python 图片抓取并保存到本地

最新推荐文章于 2024-09-12 18:31:52 发布

Waldenz

最新推荐文章于 2024-09-12 18:31:52 发布

阅读量2.6k

点赞数 1

分类专栏： Python 文章标签： python 图片抓取图片下载爬虫

本文链接：https://blog.csdn.net/enter89/article/details/89555795

版权

Python 专栏收录该内容

45 篇文章 8 订阅

订阅专栏

首先安装包：

# html的解析库
pip install BeautifulSoup4
# 图片处理的库
pip install pillow
pip install requests

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_all('img', class_='img-responsive')
items = soup.find_all('img', attrs={'data-v-32e60122':''})
 
folder_path = './photo'
 
if os.path.exists(folder_path) == False:
   os.makedirs(folder_path)
 
for index, item in enumerate(items):
    if item:
        turl = item.get('src')
        if not turl.startswith('http:'):
            continue
        html = requests.get(item.get('src'))
        img_name = str(index + 1) + '.png'
        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')