爬虫入门实例（四）

import requests
from bs4 import BeautifulSoup
import bs4


def getHTMLText (url):
    try:
        r = requests.get(url, timeout = 30)
        # timeout 时间限制
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def fillUnivList(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    # 解析html文件
    #tbody是一个HTML语言标签表格主体，该标签用于组合 HTML 表格的主体内容。
    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):
    split = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    #输出文本标齐
    print(split.format("排名", "学校名称",  "总分", chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(split.format(u[0], u[1], u[2],chr(12288)))

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

main()