/* * NutchCrawler.java * Copyright (c) 1998-2008, The University of Sheffield. * * This code is from the GATE project (http://gate.ac.uk/) and is free * software licenced under the GNU General Public License version 3. It is * distributed without any warranty. For more details see COPYING.txt in the * top level directory (or at http://gatewiki.sf.net/COPYING.txt). * * Niraj Aswani 13 March 2009 * */ package gate.solr; import java.util.*; import java.text.*; // Commons Logging imports import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.nutch.fetcher.*; import org.apache.hadoop.fs.*; import org.apache.hadoop.conf.*; import org.apache.hadoop.mapred.*; import org.apache.nutch.parse.ParseSegment; import org.apache.nutch.util.HadoopFSUtil; import org.apache.nutch.util.NutchConfiguration; import org.apache.nutch.util.NutchJob; import org.apache.nutch.crawl.*; /** * Literally a copy of the Crawl.java. The only difference is that it uses the * Fetcher2 implementation instead of the Fetcher implementation. */ public class NutchCrawler { // logging public static final Log LOG = LogFactory.getLog(NutchCrawler.class); /** Return current date in the yyyMMddHHmmss format */ private static String getDate() { return new SimpleDateFormat("yyyyMMddHHmmss").format (new Date(System.currentTimeMillis())); } /* Perform complete crawling given a set of root urls. */ public static void main(String args[]) throws Exception { System.out.println("Using Fetcher2 implementation"); if (args.length < 1) { System.out.println("Usage: NutchCrawler " + "<urlDir> [-dir d] [-threads n] [-depth i] [-topN N]"); return; } // create a configuration object Configuration conf = NutchConfiguration.create(); conf.addResource("crawl-tool.xml"); JobConf job = new NutchJob(conf); Path rootUrlDir = null; Path dir = new Path("crawl-" + getDate()); int threads = job.getInt("fetcher.threads.fetch", 10); int depth = 5; long topN = Long.MAX_VALUE; // parsing arguments for (int i = 0; i < args.length; i++) { if ("-dir".equals(args[i])) { dir = new Path(args[i+1]); i++; } else if ("-threads".equals(args[i])) { threads = Integer.parseInt(args[i+1]); i++; } else if ("-depth".equals(args[i])) { depth = Integer.parseInt(args[i+1]); i++; } else if ("-topN".equals(args[i])) { topN = Integer.parseInt(args[i+1]); i++; } else if (args[i] != null) { rootUrlDir = new Path(args[i]); } } FileSystem fs = FileSystem.get(job); if (LOG.isInfoEnabled()) { LOG.info("crawl started in: " + dir); LOG.info("rootUrlDir = " + rootUrlDir); LOG.info("threads = " + threads); LOG.info("depth = " + depth); if (topN != Long.MAX_VALUE) LOG.info("topN = " + topN); } Path crawlDb = new Path(dir + "/crawldb"); Path linkDb = new Path(dir + "/linkdb"); Path segments = new Path(dir + "/segments"); Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate()); Injector injector = new Injector(conf); Generator generator = new Generator(conf); // using fetcher2 implementation Fetcher2 fetcher = new Fetcher2(conf); // Fetcher 1 implementation //Fetcher fetcher = new Fetcher(conf); // segmenter parser ParseSegment parseSegment = new ParseSegment(conf); CrawlDb crawlDbTool = new CrawlDb(conf); LinkDb linkDbTool = new LinkDb(conf); // initialize crawlDb injector.inject(crawlDb, rootUrlDir); int i; for (i = 0; i < depth; i++) { // generate new segment Path segment = generator.generate(crawlDb, segments, -1, topN, System.currentTimeMillis()); if (segment == null) { System.out.println("Stopping at depth=" + i + " - no more URLs to fetch."); break; } // fetch it fetcher.fetch(segment, threads, true); // parse it, if needed if (!Fetcher2.isParsing(job)) { parseSegment.parse(segment); } // update crawldb crawlDbTool.update(crawlDb, new Path[]{segment}, true, true); } if (i > 0) { // invert links linkDbTool.invert(linkDb, segments, true, true, false); } else { LOG.warn("No URLs to fetch - check your seed list and URL filters."); } if (LOG.isInfoEnabled()) { LOG.info("crawl finished: " + dir); } } }