#QQ：@qq.com
#本截圖適合安康碼截圖，如需其他地區(qū)截圖統(tǒng)計，可與我QQ或QQ郵箱聯(lián)系
#1、在當(dāng)前文件夾下創(chuàng)建imgs文件夾用于存放圖片，圖片格式.jpg
#2、在當(dāng)前文件夾下創(chuàng)建“shuju.xlsx”的Excel用于存放統(tǒng)計結(jié)果

文件夾目錄樣式

黃浦網(wǎng)站建設(shè)公司創(chuàng)新互聯(lián)建站,黃浦網(wǎng)站設(shè)計制作，有大型網(wǎng)站制作公司豐富經(jīng)驗。已為黃浦上千提供企業(yè)網(wǎng)站建設(shè)服務(wù)。企業(yè)網(wǎng)站搭建\外貿(mào)營銷網(wǎng)站建設(shè)要多少錢，請找那個售后服務(wù)好的黃浦做網(wǎng)站的公司定做！

統(tǒng)計結(jié)果Excel樣式

具體代碼如下：

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

# @Author : CFang

# @File : hesuan_results.py

# @Software: PyCharm
#QQ：@qq.com
#本截圖適合安康碼截圖，如需其他地區(qū)截圖統(tǒng)計，可與我QQ或QQ郵箱聯(lián)系
#1、在當(dāng)前文件夾下創(chuàng)建imgs文件夾用于存放圖片，圖片格式.jpg
#2、在當(dāng)前文件夾下創(chuàng)建“shuju.xlsx”的Excel用于存放統(tǒng)計結(jié)果

#獲得截圖結(jié)果
def get_hesuan_res(path):
#獲得API的access_token
    import requests
    AK= '*******'#輸入自己的百度智能云的AK和SK
    SK = '*******'
    # client_id 為官網(wǎng)獲取的AK， client_secret 為官網(wǎng)獲取的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
    #文字識別接口，可自己調(diào)整不同接口獲得不同精度要求
    import requests
import base64

'''
    通用文字識別
'''

    request_url= "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic"
    # 二進(jìn)制方式打開圖片文件
    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])

# 對圖片識別結(jié)果的數(shù)據(jù)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'] != '身份證件號碼：':
                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)

#獲取文件夾imgs內(nèi)的所有圖片
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)

#保存識別清洗后的數(shù)據(jù)結(jié)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] == "檢測機構(gòu)" or all_lists_deals[j][i].split("：")[0] == "身份證件號碼":
            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')