import requests
url = ‘https://www.amazon.cn/gp/product/b01MBL5Z3Y‘
try :
    kv = {‘user-agent‘:‘Mozilla/5.0‘}
    r = requests.get(url,headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print(‘获取失败‘)

import requests
path = ‘D:/图片/abc.jpg‘
kv = {‘user-agent‘:‘Mozilla/5.0‘}
url = ‘https://inews.gtimg.com/newsapp_bt/0/10881420534/1000‘
r = requests.get(url,headers=kv)
with open(path,‘wb‘) as f:
    f.write(r.content)
    f.close()

import requests
from bs4 import BeautifulSoup
import bs4


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[2].string])


def printUnivList(ulist, num):
    print(‘{:^10}\t{:^6}\t{:^10}‘.format(‘排名‘, ‘学校‘, ‘总分‘,chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(‘{:^10}\t{:^6}\t{:^10}‘.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)