python数据爬虫示例一

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 "exception"

def  fillUniveList(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[ 3 ].string])

def printUnivList(ulist,num):

  print ( "{:^10} \t {:^6} \t {:^10}" .format( "排名" , "学校名称" , "总分" ))

  for i in range (num):

      u=ulist[i]

      print ( "{:^10} \t {:^6} \t {:^10}" .format(u[ 0 ],u[ 1 ],u[ 2 ]))

  print ( "Suc" + str (num))

def main():

    unifo=[]

    url= "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2017.html"

    html=getHTMLText(url)

    fillUniveList(unifo,html)

    printUnivList(unifo, 20 )

main()