代码改变世界

网络爬虫基础练习

2018-03-29 12:53  129赖锐扬  阅读(162)  评论(0编辑  收藏  举报
import requests
url = 'http://localhost:63342/bd/gouxueyuan.html?_ijt=kn4osq2f4cqos8pf8vjvmkrah7'
res = requests.get(url)
res.encoding = 'utf-8'

from bs4 import BeautifulSoup
soup = BeautifulSoup(res.text,'html.parser')


print(soup.select('h1')[0].text)


for link in soup.select('a'):
    print(link.get('href'))

for i in soup.select('li'):
    print(i.contents)

print(soup.select('.news-list-title')[0].text)
print(soup.select('li')[1].a.attrs['href'])
print(soup.select('.news-list-info')[0].contents[0].text)
print(soup.select('.news-list-info')[0].contents[1].text)