# -*- coding:utf-8 -*-
import re

import urllib
import urllib.request


import gzip
# 处理页面标签类


class Tool:
 """处理页面标签类"""

 # 去除img标签,7为长空格
 removeImg = re.compile('<img.*?>| {7}|')
 # 删除超链接标签
 removeAddr = re.compile('<a.*?>|</a>')
 # 把换行的标签换为\n
 replaceLine = re.compile('<tr>|<div>|</div>|</p>')
 # 将表格制表<td>替换为\t
 replaceTD = re.compile('<td>')
 # 把段落开头换为\n加空两格
 replacePara = re.compile('<p.*?>')
 # 将换行符或双换行符替换为\n
 replaceBR = re.compile('<br><br>|<br>')
 # 将其余标签剔除
 removeExtraTag = re.compile('<.*?>')

 def replace(self, x):
 x = re.sub(self.removeImg, "", x)
 x = re.sub(self.removeAddr, "", x)
 x = re.sub(self.replaceLine, "\n", x)
 x = re.sub(self.replaceTD, "\t", x)
 x = re.sub(self.replacePara, "\n ", x)
 x = re.sub(self.replaceBR, "\n", x)
 x = re.sub(self.removeExtraTag, "", x)
 # strip()将前后多余内容删除
 return x.strip()

# 处理页面标签类


class Tool:
 # 去除img标签,7位长空格
 removeImg = re.compile('<img.*?>| {7}|')
 # 删除超链接标签
 removeAddr = re.compile('<a.*?>|</a>')
 # 把换行的标签换为\n
 replaceLine = re.compile('<tr>|<div>|</div>|</p>')
 # 将表格制表<td>替换为\t
 replaceTD = re.compile('<td>')
 # 把段落开头换为\n加空两格
 replacePara = re.compile('<p.*?>')
 # 将换行符或双换行符替换为\n
 replaceBR = re.compile('<br><br>|<br>')
 # 将其余标签剔除
 removeExtraTag = re.compile('<.*?>')

 def replace(self, x):
 x = re.sub(self.removeImg, "", x)
 x = re.sub(self.removeAddr, "", x)
 x = re.sub(self.replaceLine, "\n", x)
 x = re.sub(self.replaceTD, "\t", x)
 x = re.sub(self.replacePara, "\n ", x)
 x = re.sub(self.replaceBR, "\n", x)
 x = re.sub(self.removeExtraTag, "", x)
 # strip()将前后多余内容删除
 return x.strip()


class BDTB:
 """百度贴吧"""
 # 初始化,传入基地址,是否只看楼主

 def __init__(self, baseUrl, seeLZ):
 self.baseUrl = baseUrl
 self.seeLZ = '?see_lz=' + str(seeLZ)
 self.tool = Tool()

 # 获得页面html代码

 def getPage(self, pageNum):
 try:
 url = self.baseUrl + self.seeLZ + '&pn=' + str(pageNum)
 print(url)
 request = urllib.request.Request(url)
 response = urllib.request.urlopen(request)
 data = response.read().decode('utf-8') # bytes -> str
 print(type(data))
 # print(type(data))
 # data = self.ungzip(data)
 # self.saveFile(data)
 return data
 except Exception as e:
 print('连接百度贴吧失败,错误原因:' + e)
 return None

 # 保存文件

 def saveFile(self, data):
 data = data.encode('utf-8') # str -> bytes
 savePath = 'E:\\python\\python\\bdtb.out'
 f_obj = open(savePath, 'wb')
 f_obj.write(data)
 f_obj.close()

 # 获得帖子标题

 def getTitle(self):
 page = self.getPage(1)
 pattern = re.compile(
 '<h3 class="core_title_txt pull-left text-overflow ".*?>(.*?)</h3>', re.S)
 result = re.search(pattern, page)
 if result:
 return result.group(1).strip()
 else:
 return None

 # 提取帖子页数

 def getPageNum(self):
 page = self.getPage(1)
 pattern = re.compile('共<span class="red">(.*?)</span>', re.S)
 result = re.search(pattern, page)
 if result:
 return result.group(1).strip()
 else:
 return None

 # 提取正文内容
 def getContent(self, page):
 divStr = '<div id="post_content.*?".*?>(.*?)</div>'
 pattern = re.compile(divStr, re.S)
 items = re.findall(pattern, page)
 floor = 1
 for item in items:
 print(str(floor) + "楼-------------\n")
 print(self.tool.replace(item))
 floor += 1


baseUrl = 'http://tieba.baidu.com/p/3138733512'
bdtb = BDTB(baseUrl, 1)
page = bdtb.getPage(1)
bdtb.getContent(page)