2018最好大学排行榜 爬虫爬取

需要的库有requests、BeautifulSoup

import requests
from bs4 import BeautifulSoup
import bs4
uinfo = []
ulist = []
try:
    r = requests.get("http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html",timeout = 30)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
except:
    r.text = ""
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
for tr in soup.find('tbody').children:
     if isinstance(tr,bs4.element.Tag):
         tds = tr('td')
         ulist.append([tds[0].string,tds[1].string,tds[2].string,tds[3].string,tds[4].string])
tplp = "{0:^10}\t{1:{3}^14}\t{2:^4}"
print( "{0:^10}\t{1:{3}^10}\t{2:^10}".format("排名","大学名字","分数",chr(12288)))
for i in range(516):
    u = ulist[i]
    print(tplp.format(u[0],u[1],u[3],chr(12288)))
print("Success")