Package org.apache.nutch.crawl

Examples of org.apache.nutch.crawl.CrawlDatum

93
94
95
96
97
98
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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
          String sig = parseData.getContentMeta().get(Nutch.SIGNATURE_KEY);
          if (sig != null) {
            byte[] signature = StringUtil.fromHexString(sig);
            if (signature != null) {
              // append a CrawlDatum with a signature
              CrawlDatum d = new CrawlDatum(CrawlDatum.STATUS_SIGNATURE, 0.0f);
              d.setSignature(signature);
              crawlOut.append(key, d);
            }
          }

          // collect outlinks for subsequent db update
          Outlink[] links = parseData.getOutlinks();
          if (ignoreExternalLinks) {
            try {
              fromHost = new URL(fromUrl).getHost().toLowerCase();
            } catch (MalformedURLException e) {
              fromHost = null;
            }
          } else {
            fromHost = null;
          }

          String[] toUrls = new String[links.length];
          int validCount = 0;
          for (int i = 0; i < links.length; i++) {
            String toUrl = links[i].getToUrl();
            try {
              toUrl = urlNormalizers.normalize(toUrl, URLNormalizers.SCOPE_OUTLINK); // normalize the url
              toUrl = filters.filter(toUrl);   // filter the url
            } catch (Exception e) {
              toUrl = null;
            }
            // ignore links to self (or anchors within the page)
            if (fromUrl.equals(toUrl)) toUrl = null;
            if (toUrl != null) validCount++;
            toUrls[i] = toUrl;
          }
          CrawlDatum adjust = null;
          // compute score contributions and adjustment to the original score
          for (int i = 0; i < toUrls.length; i++) {
            if (toUrls[i] == null) continue;
            if (ignoreExternalLinks) {
              try {
                toHost = new URL(toUrls[i]).getHost().toLowerCase();
              } catch (MalformedURLException e) {
                toHost = null;
              }
              if (toHost == null || !toHost.equals(fromHost)) { // external links
                continue; // skip it
              }
            }
            CrawlDatum target = new CrawlDatum(CrawlDatum.STATUS_LINKED, interval);
            Text targetUrl = new Text(toUrls[i]);
            adjust = null;
            try {
              adjust = scfilters.distributeScoreToOutlink((Text)key, targetUrl,
                      parseData, target, null, links.length, validCount);
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
    if (LOG.isInfoEnabled()) { LOG.info("fetching: "+url); }

    Configuration conf = NutchConfiguration.create();
    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);
    Content content = protocol.getProtocolOutput(new Text(url), new CrawlDatum()).getContent();

    if (force) {
      content.setContentType(contentType);
    } else {
      contentType = content.getContentType();
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    for (int i=0; i<sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      Configuration conf = NutchConfiguration.create();
      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-pdf", content);

      int index = parse.getText().indexOf(expectedText);
      assertTrue(index > 0);
    }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
  public void map(WritableComparable key, Writable value, OutputCollector output,
      Reporter reporter) throws IOException {
    newKey.set(key.toString());
    if (withMetadata) {
      CrawlDatum datum = (CrawlDatum)value;
      MapWritable meta = datum.getMetaData();
      if (meta.size() > 0) {
        MapWritable newMeta = new MapWritable();
        Iterator it = meta.keySet().iterator();
        while (it.hasNext()) {
          WritableComparable k = (WritableComparable)it.next();
          Writable v = meta.get(k);
          if (k instanceof UTF8) {
            Text t = new Text(k.toString());
            k = t;
          }
          newMeta.put(k, v);
        }
        datum.setMetaData(newMeta);
      }
    }
    output.collect(newKey, value);
  }
View Full Code Here
43
44
45
46
47
48
49
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1 + " " + class2);

    IndexingFilters filters = new IndexingFilters(conf);
    filters.filter(new Document(), new ParseImpl("text", new ParseData(
        new ParseStatus(), "title", new Outlink[0], new Metadata())), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
  }
View Full Code Here
215
216
217
218
219
220
221
222
223
224
    String url = args[0];
    Configuration conf = NutchConfiguration.create();
    RSSParser parser = new RSSParser();
    parser.setConf(conf);
    Protocol protocol = new ProtocolFactory(conf).getProtocol(url);
    Content content = protocol.getProtocolOutput(new Text(url), new CrawlDatum()).getContent();
    Parse parse = parser.getParse(content);
    System.out.println("data: "+ parse.getData());
    System.out.println("text: "+parse.getText());
  }
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
      datum2.put(new DummyWritable(i), new DummyWritable(i));
    }
    assertEquals(100, datum2.size());
    testWritable(datum2);

    CrawlDatum c = new CrawlDatum(CrawlDatum.STATUS_DB_FETCHED, 1f);
    c.setMetaData(new MapWritable());
    for (int i = 0; i < 100; i++) {
      c.getMetaData().put(new LongWritable(i), new Text("" + 1));
    }
    testWritable(c);
  }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
    Configuration conf = NutchConfiguration.create();
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-zip",content);
      assertTrue(parse.getText().equals(expectedText));
    }
  }
View Full Code Here
81
82
83
84
85
86
87
88
    fos.write(expectedText.getBytes());
    fos.close();

    // get nutch content
    Protocol protocol = new ProtocolFactory(NutchConfiguration.create()).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
    protocol = null;
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = factory.getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString),
                                           new CrawlDatum()).getContent();
      parse = parser.parseByExtensionId("parse-msexcel", content);

      assertTrue(parse.getText().equals(expectedText));
    }
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.crawl.CrawlDatum

  • com.atlantbh.nutch.index.alternativedataflow.AlternativeDataFlowIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.flow.CsvDataFlowTest
  • com.flaptor.hounder.crawler.Nutch9Fetcher
  • com.flaptor.hounder.crawler.Nutch9Fetcher$NutchSegment$SegmentIterator
  • org.apache.nutch.analysis.lang.LanguageIdentifier
  • org.apache.nutch.crawl.AdaptiveFetchSchedule
  • org.apache.nutch.crawl.DeduplicationJob$DedupReducer
  • org.apache.nutch.crawl.DeduplicationJob$StatusUpdateReducer
  • org.apache.nutch.crawl.MimeAdaptiveFetchSchedule
  • org.apache.nutch.crawl.TestCrawlDbStates
    • 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.