#!/usr/bin/env python
# -*- coding:utf-8 -*-
import urllib2
import urllib
import os
from lxml import etree
keyword = raw_input('请输入要查询的关键字： ')

keyword = {'kw':keyword}

kw = urllib.urlencode(keyword)

startpage = raw_input('请输入开始页数： ')

endpage = raw_input('请输入结束页数： ')

url = 'https://tieba.baidu.com/f' + '"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko"}
    request = urllib2.Request(fullurl,headers=headers)
    response = urllib2.urlopen(request)
    html = response.read()

    # 解析html 为 HTML DOM文档
    content = etree.HTML(html)
    # xpath使用下面括号内容进行匹配，使用a的属性使用了class='j_th_tit'去过滤广告则匹配结果为空；换成a的属性rel="noreferrer"就解决。为啥换不清楚。思路，这个属性不行换个属性。
    # 获取每个分页里面的帖子的链接列表
    link_list = content.xpath('//div[@class="threadlist_lz clearfix"]/div/a[@rel="noreferrer"]/@href')
    # 获取该帖子楼主所发的图片链接列表
    for link in link_list:
      link = 'https://tieba.baidu.com' + link 
      request2 = urllib2.Request(link,headers=headers)
      response2 = urllib2.urlopen(request2)
      html2 = response2.read()

      # 把html字符串解析为html dom
      content2 = etree.HTML(html2)

      # 使用xpath匹配其里面层主所发的图片的链接
      link_list2 = content2.xpath('//img[@class="BDE_Image"]/@src')

      # 遍历图片链接列表，保存图片到文件夹images内
      for link2 in link_list2:

        request3 = urllib2.Request(link2,headers=headers)
        response3 = urllib2.urlopen(request3)
        html3 = response3.read()
        # 指定文件名
        filename = link2[-10:]
        n += 1
        print('正在保存第 %3d 张图片'%n)

        # html3为返回的图片内容，把图片写入images2文件夹内
        with open('images' + '/' + filename,'wb') as f:
          f.write(html3)

print('下载结束！')