#!/usr/bin/env python

 # -*- coding:utf-8 -*-

 __author__ = 'ziv·chan'

 import requests

 import re

 url = 'http://tieba.baidu.com/p/3138733512?see_lz=1&pn=3'

 html = requests.get(url)

 html.encoding = 'utf-8'

 pageCode = html.text

 pattern = re.compile('d_post_content j_d_post_content ">(.*?)</div><br>',re.S)

 items = re.findall(pattern,pageCode)

 i = 1

 for item in items:

     hasImg = re.search('<img',item)

     hasHref = re.search('href',item)

     # 过滤img

     if hasImg:

         pattern_1 = re.compile('<img class="BDE_Image".*?<br><br>')

         item = re.sub(pattern_1,'',item)

     # 过滤href

     if hasHref:

         pattern_2 = re.compile('onclick="Stats.sendRequest.*?class="at">(.*?)</a>',re.S)

         item = re.findall(pattern_2,item)

     print str(i) + ':'

     # 提取href标签下的用户

     if type(item) is list:

         for each in item:

             print each

     else:

         # 过滤多余标签 ' <br> '

         pattern_Br = re.compile('<br>')

         item = re.sub(pattern_Br, '\n', item)

         # 默认删除空白符

         print item.strip()

     print '\n'

     i += 1

     # if not hasImg and not hasHref:

     #     print i

     #     print item.strip()

     #     i += 1