思路:
1. 读取敏感词汇文件,把词汇以list储存。
2. 匹配用户输入的内容是否含有敏感词汇,
import re
def is_Chinese(word):
for ch in word:
if '\u4e00' <= ch <= '\u9fff':
return True
return False
with open('./vocabulary.txt', encoding="utf-8") as ff:
text = ff.read()
text = re.sub('\s', ' ', text).split(' ')
name = input()
for x in text:
if re.findall(x, name):
for item in re.findall(x, name):
if is_Chinese(item):
name = re.sub(x, '*' * len(x), name)
else:
name = re.sub(x, '*', name)
print(name)