如何从本地存储的多个html文件中解析文本并将其写入excel文件

import os
from bs4 import BeautifulSoup
from openpyxl import Workbook

# 遍历本地存储的HTML文件夹
html_folder = 'path/to/html/folder'
html_files = os.listdir(html_folder)

# 创建Excel文件
wb = Workbook()
ws = wb.active

# 遍历HTML文件并解析文本
for file in html_files:
    if file.endswith('.html'):
        file_path = os.path.join(html_folder, file)
        with open(file_path, 'r', encoding='utf-8') as f:
            html_content = f.read()
        
        # 解析HTML文件
        soup = BeautifulSoup(html_content, 'html.parser')
        
        # 提取和整理文本数据
        text_data = soup.get_text()
        # 进行数据清洗和格式化
        
        # 写入文本数据到Excel文件
        ws.append([text_data])

# 保存并关闭Excel文件
excel_file = 'path/to/output/excel/file.xlsx'
wb.save(excel_file)
wb.close()