View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *  http://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  
18  package org.apache.any23.extractor.html;
19  
20  import org.apache.any23.extractor.ExtractionContext;
21  import org.apache.any23.extractor.ExtractionException;
22  import org.apache.any23.extractor.ExtractionParameters;
23  import org.apache.any23.extractor.ExtractionResult;
24  import org.apache.any23.extractor.ExtractorDescription;
25  import org.apache.any23.rdf.Any23ValueFactoryWrapper;
26  import org.apache.any23.vocab.DCTerms;
27  import org.apache.any23.extractor.Extractor.TagSoupDOMExtractor;
28  import org.eclipse.rdf4j.model.impl.SimpleValueFactory;
29  import org.w3c.dom.Document;
30  
31  import java.io.IOException;
32  
33  /**
34   * Extracts the value of the <title> element of an HTML or XHTML page.
35   *
36   * @author Richard Cyganiak (richard@cyganiak.de)
37   */
38  public class TitleExtractor implements TagSoupDOMExtractor {
39  
40      private static final DCTerms vDCTERMS = DCTerms.getInstance();
41  
42      @Override
43      public void run(ExtractionParameters extractionParameters, ExtractionContext extractionContext, Document in,
44              ExtractionResult out) throws IOException, ExtractionException {
45          final Any23ValueFactoryWrapperl#Any23ValueFactoryWrapper">Any23ValueFactoryWrapper valueFactory = new Any23ValueFactoryWrapper(SimpleValueFactory.getInstance(),
46                  out, extractionContext.getDefaultLanguage());
47  
48          try {
49              String title = DomUtils.find(in, "/HTML/HEAD/TITLE/text()").trim();
50              if (title != null && (title.length() != 0)) {
51                  out.writeTriple(extractionContext.getDocumentIRI(), vDCTERMS.title, valueFactory.createLiteral(title));
52              }
53          } finally {
54              valueFactory.setIssueReport(null);
55          }
56      }
57  
58      @Override
59      public ExtractorDescription getDescription() {
60          return TitleExtractorFactory.getDescriptionInstance();
61      }
62  
63  }