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?
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
重复作为匆匆.filesize()替代方案提供的代码段,下面的代码段根据所使用的前缀给出不同的精度数字。它不像某些片段那样简洁,但我喜欢这样的结果。
def human_size(size_bytes):
"""
format a size in bytes into a 'human' file size, e.g. bytes, KB, MB, GB, TB, PB
Note that bytes/KB will be reported in whole numbers but MB and above will have greater precision
e.g. 1 byte, 43 bytes, 443 KB, 4.3 MB, 4.43 GB, etc
"""
if size_bytes == 1:
# because I really hate unnecessary plurals
return "1 byte"
suffixes_table = [('bytes',0),('KB',0),('MB',1),('GB',2),('TB',2), ('PB',2)]
num = float(size_bytes)
for suffix, precision in suffixes_table:
if num < 1024.0:
break
num /= 1024.0
if precision == 0:
formatted_size = "%d" % num
else:
formatted_size = str(round(num, ndigits=precision))
return "%s %s" % (formatted_size, suffix)
其他回答
def human_readable_data_quantity(quantity, multiple=1024):
if quantity == 0:
quantity = +0
SUFFIXES = ["B"] + [i + {1000: "B", 1024: "iB"}[multiple] for i in "KMGTPEZY"]
for suffix in SUFFIXES:
if quantity < multiple or suffix == SUFFIXES[-1]:
if suffix == SUFFIXES[0]:
return "%d%s" % (quantity, suffix)
else:
return "%.1f%s" % (quantity, suffix)
else:
quantity /= multiple
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
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
这是我的版本。它不使用for循环。它具有常数复杂度O(1),理论上比这里使用for循环的答案更有效。
from math import log
unit_list = zip(['bytes', 'kB', 'MB', 'GB', 'TB', 'PB'], [0, 0, 1, 2, 2, 2])
def sizeof_fmt(num):
"""Human friendly file size"""
if num > 1:
exponent = min(int(log(num, 1024)), len(unit_list) - 1)
quotient = float(num) / 1024**exponent
unit, num_decimals = unit_list[exponent]
format_string = '{:.%sf} {}' % (num_decimals)
return format_string.format(quotient, unit)
if num == 0:
return '0 bytes'
if num == 1:
return '1 byte'
为了更清楚地说明发生了什么,我们可以省略字符串格式化的代码。以下是真正起作用的台词:
exponent = int(log(num, 1024))
quotient = num / 1024**exponent
unit_list[exponent]
根据之前所有的答案,以下是我的看法。它是一个以字节为单位以整数形式存储文件大小的对象。但是当你尝试打印对象时,你会自动得到一个人类可读的版本。
class Filesize(object):
"""
Container for a size in bytes with a human readable representation
Use it like this::
>>> size = Filesize(123123123)
>>> print size
'117.4 MB'
"""
chunk = 1024
units = ['bytes', 'KB', 'MB', 'GB', 'TB', 'PB']
precisions = [0, 0, 1, 2, 2, 2]
def __init__(self, size):
self.size = size
def __int__(self):
return self.size
def __str__(self):
if self.size == 0: return '0 bytes'
from math import log
unit = self.units[min(int(log(self.size, self.chunk)), len(self.units) - 1)]
return self.format(unit)
def format(self, unit):
if unit not in self.units: raise Exception("Not a valid file size unit: %s" % unit)
if self.size == 1 and unit == 'bytes': return '1 byte'
exponent = self.units.index(unit)
quotient = float(self.size) / self.chunk**exponent
precision = self.precisions[exponent]
format_string = '{:.%sf} {}' % (precision)
return format_string.format(quotient, unit)