#QQ：502440275@qq.com
#本截图适合安康码截图，如需其他地区截图统计，可与我QQ或QQ邮箱联系
#1、在当前文件夹下创建imgs文件夹用于存放图片，图片格式.jpg
#2、在当前文件夹下创建“shuju.xlsx”的Excel用于存放统计结果

文件夹目录样式

 统计结果Excel样式

具体代码如下：

# @Time : 2022/4/19 22:00 

# @Author : CFang

# @File : hesuan_results.py 

# @Software: PyCharm
#QQ：502440275@qq.com
#本截图适合安康码截图，如需其他地区截图统计，可与我QQ或QQ邮箱联系
#1、在当前文件夹下创建imgs文件夹用于存放图片，图片格式.jpg
#2、在当前文件夹下创建“shuju.xlsx”的Excel用于存放统计结果

#获得截图结果
def get_hesuan_res(path):
    #获得API的access_token
    import requests
    AK = '*******'#输入自己的百度智能云的AK和SK
    SK = '*******'
    # client_id 为官网获取的AK， client_secret 为官网获取的SK
    host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id='+AK+'&client_secret='+SK
    response = requests.get(host)
    if response:
        print(response.json())
        print(response.json()['access_token'])


    # encoding:utf-8
    #文字识别接口，可自己调整不同接口获得不同精度要求
    import requests
    import base64

    '''
    通用文字识别
    '''

    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic"
    # 二进制方式打开图片文件
    f = open(path, 'rb')
    img = base64.b64encode(f.read())

    params = {"image":img}
    access_token = response.json()['access_token']
    request_url = request_url + "?access_token=" + access_token
    headers = {'content-type': 'application/x-www-form-urlencoded'}
    response = requests.post(request_url, data=params, headers=headers)
    if response:
        # print (response.json())
        # print(response.json()['words_result'])
        all_res = response.json()['words_result']
        return all_res
        # for i in range(len(all_res)):
        #     print(i,all_res[i])

# 对图片识别结果的数据清洗
all_lists_deals = []
def deal_datas(all_lists):
    all_lists_deal = []
    if all_lists[5]['words'].split("：")[0] == "姓名":
        for i in range(5, len(all_lists)):
            print(i, all_lists[i]['words'])  # ,all_lists_display[i]['words']
            if all_lists[i]['words'] != '>' and all_lists[i]['words'] != '身份证件号码：':
                all_lists_deal.append(all_lists[i]['words'])
        all_lists_deal[0] = all_lists_deal[0].split("：")[1][:-1]
        # print(all_lists_deal)
    else:
        for i in range(6, len(all_lists)):
            print(i, all_lists[i]['words'])  # ,all_lists_display[i]['words']
            if all_lists[i]['words'] != '>':
                all_lists_deal.append(all_lists[i]['words'])
        all_lists_deal[0] = all_lists_deal[0].split("：")[1]
        all_lists_deal[1] = all_lists_deal[1].split("：")[1]
        # print(all_lists_deal)

    print(all_lists_deal)
    all_lists_deals.append(all_lists_deal)

#获取文件夹imgs内的所有图片
import os
def get_imlist(path):
    return [os.path.join(path,f) for f in os.listdir(path) if f.endswith('.jpg')]

img_path = get_imlist("imgs")
print(img_path)

for path in img_path:
    all_lists = get_hesuan_res(path)
    deal_datas(all_lists)

#保存识别清洗后的数据结果到“shuju.xlsx”表中
# -*- coding: UTF-8 -*-
from openpyxl import load_workbook

wb = load_workbook('shuju.xlsx')
ws = wb['Sheet1']

row = ws.max_row+1
for j in range(len(all_lists_deals)):
    for i in range(len(all_lists_deals[j])):
        if len(all_lists_deals[j][i].split("：")) == 1:
            ws.cell(row+j,i+1).value = all_lists_deals[j][i]
        elif all_lists_deals[j][i].split("：")[0] == "检测机构" or all_lists_deals[j][i].split("：")[0] == "身份证件号码":
            ws.cell(row+j, i + 1).value = all_lists_deals[j][i].split("：")[1]
        else:
            ws.cell(row+j, i + 1).value = all_lists_deals[j][i].split("：")[1][:10]
wb.save('shuju.xlsx')