Python中pathlib库的使用小结_Python

1.pathlib库介绍

相比常用的 os.path 而言，pathlib 对于目录路径的操作更简洁也更贴近 pythonic（python代码风格的）。但是它不单纯是为了简化操作，还有更大的用途。

pathlib 是python内置库，python 文档给它的定义是：

the pathlib module – object-oriented filesystem paths(面向对象的文件系统路径)

pathlib 提供表示文件系统路径的类，其语义适用于不同的操作系统。

2.pathlib库下path类的基本使用

2.1 获取文件名

from pathlib import path  # 导入pathlib的path类
import os

path = "/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb"

p = path(path)
print(f"获取文件名：{p.name}")  # 获取文件名：pathlib库的使用.ipynb

2.2 获取文件前缀和后缀 ——.stem&.suffix

from pathlib import path
import os

path = "/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb"

p = path(path)
print(f"获取前缀：{p.stem}")  # 获取前缀：pathlib库的使用
print(f"获取后缀：{p.suffix}")  # 获取后缀：.ipynb

2.3 获取文件的文件夹及上一级、上上级文件夹 ——.parent

from pathlib import path
import os

path = "/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb"

p = path(path)
print(f"获取当前文件所属文件夹：{p.parent}")
print(f"获取上一级文件夹：{p.parent.parent}")
print(f"获取上上一级文件夹：{p.parent.parent.parent}")

"""
获取当前文件所属文件夹：/home/leovin/jupyternotebookfolders
获取上一级文件夹：/home/leovin
获取上上一级文件夹：/home
"""

note: 最上级的文件夹是一个/😂

2.4 获取该文件所属的文件夹及其父文件夹 ——.parents

from pathlib import path
import os

path = "/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb"

p = path(path)
print(f"获取当前文件所属文件夹及其父文件夹：{p.parents}\n")

# 遍历
for idx, folder_path in enumerate(p.parents):
    print(f"no.{idx}: {folder_path}")

"""
获取当前文件所属文件夹及其父文件夹：<posixpath.parents>

no.0: /home/leovin/jupyternotebookfolders
no.1: /home/leovin
no.2: /home
no.3: /
"""

2.5 文件绝对路径按照/进行分割 ——.parts

from pathlib import path
import os

path = "/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb"

p = path(path)
print(f"将文件的绝对路径按照`/`进行分割，返回一个tuple：{p.parts}\n")

# 遍历
for idx, element in enumerate(p.parts):
    print(f"no.{idx}: {element}")

"""
获取当前文件所属文件夹及其父文件夹：<posixpath.parents>

no.0: /
no.1: home
no.2: leovin
no.3: jupyternotebookfolders
no.4: pathlib库的使用.ipynb
"""

2.6 获取当前工作目录 ——path.cwd()

from pathlib import path
import os

path_1 = path.cwd()
path_2 = os.getcwd()

print(f"path.cwd(): {path_1}")
print(f"os.getcwd(): {path_2}")

"""
path.cwd(): /home/leovin/jupyternotebookfolders
os.getcwd(): /home/leovin/jupyternotebookfolders
"""

2.7 获取用户home目录路径 ——path.home()系列

from pathlib import path

print(f"获取用户home路径: {path.home()}")

"""
获取用户home路径: /home/leovin
"""

2.8 获取文件详细信息 ——object.stat()

from pathlib import path

p = path("/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb")
print(f"获取文件详细信息: {p.stat()}\n")
print(f"获取文件字节大小: {p.stat().st_size}\n")
print(f"获取文件创建时间: {p.stat().st_ctime}\n")  # c: create
print(f"获取文件上次修改时间: {p.stat().st_mtime}\n")  # m:: modify

"""
获取文件详细信息: os.stat_result(st_mode=33204, st_ino=23860358, st_dev=2052, st_nlink=1, st_uid=1000, st_gid=1000, st_size=12125, st_atime=1653039478, st_mtime=1653039478, st_ctime=1653039478)

获取文件字节大小: 12125

获取文件创建时间: 1653039478.703161

获取文件上次修改时间: 1653039478.703161
"""

可以看到，object.stat().xxx就是在调用attr 😂

2.9 检查目录或者文件是否存在 ——path("路径").exists()

from pathlib import path

print(f"目标路径的文件是否存在: {path('/home/leovin/jupyternotebookfolders/xxx').exists()}")  # false
print(f"目标路径的文件是否存在: {path('/home/leovin/jupyternotebookfolders').exists()}")  # true

2.10 检查指定指定路径是否为folder或者file ——path("路径").is_file()&path("路径").is_dir()

from pathlib import path

print(f"目标路径是否为文件: {path('/home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb').is_file()}")  # true
print(f"目标路径是否为文件夹: {path('/home/leovin/jupyternotebookfolders/').is_dir()}")  # true

directory为文件夹

2.11 将相对路径转换为绝对路径 ——path("路径").resolve()

from pathlib import path

print(f"转换前的路径为: {path('./pathlib库的使用.ipynb')}")
print(f"转换后的路径为: {path('./pathlib库的使用.ipynb').resolve()}")

"""
转换前的路径为: pathlib库的使用.ipynb
转换后的路径为: /home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb
"""

2.12 遍历一个目录 ——path("路径").iterdir()

from pathlib import path

path_object = path("/home/leovin/jupyternotebookfolders/").iterdir()
print(f"path_object: {path_object}")  # path_object: <generator object path.iterdir at 0x7f0ca0061c10>

