中国大学排名(爬虫)

跟随视频学习过程中，让我更加的理解了requests库和BeautifulSoup库的使用。虽然现在还有点生疏，不过我会更加努力的，让自己能熟练的使用这两个库。

 

下面贴出在中国最好大学网上爬取的代码：

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):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string,tds[3].string])

def printUnivList(ulist,num):
    tplt = "{0:^10}\t{1:{4}^10}\t{2:^10}\t{3:^10}"
    print(tplt.format("排名","学校名称","省份","分数",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0], u[1], u[2],u[3],chr(12288)))
        
def main():
    uinfo = []
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)

main()

下面是运行结果：