发票合同20.

赵乾舟 发表于 2024-11-25 19:25:03

import pdfplumber,os
from openpyxl import Workbook
from datetime import datetime

# path = r'D:\发票'
path = input('file_path:')
wenjian = Workbook()# 创建存放发票信息的文件
D = wenjian.active
D.column_dimensions['A'].width = 40
D.column_dimensions['B'].width = 20
D.column_dimensions['C'].width = 30
D.column_dimensions['D'].width = 40
D.column_dimensions['E'].width = 20
title = ["开票号码","开票日期", "买方信息","卖方信息","价税合计" ]# 先把要提取内容的抬头写入单元格
for h in range(1, 6):
D.cell(1, h, title)

now = datetime.now()
nt = str(now)
file_houzhui = nt.replace(':','')
# print(file_houzhui)

i = 2

list = []
files = os.listdir(path)
print(files)
for file in files:
if file.endswith('pdf'):

   # print(path+'\\'+file)
   with pdfplumber.open(path+'\\'+file) as pdf:
         page = pdf.pages
         text = page.extract_text()
         # print(text)
         xuhao = text.split('发票号码：').split()
         # print(xuhao)
         riqi = text.split('开票日期：').split()
         # print(type(riqi))
         riqi = datetime.strptime(riqi, "%Y年%m月%d日")
         # riqi = riqi.strftime('%Y-%m-%d')
         # print(type(riqi))
         goumai = text.split('购名称：').split()
         # print(goumai)
         maijia = text.split('销名称：').split()
         # print(maijia)
         total = text.split('（小写）¥').split()
         total = float(total)
         # print(total)

         wenjian.active.cell(i,1,xuhao)
         wenjian.active.cell(i,2,riqi)
         wenjian.active.cell(i,3,goumai)
         wenjian.active.cell(i,4,maijia)
         wenjian.active.cell(i,5,total)
         # print(list)
         i = i +1
wenjian.save(f'{path}\\发票-{file_houzhui}.xlsx')
import pdfplumber,os
from openpyxl import Workbook
from datetime import datetime

path = input('file_path:')
wenjian = Workbook()# 创建存放信息的文件
D = wenjian.active
D.column_dimensions['A'].width = 30
D.column_dimensions['B'].width = 30
D.column_dimensions['C'].width = 20
D.column_dimensions['D'].width = 40
D.column_dimensions['E'].width = 20
title = ["甲方","乙方", "金额" ]# 先把要提取内容的抬头写入单元格
for h in range(1, 4):
D.cell(1, h, title)

i = 2
now = datetime.now()
nt = str(now)
file_houzhui = nt.replace(':','')

files = os.listdir(path)
for file in files:
if file.endswith('pdf'):

   print(path+file)
   with pdfplumber.open(path+'\\'+file) as pdf:
         page = pdf.pages
         text = page.extract_text()
         print(text)
         print('---'*20)
         jiafang = text.split('下简称甲方）：').split()
         print(jiafang)
         yifang = text.split('简称乙方）：').split()
         print(yifang)
         total = text.split('合计 ').split()
         print(total)
         total= float(total)
         wenjian.active.cell(i,1,jiafang)
         wenjian.active.cell(i,2,yifang)
         wenjian.active.cell(i,3,total)

         i = i +1
wenjian.save(f'{path}\\合同-{file_houzhui}.xlsx')

页: [1]

's Archiver

发票合同20.