使用xpath来爬取图片并保存到本地

# 解析下载图片数据
# https://pic.netbian.com/4kmeinv/

import requests
from lxml import etree
import os

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/106.0.0.0 Safari/537.36'}
res = requests.get(url = url,headers = headers)
# 手动设定响应格式，将其设置成utf-8格式
# res.encoding = 'utf-8'

# 实例化对象并进行解析
tree = etree.HTML(res.text)
# 数据解析：src的属性值    alt的属性
li_list = tree.xpath('//ul[@class="clearfix"]/li')

# 创建一个文件夹
if not os.path.exists('.picLibs'):
    os.mkdir('./picLibs')

for li in li_list:
    img_src = 'https://pic.netbian.com/'+li.xpath('./a/img/@src')[0]
    title = li.xpath('./a/img/@alt')[0]+'.jpg'
    #通用处理中文乱码的解决方案，（当更改完编码格式后，需要重新给他赋值）
    img_name = title.encode('iso-8859-1').decode('gbk')

    #请求图片进行持久化存储
    img_data = requests.get(url = img_src,headers = headers).content
    img_path = 'picLibs/'+img_name
    with open(img_path,'wb') as fb:
        fb.write(img_data)
        print(img_name,"下载成功")

使用xpath来爬取图片并保存到本地