尚硅谷Python爬虫教程小白零基础速通（含python基础+爬虫案例）

P76笔记

拓展：爬取星巴克菜单样品图片

import urllib.request

url = 'https://www.starbucks.com.cn/menu/'

response = urllib.request.urlopen(url)

content = response.read().decode('utf-8')


from bs4 import BeautifulSoup

soup = BeautifulSoup(content,'lxml')

# //ul[@class="grid padded-3 product"]//strong/text()
url_list = soup.select('div[class="preview circle"]')
name_list = soup.select('ul[class="grid padded-3 product"] strong')
tittle="https://www.starbucks.com.cn"
for i in range(10):
    urls=tittle+url_list[i].get('style').split(" ")[1].split('"')[1]
    name=name_list[i].get_text()
    str="/"
    if str in name:
        name=name.replace('/','')
    print(urls)
    print(name)
    urllib.request.urlretrieve(url=urls, filename='./XBKImg/' + name + '.jpg')