中国大学排名定向爬虫

import requests from bs4 import BeautifulSoup 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: return '' 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标签的类型,如果tr标签的类型不是bs4库定义的Tag类型,将被过滤掉 tds = tr('td')#等价于tds = tr.find_all('td') ulist.append([tds[0].string,tds[1].string,tds[3].string]) def printUnivList(ulist,num): print("{0:^10}\t{1:{3}^10}\t{2:^10}".format("排名","学校名称","总分",chr(12288))) for i in range(num): u=ulist[i] print("{0:^10}\t{1:{3}^10}\t{2:^10}".format(u[0],u[1],u[2],chr(12288))) def main(): uinfo = [] url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html' html = getHTMLText(url) fillUnivList(uinfo,html) printUnivList(uinfo,20)#打印20所学校的信息 main()