Package org.apache.nutch.fetcher

Examples of org.apache.nutch.fetcher.Fetcher$FetcherThread

113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
    Path index = new Path(dir + "/index");

    Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate());
    Injector injector = new Injector(conf);
    Generator generator = new Generator(conf);
    Fetcher fetcher = new Fetcher(conf);
    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[] 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, org.apache.nutch.fetcher.Fetcher.isParsing(conf));  // fetch it
      if (!Fetcher.isParsing(job)) {
        parseSegment.parse(segs[0]);    // parse it, if needed
      }
      crawlDbTool.update(crawlDb, segs, true, true); // update crawldb
    }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    Path index = new Path(dir + "/index");

    Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate());
    Injector injector = new Injector(conf);
    Generator generator = new Generator(conf);
    Fetcher fetcher = new Fetcher(conf);
    ParseSegment parseSegment = new ParseSegment(conf);
    CrawlDb crawlDbTool = new CrawlDb(conf);
    LinkDb linkDbTool = new LinkDb(conf);
    Indexer indexer = new Indexer(conf);
    DeleteDuplicates dedup = new DeleteDuplicates(conf);
    IndexMerger merger = new IndexMerger(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(), false, false);
      if (segment == null) {
        LOG.info("Stopping at depth=" + i + " - no more URLs to fetch.");
        break;
      }
      fetcher.fetch(segment, threads);  // fetch it
      if (!Fetcher.isParsing(job)) {
        parseSegment.parse(segment);    // parse it, if needed
      }
      crawlDbTool.update(crawlDb, new Path[]{segment}, true, true); // update crawldb
    }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    Path index = new Path(dir + "/index");

    Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate());
    Injector injector = new Injector(conf);
    Generator generator = new Generator(conf);
    Fetcher fetcher = new Fetcher(conf);
    ParseSegment parseSegment = new ParseSegment(conf);
    CrawlDb crawlDbTool = new CrawlDb(conf);
    LinkDb linkDbTool = new LinkDb(conf);
    Indexer indexer = new Indexer(conf);
    DeleteDuplicates dedup = new DeleteDuplicates(conf);
    IndexMerger merger = new IndexMerger(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(), false, false);
      if (segment == null) {
        LOG.info("Stopping at depth=" + i + " - no more URLs to fetch.");
        break;
      }
      fetcher.fetch(segment, threads);  // fetch it
      if (!Fetcher.isParsing(job)) {
        parseSegment.parse(segment);    // parse it, if needed
      }
      crawlDbTool.update(crawlDb, new Path[]{segment}, true, true); // update crawldb
    }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
     */
    public Nutch9Fetcher() {
        Config config = Config.getConfig("nutchfetcher.properties");
        segmentsDir = config.getString("fetchlist.dir");
        keepUrl = config.getBoolean("keep.original.url.on.redirect");
        fetcher = new Fetcher();
        Configuration conf = new Configuration();
        // conf.addDefaultResource("crawl-tool.xml");
        conf.addDefaultResource("nutch-default.xml");
        conf.addDefaultResource("nutch-site.xml");
        JobConf job = new NutchJob(conf);
View Full Code Here
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
            // generate
            Generator g = new Generator(conf);
            // fetch
            conf.setBoolean("fetcher.parse", true);
            Fetcher fetcher = new Fetcher(conf);
            CrawlDb crawlDbTool = new CrawlDb(conf);

            int depth = 5;
            int threads = 4;
            for (int i = 0; i < depth; i++) { // generate new segment
                Path generatedSegment = g.generate(crawldbPath, segmentsPath, 1, Long.MAX_VALUE, Long.MAX_VALUE, false,
                        false);

                if (generatedSegment == null) {
                    logger.info("Stopping at depth=" + i + " - no more URLs to fetch.");
                    break;
                }
                fetcher.fetch(generatedSegment, threads, true);
                crawlDbTool.update(crawldbPath, new Path[] { generatedSegment }, true, true);
            }
        } catch (IOException e) {
            logger.error("Exception while crawling", e);
        }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
    Path index = new Path(dir + "/index");

