Python爬虫爬取多张图片代码3

易软科技(河源)有限公司

已于 2024-09-14 00:18:49 修改

阅读量217

点赞数 1

文章标签： python 开发语言算法

于 2024-09-13 07:43:22 首次发布

本文链接：https://blog.csdn.net/qq_32257509/article/details/142193229

版权

下载子页面全部

import os
import requests
import parsel

url = ‘https://app.zol.com.cn/bizhi/detail_12901.html’ # 请求地址

模拟伪装

headers = {‘user-agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36’}
response = requests.get(url=url,headers=headers)
selector = parsel.Selector(response.text)
lis = selector.css(’.album-list li’)
i = 0
for li in lis:
# Get all img elements within the current li
img_tags = li.css(‘img::attr(src)’).getall() # This gets all the img src attributes

for href in img_tags:  # Iterate over all img src attributes
    img_content = requests.get(url=href, headers=headers).content
    img_folder = 'img4\\'
    if not os.path.exists(img_folder):
        os.makedirs(img_folder)

    with open( str(i) + '.jpg', mode='wb') as f:
        f.write(img_content)
        # print(href, i)
        print('正在保存：', i, href)

    i += 1  # Increment i for each image saved