爬取中国大学排名

buhaoshuooo

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.     except:
    
12.         return ''
    
13. 
    
14. def fillUnivList(ulist,html):
    
15.     soup = BeautifulSoup(html,'html.parser')
    
16.     for tr in soup.find('tbody').children:
    
17.         if isinstance(tr,bs4.element.Tag):  #确定tbody的儿子都是标签，无字符串
    
18.             tds = tr('td')
    
19.             ulist.append([tds[0].string,tds[1].string,tds[3].string])
    
20. 
    
21. def printUnivlist(ulist,num):
    
22.     print('{:^10}\t{:^6}\t{:^10}'.format ('排名','学校','分数'))
    
23.     for i in range(num):
    
24.         u = ulist[i]
    
25.         print('{:^10}\t{:^6}\t{:^10}'.format (u[0],u[1],u[3]))
    
26. 
    
27. def main():
    
28.     uinfo = []
    
29.     url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
    
30.     html = getHTMLText(url)
    
31.     fillUnivList(uinfo,html)
    
32.     printUnivlist(uinfo,10)
    
33. main()

复制代码

运行一直显示错误，IndexError: list index out of range，请大佬帮忙看一下~

一个账号

就是超出索引访问了