Python爬虫爬取多张图片代码1

import os
import re
import requests
import parsel

for page in range(1,3):
print(f’--------- 正在爬取第{page}的内容 ----------’)
if page==1:
url = ‘https://sj.zol.com.cn/bizhi/5/’ # 请求地址
else:
url = f’https://sj.zol.com.cn/bizhi/5/{page}.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)
# 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 = 'img6\\'
            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
  • 1
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

EYYLTV

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值