00009 python3爬虫简单实例

Posted 2020-12-01 python-abc

OS: ubuntu-18.04.1

apt install -y python3-pip

pip3 install bs4

pip3 install lxml

#!/usr/bin/env python3

import requests

r = requests.get(‘http://www.wise.xmu.edu.cn/people/faculty‘)  
html = r.content

from bs4 import BeautifulSoup  
soup = BeautifulSoup(html, ‘html.parser‘)

div_people_list = soup.find(‘div‘, attrs={‘class‘: ‘people_list‘})  
a_s = div_people_list.find_all(‘a‘, attrs={‘target‘: ‘_blank‘})

for a in a_s:  
    url = a[‘href‘]  
    name = a.get_text()  
    print(name, url)