1 | |
|
2 | |
|
3 | |
|
4 | |
|
5 | |
|
6 | |
|
7 | |
|
8 | |
|
9 | |
|
10 | |
|
11 | |
|
12 | |
|
13 | |
|
14 | |
|
15 | |
|
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.extractor.ExtractorFactory; |
26 | |
import org.apache.any23.extractor.SimpleExtractorFactory; |
27 | |
import org.apache.any23.rdf.PopularPrefixes; |
28 | |
import org.apache.any23.vocab.XHTML; |
29 | |
import org.apache.any23.extractor.Extractor.TagSoupDOMExtractor; |
30 | |
import org.openrdf.model.URI; |
31 | |
import org.w3c.dom.Document; |
32 | |
import org.w3c.dom.Node; |
33 | |
|
34 | |
import java.io.IOException; |
35 | |
import java.util.Arrays; |
36 | |
|
37 | |
|
38 | |
|
39 | |
|
40 | |
|
41 | |
|
42 | |
|
43 | |
|
44 | |
|
45 | 0 | public class LicenseExtractor implements TagSoupDOMExtractor { |
46 | |
|
47 | 0 | private static final XHTML vXHTML = XHTML.getInstance(); |
48 | |
|
49 | 0 | public final static ExtractorFactory<LicenseExtractor> factory = |
50 | |
SimpleExtractorFactory.create( |
51 | |
"html-mf-license", |
52 | |
PopularPrefixes.createSubset("xhtml"), |
53 | |
Arrays.asList("text/html;q=0.01", "application/xhtml+xml;q=0.01"), |
54 | |
"example-mf-license.html", |
55 | |
LicenseExtractor.class |
56 | |
); |
57 | |
|
58 | |
public void run( |
59 | |
ExtractionParameters extractionParameters, |
60 | |
ExtractionContext extractionContext, |
61 | |
Document in, |
62 | |
ExtractionResult out |
63 | |
) throws IOException, ExtractionException { |
64 | 0 | HTMLDocument document = new HTMLDocument(in); |
65 | 0 | final URI documentURI = extractionContext.getDocumentURI(); |
66 | 0 | for (Node node : DomUtils.findAll(in, "//A[@rel='license']/@href")) { |
67 | 0 | String link = node.getNodeValue(); |
68 | 0 | if ("".equals(link)) { |
69 | 0 | out.notifyError( |
70 | |
ExtractionResult.ErrorLevel.WARN, |
71 | |
String.format( |
72 | |
"Invalid license link detected within document %s.", |
73 | |
documentURI.toString() |
74 | |
), |
75 | |
0, 0 |
76 | |
); |
77 | 0 | continue; |
78 | |
} |
79 | 0 | out.writeTriple(documentURI, vXHTML.license, document.resolveURI(link)); |
80 | 0 | } |
81 | 0 | } |
82 | |
|
83 | |
public ExtractorDescription getDescription() { |
84 | 0 | return factory; |
85 | |
} |
86 | |
|
87 | |
} |