python爬取新浪微博（爬取微博帐号所发内容，不爬取历史内容）

实现：

跟踪比较活跃的微博号所发的微博内容，隔3-5分钟刷新（爬取）一次，只有更新了才爬的到，不爬取历史微博内容哦，爬取正文、文中图片、所属微博昵称、发布时间（时间戳格式)。

python_service.py

import win32serviceutil
import win32service
import win32event
import re,requests,time,datetime,pymysql,random
'''
遇到不懂的问题？Python学习交流群：821460695满足你的需求，资料都已经上传群文件，可以自行下载！
'''
WB_count1=8;WB_count=9;w1=0;Stop_py=1;w2=0
get_status=0
class SmallestPythonService(win32serviceutil.ServiceFramework):
    _svc_name_ = "SmallestPythonService"
    _svc_display_name_ = "The smallest possible Python Service"
    def __init__(self, args):
        win32serviceutil.ServiceFramework.__init__(self, args)
        # Create an event which we will use to wait on.
        # The "service stop" request will set this event.
        self.hWaitStop = win32event.CreateEvent(None, 0, 0, None)
    def SvcStop(self):
        # Before we do anything, tell the SCM we are starting the stop process.
        self.ReportServiceStatus(win32service.SERVICE_STOP_PENDING)
        # And set my event.
        win32event.SetEvent(self.hWaitStop)
    def SvcDoRun(self):
        global get_status
        class crawl1:
            def __init__(self):
                pass
            def getcontent(self,start_url1):
                '''获取信息'''
                global WB_count1,time_int,picture_name,cont_soure,cont,WB_count
                html=requests.get(start_url1,cookies=cookie,headers=header,timeout=15)
                html=html.content
                reg=r't2\\">粉丝.*?ong clas.*?">(.*?)微博'
                WB_count=re.findall(re.compile(reg),html)  #发微博数量
                if WB_count==[]:
                    self.GetBadCookie(I_D)
                    print 'cookie 被冻结'
                    cont,picture_name,cont_soure,time_int='1','1','1','1'
                    return cont,picture_name,cont_soure,time_int
                else:
                    reg1=r' 来自