xpath学习之爬取4K图片

from lxml import etree
import requests
import os
#请求连接
url = 'http://pic.netbian.com/4kmeinv/'
#UA伪装
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'
}
#请求页面源码
page_text = requests.get(url=url,headers=headers).text
#创建xpath对象
tree = etree.HTML(page_text)
#获取当前源码文件中所有存放图片信息的li标签
pic_list = tree.xpath('//ul[@class="clearfix"]/li')
#创建文件目录
if not os.path.exists('./pics'):
    os.mkdir('./pics')

for li in pic_list:
    src = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
    #图片名称徐解决乱码问题
    name = li.xpath('./a/img/@alt')[0]
    name = name.encode('iso-8859-1').decode('gbk')
    #开始下载图片文件
    image_data = requests.get(url=src,headers=headers).content
    #保存图片
    image_path = 'pics/'+name
    with open(image_path,'wb') as pf:
        pf.write(image_data)
        print(name+' download success!!!')