#016 爬虫第一次尝试

 1 import requests
 2 from bs4 import BeautifulSoup
 3 import bs4
 4 
 5 def getHTMLText(url):
 6      try:
 7           r = requests.get(url, timeout = 30)
 8           r.raise_for_status()
 9           r.encoding = r.apparent_encoding
10           return r.text
11      
12           
13      except:
14           return ""
15           
16      return ""
17 
18 def fillUnivList(ulist,html):
19      soup = BeautifulSoup(html, "html.parser")
20      for tr in soup.find('tbody').children:
21           if isinstance(tr, bs4.element.Tag):
22                tds = tr('td')
23                ulist.append([tds[0].string, tds[1].string, tds[2].string])
24 
25                
26                
27      
28 
29 def printUnivList(ulist, num):
30      print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
31      for i in range(num):
32           u=ulist[i]
33           print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))
34 
35 def main():
36      uinfo = []
37      url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html'
38      html = getHTMLText(url)
39      fillUnivList(uinfo,html)
40      printUnivList(uinfo, 20)
41 main()
42