Master Python’s os.walk: Build a Powerful File Management Tool in Minutes

Have you ever wondered how to write a file management program in Python? Thanks to the powerful os.walk module, it’s straightforward. os.walk is a simple and easy‑to‑use iterator that traverses files and directories, enabling efficient handling of file‑system tasks.

1. Basic Introduction

os.walk()

scans a specified directory and returns an iterator over its subdirectories and files.

2. Basic Usage

Assume the folder data has the following structure:

2.1 Scan all files

Scanning content:

Subfolders and files

Files within subfolders

Output format:

folder_name/file_name

Scanning direction:

Top‑down (default, topdown=True)

Bottom‑up ( topdown=False)

from os import walk
path="data"
for curDir, dirs, files in walk(path):
    # for curDir, dirs, files in walk(path, topdown=False):
    print("Current directory:", curDir)
    print("Subdirectories:", str(dirs))
    print("Files:", str(files))
    print("*"*20)

Top‑down scan result:

Current directory: data
Subdirectories: ['testA', 'testB', 'testC']
Files: ['2020-07-12 - 第一层.xlsx', '2020-07-13 - 第一层.xlsx', '2020-07-14 - 第一层.xlsx']
********************
Current directory: data\testA
Subdirectories: []
Files: ['2020-07-12-A.xlsx', '2020-07-13-A.xlsx', '2020-07-14-A.xlsx']
********************
...

Bottom‑up scan result:

Current directory: data\testA
Subdirectories: []
Files: ['2020-07-12-A.xlsx', '2020-07-13-A.xlsx', '2020-07-14-A.xlsx']
********************
...
Current directory: data
Subdirectories: ['testA', 'testB', 'testC']
Files: ['2020-07-12 - 第一层.xlsx', '2020-07-13 - 第一层.xlsx', '2020-07-14 - 第一层.xlsx']
********************

2.2 Scan and output all file paths

import os
path="data"
for curDir, dirs, files in os.walk(path):
    for file in files:
        print(os.path.join(curDir, file))

Example output:

data\2020-07-12 - 第一层.xlsx
data\2020-07-13 - 第一层.xlsx
...
data\testC\2020-07-14-C.xlsx

2.3 Scan and output all subdirectories

# List all subfolders under a directory
import os
path="data"
for curDir, dirs, files in os.walk(path):
    for _dir in dirs:
        print(os.path.join(curDir, _dir))

data\testA
data\testB
data\testC

Case code – File organization script based on dates

import pandas as pd
import numpy as np
import os, openpyxl

def move_file(file_path, _new_path, date_xl_str):
    # Move files of the current month to the new folder, delete others
    for curDir, dirs, files in os.walk(file_path):
        for file in files:
            old_path = os.path.join(curDir, file)
            new_path = os.path.join(_new_path, file)
            file_date = file.split("_")[-1][:10]
            try:
                os.rename(old_path, new_path) if file_date in date_xl_str else os.remove(old_path)
            except:
                os.remove(old_path)
    # Remove subfolders
    for curDir, dirs, files in os.walk(file_path):
        for _dir in dirs:
            os.removedirs(os.path.join(curDir, _dir))
    os.mkdir("data")

def qch_date(file_path):
    wj_names = os.listdir(file_path)
    wj_list = []
    num = 0
    for wj in wj_names:
        new_wj = wj[:-11]
        if new_wj not in wj_list:
            wj_list.append(new_wj)
        else:
            os.remove(file_path + "\\" + wj)
            num += 1
    return num

def refresh_data(file_path, sheet_name, data):
    book = openpyxl.load_workbook(file_path)
    writer = pd.ExcelWriter(file_path, engine="openpyxl")
    writer.book = book
    ws = book[sheet_name]
    for row in ws.iter_rows():
        for cell in row:
            cell.value = None
    idx_num, col_num = data.shape
    for i in range(1, idx_num + 1):
        for j in range(1, col_num + 1):
            ws.cell(row=i, column=j).value = data.iloc[i-1, j-1]
    writer.save()
    writer.close()
    return None

def check_file(file_path, check_file="文件检查.xlsx"):
    wj_names = os.listdir(file_path)
    data = pd.DataFrame([wj.split("_")[2:] for wj in wj_names],
                        columns=["店铺名称", "日期"])
    data['日期'] = data['日期'].str[:10]
    nind = data.index.insert(0, '0')
    data1 = data.reindex(index=nind)
    data1.loc['0'] = data.columns
    data1.reset_index(drop=True, inplace=True)
    refresh_data(check_file, "数据源", data1)
    return None

file_path = "data"
start_date = input("请输入开始日期：")
end_date = input("请输入结束日期：")
date_xl_str = [str(i)[:10] for i in pd.date_range(start_date, end_date, freq='D')]
new_path = start_date + "~" + end_date
try:
    os.mkdir(new_path)
except:
    print("文件夹 【%s】 已存在" % new_path)

move_file(file_path, new_path, date_xl_str)
num = qch_date(new_path)
print("去除重复文件 %s 个" % num)
check_file(new_path)

Article source: Python Programming