    Path tmpDir = job.getLocalPath("crawl"+Path.SEPARATOR+getDate());
    Injector injector = new Injector(conf);
    Generator generator = new Generator(conf);
    Fetcher fetcher = new Fetcher(conf);
    ParseSegment parseSegment = new ParseSegment(conf);
    CrawlDb crawlDbTool = new CrawlDb(conf);
    LinkDb linkDbTool = new LinkDb(conf);
    Indexer indexer = new Indexer(conf);
    DeleteDuplicates dedup = new DeleteDuplicates(conf);
    IndexMerger merger = new IndexMerger(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) {
        LOG.info("Stopping at depth=" + i + " - no more URLs to fetch.");
        break;
      }
      fetcher.fetch(segment, threads, org.apache.nutch.fetcher.Fetcher.isParsing(conf));  // fetch it
      if (!Fetcher.isParsing(job)) {
        parseSegment.parse(segment);    // parse it, if needed
      }
      crawlDbTool.update(crawlDb, new Path[]{segment}, true, true); // update crawldb
    }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
    Path index = new Path(dir + "/index");

    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
    }
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
     
    for (int i = 0; i < depth; i++) {             // generate new segment
      Path segment =
        new Generator(job).generate(crawlDb, segments, -1,
                                     topN, System.currentTimeMillis());
      new Fetcher(job).fetch(segment, threads, Fetcher.isParsing(job));  // fetch it
      if (!Fetcher.isParsing(job)) {
        new ParseSegment(job).parse(segment);    // parse it, if needed
      }
      new CrawlDb(job).update(crawlDb, segment); // update crawldb
    }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
    Path index = new Path(dir + "/index");

    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, org.apache.nutch.fetcher.Fetcher.isParsing(getConf()));  // fetch it
      if (!Fetcher.isParsing(job)) {
        parseSegment.parse(segs[0]);    // parse it, if needed
      }
      crawlDbTool.update(crawlDb, segs, true, true); // update crawldb
    }
View Full Code Here
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
    Path linkDb = new Path(dir + "/linkdb");
    Path segments = new Path(dir + "/segments");
    res.elapsed = System.currentTimeMillis();
    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
    long start = System.currentTimeMillis();
    injector.inject(crawlDb, rootUrlDir);
    long delta = System.currentTimeMillis() - start;
    res.addTiming("inject", "0", delta);
    int i;
    for (i = 0; i < depth; i++) {             // generate new segment
      start = System.currentTimeMillis();
      Path[] segs = generator.generate(crawlDb, segments, -1, topN, System
          .currentTimeMillis());
      delta = System.currentTimeMillis() - start;
      res.addTiming("generate", i + "", delta);
      if (segs == null) {
        LOG.info("Stopping at depth=" + i + " - no more URLs to fetch.");
        break;
      }
      start = System.currentTimeMillis();
      fetcher.fetch(segs[0], threads, org.apache.nutch.fetcher.Fetcher.isParsing(getConf()));  // fetch it
      delta = System.currentTimeMillis() - start;
      res.addTiming("fetch", i + "", delta);
      if (!Fetcher.isParsing(job)) {
        start = System.currentTimeMillis();
        parseSegment.parse(segs[0]);    // parse it, if needed
View Full Code Here
TOP

Related Classes of org.apache.nutch.fetcher.Fetcher$FetcherThread

  • backtype.storm.tuple.Values
  • cn.edu.hfut.dmic.webcollector.handler.Message
  • cn.edu.hfut.dmic.webcollector.model.Content
  • cn.edu.hfut.dmic.webcollector.model.CrawlDatum
  • cn.edu.hfut.dmic.webcollector.model.Page
  • cn.edu.hfut.dmic.webcollector.net.Request
  • cn.edu.hfut.dmic.webcollector.net.Response
  • cn.edu.hfut.dmic.webcollector.parser.Parser
  • cn.edu.hfut.dmic.webcollector.parser.ParseResult
  • com.digitalpebble.storm.crawler.protocol.Protocol
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.