步骤一，开通腾讯云的【通用文字识别服务】

步骤二、申请一个apiKey

步骤三 安装腾讯的 python库

pip3 install tencentcloud_sdk_python

步骤四 建立脚本

imgToExcel.py

python
#coding=utf-8
import sys
import ocr
import yaml

def get_yaml_data(yaml_file):
    # 打开yaml文件
    file = open(yaml_file, 'r', encoding="utf-8")
    file_data = file.read()
    file.close()
    # 将字符串转化为字典或列表
    data = yaml.load(file_data, Loader=yaml.FullLoader)
    return data

def imageToExcel(pic_path):

    config = get_yaml_data("config.yml")

    # 使用ocr进行转换
    trans = ocr.OCR()
    path_excel = trans.img_to_excel(
        pic_path,
        image_path=pic_path,
        secret_id=config['secret_id'],
        secret_key=config['secret_key'],
    )

if __name__ == '__main__':
    pic_path = sys.argv[1]
    imageToExcel(pic_path)

ocr.py

python
#coding=utf-8
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.ocr.v20181119 import ocr_client, models
import base64

# OCR识别封装
class OCR(object):

    def img_to_excel(self,
                     output_file_name,
                     image_path,
                     secret_id,
                     secret_key):
        # 实例化一个认证对象，入参需要传入腾讯云账户secretId，secretKey
        cred = credential.Credential(
            secret_id,
            secret_key
        )
        # 实例化client对象
        httpProfile = HttpProfile()
        httpProfile.endpoint = "ocr.tencentcloudapi.com"
        clientProfile = ClientProfile()
        clientProfile.httpProfile = httpProfile
        clientProfile.signMethod = "TC3-HMAC-SHA256"
        client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
        # 实例化一个请求对象
        #req = models.GeneralFastOCRRequest()
        req = models.GeneralFastOCRRequest()
        # 读取图片数据，使用Base64编码
        with open(image_path, 'rb') as f:
            image = f.read()
            image_base64 = str(base64.b64encode(image), encoding='utf-8')
        req.ImageBase64 = image_base64
        # 通过client对象调用访问接口，传入请求对象
        resp = client.RecognizeTableOCR(req)
        # 获取返回数据（Data为Base64编码后的Excel数据）
        data = resp.Data
        # 转换为Excel
        output_file_name = str(output_file_name)
        path_excel = output_file_name + ".xlsx"
        with open(path_excel, 'wb') as f:
            f.write(base64.b64decode(data))
        return path_excel

config.yml 替换你自己的apikey信息

#coding=utf-8
secret_id: a
secret_key: a

步骤五 执行脚本见证奇迹

python
python3 imgToExcel.py 111.png