# 迭代目录对象
for idx, element in enumerate(path_object):
    print(f"no.{idx}: {element}")
    
"""
path_object: <generator object path.iterdir at 0x7f0ca0061c10>
no.0: /home/leovin/jupyternotebookfolders/temp
no.1: /home/leovin/jupyternotebookfolders/torch.meshgrid().ipynb
no.2: /home/leovin/jupyternotebookfolders/array.argsort().ipynb
no.3: /home/leovin/jupyternotebookfolders/切片....ipynb
no.4: /home/leovin/jupyternotebookfolders/logging信息.log
no.5: /home/leovin/jupyternotebookfolders/python中类的私有变量、私有方法、静态方法.ipynb
no.6: /home/leovin/jupyternotebookfolders/temp_file.ipynb
no.7: /home/leovin/jupyternotebookfolders/example.log
no.8: /home/leovin/jupyternotebookfolders/python语法.ipynb
no.9: /home/leovin/jupyternotebookfolders/.ipynb_checkpoints
no.10: /home/leovin/jupyternotebookfolders/craw.data.txt
no.11: /home/leovin/jupyternotebookfolders/test.txt
no.12: /home/leovin/jupyternotebookfolders/logging的学习.ipynb
no.13: /home/leovin/jupyternotebookfolders/test.ipynb
no.14: /home/leovin/jupyternotebookfolders/算法题
no.15: /home/leovin/jupyternotebookfolders/functions.ipynb
no.16: /home/leovin/jupyternotebookfolders/mask转0&1.ipynb
no.17: /home/leovin/jupyternotebookfolders/multi_task_in_python.ipynb
no.18: /home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb
no.19: /home/leovin/jupyternotebookfolders/三种激活函数绘制.ipynb
"""

2.13 获取所有符合pattern的文件 ——path("路径").glob("folder1/xxx.格式")

from pathlib import path

pattern = "jupyternotebookfolders/*.ipynb"
glob_generator = path("/home/leovin/").glob(pattern)

# 遍历返回的对象 -> 返回的是绝对路径
for idx, element in enumerate(glob_generator):
    print(f"no.{idx}: {element}")
    
"""
no.0: /home/leovin/jupyternotebookfolders/torch.meshgrid().ipynb
no.1: /home/leovin/jupyternotebookfolders/array.argsort().ipynb
no.2: /home/leovin/jupyternotebookfolders/切片....ipynb
no.3: /home/leovin/jupyternotebookfolders/python中类的私有变量、私有方法、静态方法.ipynb
no.4: /home/leovin/jupyternotebookfolders/temp_file.ipynb
no.5: /home/leovin/jupyternotebookfolders/python语法.ipynb
no.6: /home/leovin/jupyternotebookfolders/logging的学习.ipynb
no.7: /home/leovin/jupyternotebookfolders/test.ipynb
no.8: /home/leovin/jupyternotebookfolders/functions.ipynb
no.9: /home/leovin/jupyternotebookfolders/mask转0&1.ipynb
no.10: /home/leovin/jupyternotebookfolders/multi_task_in_python.ipynb
no.11: /home/leovin/jupyternotebookfolders/pathlib库的使用.ipynb
no.12: /home/leovin/jupyternotebookfolders/三种激活函数绘制.ipynb
"""

2.14 删除文件（非目录）——path("路径").unlink()

from pathlib import path

# 当前文件夹下的txt文件
for idx, element in enumerate(path("./").glob("*.txt")):
    print(f"no.{idx}: {element}")
    
print("-" * 30)

"""
    删除指定的文件（非目录）
        1. 是真的删除而非unlink
        2. 如果文件不存在则保存
"""
try:
    path("./will_be_deleted.txt").unlink()
except exception as e:
    print(f"删除文件发生错误，原因为: {e}")

# 当前文件夹下的txt文件
for idx, element in enumerate(path("./").glob("*.txt")):
    print(f"no.{idx}: {element}")

"""
no.0: will_be_deleted.txt
no.1: craw.data.txt
no.2: test.txt
------------------------------
no.0: craw.data.txt
no.1: test.txt


报错的输出：
no.0: craw.data.txt
no.1: test.txt
------------------------------
删除文件发生错误，原因为: [errno 2] no such file or directory: 'will_be_deleted.txt'
no.0: craw.data.txt
no.1: test.txt
"""

3.pathlib库与os库的对比

os库	pathlib库	描述	英文说明
os.path.abspath(("文件路径"))	path("文件路径").resolve()	将路径转换为绝对路径	-
os.chmod()	path("文件路径").chmod(xxx)	更改文件权限	change mode
os.mkdir(("文件路径"))	path("文件路径").mkdir()	新建文件夹	make directory
os.rename("文件路径", "xxx")	path("文件路径").rename("xxx")	重命名文件/文件夹名称	-
os.replace(a, b)	path("文件路径").replace(a, b)	替换字符串	-
os.rmdir()	path("文件路径").rmdir()	删除文件夹（里面必须是空的）	remove directory
os.remove("文件路径") / os.unlink("文件路径")	path("文件路径").unlink()	删除文件（非目录）	-
os.getcwd()	path("文件路径").cwd()	获取当前文件工作目录	current work directory
os.path.isdir()	path("文件路径").is_dir()	判断当前路径是否为目录	-
os.path.isfile()	path("文件路径").is_file()	判断当前路径是否为文件	-
os.stat()	path("文件路径").stat()	返回当前路径的信息	status
os.path.isabs()	path("文件路径").is_absolute()	判断当前路径是否为绝对路径	-
os.path.basename()	path("文件路径").name	返回文件/目录的基础名称（不带路径）	-
os.path.dirname()	path("文件路径").parent	返回路径所属文件夹名称	-
os.path.samefile()	path("文件路径").samefile(xxx)	判断两个文件是否相同	-
os.path.splitext("文件路径")	(path("文件路径").stem, path("文件路径").suffix)	将文件名分离，分成前缀和后缀	stem + suffix