使用GLOB、BS4从多个本地.html文件中提取元素并写入CSV Excel

import glob
import csv
from bs4 import BeautifulSoup

file_paths = glob.glob('*.html')  # 替换为你的本地.html文件路径

csv_file = open('output.csv', 'w', newline='')
csv_writer = csv.writer(csv_file)
csv_writer.writerow(['Element 1', 'Element 2', 'Element 3'])  # 替换为你要提取的元素名称

for file_path in file_paths:
    with open(file_path, 'r') as html_file:
        soup = BeautifulSoup(html_file, 'html.parser')
        element1 = soup.find('element1_tag').text  # 替换为你要提取的第一个元素的标签
        element2 = soup.find('element2_tag').text  # 替换为你要提取的第二个元素的标签
        element3 = soup.find('element3_tag').text  # 替换为你要提取的第三个元素的标签
        csv_writer.writerow([element1, element2, element3])

csv_file.close()