从字节大小返回人类可读大小的函数:

>>> human_readable(2048)
'2 kilobytes'
>>>

如何做到这一点?


当前回答

这将在几乎任何情况下做你需要做的事情,是可选参数自定义的,正如你所看到的,几乎是自文档化的:

from math import log
def pretty_size(n,pow=0,b=1024,u='B',pre=['']+[p+'i'for p in'KMGTPEZY']):
    pow,n=min(int(log(max(n*b**pow,1),b)),len(pre)-1),n*b**pow
    return "%%.%if %%s%%s"%abs(pow%(-pow-1))%(n/b**float(pow),pre[pow],u)

示例输出:

>>> pretty_size(42)
'42 B'

>>> pretty_size(2015)
'2.0 KiB'

>>> pretty_size(987654321)
'941.9 MiB'

>>> pretty_size(9876543210)
'9.2 GiB'

>>> pretty_size(0.5,pow=1)
'512 B'

>>> pretty_size(0)
'0 B'

高级定制:

>>> pretty_size(987654321,b=1000,u='bytes',pre=['','kilo','mega','giga'])
'987.7 megabytes'

>>> pretty_size(9876543210,b=1000,u='bytes',pre=['','kilo','mega','giga'])
'9.9 gigabytes'

此代码与Python 2和Python 3兼容。对读者来说,遵从PEP8是一个练习。记住,漂亮的是输出。

更新:

如果你需要数千个逗号,只需应用明显的扩展:

def prettier_size(n,pow=0,b=1024,u='B',pre=['']+[p+'i'for p in'KMGTPEZY']):
    r,f=min(int(log(max(n*b**pow,1),b)),len(pre)-1),'{:,.%if} %s%s'
    return (f%(abs(r%(-r-1)),pre[r],u)).format(n*b**pow/b**float(r))

例如:

>>> pretty_units(987654321098765432109876543210)
'816,968.5 YiB'

其他回答

你应该用humanize。

>>> humanize.naturalsize(1000000)
'1.0 MB'
>>> humanize.naturalsize(1000000, binary=True)
'976.6 KiB'
>>> humanize.naturalsize(1000000, gnu=True)
'976.6K'

参考: https://pypi.org/project/humanize/

一个拥有你所寻找的所有功能的库似乎是人性化的。Humanize.naturalsize()似乎可以做您所寻找的所有事情。

示例代码(python 3.10)

import humanize

disk_sizes_list = [1, 100, 999, 1000,1024, 2000,2048, 3000, 9999, 10000, 2048000000, 9990000000, 9000000000000000000000]
for size in disk_sizes_list:
    natural_size = humanize.naturalsize(size)
    binary_size = humanize.naturalsize(size, binary=True)
    print(f" {natural_size} \t| {binary_size}\t|{size}")

输出

 1 Byte     | 1 Byte    |1
 100 Bytes  | 100 Bytes |100
 999 Bytes  | 999 Bytes |999
 1.0 kB     | 1000 Bytes    |1000
 1.0 kB     | 1.0 KiB   |1024
 2.0 kB     | 2.0 KiB   |2000
 2.0 kB     | 2.0 KiB   |2048
 3.0 kB     | 2.9 KiB   |3000
 10.0 kB    | 9.8 KiB   |9999
 10.0 kB    | 9.8 KiB   |10000
 2.0 GB     | 1.9 GiB   |2048000000
 10.0 GB    | 9.3 GiB   |9990000000
 9.0 ZB     | 7.6 ZiB   |9000000000000000000000

为了以人类可读的形式获取文件大小,我创建了这个函数:

import os

def get_size(path):
    size = os.path.getsize(path)
    if size < 1024:
        return f"{size} bytes"
    elif size < pow(1024,2):
        return f"{round(size/1024, 2)} KB"
    elif size < pow(1024,3):
        return f"{round(size/(pow(1024,2)), 2)} MB"
    elif size < pow(1024,4):
        return f"{round(size/(pow(1024,3)), 2)} GB"
>>> get_size("a.txt")
1.4KB

下面是一个使用while的选项:

def number_format(n):
   n2, n3 = n, 0
   while n2 >= 1e3:
      n2 /= 1e3
      n3 += 1
   return '%.3f' % n2 + ('', ' k', ' M', ' G')[n3]

s = number_format(9012345678)
print(s == '9.012 G')

https://docs.python.org/reference/compound_stmts.html#while

参考Sridhar Ratnakumar的回答,更新为:

def formatSize(sizeInBytes, decimalNum=1, isUnitWithI=False, sizeUnitSeperator=""):
  """format size to human readable string"""
  # https://en.wikipedia.org/wiki/Binary_prefix#Specific_units_of_IEC_60027-2_A.2_and_ISO.2FIEC_80000
  # K=kilo, M=mega, G=giga, T=tera, P=peta, E=exa, Z=zetta, Y=yotta
  sizeUnitList = ['','K','M','G','T','P','E','Z']
  largestUnit = 'Y'

  if isUnitWithI:
    sizeUnitListWithI = []
    for curIdx, eachUnit in enumerate(sizeUnitList):
      unitWithI = eachUnit
      if curIdx >= 1:
        unitWithI += 'i'
      sizeUnitListWithI.append(unitWithI)

    # sizeUnitListWithI = ['','Ki','Mi','Gi','Ti','Pi','Ei','Zi']
    sizeUnitList = sizeUnitListWithI

    largestUnit += 'i'

  suffix = "B"
  decimalFormat = "." + str(decimalNum) + "f" # ".1f"
  finalFormat = "%" + decimalFormat + sizeUnitSeperator + "%s%s" # "%.1f%s%s"
  sizeNum = sizeInBytes
  for sizeUnit in sizeUnitList:
      if abs(sizeNum) < 1024.0:
        return finalFormat % (sizeNum, sizeUnit, suffix)
      sizeNum /= 1024.0
  return finalFormat % (sizeNum, largestUnit, suffix)

示例输出如下:

def testKb():
  kbSize = 3746
  kbStr = formatSize(kbSize)
  print("%s -> %s" % (kbSize, kbStr))

def testI():
  iSize = 87533
  iStr = formatSize(iSize, isUnitWithI=True)
  print("%s -> %s" % (iSize, iStr))

def testSeparator():
  seperatorSize = 98654
  seperatorStr = formatSize(seperatorSize, sizeUnitSeperator=" ")
  print("%s -> %s" % (seperatorSize, seperatorStr))

def testBytes():
  bytesSize = 352
  bytesStr = formatSize(bytesSize)
  print("%s -> %s" % (bytesSize, bytesStr))

def testMb():
  mbSize = 76383285
  mbStr = formatSize(mbSize, decimalNum=2)
  print("%s -> %s" % (mbSize, mbStr))

def testTb():
  tbSize = 763832854988542
  tbStr = formatSize(tbSize, decimalNum=2)
  print("%s -> %s" % (tbSize, tbStr))

def testPb():
  pbSize = 763832854988542665
  pbStr = formatSize(pbSize, decimalNum=4)
  print("%s -> %s" % (pbSize, pbStr))


def demoFormatSize():
  testKb()
  testI()
  testSeparator()
  testBytes()
  testMb()
  testTb()
  testPb()

  # 3746 -> 3.7KB
  # 87533 -> 85.5KiB
  # 98654 -> 96.3 KB
  # 352 -> 352.0B
  # 76383285 -> 72.84MB
  # 763832854988542 -> 694.70TB
  # 763832854988542665 -> 678.4199PB