Repository: any23 Updated Branches: refs/heads/master f88cc51f3 -> 93c38a69e
ANY23-226 Extract JSON-LD embedded in HTML Project: http://git-wip-us.apache.org/repos/asf/any23/repo Commit: http://git-wip-us.apache.org/repos/asf/any23/commit/1e3eb9c3 Tree: http://git-wip-us.apache.org/repos/asf/any23/tree/1e3eb9c3 Diff: http://git-wip-us.apache.org/repos/asf/any23/diff/1e3eb9c3 Branch: refs/heads/master Commit: 1e3eb9c31af2f93906eee1081179d73c30a0881b Parents: f88cc51 Author: Lewis John McGibbney <[email protected]> Authored: Fri Mar 20 10:55:29 2015 -0500 Committer: Lewis John McGibbney <[email protected]> Committed: Fri Mar 20 10:55:29 2015 -0500 ---------------------------------------------------------------------- .../apache/any23/extractor/html/DomUtils.java | 70 ++++++ .../extractor/html/EmbeddedJSONLDExtractor.java | 242 +++++++++++++++++++ .../html/EmbeddedJSONLDExtractorFactory.java | 58 +++++ .../any23/extractor/rdf/BaseRDFExtractor.java | 3 +- .../extractor/html/example-embedded-jsonld.html | 34 +++ .../apache/any23/prefixes/prefixes.properties | 1 + .../html/EmbeddedJSONLDExtractorTest.java | 50 ++++ .../java/org/apache/any23/plugin/PluginIT.java | 2 +- .../html/html-embedded-jsonld-extractor.html | 34 +++ 9 files changed, 492 insertions(+), 2 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/main/java/org/apache/any23/extractor/html/DomUtils.java ---------------------------------------------------------------------- diff --git a/core/src/main/java/org/apache/any23/extractor/html/DomUtils.java b/core/src/main/java/org/apache/any23/extractor/html/DomUtils.java index 0fd8cdc..be27fda 100644 --- a/core/src/main/java/org/apache/any23/extractor/html/DomUtils.java +++ b/core/src/main/java/org/apache/any23/extractor/html/DomUtils.java @@ -17,6 +17,7 @@ package org.apache.any23.extractor.html; +import org.w3c.dom.Document; import org.w3c.dom.NamedNodeMap; import org.w3c.dom.Node; import org.w3c.dom.NodeList; @@ -25,17 +26,25 @@ import org.w3c.dom.traversal.NodeFilter; import org.w3c.dom.traversal.NodeIterator; import javax.xml.transform.OutputKeys; +import javax.xml.transform.Result; import javax.xml.transform.Transformer; +import javax.xml.transform.TransformerConfigurationException; import javax.xml.transform.TransformerException; import javax.xml.transform.TransformerFactory; +import javax.xml.transform.TransformerFactoryConfigurationError; import javax.xml.transform.dom.DOMSource; import javax.xml.transform.stream.StreamResult; import javax.xml.xpath.XPath; import javax.xml.xpath.XPathConstants; import javax.xml.xpath.XPathExpressionException; import javax.xml.xpath.XPathFactory; + +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; import java.io.IOException; +import java.io.InputStream; import java.io.StringWriter; +import java.io.UnsupportedEncodingException; import java.util.ArrayList; import java.util.List; import java.util.regex.Pattern; @@ -459,5 +468,66 @@ public class DomUtils { return result; } + + /** + * Given a {@link org.w3c.dom.Document} this method will return an + * input stream representing that document. + * @param doc the input {@link org.w3c.dom.Document} + * @return an {@link java.io.InputStream} + */ + public static InputStream documentToInputStream(Document doc) { + DOMSource source = new DOMSource(doc); + StringWriter xmlAsWriter = new StringWriter(); + StreamResult result = new StreamResult(xmlAsWriter); + try { + TransformerFactory.newInstance().newTransformer().transform(source, result); + } catch (TransformerConfigurationException e) { + throw new RuntimeException("Error within Document to InputStream transformation configuration!"); + } catch (TransformerException e) { + throw new RuntimeException("Error whilst transforming the Document to InputStream!"); + } catch (TransformerFactoryConfigurationError e) { + throw new RuntimeException("Error within Document to InputStream transformation configuration!"); + } + + InputStream is = null; + try { + is = new ByteArrayInputStream(xmlAsWriter.toString().getBytes("UTF-8")); + } catch (UnsupportedEncodingException e) { + e.printStackTrace(); + } + return is; + } + + + /** + * Convert a w3c dom node to a InputStream + * @param node + * @return + * @throws TransformerException + */ + public static InputStream nodeToInputStream(Node node) { + ByteArrayOutputStream outputStream = new ByteArrayOutputStream(); + Result outputTarget = new StreamResult(outputStream); + Transformer t = null; + try { + t = TransformerFactory.newInstance().newTransformer(); + } catch (TransformerConfigurationException e) { + // TODO Auto-generated catch block + e.printStackTrace(); + } catch (TransformerFactoryConfigurationError e) { + // TODO Auto-generated catch block + e.printStackTrace(); + } + t.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes"); + try { + t.transform(new DOMSource(node), outputTarget); + } catch (TransformerException e) { + // TODO Auto-generated catch block + e.printStackTrace(); + } + return new ByteArrayInputStream(outputStream.toByteArray()); + } + + } http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractor.java ---------------------------------------------------------------------- diff --git a/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractor.java b/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractor.java new file mode 100644 index 0000000..5506a10 --- /dev/null +++ b/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractor.java @@ -0,0 +1,242 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.any23.extractor.html; + +import org.apache.any23.extractor.ExtractionContext; +import org.apache.any23.extractor.ExtractionException; +import org.apache.any23.extractor.ExtractionParameters; +import org.apache.any23.extractor.ExtractionResult; +import org.apache.any23.extractor.Extractor; +import org.apache.any23.extractor.ExtractorDescription; +import org.apache.any23.extractor.rdf.JSONLDExtractor; +import org.apache.any23.extractor.rdf.JSONLDExtractorFactory; +import org.apache.any23.rdf.RDFUtils; +import org.apache.any23.vocab.SINDICE; +import org.openrdf.model.URI; +import org.openrdf.model.impl.LiteralImpl; +import org.openrdf.model.impl.URIImpl; +import org.w3c.dom.Document; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Node; + +import java.io.IOException; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Set; + +/** + * This extractor represents the HTML script tags used to embed blocks of data in documents. + * This way, JSON-LD content can be easily embedded in HTML by placing it in a script element + * with the type attribute set to application/ld+json + * according the <a href="http://www.w3.org/TR/json-ld/#embedding-json-ld-in-html-documents";>JSON-LD specification</a>. + * + */ +public class EmbeddedJSONLDExtractor implements Extractor.TagSoupDOMExtractor { + + private static final SINDICE vSINDICE = SINDICE.getInstance(); + + private URI profile; + + private Map<String, URI> prefixes = new HashMap<String, URI>(); + + private String documentLang; + + private JSONLDExtractor extractor; + + /** + * {@inheritDoc} + */ + @Override + public void run( + ExtractionParameters extractionParameters, + ExtractionContext extractionContext, + Document in, + ExtractionResult out + ) throws IOException, ExtractionException { + profile = extractProfile(in); + documentLang = getDocumentLanguage(in); + extractLinkDefinedPrefixes(in); + + String baseProfile = vSINDICE.NS; + if(profile != null) { + baseProfile = profile.toString(); + } + + final URI documentURI = extractionContext.getDocumentURI(); + Set<JSONLDScript> jsonldScripts = extractJSONLDScript(in, baseProfile, extractionParameters, extractionContext, out); + for(JSONLDScript jsonldScript : jsonldScripts) { + String lang = documentLang; + if(jsonldScript.getLang() != null) { + lang = jsonldScript.getLang(); + } + out.writeTriple( + documentURI, + jsonldScript.getName(), + new LiteralImpl(jsonldScript.getContent(), lang) + ); + } + } + + /** + * Returns the {@link Document} language if declared, <code>null</code> otherwise. + * + * @param in a instance of {@link