初学爬虫（一）

 1 # -*- coding=utf8 -*-
 2 
 3 import requests
 4 from bs4 import BeautifulSoup
 5 
 6 def qiushibaike():
 7     content = requests.get(‘http://www.qiushibaike.com‘).content
 8     soup = BeautifulSoup(content, ‘html.parser‘)
 9 
10     for div in soup.find_all(‘div‘, {‘class‘ : ‘content‘}):
11         print div.text.strip()
12 
13 def ustcjob():
14     headers = {‘User-Agent‘:‘Mozilla / 5.0(X11;Linux x86_64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 50.0.2661.102 Safari / 537.36‘}
15     content = requests.get(‘http://job.ustc.edu.cn/list.php?MenuID=002‘, headers = headers).content
16     soup = BeautifulSoup(content, ‘html.parser‘)
17 
18     for Jop in soup.find_all(‘div‘, {‘class‘ : ‘Joplistone‘}):
19         for item in Jop.find_all(‘li‘):
20             print "%-30s%-20s%-40s" % (item.a.text.strip() , item.span.text.strip() , item.span.next_sibling.text.strip())
21 
22 
23 if __name__ == ‘__main__‘:
24     #qiushibaike()
25     ustcjob()