将字符串拆分为单词和标点符号

import re

text = "Hello, world! This is a test string."

# 使用正则表达式匹配单词和标点符号
words_and_punctuation = re.findall(r'\w+|[^\w\s]+', text)

print(words_and_punctuation)

['Hello', ',', 'world', '!', 'This', 'is', 'a', 'test', 'string', '.']