在Python中快速将multipule HTML转换为CSV文件

pip install beautifulsoup4

from bs4 import BeautifulSoup
import csv
import os

# 定义HTML文件夹路径和CSV文件路径
html_folder = 'path/to/html/folder'
csv_file = 'path/to/output/csv/file.csv'

# 获取HTML文件列表
html_files = [f for f in os.listdir(html_folder) if f.endswith('.html')]

# 创建CSV文件并写入表头
with open(csv_file, 'w', newline='') as file:
    writer = csv.writer(file)
    writer.writerow(['Title', 'Content'])

    # 遍历HTML文件
    for html_file in html_files:
        # 读取HTML文件内容
        with open(os.path.join(html_folder, html_file), 'r') as f:
            html_content = f.read()

        # 使用BeautifulSoup解析HTML
        soup = BeautifulSoup(html_content, 'html.parser')

        # 提取标题和内容
        title = soup.title.text if soup.title else ''
        content = soup.get_text()

        # 写入CSV文件
        writer.writerow([title, content])

print('HTML转换为CSV成功！')