需求:需要将指定文件夹下的压缩包,解压后将其中的pdf文件统一拷贝到指定文件夹,并提取每一个压缩包中的excel 文件内容,合并成一个EXCEl
代码如下:
# -*- coding:utf-8*-
import os.path
import zipfile
import shutil
from pathlib import Path
from openpyxl import load_workbook
zl_dir = "./专利"
zl_dir_pdf_cpy = './专利_copy'
excel_name = './Patents.xlsx'
def get_all_files(dir):
files_ = []
list = os.listdir(dir)
for i in range(0, len(list)):
path = os.path.join(dir, list[i])
if os.path.isdir(path):
files_.extend(get_all_files(path))
if os.path.isfile(path):
files_.append(path)
return files_
def file_extension(path):
return os.path.splitext(path)[1]
def InsertExcelData(row, sheet, data):
# print( 'row :', row)
for com, val in enumerate(data):
# print( 'com :', com)
sheet.write(r