python爬虫实战：爬取中国大学排名网站的 2019年中国大学排名情况

爬取这个网页：软科中国最好大学排名2019

 

#采用bs4--Beautiful库实现
import requests
from bs4 import BeautifulSoup
import bs4

#得到网页内容
def getHTMLText(url):
    try:
        r = requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "获取网页内容失败！"

#获取大学信息,将其储存在列表
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])

#打印结果
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","省市","总分",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.com/zuihaodaxuepaiming2019.html"
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20)

if __name__=="__main__":
    main()

 

 运行结果：