import requests
from bs4 import BeautifulSoup
import pandas
res = requests.get("http://news.qq.com/")
soup = BeautifulSoup(res.text, 'html.parser')
newsary = []
for news in soup.select('.Q-tpWrap .text'):
newsary.append({"title":news.select('a')[0].text,"url":news.select('a')[0]['href']})
newsdf = pandas.DataFrame(newsary)
newsdf.to_excel("news.xlsx")
python bs4爬取腾讯新闻简单练习版
最新推荐文章于 2024-05-22 21:02:56 发布