Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseSegment

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
139
140
    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
    }
    if (i > 0) {
      linkDbTool.invert(linkDb, segments, true, true, false); // invert links
View Full Code Here
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
130
131
    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
    }
    if (i > 0) {
      linkDbTool.invert(linkDb, segments, true, true, false); // invert links
View Full Code Here
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
130
131
    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
    }
    if (i > 0) {
      linkDbTool.invert(linkDb, segments, true, true, false); // invert links
View Full Code Here
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
128
129
    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
    }
    if (i > 0) {
      linkDbTool.invert(linkDb, segments, true, true, false); // invert links
View Full Code Here
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
147
148
    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
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
      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
    }
     
    new LinkDb(job).invert(linkDb, segments); // invert links
View Full Code Here
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
141
142
    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
    }
    if (i > 0) {
      linkDbTool.invert(linkDb, segments, true, true, false); // invert links
View Full Code Here
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
240
241
242
243
244
    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
        delta = System.currentTimeMillis() - start;
        res.addTiming("parse", i + "", delta);
      }
      start = System.currentTimeMillis();
      crawlDbTool.update(crawlDb, segs, true, true); // update crawldb
View Full Code Here
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
240
241
242
243
244
    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);  // 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
        delta = System.currentTimeMillis() - start;
        res.addTiming("parse", i + "", delta);
      }
      start = System.currentTimeMillis();
      crawlDbTool.update(crawlDb, segs, true, true); // update crawldb
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
    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
View Full Code Here
TOP

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

  • org.apache.hadoop.fs.Path
  • org.apache.nutch.crawl.Crawl
  • org.apache.nutch.metadata.Metadata
  • org.apache.nutch.scoring.ScoringFilters
  • org.apache.nutch.tools.Benchmark
  • java.text.SimpleDateFormat
    • 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.