Beispiel #1
0
    def initialize(self,storm_conf, context):
        try:

            settings = all_settings.get_settings(storm_conf['topology.deployment'])
            self.conf = settings
            self.connector = factory.getEntityDataConnector(self.conf)
        except:
            self.log(traceback.format_exc(),level='error')
            raise
Beispiel #2
0
 def initialize(self, storm_conf, context):
     try:
         self.log("WriterBolt INIT")
         settings = all_settings.get_settings(
             storm_conf['topology.deployment'])
         self.conf = settings
         self.connector = factory.getEntityDataConnector(self.conf)
     except:
         self.log("WriterBolt initialize error", level='error')
         self.log(traceback.format_exc(), level='error')
         raise
Beispiel #3
0
 def initialize(self, stormconf, context):
     try:
         settings = all_settings.get_settings(stormconf['topology.deployment'])
         self.topic = settings['crawler-out-topic'].encode()
         self.conn_pool = settings['conn_pool'].encode()
         self.log('KafkaDatawakeLookaheadSpout initialized with topic =' + self.topic + ' conn_pool=' + self.conn_pool)
         self.kafka = KafkaClient(self.conn_pool)
         self.consumer = SimpleConsumer(self.kafka, self.group, self.topic, max_buffer_size=None)
         self.consumer.seek(0, 2)  # move to the tail of the queue
     except:
         self.log("KafkaDatawakeLookaheadSpout initialize error", level='error')
         self.log(traceback.format_exc(), level='error')
         raise
Beispiel #4
0
 def initialize(self,storm_conf, context):
     try:
         self.log("CrawlerBolt INIT")
         settings = all_settings.get_settings(storm_conf['topology.deployment'])
         self.topic = settings['crawler-out-topic'].encode()
         self.conn_pool = settings['conn_pool'].encode()
         self.log('CrawlerQueueWriter initialized with topic ='+self.topic+' conn_pool='+self.conn_pool)
         self.kafka = KafkaClient(self.conn_pool)
         self.producer = SimpleProducer(self.kafka, async=False)
     except:
         self.log("CrawlerBolt initialize error",level='error')
         self.log(traceback.format_exc(),level='error')
         raise
 def initialize(self, storm_conf, context):
     try:
         self.log("CrawlerBolt INIT")
         settings = all_settings.get_settings(storm_conf['topology.deployment'])
         self.topic = settings['crawler-out-topic'].encode()
         self.conn_pool = settings['conn_pool'].encode()
         self.log('CrawlerQueueWriter initialized with topic =' + self.topic + ' conn_pool=' + self.conn_pool)
         self.kafka = KafkaClient(self.conn_pool)
         self.producer = SimpleProducer(self.kafka, async=False)
     except:
         self.log("CrawlerBolt initialize error", level='error')
         self.log(traceback.format_exc(), level='error')
         raise
    def initialize(self, stormconf, context):
        try:
            settings = all_settings.get_settings(stormconf['topology.deployment'])
            self.topic = settings['crawler-in-topic'].encode()
            self.conn_pool = settings['conn_pool'].encode()
            self.log('CrawlerSpout initialized with topic ='+self.topic+' conn_pool='+self.conn_pool)
            self.kafka = KafkaClient(self.conn_pool)
	    self.kafka.ensure_topic_exists(self.topic)
            self.consumer = SimpleConsumer(self.kafka,self.group,self.topic,max_buffer_size=None, fetch_size_bytes=2000000)
            self.consumer.seek(0,2) # move to the tail of the queue
        except:
            self.log("CrawlerSpout initialize error",level='error')
            self.log(traceback.format_exc(),level='error')
            raise