import requests
from bs4 import BeautifulSoup
from PIL import Image
import os 
from io import BytesIO
import time
 
url = "http://www.yestone.com/gallery/1501754333627"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
 
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.content, \'html.parser\')
items = soup.find(\'div\',class_=\'images-list\')
 
folder_path = \'./photo\'


# html = requests.get(\'http://st2.cdn.yestone.com/thumbs/2704315/vector/11688/116887226/api_thumb_450.jpg\')
# html = requests.get(\'/_nuxt/img/4c1a746.jpg\')
# print(html.content)
# image = Image.open(BytesIO(html.content))
# image.save(folder_path+"/aaa.jpg")
# print(items.find_all(\'img\'))
# exit()

if os.path.exists(folder_path) == False:
   os.makedirs(folder_path)
 
for index, item in enumerate(items.find_all(\'img\')):
    if item:
        html = requests.get(item.get(\'src\'))
        img_name = str(index + 1) + \'.jpg\'
        image = Image.open(BytesIO(html.content))
        image.save(folder_path+"/"+img_name)
        print(\'第%d张图片下载完成\' % (index + 1))
        time.sleep(1)  # 自定义延时
print(\'抓取完成\')
# html的解析库
pip install BeautifulSoup4
# 图片处理的库
pip install pillow
pip install requests

转 ：https://blog.csdn.net/enter89/article/details/89555795?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase

版权声明：本文为ygyy原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://www.cnblogs.com/ygyy/p/12944924.html