提取特定字段导入Excel

港控/mmm° 2024-03-22 10:51 38阅读 0赞

### 提取特定字段导入Excel ###

*学习目标：调用身份证识别API，并从获取到的JSON结果中，提取所需的字段，填入至Excel。*

**前提条件：**

*  开通身份证识别。
 *  本地调用请安装OCR Python SDK。
 *  执行`pip install xlsxwriter`命令安装依赖包。
 *  登录访问秘钥页面，获取AK、SK。可以新增访问秘钥，或使用已有的访问秘钥。访问秘钥为credentials.csv文件，包含AK/SK信息。

代码示例

# -*- coding: utf-8 -*-
    import base64
    import xlsxwriter
    
    from huaweicloudsdkcore.auth.credentials import BasicCredentials
    from huaweicloudsdkocr.v1.region.ocr_region import OcrRegion
    from huaweicloudsdkcore.exceptions import exceptions
    from huaweicloudsdkocr.v1 import *
    from huaweicloudsdkcore.http.http_config import HttpConfig
    
    
    def recognize_id_card_request():
        try:
            request = RecognizeIdCardRequest()
            request.body = IdCardRequestBody(
                image=image_base64
            )
            response = client.recognize_id_card(request)
            return response
        except exceptions.ClientRequestException as e:
            print(e.status_code)
            print(e.request_id)
            print(e.error_code)
            print(e.error_msg)
    
    
    def get_credential():
        return BasicCredentials(ak, sk)
    
    
    def get_client():
        config = HttpConfig.get_default_config()
        config.ignore_ssl_verification = True
        return OcrClient.new_builder(OcrClient) \
            .with_credentials(credentials) \
            .with_region(OcrRegion.CN_NORTH_4) \
            .with_http_config(config) \
            .build()
    
    
    def image_to_base64(imagepath):
        """
        将本地图片转化为base64编码
        """
        with open(imagepath, "rb") as bin_data:
            image_data = bin_data.read()
        base64_data = base64.b64encode(image_data).decode("utf-8")
        return base64_data
    
    
    def response_to_execl(save_file, data):
        """
        :param save_file: 文件名
        :param data: result data
        """
    
        # 处理调用API返回的result数据
        keys_list = list(data["result"].keys())
        values_list = list(data["result"].values())
    
        options = {
        'in_memory': True}
        with xlsxwriter.Workbook(save_file, options) as workbook:
            worksheet = workbook.add_worksheet()
            worksheet.set_column('A1:A20', 23)
            worksheet.set_column('B1:B20', 100)
            worksheet.write_column('A1', keys_list)
            worksheet.write_column('B1', values_list)
        workbook.close()
    
    
    if __name__ == '__main__':
        # 填写访问秘钥AK、SK
        ak = "填写AK"
        sk = "填写SK"
    
        # Init Auth Info
        credentials = get_credential()
    
        # Create OcrClient
        client = get_client()
    
        image_base64 = image_to_base64(r"图片的路径，例如D:\local\test.png")
    
        # request id card service
        response = recognize_id_card_request().to_dict()
    
        # 数据保存在execl上
        response_to_execl(r"excel路径，例如D:\local\test.xlsx", response)