一、代码详情

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 "error"
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):
    print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名字","省份","总分","培养规模"))
    for i in range(num):
        u=alluniv[i]
        print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))
def main(num):
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html"
    html=getHTMLText(url)
    soup=BeautifulSoup(html,"html.parser")
    fillunivlist(soup)
    printunivlist(num)
main(100)

 

posted on 2019-05-30 00:00  em对的  阅读(175)  评论(0编辑  收藏  举报