利用Python批量识别电子账单数据的方法

pip install baidu-aip -i http://pypi.douban.com/simple --trusted-host pypi.douban.com

from aip import AipOcr

""" 你的 APPID AK SK """
APP_ID = '你的 App ID'
API_KEY = '你的 Api Key'
SECRET_KEY = '你的 Secret Key'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

""" 读取图片 """
def get_file_content(filePath):
 with open(filePath, 'rb') as fp:
  return fp.read()

image = get_file_content('example.jpg')

""" 调用通用文字识别, 图片参数为本地图片 """
client.basicGeneral(image)
""" 调用通用文字识别（高精度版） 图片参数为本地图片 """
client.basicAccurate(image)

from aip import AipOcr

# """ 改成你的 百度云服务的 ID AK SK """
APP_ID = '18690701'
API_KEY = 'QFaTVXvZdPrR05dNlR5I49xA'
SECRET_KEY = '*******************************'
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

def get_file_content(filePath):
 with open(filePath, 'rb') as fp:
  return fp.read()

image = get_file_content('example.jpg')
# 调用通用文字识别, 图片参数为本地图片
result = client.basicGeneral(image)
print(result)
# 提取识别结果
info = '\n'.join([i['words'] for i in result['words_result']])
print(info)

from pathlib import Path

# 换成你放图片的路径
p = Path(r'D:\test\test_img')
# 得到所有文件夹下 .jpg 图片
file = p.glob('**/*.jpg')
for img_file in file:
 print(type(img_file)) # <class 'pathlib.WindowsPath'> 转成str
 img_file = str(img_file)
 print(img_file)

from pathlib import Path
import cv2 as cv
from aip import AipOcr
from time import sleep

APP_ID = '18690701'
API_KEY = 'QFaTVXvZdPrR05dNlR5I49xA'
SECRET_KEY = '**********************************'
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

""" 读取图片 """
def get_file_content(filePath):
 with open(filePath, 'rb') as fp:
  return fp.read()

def identity(num):
 result_list = []
 for i in range(num):
  image = get_file_content('img{}.jpg'.format(i))
  """ 调用通用文字识别, 图片参数为本地图片 """
  result = client.basicGeneral(image)
  print(result)
  sleep(2)
  # 识别结果
  info = ''.join([i['words'] for i in result['words_result']])
  result_list.append(info)
 print(result_list)

src = cv.imread(r'D:\test\test_img\001.jpg')
src = cv.resize(src, None, fx=0.5, fy=0.5)
# print(src.shape)
img = src[280:850, 10:580]  # 截取图片 高 宽
money = img[70:130, 150:450]  # 支出 收入金额
goods = img[280:330, 160:560]  # 商品
time_1 = img[380:425, 160:292] # 支付时间 年月日
time_2 = img[380:425, 160:390] # 支付时间 完整
way = img[430:475, 160:560]  # 支付方式
num_1 = img[480:520, 160:560]  # 交易单号
num_2 = img[525:570, 160:560]  # 商户单号
img_list = [money, goods, time_1, time_2, way, num_1, num_2]
for index_, item in enumerate(img_list):
 cv.imwrite(f'img{index_}.jpg', item)

identity(len(img_list))

"""
@File ：test_01.py
@Author ：叶庭云
@CSDN ：https://yetingyun.blog.csdn.net/
"""
from aip import AipOcr
from pathlib import Path
import cv2 as cv
from time import sleep
import openpyxl


wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(['消费', '商品', '支付时间', '支付方式', '交易单号', '商品单号'])
# """ 改成你的 百度云服务的 ID AK SK """
APP_ID = '18690701'
API_KEY = 'QFaTVXvZdPrR05dNlR5I49xA'
SECRET_KEY = '*******************************'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

""" 读取图片 """
def get_file_content(filePath):
 with open(filePath, 'rb') as fp:
  return fp.read()


def identity(num):
 result_list = []
 for i in range(num):
  image = get_file_content('img{}.jpg'.format(i))
  """ 调用通用文字识别, 图片参数为本地图片 """
  result = client.basicAccurate(image)
  print(result)
  sleep(1)
  # 识别结果
  info = ''.join([i['words'] for i in result['words_result']])
  result_list.append(info)

 result_list[2] = result_list[2] + ' ' + result_list[3]
 result_list.pop(3)
 print(result_list)
 sheet.append(result_list)


# 换成你放图片的路径
p = Path(r'D:\test\test_img')
# 得到所有文件夹下 .jpg 图片
file = p.glob('**/*.jpg')
for img_file in file:
 img_file = str(img_file)
 src = cv.imread(r'{}'.format(img_file))
 src = cv.resize(src, None, fx=0.5, fy=0.5)
 # print(src.shape)
 img = src[280:850, 10:580]  # 截取图片 高、宽范围
 money = img[70:130, 150:450]  # 支出金额
 goods = img[280:330, 160:560]  # 商品
 time_1 = img[380:425, 160:292] # 支付时间 年月日
 time_2 = img[380:425, 290:390] # 支付时间 时分秒
 way = img[430:475, 160:560]  # 支付方式
 num_1 = img[480:520, 160:560]  # 交易单号
 num_2 = img[525:570, 160:560]  # 商户单号
 img_list = [money, goods, time_1, time_2, way, num_1, num_2]
 for index_, item in enumerate(img_list):
  cv.imwrite(f'img{index_}.jpg', item)
 identity(len(img_list))
 # cv.imshow('img', img)
 # cv.imshow('goods', time_2)
 # cv.waitKey(0)

wb.save(filename='识别账单结果.xlsx')