#coding:utf-8 import requests #引入库 from bs4 import BeautifulSoup url = 'http://news.qq.com' wbdata = requests.get(url).text soup = BeautifulSoup(wbdata,'lxml') #BS4库解析 news_titles = soup.select('div > div > em > a') #获取标题的定位 for n in news_titles: title = n.get_text() link = n.get('href') data = { '标题':title, '链接':link, }
print(data) #打印出数据