python自学2——爬虫

Posted 2020-10-05

爬取的是 ‘’最好大学网‘’，提取2017年排名前20名大学的名称和分数

 1 #coding: utf-8
 2 import requests
 3 from bs4 import BeautifulSoup
 4 import bs4
 5 
 6 def getHTMLText(url):
 7     try:
 8         r = requests.get(url, timeout=30)
 9         r.raise_for_status()
10         r.encoding = r.apparent_encoding
11         return r.text
12     except:
13         return "fail"
14 
15 def fillUnivList(ulist, html):
16     soup = BeautifulSoup(html, "html.parser")
17     for tr in soup.find(‘tbody‘).children:
18         if isinstance(tr, bs4.element.Tag):
19             tds = tr(‘td‘)
20             ulist.append([tds[0].string, tds[1].string, tds[3].string])
21 
22 def printUnivList(ulist, num):
23     tplt = "{0:^10}\\t{1:{3}^10}\\t{2:^10}"
24     for i in range(num):
25         u=ulist[i]
26         print(u[1],u[2])
27     
28 def main():
29     uinfo = []
30     url = ‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2017.html‘
31     html = getHTMLText(url)
32     fillUnivList(uinfo, html)
33     printUnivList(uinfo, 20) 
34 
35 main()

结果：