Examples of org.apache.nutch.parse.ParseSegment


    Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate());
    Injector injector = new Injector(getConf());
    Generator generator = new Generator(getConf());
    Fetcher fetcher = new Fetcher(getConf());
    ParseSegment parseSegment = new ParseSegment(getConf());
    CrawlDb crawlDbTool = new CrawlDb(getConf());
    LinkDb linkDbTool = new LinkDb(getConf());
      
    // initialize crawlDb
    injector.inject(crawlDb, rootUrlDir);
    int i;
    for (i = 0; i < depth; i++) {             // generate new segment
      Path[] segs = generator.generate(crawlDb, segments, -1, topN, System
          .currentTimeMillis());
      if (segs == null) {
        LOG.info("Stopping at depth=" + i + " - no more URLs to fetch.");
        break;
      }
      fetcher.fetch(segs[0], threads);  // fetch it
      if (!Fetcher.isParsing(job)) {
        parseSegment.parse(segs[0]);    // parse it, if needed
      }
      crawlDbTool.update(crawlDb, segs, true, true); // update crawldb
    }
    if (i > 0) {
      linkDbTool.invert(linkDb, segments, true, true, false); // invert links

      Path segment =
        new Generator(job).generate(crawlDb, segments, -1,
                                     topN, System.currentTimeMillis());
      new Fetcher(job).fetch(segment, threads);  // fetch it
      if (!Fetcher.isParsing(job)) {
        new ParseSegment(job).parse(segment);    // parse it, if needed
      }
      new CrawlDb(job).update(crawlDb, segment); // update crawldb
    }
      
    new LinkDb(job).invert(linkDb, segments); // invert links

Examples of org.apache.nutch.parse.ParseSegment

Related Classes of org.apache.nutch.parse.ParseSegment