Python批量识别发票

from PIL import Image as PI

import pyocr

import pyocr.builders

from cnocr import CnOcr

pip install pyocr

pip install cnocr

tool = pyocr.get_available_tools()[0]

img_url = "pic/pic1.jpg"

with open(img_url, 'rb') as f:

    a = f.read()

new_img = PI.open(io.BytesIO(a))

## 金额

left = 741

top = 420

right = 850

bottom = 445

image_text1 = new_img.crop((left, top, right, bottom))

#展示图片

image_text1.show()

left = 155

top = 450

right = 450

bottom = 470

image_obj2 = new_img.crop((left, top, right, bottom))

image_obj2.show()

image_obj2.save("tmp.jpg")

ocr = CnOcr()

res = ocr.ocr("tmp.jpg")

print("".join(res[0]))

#纳税人识别号

left = 155

top = 470

right = 450

bottom = 490

image_text3 = new_img.crop((left, top, right, bottom))

#展示图片

image_text3.show()

txt3 = tool.image_to_string(image_text3)

print(txt3)

left = 528

top = 550

right = 670

bottom = 600

image_obj4 = new_img.crop((left, top, right, bottom))

image_obj4.show()

image_obj4.save("tmp.jpg")

ocr = CnOcr()

res = ocr.ocr("tmp.jpg")

print("".join(res[0]))

filePath = 'pic'

pic_name = []

for i,j,name in os.walk(filePath):

    pic_name = name

for i in pic_name:

    print(i)

for i in pic_name:

    img_url = filePath+"/"+i

    with open(img_url, 'rb') as f:

        a = f.read()

    new_img = PI.open(io.BytesIO(a))

    ## 写入csv

    outws.cell(row=count, column=1, value=text2(new_img))

    outws.cell(row=count, column=2, value=text3(new_img))

    outws.cell(row=count, column=3, value=text1(new_img))

    outws.cell(row=count, column=4, value=text4(new_img))

    count = count + 1

outwb.save("发票汇总-李运辰.xls")  # 保存结果

# 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=【官网获取的AK】&client_secret=【官网获取的SK】'

response = requests.get(host)

if response:

    print(response.json()['access_token']