第一个爬虫和测试

import requests
for i in range(20):
    r=requests.get("http://www.baidu.com")
    s=r.text
    f=r.content
    d1=len(r.text)
    d2=len(r.content)
    print(s,f,d1,d2)

1，访问百度网页20次，结果：content

 text：

 长度都为2381

2,中国最好大学排名

import requests
import bs4
from bs4 import BeautifulSoup
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')
    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[3].string])
def printUnivList(ulist,num):
    tplt="{0:^10}	{1:{3}^10}	{2:^10}"
    print(tplt.format('排名','学校名称','总分',chr(12288))) 
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
def main():
    uinfo=[]
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html=getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,10)  
main() 

结果：