python爬虫学习（十三）xpath爬取妹子图片

# -*- coding: utf-8 -*-
import requests
from lxml import etree
import os
if __name__ == '__main__':
    #爬取页面源码数据
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36'
    }
    url='http://pic.netbian.com/4kmeinv/'
    response=requests.get(url=url,headers=headers)
    # #手动改变响应数据为utf-8
    # response.encoding = 'utf-8'
    page_text = response.text

    #数据解析：src的属性值 alt属性值
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//div[@class="slist"]/ul/li')

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

    for li in li_list:
        img_src = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
        img_name = li.xpath('./a/img/@alt')[0]+'.jpg'
        #转码,处理乱码
        img_name = img_name.encode('iso-8859-1').decode('gbk')
        #print(img_name,img_src)
        #请求图片做存储
        img_data =requests.get(url=img_src,headers=headers).content
        img_path = 'piclibs/'+img_name
        with open(img_path,'wb') as fp:
            fp.write(img_data)
            print(img_name,'下载成功')
    print("操作完成")