嵩天老师慕课_Python网络爬虫与信息提取_大学排名实例

此代码为嵩天老师慕课实例代码，不想全部敲的朋友可以复制部分进行学习

import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
    try:
        hd={'user-agent':'chrome/10'}
        r=requests.get(url,timeout=30,headers=hd)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return "失败"
def fillUnivList(ulist,html):
    soup = BeautifulSoup(html,"html.parser")
    for tr in soup.find('tbody').children:     #soup.find('tbody')返回Tag类型，soup中第一个tbody标签
        if isinstance(tr, bs4.element.Tag):
            tds=tr('td')   #tr.find_all('td'),返回列表
            ulist.append([tds[0].string,tds[1].string,tds[2].string,tds[3].string])
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","地址","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)