广东技术师范大学

Posted 2020-11-30 marcoreus11

import requests
from bs4 import BeautifulSoup
allUniv=[]
def gethtmlText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = ‘utf-8‘
        return r.text
    except:
        return ""
def fillUnivList(soup):
    data = soup.find_all(‘tr‘)
    for tr in data:
        ltd = tr.find_all(‘td‘)
        if len(ltd)==0:
            continue
        singleUniv = []
        for td in ltd:
            singleUniv.append(td.string)
        allUniv.append(singleUniv)
def printUnivList(num):
    a="广东技术师范大学"
    print("{1:^4}{2:{0}^8}{3:{0}^6}{4:{0}^6}{5:{0}^8}".format((chr(12288)),"排名","学校名称","省市","总分","科研服务"))
    for i in range(num):
        u=allUniv[i]
        if a in u:
            print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^10}".format((chr(12288)),u[0],u[1],u[2],eval(u[3]),u[11]))
def main(num):
    url=‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html‘
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)
main(500)