Python之遍历文件夹及合并文件内容

# -*- coding: utf-8 -*-

import os
import linecache
from pptx import Presentation as pra

#循环遍历文件
def loop_allfile(basepath,file_ob_list=[]):
    #读取指定路径下的所有文件并放入列表中
    file_names=os.listdir(basepath)
    for file_name in file_names:
        file_ob=basepath + '/' + file_name
        #获取文件扩展名
        file_ex=os.path.splitext(file_name)[-1]
        klist=[".txt",".gsql",".sql",".py",".pl",".sh",".vba",".bat",".xml",".json"]
        print(file_ob + '：****' + file_ex)
        #判断是否是文件夹
        if os.path.isdir(file_ob):
            loop_allfile(file_ob)
        else:
            #判断文件后缀名
            if file_name == "vxx.txt" or file_ex not in klist:
                print(file_name + "：---------")
            else:
                file_ob_list.append(file_ob)
    return file_ob_list

#合并文件内容
def combine_file(root):
    file_ob_list=loop_allfile(root)
    #对每个文件按行读取
    data=[]
    for file_nm in file_ob_list:
        line_num=1
        length_file=len(open(file_nm,encoding='utf-8').readlines())
        while line_num <= length_file:
            line = linecache.getline(file_nm,line_num)
            line = line.strip()
            data.append(line)
            line_num = line_num + 1
        print(len(data))
        
combine_file("C:/Users/2023")