适用场景：会员帐号下的文章、视频，老网站的数据下载
可以爬取网页的数据：文章标题，内容，联系方式;使用Selenium模拟浏览器行为：点击，提交，浏览。

目标网站： https://pic.netbian.com/4kmeinv/

from lxml import etree
import requests
import os

if __name__=="__main__":
    headers = {
'user-agent': 'Mozilla/5.0(Windows NT 6.1;Win64;x64) AppleWebKit/537.36(KHTML, likeGecko) Chrome/85.0.4183.121Safari/537.36'
}

    url="http://pic.netbian.com/4kmeinv/"

response=requests.get(url=url,headers=headers)
    response.encoding='gb2312'
#response.encoding=response.apparent_encoding
text=response.text

    tree=etree.HTML(text)

    li_list=tree.xpath("//div[@class='slist']/ul/li")

if not os.path.exists('./piclibs'):
        os.mkdir('./piclibs')

for li in li_list:
        li_src=li.xpath('./a/img/@src')[0]
        li_src="http://pic.netbian.com/"+li_src
        li_name=li.xpath('./a/img/@alt')[0]+".jpg"
#li_name.encode('iso-8859-1').decode('gbk')
        #print(li_src)
        #print(li_name)
img_data=requests.get(url=li_src,headers=headers).content
        img_path='piclibs/'+li_name
with open(img_path,'wb') as fp:
            fp.write(img_data)
print(li_name,'下载成功')