSONObject) words_result.get("注册资本");
            dict.set("registeredCapital", registeredCapital.get("words"));
            JSONObject idNum = (JSONObject) words_result.get("证件编号");
            dict.set("idNum", idNum.get("words"));
            JSONObject address = (JSONObject) words_result.get("地址");
            dict.set("address", address.get("words"));
            JSONObject unitName = (JSONObject) words_result.get("单位名称");
            dict.set("unitName", unitName.get("words"));
            JSONObject type = (JSONObject) words_result.get("类型");
            dict.set("type", type.get("words"));
            JSONObject termOfValidity = (JSONObject) words_result.get("有效期");
            dict.set("termOfValidity", termOfValidity.get("words"));
        } catch (Exception e) {
            System.out.println(e.getMessage());
        }
        return dict;
    }

需要注意的是，百度文字识别开始我写的时候只能识别本地的，所以如果需要识别url图片的话就会出错，所以现在有两个方法把url图片转成byt[]

    public static byte[] GetImage(String imgs) {
        try {
            URL url = new URL(imgs);
            HttpURLConnection conn = (HttpURLConnection) url.openConnection();
            conn.setRequestMethod("GET");
            conn.setConnectTimeout(5 * 1000);
            InputStream inStream = conn.getInputStream();//通过输入流获取图片数据
            byte data[] = readInputStream(inStream);
            return data;
        } catch (Exception e) {
            e.printStackTrace();
        }
        return null;
    }


    public static byte[] readInputStream(InputStream inStream) throws Exception {
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        byte[] buffer = new byte[2048];
        int len = 0;
        while ((len = inStream.read(buffer)) != -1) {
            outStream.write(buffer, 0, len);
        }
        inStream.close();
        return outStream.toByteArray();
    }

这样直接用测试类调用方法就可以了

    public static void main(String[] args) {
        // 初始化一个AipOcr
        AipOcr client = new AipOcr(APP_ID, API_KEY, SECRET_KEY);
        Dict dict = idCard(client, "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1574325838156&di=c8be68c0a31ea3891301e3b818211c4d&imgtype=0&src=http%3A%2F%2Fimg.mp.itc.cn%2Fupload%2F20161021%2F719894bc6f594beb8dfa000a359aa345_th.jpeg", "back");
        System.out.println(dict);
    }

具体的运行结果就不贴出来了，还有就是Dict是hutool的封装方法实现是map，要用的话需要导hutool的maven包