python 爬虫实例 爬取中国大学排名

import requests
from bs4 import BeautifulSoup
import bs4
def gegHTMLText(url):
    try:
        r = requests.get(url)
        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: #采用循环查找html文本中的tbody标签并且将它的孩子children做一个遍历
        if isinstance(tr, bs4.element.Tag): #检测tr标签的标签类型 如果不是bs4库里面定义的Tag类型 则过滤掉
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string])

def printUnivList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校", "分数")) #表头信息的打印
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))


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