import requests from bs4 import BeautifulSoup import bs4 def getHTMLText(url): try: r = requests.get(url,timeout=30) r.raise_for_status() # 如果状态不是200,引发HTTPError异常 r.encoding = r.apparent_encoding return r.text except: return "产生异常" def fillUnivList(ulist, html): soup = BeautifulSoup(html, "html.parser") for tr in soup.find('tbody').children: if isinstance(tr, bs4.element.Tag): # 检测tr的类型是否是Tag标签 tds = tr('td') ulist.append([tds[0].string, tds[1].string, tds[4].string]) def printUnivList(ulist, num): tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}" print("{0:^10}\t{1:{3}^6}\t{2:{3}^10}".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))) if __name__ == '__main__': uinfo = [] url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2020.html' html = getHTMLText(url) fillUnivList(uinfo, html) printUnivList(uinfo, 100) # 20 univs