代码拉取完成,页面将自动刷新
import requests
from lxml import etree
import os
if __name__ == '__main__':
url = 'https://pic.netbian.com/4kmeinv/'
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54'
}
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li')
if not os.path.exists('./imglibs'):
os.mkdir('./imglibs')
for li in li_list:
src_url = 'https://pic.netbian.com'+li.xpath('./a/img/@src')[0]
title = li.xpath('./a/img/@alt')[0]+'.jpg'
title = title.encode('iso-8859-1').decode('gbk')
img_data = requests.get(url=src_url,headers=headers).content
img_path = 'imglibs/'+title
with open(img_path,'wb') as fp:
fp.write(img_data)
print(title,'over!!!')
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。