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