天天看點

python3.x爬蟲:爬取大學排名資料

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 "通路出錯"

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,tds[3].string,tds[4].string])


def printUnivList(ulist,num):
    tplt="{0:^10}\t{1:{5}^10}\t{2:^10}\t{3:^10}\t{4:^10}" #中英文對齊,格式化
    print(tplt.format("排名","學校名稱","省份","總分","名額得分",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0],u[1],u[2],u[3],u[4],chr(12288)))


def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    print(html)
    fillUnivList(uinfo,html)
    printUnivList(uinfo, 20)

main()
           

繼續閱讀