python + request + bs4 获取新华网新闻列表的标题，日期，详情url

import requests from bs4 import BeautifulSoup def get_data(): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36', 'cookie': '', } url = 'http://www.news.cn/tech/index.html' response = requests.get(url, headers=headers) soup = BeautifulSoup(response.text, 'lxml') # 用beatifulSoup解析网页 soup_item = soup.select('.item.item-style1') for si in soup_item: data = {} data['标题'] = si.select('.tit')[0].text data['日期'] = si.select('.time')[0].text data['详情链接'] = si.select('a')[0]['href'] print(data) get_data()