Python爬虫爬取多张图片代码2

EYYLTV

于 2024-09-13 07:42:35 发布

阅读量244

点赞数 4

文章标签： python 开发语言算法

本文链接：https://blog.csdn.net/qq_32257509/article/details/142193164

版权

import os
import re
import requests
import parsel

url = ‘https://sj.zol.com.cn/bizhi/5/’ # 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)
#print(response.text)
selector = parsel.Selector(response.text)
#lis = selector.css(’.pic-list2 li’)

筛除包含的底部 3个猜你喜欢

lis=selector.css(’.pic-list2 .photo-list-padding’)
for li in lis:
#href = li.css(‘a::attr(href)’).get()
title = li.css(’.pic img::attr(title)’).get()
href = li.css(‘a::attr(href)’).get()
#print(title, href)
# https://sj.zol.com.cn/bizhi/detail_12901_139948.html
#url = “https://sj.zol.com.cn/bizhi/detail_12901_139948.html”
pattern = r’/bizhi/detail_(\d+)\d+.html’
replacement = r’https://app.zol.com.cn/bizhi/detail\1.html’
new_url = re.sub(pattern, replacement, href)
#print(href, new_url)
#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=new_url, headers=headers)
selector = parsel.Selector(response.text)
lis1 = selector.css(’.album-list li’)
i = 0
for li1 in lis1:
# Get all img elements within the current li
img_tags = li1.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 = 'img5\\'
        if not os.path.exists(img_folder):
            os.makedirs(img_folder)

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

        i += 1  # Increment i for each image saved