xpath之图片数据解析与爬取

# 需求 ：图片数据解析http://pic.netbian.com/4kmeinv/
import requests
import os
from lxml import etree
if __name__ == "__main__":

    # 爬取页面源码数据
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }   # UA伪装
    url = 'http://pic.netbian.com/4kmeinv/'
    page_text = requests.get(url=url,headers = headers).text
    # 手动设定响应数据的编码格式
    # res = requests.get(url=url,headers = headers)
    # res.encoding = 'utf-8'
    # page_text = res.text

    # 页面数据解析
    tree = etree.HTML(page_text)
    # 创建一个文件夹
    if not os.path.exists('./girlpiclib'):
        os.mkdir('./girlpiclib')
    li_list = tree.xpath('//div[@class="slist"]//li')
    for li in li_list:
        #局部解析 获取src 与 alt
        img_src = li.xpath('./a/img/@src')[0]
        img_name = li.xpath('./a/img/@alt')[0]+'.jpg'

        # 通用处理中文乱码的解析方式
        img_name = img_name.encode('iso-8859-1').decode('gbk')

        url = 'http://pic.netbian.com/'+img_src
        # 爬取图片数据content
        pic_content = requests.get(url= url,headers = headers).content

        #持久化存储
        img_path = 'girlpiclib/' + img_name
        fp = open(img_path,'wb')
        fp.write(pic_content)
        print(img_name,'下载成功')