在我重新发明这个特殊的轮子之前,有没有人有一个很好的用Python计算目录大小的例程?如果该例程能以Mb/Gb等格式格式化大小,那就太好了。


当前回答

当计算子目录的大小时,它应该更新其父目录的文件夹大小,这将一直进行下去,直到它到达根父目录。

下面的函数计算文件夹及其所有子文件夹的大小。

import os

def folder_size(path):
    parent = {}  # path to parent path mapper
    folder_size = {}  # storing the size of directories
    folder = os.path.realpath(path)

    for root, _, filenames in os.walk(folder):
        if root == folder:
            parent[root] = -1  # the root folder will not have any parent
            folder_size[root] = 0.0  # intializing the size to 0

        elif root not in parent:
            immediate_parent_path = os.path.dirname(root)  # extract the immediate parent of the subdirectory
            parent[root] = immediate_parent_path  # store the parent of the subdirectory
            folder_size[root] = 0.0  # initialize the size to 0

        total_size = 0
        for filename in filenames:
            filepath = os.path.join(root, filename)
            total_size += os.stat(filepath).st_size  # computing the size of the files under the directory
        folder_size[root] = total_size  # store the updated size

        temp_path = root  # for subdirectories, we need to update the size of the parent till the root parent
        while parent[temp_path] != -1:
            folder_size[parent[temp_path]] += total_size
            temp_path = parent[temp_path]

    return folder_size[folder]/1000000.0

其他回答

python3.5 +

from pathlib import Path

def get_size(folder: str) -> int:
    return sum(p.stat().st_size for p in Path(folder).rglob('*'))

用法::

In [6]: get_size('/etc/not-exist-path')
Out[6]: 0
In [7]: get_size('.')
Out[7]: 12038689
In [8]: def filesize(size: int) -> str:
   ...:     for unit in ("B", "K", "M", "G", "T"):
   ...:         if size < 1024:
   ...:             break
   ...:         size /= 1024
   ...:     return f"{size:.1f}{unit}"
   ...:

In [9]: filesize(get_size('.'))
Out[9]: '11.5M'

import os
def get_size(path = os.getcwd()):
    print("Calculating Size: ",path)
    total_size = 0
    #if path is directory--
    if os.path.isdir(path):
      print("Path type : Directory/Folder")
      for dirpath, dirnames, filenames in os.walk(path):
          for f in filenames:
              fp = os.path.join(dirpath, f)
              # skip if it is symbolic link
              if not os.path.islink(fp):
                  total_size += os.path.getsize(fp)
    #if path is a file---
    elif os.path.isfile(path):
      print("Path type : File")
      total_size=os.path.getsize(path)
    else:
      print("Path Type : Special File (Socket, FIFO, Device File)" )
      total_size=0
    bytesize=total_size
    print(bytesize, 'bytes')
    print(bytesize/(1024), 'kilobytes')
    print(bytesize/(1024*1024), 'megabytes')
    print(bytesize/(1024*1024*1024), 'gegabytes')
    return total_size


x=get_size("/content/examples")

我相信这很有帮助!文件夹和文件!

当计算子目录的大小时,它应该更新其父目录的文件夹大小,这将一直进行下去,直到它到达根父目录。

下面的函数计算文件夹及其所有子文件夹的大小。

import os

def folder_size(path):
    parent = {}  # path to parent path mapper
    folder_size = {}  # storing the size of directories
    folder = os.path.realpath(path)

    for root, _, filenames in os.walk(folder):
        if root == folder:
            parent[root] = -1  # the root folder will not have any parent
            folder_size[root] = 0.0  # intializing the size to 0

        elif root not in parent:
            immediate_parent_path = os.path.dirname(root)  # extract the immediate parent of the subdirectory
            parent[root] = immediate_parent_path  # store the parent of the subdirectory
            folder_size[root] = 0.0  # initialize the size to 0

        total_size = 0
        for filename in filenames:
            filepath = os.path.join(root, filename)
            total_size += os.stat(filepath).st_size  # computing the size of the files under the directory
        folder_size[root] = total_size  # store the updated size

        temp_path = root  # for subdirectories, we need to update the size of the parent till the root parent
        while parent[temp_path] != -1:
            folder_size[parent[temp_path]] += total_size
            temp_path = parent[temp_path]

    return folder_size[folder]/1000000.0

Du默认情况下不遵循符号链接。这里没有答案,使用follow_symlinks=False。

下面是一个遵循du默认行为的实现:

def du(path) -> int:
    total = 0
    for entry in os.scandir(path):
        if entry.is_file(follow_symlinks=False):
            total += entry.stat().st_size
        elif entry.is_dir(follow_symlinks=False):
            total += du(entry.path)
    return total

测试:

class Test(unittest.TestCase):
    def test_du(self):
        root = '/tmp/du_test'
        subprocess.run(['rm', '-rf', root])
        test_utils.mkdir(root)
        test_utils.create_file(root, 'A', '1M')
        test_utils.create_file(root, 'B', '1M')
        sub = '/'.join([root, 'sub'])
        test_utils.mkdir(sub)
        test_utils.create_file(sub, 'C', '1M')
        test_utils.create_file(sub, 'D', '1M')
        subprocess.run(['ln', '-s', '/tmp', '/'.join([root, 'link']), ])
        self.assertEqual(4 << 20, util.du(root))

这个脚本告诉您CWD中哪个文件最大,还告诉您文件在哪个文件夹中。 这个脚本适用于win8和python 3.3.3 shell

import os

folder=os.cwd()

number=0
string=""

for root, dirs, files in os.walk(folder):
    for file in files:
        pathname=os.path.join(root,file)
##        print (pathname)
##        print (os.path.getsize(pathname)/1024/1024)
        if number < os.path.getsize(pathname):
            number = os.path.getsize(pathname)
            string=pathname


##        print ()


print (string)
print ()
print (number)
print ("Number in bytes")