我用perfplot(我的一个项目)检查了结果，发现对于短字符串，

"".join(filter(str.isalnum, s))

是最快的。对于长字符串(200+字符)

re.sub("[\W_]", "", s)

是最快的。

代码重现情节:

import perfplot
import random
import re
import string

pattern = re.compile("[\W_]+")


def setup(n):
    return "".join(random.choices(string.ascii_letters + string.digits, k=n))


def string_alphanum(s):
    return "".join(ch for ch in s if ch.isalnum())


def filter_str(s):
    return "".join(filter(str.isalnum, s))


def re_sub1(s):
    return re.sub("[\W_]", "", s)


def re_sub2(s):
    return re.sub("[\W_]+", "", s)


def re_sub3(s):
    return pattern.sub("", s)


b = perfplot.bench(
    setup=setup,
    kernels=[string_alphanum, filter_str, re_sub1, re_sub2, re_sub3],
    n_range=[2**k for k in range(10)],
)
b.save("out.png")
b.show()

Python 3

使用与@John Machin的答案相同的方法，但针对Python 3进行了更新:

更大的字符集 对翻译工作方式的轻微改变。

现在假定Python代码是用UTF-8编码的 (来源:PEP 3120)

这意味着包含你想要删除的所有字符的字符串会变得更大:

    
del_chars = ''.join(c for c in map(chr, range(1114111)) if not c.isalnum())
    

翻译方法现在需要使用一个翻译表，我们可以用maketrans()创建:

    
del_map = str.maketrans('', '', del_chars)
    

现在，像以前一样，任何你想要“捏碎”的字符串:

    
scrunched = s.translate(del_map)
    

使用来自@Joe Machin的最后一个计时例子，我们可以看到它仍然比re强一个数量级:

    
> python -mtimeit -s"d=''.join(c for c in map(chr,range(1114111)) if not c.isalnum());m=str.maketrans('','',d);s='foo-'*25" "s.translate(m)"
    
1000000 loops, best of 5: 255 nsec per loop
    
> python -mtimeit -s"import re;s='foo-'*25;r=re.compile(r'[\W_]+')" "r.sub('',s)"
    
50000 loops, best of 5: 4.8 usec per loop
    

>>> import re
>>> string = "Kl13@£$%[};'\""
>>> pattern = re.compile('\W')
>>> string = re.sub(pattern, '', string)
>>> print string
Kl13

使用ASCII可打印文件的随机字符串计时:

from inspect import getsource
from random import sample
import re
from string import printable
from timeit import timeit

pattern_single = re.compile(r'[\W]')
pattern_repeat = re.compile(r'[\W]+')
translation_tb = str.maketrans('', '', ''.join(c for c in map(chr, range(256)) if not c.isalnum()))


def generate_test_string(length):
    return ''.join(sample(printable, length))


def main():
    for i in range(0, 60, 10):
        for test in [
            lambda: ''.join(c for c in generate_test_string(i) if c.isalnum()),
            lambda: ''.join(filter(str.isalnum, generate_test_string(i))),
            lambda: re.sub(r'[\W]', '', generate_test_string(i)),
            lambda: re.sub(r'[\W]+', '', generate_test_string(i)),
            lambda: pattern_single.sub('', generate_test_string(i)),
            lambda: pattern_repeat.sub('', generate_test_string(i)),
            lambda: generate_test_string(i).translate(translation_tb),

        ]:
            print(timeit(test), i, getsource(test).lstrip('            lambda: ').rstrip(',\n'), sep='\t')


if __name__ == '__main__':
    main()

结果(Python 3.7):

       Time       Length                           Code                           
6.3716264850008880  00  ''.join(c for c in generate_test_string(i) if c.isalnum())
5.7285426190064750  00  ''.join(filter(str.isalnum, generate_test_string(i)))
8.1875841680011940  00  re.sub(r'[\W]', '', generate_test_string(i))
8.0002205439959650  00  re.sub(r'[\W]+', '', generate_test_string(i))
5.5290945199958510  00  pattern_single.sub('', generate_test_string(i))
5.4417179649972240  00  pattern_repeat.sub('', generate_test_string(i))
4.6772285089973590  00  generate_test_string(i).translate(translation_tb)
23.574712151996210  10  ''.join(c for c in generate_test_string(i) if c.isalnum())
22.829975890002970  10  ''.join(filter(str.isalnum, generate_test_string(i)))
27.210196289997840  10  re.sub(r'[\W]', '', generate_test_string(i))
27.203713296003116  10  re.sub(r'[\W]+', '', generate_test_string(i))
24.008979928999906  10  pattern_single.sub('', generate_test_string(i))
23.945240008994006  10  pattern_repeat.sub('', generate_test_string(i))
21.830899796994345  10  generate_test_string(i).translate(translation_tb)
38.731336012999236  20  ''.join(c for c in generate_test_string(i) if c.isalnum())
37.942474347000825  20  ''.join(filter(str.isalnum, generate_test_string(i)))
42.169366310001350  20  re.sub(r'[\W]', '', generate_test_string(i))
41.933375883003464  20  re.sub(r'[\W]+', '', generate_test_string(i))
38.899814646996674  20  pattern_single.sub('', generate_test_string(i))
38.636144253003295  20  pattern_repeat.sub('', generate_test_string(i))
36.201238164998360  20  generate_test_string(i).translate(translation_tb)
49.377356811004574  30  ''.join(c for c in generate_test_string(i) if c.isalnum())
48.408927293996385  30  ''.join(filter(str.isalnum, generate_test_string(i)))
53.901889764994850  30  re.sub(r'[\W]', '', generate_test_string(i))
52.130339455994545  30  re.sub(r'[\W]+', '', generate_test_string(i))
50.061149017004940  30  pattern_single.sub('', generate_test_string(i))
49.366573111998150  30  pattern_repeat.sub('', generate_test_string(i))
46.649754120997386  30  generate_test_string(i).translate(translation_tb)
63.107938601999194  40  ''.join(c for c in generate_test_string(i) if c.isalnum())
65.116287978999030  40  ''.join(filter(str.isalnum, generate_test_string(i)))
71.477421126997800  40  re.sub(r'[\W]', '', generate_test_string(i))
66.027950693998720  40  re.sub(r'[\W]+', '', generate_test_string(i))
63.315361931003280  40  pattern_single.sub('', generate_test_string(i))
62.342320287003530  40  pattern_repeat.sub('', generate_test_string(i))
58.249303059004890  40  generate_test_string(i).translate(translation_tb)
73.810345625002810  50  ''.join(c for c in generate_test_string(i) if c.isalnum())
72.593953348005020  50  ''.join(filter(str.isalnum, generate_test_string(i)))
76.048324580995540  50  re.sub(r'[\W]', '', generate_test_string(i))
75.106637657001560  50  re.sub(r'[\W]+', '', generate_test_string(i))
74.681338128997600  50  pattern_single.sub('', generate_test_string(i))
72.430461594005460  50  pattern_repeat.sub('', generate_test_string(i))
69.394243567003290  50  generate_test_string(i).translate(translation_tb)

str.maketrans & str.translate是最快的，但包括所有非ascii字符。 重新编译&模式。Sub较慢，但不知何故比"快。加入&过滤。

for char in my_string:
    if not char.isalnum():
        my_string = my_string.replace(char,"")

这是一个简单的解决方案，因为这里所有的答案都很复杂

filtered = ''
for c in unfiltered:
    if str.isalnum(c):
        filtered += c
    
print(filtered)