Storm怎么写一个爬虫

这篇文章主要讲解了"Storm怎么写一个爬虫"，文中的讲解内容简单清晰，易于学习与理解，下面请大家跟着小编的思路慢慢深入，一起来研究和学习"Storm怎么写一个爬虫"吧！

package com.digitalpebble.storm.crawler.bolt.indexing;import java.util.Map;import org.slf4j.LoggerFactory;import backtype.storm.task.OutputCollector;import backtype.storm.task.TopologyContext;import backtype.storm.topology.OutputFieldsDeclarer;import backtype.storm.topology.base.BaseRichBolt;import backtype.storm.tuple.Tuple;import com.digitalpebble.storm.crawler.StormConfiguration;import com.digitalpebble.storm.crawler.util.Configuration;/** * A generic bolt for indexing documents which determines which endpoint to use * based on the configuration and delegates the indexing to it. ***/@SuppressWarnings("serial")public class IndexerBolt extends BaseRichBolt {    private Configuration config;    private BaseRichBolt endpoint;    private static final org.slf4j.Logger LOG = LoggerFactory            .getLogger(IndexerBolt.class);    public void prepare(Map conf, TopologyContext context,            OutputCollector collector) {        config = StormConfiguration.create();        // get the implementation to use        // and instanciate it        String className = config.get("stormcrawler.indexer.class");        if (className == null) {            throw new RuntimeException("No configuration found for indexing");        }        try {            final Class implClass = (Class) Class                    .forName(className);            endpoint = implClass.newInstance();        } catch (final Exception e) {            throw new RuntimeException("Couldn't create " + className, e);        }        if (endpoint != null)            endpoint.prepare(conf, context, collector);    }    public void execute(Tuple tuple) {        if (endpoint != null)            endpoint.execute(tuple);    }    public void declareOutputFields(OutputFieldsDeclarer declarer) {        if (endpoint != null)            endpoint.declareOutputFields(declarer);    }}

感谢各位的阅读，以上就是"Storm怎么写一个爬虫"的内容了，经过本文的学习后，相信大家对Storm怎么写一个爬虫这一问题有了更深刻的体会，具体使用情况还需要大家实践验证。这里是，小编将为大家推送更多相关知识点的文章，欢迎关注！