Document}. + * @return the language declared, could be <code>null</code>. + */ + private String getDocumentLanguage(Document in) { + String lang = DomUtils.find(in, "string(/HTML/@lang)"); + if (lang.equals("")) { + return null; + } + return lang; + } + + private URI extractProfile(Document in) { + String profile = DomUtils.find(in, "string(/HTML/@profile)"); + if (profile.equals("")) { + return null; + } + return new URIImpl(profile); + } + + /** + * It extracts prefixes defined in the <i>LINK</i> meta tags. + * + * @param in + */ + private void extractLinkDefinedPrefixes(Document in) { + List<Node> linkNodes = DomUtils.findAll(in, "/HTML/HEAD/LINK"); + for(Node linkNode : linkNodes) { + NamedNodeMap attributes = linkNode.getAttributes(); + String rel = attributes.getNamedItem("rel").getTextContent(); + String href = attributes.getNamedItem("href").getTextContent(); + if(rel != null && href !=null && RDFUtils.isAbsoluteURI(href)) { + prefixes.put(rel, new URIImpl(href)); + } + } + } + + private Set<JSONLDScript> extractJSONLDScript(Document in, String baseProfile, ExtractionParameters extractionParameters, + ExtractionContext extractionContext, ExtractionResult out) throws IOException, ExtractionException { + List<Node> scriptNodes = DomUtils.findAll(in, "/HTML/HEAD/SCRIPT"); + Set<JSONLDScript> result = new HashSet<JSONLDScript>(); + extractor = new JSONLDExtractorFactory().createExtractor(); + for (Node jsonldNode : scriptNodes) { + NamedNodeMap attributes = jsonldNode.getAttributes(); + for (int i = 0; i < attributes.getLength(); i++) { + if (attributes.item(i).getTextContent().equalsIgnoreCase("application/ld+json")) { + extractor.run(extractionParameters, extractionContext, DomUtils.nodeToInputStream(jsonldNode), out); + } + } + Node nameAttribute = attributes.getNamedItem("name"); + Node contentAttribute = attributes.getNamedItem("content"); + if (nameAttribute == null || contentAttribute == null) { + continue; + } + String name = nameAttribute.getTextContent(); + String content = contentAttribute.getTextContent(); + String xpath = DomUtils.getXPathForNode(jsonldNode); + URI nameAsURI = getPrefixIfExists(name); + if (nameAsURI == null) { + nameAsURI = new URIImpl(baseProfile + name); + } + JSONLDScript jsonldScript = new JSONLDScript(xpath, nameAsURI, content); + result.add(jsonldScript); + } + return result; + } + + private URI getPrefixIfExists(String name) { + String[] split = name.split("\\."); + if(split.length == 2 && prefixes.containsKey(split[0])) { + return new URIImpl(prefixes.get(split[0]) + split[1]); + } + return null; + } + + @Override + public ExtractorDescription getDescription() { + return HTMLMetaExtractorFactory.getDescriptionInstance(); + } + + private class JSONLDScript { + + private String xpath; + + private URI name; + + private String lang; + + private String content; + + public JSONLDScript(String xpath, URI name, String content) { + this.xpath = xpath; + this.name = name; + this.content = content; + } + + public JSONLDScript(String xpath, URI name, String content, String lang) { + this(xpath, name, content); + this.lang = lang; + } + + public URI getName() { + return name; + } + + public void setName(URI name) { + this.name = name; + } + + public String getLang() { + return lang; + } + + public void setLang(String lang) { + this.lang = lang; + } + + public String getContent() { + return content; + } + + public void setContent(String content) { + this.content = content; + } + + @Override + public boolean equals(Object o) { + if (this == o) return true; + if (o == null || getClass() != o.getClass()) return false; + + JSONLDScript meta = (JSONLDScript) o; + + if (xpath != null ? !xpath.equals(meta.xpath) : meta.xpath != null) return false; + + return true; + } + + @Override + public int hashCode() { + return xpath != null ? xpath.hashCode() : 0; + } + } + +} http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorFactory.java ---------------------------------------------------------------------- diff --git a/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorFactory.java