文字识别 OCR-识别结果后处理:提取特定字段导入Excel

时间：2024-11-07 17:17:46

文字识别 OCR

提取特定字段导入Excel

本示例调用身份证识别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。
- 参考本地调用，安装OCR Python SDK。并执行pip install xlsxwriter命令安装依赖包。
- 登录访问密钥页面，获取AK、SK。可以新增访问密钥，或使用已有的访问密钥。访问密钥为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__':
    # 填写访问密钥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)

上一篇：文字识别 OCR-V1版本APIs切换至V2版指导:APIs切换步骤

下一篇：文字识别 OCR-解读识别结果