Python:使用正则表达式获取字符串中的未知词，并使用其边界

import re

def get_unknown_words(text):
    pattern = r'\b\w+\b'  # 匹配单词的正则表达式模式
    known_words = ['apple', 'banana', 'cat']  # 已知的单词列表

    unknown_words = []
    matches = re.findall(pattern, text)  # 查找所有匹配的单词
    for word in matches:
        if word not in known_words:
            unknown_words.append(word)

    return unknown_words

text = "I have an apple and a banana. The cat is sleeping."
unknown_words = get_unknown_words(text)
print(unknown_words)