__author__ = 'CQC'
# -*- coding:utf-8 -*-
import urllib
try:
    import urllib.request as urllib2
    import urllib.parse 
    from requests.auth import HTTPBasicAuth
except ImportError:
    import urllib2

#gbkTypeStr = unicodeTypeStr.encode("GBK", 'ignore');
#gbkTypeStr = unicodeTypeStr.encode("GB18030", 'ignore');
import ssl
ssl._create_default_https_context = ssl._create_unverified_context


#百度贴吧爬虫类
class BDTB:

    #初始化，传入基地址，是否只看楼主的参数
    def __init__(self,baseUrl,seeLZ):
        self.baseURL = baseUrl
        self.seeLZ = '?see_lz='+str(seeLZ)
        self.user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
        #初始化headers
        self.headers = { 'User-Agent' : self.user_agent }

    #传入页码，获取该页帖子的代码
    def getPage(self,pageNum):
        try:
            url = self.baseURL+ self.seeLZ + '&pn=' + str(pageNum)
            request = urllib2.Request(url,headers = self.headers)
            response = urllib2.urlopen(request)
            print(response.read())
            return response
        except urllib.error.URLError as e:
            if hasattr(e,"reason"):
                print(u"连接百度贴吧失败,错误原因",e.reason)
                return None

baseURL = 'https://tieba.baidu.com/p/3138733512'
bdtb = BDTB(baseURL,1)
bdtb.getPage(1)