spark学习进度7-Python爬取大学排名实例

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")#bs4的html解析器
    for tr in soup.find(‘tbody‘).children:
        if isinstance(tr, bs4.element.Tag):# bs4.element.Tag是标签类型
            tds = tr(‘td‘)#将所有的td标签存为一个列表类型
            ulist.append([tds[0].string, tds[1].string, tds[2].string])

def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "所在地区"))
    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 = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)
main()