教你用Python实现自动提取并收集信息的功能

import cv2
from aip import AipOcr

# 读取图片，利用imshow显示图片
pic = cv2.imread(r'Y:\cut\img1.png')
pic = cv2.resize(pic,None,fx = 0.5, fy = 0.5)
cv2.imshow('img',pic)
cv2.waitKey(0)

# 删除不必要的部分
img = pic[210:500, 100:580]

# 截取各部分的文字
time = pic[400:430, 100:580]
business = pic[370:400, 100:580]
goods = pic[350:380, 100:580]
money = pic[210:300, 100:580]
num = pic[460:500, 100:580]
# 查看截取的部分是否合适

gener_name = ['time','business','goods','money','num']
excel_data = {}
pd_columns = ["a","b","c","d","e"] # 标题

def shotcut_image(args):
    for index in gener:
        cv2.imwrite('image/{}.png'.format(args), img)

# 导入api
AppID = '24177719'
API_Key = 'p8skmRYfHGoVGR4UU03Q5jiM'
Secret_Key = 'dyM0tzSILBZu9CFqZ7IkjWwECGaws4xo'

cilent = AipOcr(AppID,API_Key,Secret_Key)

def get_words(img_name):
    with open('image/{}.png'.format(img_name), 'rb') as f:
        result = cilent.basicAccurate(f.read())
        return result

def convert_to_dataframe(words):
    # 构建dataframe
    result = words['words_result']
    for word in result:
        excel_data.setdefault('a', []).append(word['words'])

# 将所有words读取后，取出语句存入excel
def convert_to_excel():
    frame = DataFrame(excel_data, columns=pd_columns)
    # todo 表头需要额外处理，这里指定不设置表头
    frame.to_excel('out.xls',index=False, header=False)