使用python去除txt内容代码样式

python代码如下

import re

# 定义每次读取的块大小
block_size = 1024 * 1024 * 3000  # 1MB

# 读取txt文件内容
with open('xxx_1.txt', 'r', encoding='utf-8') as file:
    while True:
        # 读取一块内容
        content = file.read(block_size)
        if not content:
            break

        # 使用正则表达式去除HTML标签和style样式
        content = re.sub(r'<style.*?>.*?</style>', '', content, flags=re.DOTALL | re.IGNORECASE)  # 去除style标签
        content = re.sub(r'<.*?>', '', content, flags=re.DOTALL | re.IGNORECASE | re.MULTILINE)  # 去除其他HTML标签

        # 将处理后的内容写入新的txt文件
        with open('xxx_out_1.txt', 'a', encoding='utf-8') as output_file:
            output_file.write(content)