如何使用Python读取目录中的所有HTML文件并将内容写入CSV文件？

import os
import csv
from bs4 import BeautifulSoup

def read_html_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        html_content = file.read()
        soup = BeautifulSoup(html_content, 'html.parser')
        # 在这里根据HTML结构提取所需的内容
        # 示例：假设需要提取标题和正文内容
        title = soup.find('title').text
        body = soup.find('body').text
        return title, body

def process_html_files(directory):
    html_files = [f for f in os.listdir(directory) if f.endswith('.html')]
    data = []
    for file in html_files:
        file_path = os.path.join(directory, file)
        title, body = read_html_file(file_path)
        data.append([title, body])
    return data

def write_to_csv(data, output_file):
    with open(output_file, 'w', newline='', encoding='utf-8') as file:
        writer = csv.writer(file)
        writer.writerow(['Title', 'Body'])  # 写入CSV文件的表头
        writer.writerows(data)  # 写入提取的内容

directory = '目录路径'  # 替换为实际的目录路径
output_file = '输出文件路径.csv'  # 替换为实际的输出文件路径
data = process_html_files(directory)
write_to_csv(data, output_file)