Python文件操作之os.path路径拼接分离判断的操作指南

# ❌ 手动拼接路径——不可靠
path = "folder" + "/" + "subfolder" + "/" + "file.txt"
# 在Windows上这个路径用/可能有问题

# ✅ 使用os.path——跨平台安全
import os
path = os.path.join("folder", "subfolder", "file.txt")
# Windows: folder\subfolder\file.txt
# Linux/Mac: folder/subfolder/file.txt

import os

# os.path.join() —— 自动使用正确的路径分隔符
base = os.path.join("home", "user", "documents")
print(base)  # Windows: home\user\documents  Linux: home/user/documents

full_path = os.path.join(base, "python", "script.py")
print(full_path)

# 多个参数——一口气拼完
path = os.path.join("data", "2024", "06", "report.txt")
print(path)  # data\2024\06\report.txt

# join()的智能之处：遇到绝对路径时，前面的会丢失
result = os.path.join("/tmp", "/home/user/file.txt")
print(result)  # /home/user/file.txt —— /tmp被忽略了！
# 因为第二个参数是绝对路径

# 使用绝对路径的参数会被当作"从头开始"
home = os.path.expanduser("~")  # 用户主目录
config_path = os.path.join(home, ".config", "myapp", "settings.json")
print(config_path)

import os

# 当前平台的路径分隔符
print(f"路径分隔符: {repr(os.sep)}")       # Windows: \   Linux: /
print(f"路径分隔符(alt): {repr(os.altsep)}") # Windows: /   Linux: None
print(f"路径列表分隔符: {repr(os.pathsep)}")  # Windows: ;   Linux: :
print(f"当前目录: {repr(os.curdir)}")          # .
print(f"上级目录: {repr(os.pardir)}")          # ..
print(f"换行符: {repr(os.linesep)}")           # Windows: \r\n  Linux: \n

import os

path = "/home/user/documents/report.txt"

# split() —— 拆分为（目录, 文件名）
dir_part, file_part = os.path.split(path)
print(f"目录: {dir_part}")    # /home/user/documents
print(f"文件名: {file_part}")  # report.txt

# basename() —— 获取路径的最后一部分
print(os.path.basename(path))      # report.txt
print(os.path.basename("/home/user/"))  # user（去掉末尾斜杠）

# dirname() —— 获取目录部分
print(os.path.dirname(path))       # /home/user/documents
print(os.path.dirname("/home/user/"))  # /home

# 实用组合
def get_file_info(path):
    """获取文件路径的详细信息"""
    return {
        "full_path": path,
        "directory": os.path.dirname(path),
        "filename": os.path.basename(path),
        "name": os.path.splitext(os.path.basename(path))[0],
        "extension": os.path.splitext(os.path.basename(path))[1],
        "parent_dir": os.path.basename(os.path.dirname(path)),
    }

info = get_file_info("/home/user/documents/report.txt")
for k, v in info.items():
    print(f"  {k}: {v}")

import os

# splitext() —— 分离文件名和扩展名
files = ["script.py", "data.csv", "archive.tar.gz", "README", ".hidden"]

for f in files:
    name, ext = os.path.splitext(f)
    print(f"  {f:20s} → name='{name}', ext='{ext}'")
# script.py           → name='script', ext='.py'
# data.csv            → name='data', ext='.csv'
# archive.tar.gz      → name='archive.tar', ext='.gz'
# README              → name='README', ext=''
# .hidden             → name='.hidden', ext=''

# 💡 splitext只分割最后一个.——所以.tar.gz只分离出.gz
# 如果需要处理双重扩展名：
def get_full_extension(filename):
    """获取完整的扩展名（处理.tar.gz等）"""
    known_compound = {".tar.gz", ".tar.bz2", ".tar.xz"}
    for compound in known_compound:
        if filename.endswith(compound):
            return compound
    return os.path.splitext(filename)[1]

import os

test_path = "test_file.txt"
with open(test_path, "w") as f:
    f.write("test")

# exists() —— 路径是否存在
print(f"存在: {os.path.exists(test_path)}")
print(f"不存在: {os.path.exists('nonexistent.txt')}")

# isfile() —— 是否是文件
print(f"是文件: {os.path.isfile(test_path)}")
print(f"目录不是文件: {os.path.isfile('.')}")

# isdir() —— 是否是目录
print(f"是目录: {os.path.isdir('.')}")
print(f"文件不是目录: {os.path.isdir(test_path)}")

# isabs() —— 是否是绝对路径
print(f"绝对路径: {os.path.isabs('/home/user')}")    # True
print(f"相对路径: {os.path.isabs('folder/file.txt')}") # False

# islink() —— 是否是符号链接（Linux/Mac）
print(f"是符号链接: {os.path.islink(test_path)}")

# ismount() —— 是否是挂载点
print(f"是挂载点: {os.path.ismount('/')}")  # Linux上通常是True

os.remove(test_path)

import os

# abspath() —— 获取绝对路径
relative = "folder/file.txt"
absolute = os.path.abspath(relative)
print(f"相对: {relative}")
print(f"绝对: {absolute}")

# normpath() —— 规范化路径（去掉多余的.和..）
messy = "folder/./subfolder/../other/./file.txt"
clean = os.path.normpath(messy)
print(f"混乱: {messy}")
print(f"规范: {clean}")  # folder/other/file.txt

# normcase() —— 统一大小写（Windows：转小写；Linux：不变）
print(os.path.normcase("C:/Users/NAME/File.txt"))
# Windows: c:\users\name\file.txt

# realpath() —— 解析符号链接，返回真实路径
# os.path.realpath("/symlink/to/file")

# expanduser() —— 展开~为用户主目录
print(os.path.expanduser("~/documents"))
# /home/username/documents 或 C:\Users\username\documents

# expandvars() —— 展开环境变量
# os.path.expandvars("$HOME/documents")  # Linux
# os.path.expandvars("%USERPROFILE%/documents")  # Windows

# relpath() —— 计算相对路径
base = "/home/user/project"
target = "/home/user/project/src/main.py"
print(os.path.relpath(target, base))  # src/main.py

import os

def find_files(directory, pattern=None, extension=None, min_size=None):
    """通用的文件搜索工具"""
    results = []

    for root, dirs, files in os.walk(directory):
        for filename in files:
            filepath = os.path.join(root, filename)

            # 按文件名模式过滤
            if pattern and pattern.lower() not in filename.lower():
                continue

            # 按扩展名过滤
            if extension and not filename.lower().endswith(extension.lower()):
                continue

            # 按文件大小过滤
            if min_size is not None:
                if os.path.getsize(filepath) < min_size:
                    continue

            results.append({
                "path": filepath,
                "name": filename,
                "size": os.path.getsize(filepath),
                "ext": os.path.splitext(filename)[1],
                "dir": os.path.dirname(filepath),
            })

    return results

# 搜索所有Python文件
# python_files = find_files(".", extension=".py")
# for f in python_files:
#     print(f"{f['name']} ({f['size']}字节)")