从0开始的爬虫之旅（day1/2/3）

import requests
import bs4

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

def fillUnivList(ulist, html):
    soup = bs4.BeautifulSoup(html, 'html.parser')
    p = 0
    for tr in soup.find('tbody').children:

        if isinstance(tr, bs4.element.Tag):

            tds = tr('td')
            Univ_name = tds[1]('span')[0].string
            ulist.append([tds[0].string.strip(), Univ_name.strip(), tds[4].string.strip()])


def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format('排名', '学校名称', '总分',chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))


def main():
    uinfo = []
    url = 'https://www.shanghairanking.cn/rankings/bcur/2024'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    # print(uinfo)
    printUnivList(uinfo, 20)

if __name__ == '__main__':
    main()

定向爬虫，后面再来优化界面吧（如果我还记得的话