获取目录大小 跨平台 多级父目录

目录

获取多级父目录：

linux 获取目录大小，包含隐藏目录

windows系统：

有个目录大小很大，子目录占用空间又很小

获取所有后缀

---

获取多级父目录：

import os



path = '/home/user/projects/example_project/subdir/file.txt'
third_level_parent = os.path.abspath(os.path.join(path, "../../.."))

print(f"The third level parent directory of {path} is {third_level_parent}")

linux 获取目录大小，包含隐藏目录

 
 
import glob
import subprocess
import os
def get_directory_size_with_du(directory):
    try:
        # 调用 du -sh 命令并捕获输出
        result = subprocess.run(['du', '-sh', directory], capture_output=True, text=True, check=True)
        # 输出是类似 "1.2G   /path/to/directory"
        size = result.stdout.split()[0]  # 提取文件大小
        return size
    except subprocess.CalledProcessError as e:
        print(f"Error occurred: {e}")
        return None
 
def find_first_level_subdirs(directory):
    first_level_subdirs = []
    for root, dirs, files in os.walk(directory):
        # 遍历一级子目录
        for subdir in dirs:
            first_level_subdirs.append(os.path.join(root, subdir))
        # 阻止 os.walk() 递归遍历
        break
    return first_level_subdirs


if __name__ == '__main__':
 
    base_dir = "/home/lixiang/workspace/giga-generativeai"
    # base_dir = "/home/lixiang/workspace/giga-generativeai/giga-train/gt_projects"
 
    dirs=glob.glob(base_dir+'/*')+glob.glob(base_dir+'/.*')
 
    for dir in dirs:
        size = get_directory_size_with_du(dir)
        if size[-1] in ["G"]:
            print(f"dir size: {size}",dir)
        elif size[-1] in ["M","G"]:
            size_number=float(size[:-1])
            if size[-1]=="M":
                if size_number>1:
                    print(f"dir size: {size}",dir)


    subdirs = find_first_level_subdirs(base_dir)

    for dir in subdirs:
        print(dir)                

windows系统：

import math
import subprocess

def convert_size(size_bytes):
    if size_bytes == 0:
        return "0B"

    size_name = ("B", "KB", "MB", "GB", "TB")
    i = int(math.floor(math.log(size_bytes, 1024)))
    p = math.pow(1024, i)
    s = round(size_bytes / p, 2)

    return f"{s} {size_name[i]}"

def get_directory_size_with_powershell(directory):
    try:
        # 使用 PowerShell 命令获取目录大小
        result = subprocess.run(['powershell', '-Command', f"(Get-ChildItem -Recurse '{directory}' | Measure-Object -Property Length -Sum).Sum"], capture_output=True, text=True, check=True)
        size_in_bytes = int(result.stdout.strip())
        return size_in_bytes
    except subprocess.CalledProcessError as e:
        print(f"Error occurred: {e}")
        return None

if __name__ == '__main__':


    # 示例使用
    directory_path =r"F:\biadu_down\jacke121-yolov5-v3.0_class"
    size_in_bytes = get_directory_size_with_powershell(directory_path)

    size_human_readable = convert_size(size_in_bytes)
    print(f"Directory size: {size_human_readable} m")

有个目录大小很大，子目录占用空间又很小

解决方法：查看隐藏文件：

ls -la /path/to/a

发现有个隐藏目录 .git 很大，

查看 .git 大小：

du -sh /path/to/a/.git

删除目录： .git

rm -R .git

获取所有后缀

import os

def get_all_file_extensions(directory):
    extensions = set()
    for root, dirs, files in os.walk(directory):
        for file in files:
            _, ext = os.path.splitext(file)
            if ext:  # 如果有扩展名
                extensions.add(ext)
    return extensions

if __name__ == '__main__':

    dir_path = r"E:\project\depth\linre\linre"
    all_extensions = get_all_file_extensions(dir_path)
    for extension in all_extensions:
        print(extension)


    img_files = ['%s/%s' % (i[0].replace("\\", "/"), j) for i in os.walk(dir_path) for j in i[-1] if j.endswith(('cu', 'xpng', 'xjpeg'))]
    for file in img_files:
        print(file)