Python Standard Library: File System and OS Modules Overview

1. os module – Offers functions to interact with the operating system, such as retrieving the current working directory and listing directory contents.

import os
current_dir = os.getcwd()
print("当前工作目录:", current_dir)
files = os.listdir('.')
print("当前目录下的文件和文件夹:", files)

2. os.path submodule – Provides utilities for pathname manipulation, including joining path components and checking path existence.

import os
path = os.path.join('用户', '文档', '报告.docx')
print("组合后的路径:", path)
exists = os.path.exists('report.docx')
print("路径存在吗:", exists)

3. shutil module – Supplies high‑level file operations such as copying and moving files or directories.

import shutil
shutil.copy('source.txt', 'destination.txt')
print("文件已复制")
shutil.move('old_location/file.txt', 'new_location/file.txt')
print("文件已移动")

4. glob module – Finds pathnames matching a pattern using Unix shell‑style wildcards.

import glob
txt_files = glob.glob('*.txt')
print("找到的文本文件:", txt_files)

5. pathlib module – Introduced in Python 3.4, it offers an object‑oriented approach to filesystem paths, allowing iteration over directory entries and pattern‑based searches.

from pathlib import Path
p = Path('.')
for file in p.iterdir():
    if file.is_file():
        print(file)
for txt_file in p.glob('*.txt'):
    print(txt_file)

6. io module – Contains classes for handling various I/O operations, including reading from and writing to text files.

import io
with open('example.txt', 'r', encoding='utf-8') as f:
    content = f.read()
    print(content)
with open('output.txt', 'w', encoding='utf-8') as f:
    f.write("这是一个测试。\n")
    print("数据已写入文件")

7. tempfile module – Provides utilities for creating temporary files and directories, useful for short‑lived data storage.

import tempfile
with tempfile.TemporaryFile() as temp:
    temp.write(b'Hello World!')  # 写入字节数据
    temp.seek(0)  # 回到文件开头
    print(temp.read())  # 读取数据

8. fileinput module – Allows iteration over lines from one or more input files, simplifying command‑line file processing.

import fileinput
for line in fileinput.input(['file1.txt', 'file2.txt']):
    print(line, end='')  # 默认会添加换行符，所以使用end=''来避免重复换行

9. pickle module – Implements object serialization (pickling) and deserialization (unpickling) for persisting complex data structures.

import pickle
data = {'key': 'value'}
# 序列化
with open('data.pkl', 'wb') as f:
    pickle.dump(data, f)
# 反序列化
with open('data.pkl', 'rb') as f:
    loaded_data = pickle.load(f)
    print("加载的数据:", loaded_data)

10. csv module – Provides functionality to read from and write to CSV (comma‑separated values) files.

import csv
with open('example.csv', newline='') as csvfile:
    reader = csv.reader(csvfile)
    for row in reader:
        print(row)
with open('output.csv', 'w', newline='') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['Name', 'Age'])
    writer.writerow(['Alice', 30])

11. zipfile module – Enables creation, reading, and extraction of ZIP archives.

import zipfile
with zipfile.ZipFile('example.zip', 'r') as zip_ref:
    zip_ref.extractall('destination_folder')
    print("文件已解压")

12. tarfile module – Offers full support for TAR archive files, including gzip‑compressed variants.

import tarfile
with tarfile.open('example.tar.gz', 'r:gz') as tar:
    tar.list()