爬取中国大学排名(爬取年费)
爬取中国大学网站http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html
代码:
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 "" 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("{1:^2}{2:{0}^10}{3:{0}^6}{4:{0}^4}{5:{0}^10}".format(chr(12288),"排名","学校名称","省市","总分","年费")) for i in range(num): u=allUniv[i] print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^11}".format(chr(12288),u[0],u[1],u[2],eval(u[3]),u[11])) def main(): url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html' html = getHTMLText(url) soup = BeautifulSoup(html, "html.parser") fillUnivList(soup) printUnivList(10) main()
结果:
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步