如何计算一个文件中有多少单词没有出现？

import re
from collections import Counter

def count_missing_words(file_path, words_to_compare):
    # 读取文件
    with open(file_path, 'r') as file:
        content = file.read()

    # 文本处理
    content = re.sub(r'[^\w\s]', '', content)  # 去除标点符号
    content = content.lower()  # 转换为小写字母

    # 单词计数
    word_counts = Counter(content.split())

    # 单词对比
    missing_words = [word for word in words_to_compare if word_counts[word] == 0]

    # 统计结果
    missing_words_count = len(missing_words)

    return missing_words_count

# 示例用法
file_path = 'example.txt'
words_to_compare = ['apple', 'banana', 'orange']
missing_words_count = count_missing_words(file_path, words_to_compare)
print("文件中有", missing_words_count, "个单词没有出现")