def init_app(self): ''' 服务矜持初始化 ''' ret = 0 self.init_log(logging.DEBUG) self._logger.info("application init start.") Spider_MySQL_DBProcess.instance().set_db_info(db_usr="******", db_password="******") ret = Spider_MySQL_DBProcess.instance().connect_to_db() if (ret != 0): return ret Spider_Openner_Builder.instance().config_builder( {'http': 'http://proxy.tencent.com:8080/'}) #Spider_Openner_Builder.instance().config_builder() Spider_Schedule_Manager.instance() Spider_Schedule_Manager.instance().init(80001,\ 10,\ True,\ "E:/My.Travel/", "127.0.0.1",\ "root",\ "zxzxzx") return 0
def init_app(self): ''' 服务矜持初始化 ''' ret = 0 self.init_log(logging.DEBUG) self._logger.info("application init start.") Spider_MySQL_DBProcess.instance().set_db_info( db_usr="******", db_password="******") ret = Spider_MySQL_DBProcess.instance().connect_to_db() if (ret != 0): return ret Spider_Openner_Builder.instance().config_builder({'http': 'http://proxy.tencent.com:8080/'}) #Spider_Openner_Builder.instance().config_builder() Spider_Schedule_Manager.instance() Spider_Schedule_Manager.instance().init(80001,\ 10,\ True,\ "E:/My.Travel/", "127.0.0.1",\ "root",\ "zxzxzx") return 0
def __init__ (self,website_id,website_domain,mysql_process,filesave_dir): ''' ''' #处理的网页站点的ID和域名 self._website_id = website_id self._website_domain = website_domain #日志模块,免得每个人都去折腾了 self._logger = logging.getLogger() #得到openner self._opener = Spider_Openner_Builder.instance().build_opener() #为了多线程考虑,用累成员对象 self._mysql_process = mysql_process #文件保存的的目录 self._filesave_dir = filesave_dir