将BeautifulSoup/Python循环导出为CSV或txt文件

pip install beautifulsoup4 requests

import requests
from bs4 import BeautifulSoup
import csv

# 假设我们要从一个网页上抓取标题和链接
url = 'http://example.com'
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')

# 假设我们要抓取的数据在一个class为'article'的div标签中
articles = soup.find_all('div', class_='article')

# 准备数据
data = []
for article in articles:
    title = article.find('h2').text.strip()
    link = article.find('a')['href']
    data.append((title, link))

# 导出为CSV文件
with open('output.csv', 'w', newline='', encoding='utf-8') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['Title', 'Link'])  # 写入表头
    writer.writerows(data)

# 导出为TXT文件
with open('output.txt', 'w', encoding='utf-8') as txtfile:
    for title, link in data:
        txtfile.write(f'{title}: {link}\n')

print("数据已成功导出为CSV和TXT文件。")