#python爬虫第二讲#

#爬取中国大学排名2019

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 ""

#难点：分析网页源html代码结构，找到所爬取数据对应的标签

def fillUnivList(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 printUnivList(ulist,num):
    tplt="{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","学校名称","所在地",chr(12288)))
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfo=[]
    url='http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,30) #20 univs
main()