bs4解析爬取星巴克数据

bs4解析爬取星巴克数据

# _*_ coding : utf-8 _*_
# @Time : 2023/1/31 14:41
# @Author : 李阶熊
# @File : bs4解析爬取星巴克数据
# @Project : pythonProject
import urllib.request
from bs4 import BeautifulSoup
import lxml
url = 'https://www.starbucks.com.cn/menu/'

headers = {
    
    
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Cookie': 'ZHh6ku4z=AxOQjAaGAQAAwP-BNpfQcHnwbl-WbW4wSe6asIydLft8g-1XYCh0tHlHnOTTAXQcXgCucnyzwH8AAEB3AAAAAA|1|1|34ae1a62720b78bbbe0f84b6845bcb73d61694a0',
    'Host': 'www.starbucks.com.cn',
    'Referer': 'https://www.starbucks.com.cn/',
    'sec-ch-ua': '"Not_A Brand";v="99", "Google Chrome";v="109", "Chromium";v="109"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-Site': 'same-origin',
    'Sec-Fetch-User': '?1',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
}

response = urllib.request.urlopen(url)

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

# print(content)

soup = BeautifulSoup(content, 'lxml')

# //ul[@class="grid padded-3 product"]//strong/text()
name_list = soup.select('ul[class="grid padded-3 product"] strong')

for name in name_list:
    print(name.get_text())