Python爬虫之bs4解析实战篇

import urllib.request
from bs4 import BeautifulSoup

def get_content():
    url = 'https://www.starbucks.com.cn/menu/'
    response = urllib.request.urlopen(url)
    content = response.read().decode('utf-8')
    return content

def down_load(content):
    soup = BeautifulSoup(content, 'lxml')
    name_list = soup.select('ul[] strong')
    img_list = soup.select('ul[] div')


    for i in range(len(name_list)):
        name = name_list[i].get_text().replace('/', '∕')
        img = img_list[i].attrs.get('style').split('"')[1].split('"')[0]

        basic_url = 'https://www.starbucks.com.cn'
        url = basic_url + img
        urllib.request.urlretrieve(url=url, filename='./Starbucks/' + name + '.jpg')


if __name__ == '__main__':
    content = get_content()
    down_load(content)

注意：要提前创建好名为Starbucks的文件夹，代码仅供学习，无商业用途，求点赞！