爬虫

对中国大学排名前20的爬取

import requests
from bs4 import BeautifulSoup
import bs4


def getHTMLText(url):#用requests库爬取网页
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()#返回状态码
        r.encoding = r.apparent_encoding#编码格式
        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):#过滤掉不是标签的内容
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])


def printUnivList(ulist, num):
    print("{:^10}\t{:^10}\t{:^20}".format("排名", "学校名称", "总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^10}\t{:^20}".format(u[0], u[1], u[2]))


if __name__=='__main__':
    uinfo = []
    url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)