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
使用1000或kibibytes的幂将更符合标准:
def sizeof_fmt(num, use_kibibyte=True):
base, suffix = [(1000.,'B'),(1024.,'iB')][use_kibibyte]
for x in ['B'] + map(lambda x: x+suffix, list('kMGTP')):
if -base < num < base:
return "%3.1f %s" % (num, x)
num /= base
return "%3.1f %s" % (num, x)
附注:永远不要相信一个以K(大写)后缀打印数千的库。
其他回答
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)
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/
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]
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'
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)