import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
print("over")
def fillUnivList(ulist,html):
soup = BeautifulSoup(html, "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[3].string])
def printUnivList(ulist, num):
print("{:^10}{:^6}\n\t\t\t\t {:^10}".format("[排名]","[学校名称]","[总分]"))
for i in range(num):
u = ulist[i]
print("{:^10}\t{:^6}\n\t\t\t\t\t{:^10}".format(u[0],u[1],u[2]))
def main():
uinfo = []
url = 'http://www.zuihaodaxue.com/Greater_China_Ranking2016_0.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
print("-"*10+"软科中国最好大学排名"+"-"*10)
printUnivList(uinfo,100)
print("-" * 10 + "前100所高校" + "-" * 10)
main()
效果图: