import requests
from bs4 import BeautifulSoup
r = requests.get('https://www.starbucks.com.cn')
soup = BeautifulSoup(r.text,'lxml')
imgs = soup.select('.padded-2 > a img[src]')
num = 0
for img in imgs:
num +=1
# print(img['src'])
# 图片链接
image_url = img['src']
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'
}
r = requests.get(image_url, headers=headers)
# 下载图片
# 二进制数据需要用r.content 进行提取
# 将图片放在‘demofile’文件夹下，‘demofile’是文件夹的名称，将图片放入该文件夹中，该文件夹与py文件在同一目录下
f = open("demofile/%s.jpg" % num, 'wb') #来个占位符 num会自己加
f.write(r.content)
f.close()
标签：src,num,img,headers,python,抓取,星巴克,文件夹,demofile From： https://www.cnblogs.com/xm666/p/17303450.html