用python实现对文档进行不同字符个数统计

问题引入：

问题解决：

1.用re模块

import re
d = {}
with open("E:\sample.txt", encoding = "utf-8") as f:
    for line in f:
        tmp = line.lower().strip() # 对一行字符串进行小写转换并切割两头空白符
        lst = re.split('[ .(),=:"»~>*]', tmp)
        for s in lst:
            # if s not in d.keys():
            #     d[s] = 1
            # else:
            #     d[s] += 1
            d[s] = d.get(s, 0) + 1  # 经改进

print(sorted(d.items(), key=lambda x:x[1], reverse=True)) # 利用key参数使字典**按值排序**

2.替换特殊分隔字符为空白字符

d = {}
def makekey(s:str):
    """遍历传入字符串s的每个字符，如果出现特殊字符则用空白字符替换，将这些字符分割转换为最简单的空白字符分隔"""
    special_chars = set('.,-