Python作業默寫和自己改編
阿新 • • 發佈:2019-01-03
默寫,爬一個靜態大學排行網頁排名
from bs4 import BeautifulSoup import bs4 import requests def gethtmltxt(url): try: r=requests.get(url,timeout=30) r.raise_for_status() r.encoding=r.apparent_encoding return r.text except: return "" def culi(ulist,html): soup=BeautifulSoup(html,"html.parser") for tr in soup.find('tbody').children: if isinstance(tr,bs4.element.Tag): tds=tr("td") ulist.append([tds[0].string,tds[1].string,tds[2].string]) def printfact(ulist,num): a="{:^10}{:^6}{:^10}" print(a.format("排名","學校","地域"))for i in range(num): u=ulist[i] print(a.format(u[0],u[1],u[2])) def main(): url="http://www.zuihaodaxue.com/zuihaodaxuepaiming2016.html" html=gethtmltxt(url) unifo=[] culi(unifo,html) printfact(unifo,20) main()
改編爬取一個類似的介面
http://gaokao.xdf.cn/201812/10838484.html
這個試試吧