爬虫--中国大学排名

import requests
import bs4
from bs4 import BeautifulSoup

def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

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[2].string])

def printUnivList(uList,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","省份"))
    for i in range(num):
        u = uList[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,30)

main()
全部评论

相关推荐

我见java多妩媚:大外包
点赞 评论 收藏
分享
点赞 收藏 评论
分享
牛客网
牛客企业服务