使用Python将一个文件夹中的多个HTML文件解析为一个或多个CSV

pip install beautifulsoup4
pip install csv

import os
from bs4 import BeautifulSoup
import csv

def parse_html_to_csv(html_folder, csv_file):
    # 遍历文件夹中的HTML文件
    for filename in os.listdir(html_folder):
        if filename.endswith(".html"):
            html_file = os.path.join(html_folder, filename)
            
            # 打开HTML文件并解析
            with open(html_file, "r", encoding="utf-8") as file:
                soup = BeautifulSoup(file, "html.parser")
                
                # 解析HTML内容，获取需要的数据
                # 这里只是一个示例，具体解析逻辑需要根据HTML文件的结构进行调整
                data = []
                for element in soup.find_all("div", class_="data"):
                    value = element.text.strip()
                    data.append(value)
                
                # 将解析的数据写入CSV文件
                with open(csv_file, "a", encoding="utf-8", newline="") as csvfile:
                    writer = csv.writer(csvfile)
                    writer.writerow(data)

# 调用函数进行解析
html_folder = "path/to/html/folder"
csv_file = "path/to/output/csv/file.csv"
parse_html_to_csv(html_folder, csv_file)