python实验任务一： 参考教材实例，完成中国大学排名爬虫

直接上代码吧，爬取http://zuihaodaxue.cn/zuihaodaxuepaiming2018.html这个页面2018年前20各个大学排名

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:
        return ""

def fillUnivList(ulist, url):
    soup = BeautifulSoup(url, 'html.parser')
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].contents[0], tds[1].string, tds[3].string])

def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    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://zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)
main()

效果截图：