b/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorFactory.java new file mode 100644 index 0000000..2e7810f --- /dev/null +++ b/core/src/main/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorFactory.java @@ -0,0 +1,58 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.any23.extractor.html; + +import java.util.Arrays; + +import org.apache.any23.extractor.ExtractorDescription; +import org.apache.any23.extractor.ExtractorFactory; +import org.apache.any23.extractor.SimpleExtractorFactory; +import org.apache.any23.rdf.PopularPrefixes; +import org.apache.any23.rdf.Prefixes; +import org.kohsuke.MetaInfServices; + +/** + * + */ +@MetaInfServices(ExtractorFactory.class) +public class EmbeddedJSONLDExtractorFactory extends SimpleExtractorFactory<EmbeddedJSONLDExtractor> implements + ExtractorFactory<EmbeddedJSONLDExtractor> { + + public static final String NAME = "html-embedded-jsonld"; + + public static final Prefixes PREFIXES = PopularPrefixes.createSubset("jsonld"); + + private static final ExtractorDescription descriptionInstance = new EmbeddedJSONLDExtractorFactory(); + + public EmbeddedJSONLDExtractorFactory() { + super( + EmbeddedJSONLDExtractorFactory.NAME, + EmbeddedJSONLDExtractorFactory.PREFIXES, + Arrays.asList("text/html;q=0.02", "application/xhtml+xml;q=0.02"), + "example-embedded-jsonld.html"); + } + + @Override + public EmbeddedJSONLDExtractor createExtractor() { + return new EmbeddedJSONLDExtractor(); + } + + public static ExtractorDescription getDescriptionInstance() { + return descriptionInstance; + } +} http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/main/java/org/apache/any23/extractor/rdf/BaseRDFExtractor.java ---------------------------------------------------------------------- diff --git a/core/src/main/java/org/apache/any23/extractor/rdf/BaseRDFExtractor.java b/core/src/main/java/org/apache/any23/extractor/rdf/BaseRDFExtractor.java index d26f762..052bfa9 100644 --- a/core/src/main/java/org/apache/any23/extractor/rdf/BaseRDFExtractor.java +++ b/core/src/main/java/org/apache/any23/extractor/rdf/BaseRDFExtractor.java @@ -100,7 +100,8 @@ public abstract class BaseRDFExtractor implements Extractor.ContentExtractor { parser.getParserConfig().addNonFatalError(BasicParserSettings.VERIFY_DATATYPE_VALUES); parser.getParserConfig().set(BasicParserSettings.NORMALIZE_DATATYPE_VALUES, false); parser.getParserConfig().addNonFatalError(BasicParserSettings.NORMALIZE_DATATYPE_VALUES); - + //ByteBuffer seems to represent incorrect content. Need to make sure it is the content + //of the <script> node and not anything else! parser.parse(in, extractionContext.getDocumentURI().stringValue()); } catch (RDFHandlerException ex) { throw new IllegalStateException("Unexpected exception.", ex); http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/main/resources/org/apache/any23/extractor/html/example-embedded-jsonld.html ---------------------------------------------------------------------- diff --git a/core/src/main/resources/org/apache/any23/extractor/html/example-embedded-jsonld.html b/core/src/main/resources/org/apache/any23/extractor/html/example-embedded-jsonld.html new file mode 100644 index 0000000..09859ff --- /dev/null +++ b/core/src/main/resources/org/apache/any23/extractor/html/example-embedded-jsonld.html @@ -0,0 +1,34 @@ +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> +<html> + <head> + <title>Hello World!</title> + <meta name="title" content="Embedded JSONLD extractor"/> + <!-- As per spec in http://www.w3.org/TR/json-ld/#embedding-json-ld-in-html-documents --> + <script type="application/ld+json"> + { + "@context": "http://json-ld.org/contexts/person.jsonld";, + "@id": "http://dbpedia.org/resource/Robert_Millar";, + "name": "Robert Millar", + "born": "1958-09-13", + "birthPlace": "http://dbpedia.org/resource/Glasgow"; + } + </script> + </head> + <h1>Embedded JSONLD Extractor</h1> + <p>It extracts only the embedded JSON-LD elements. +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/main/resources/org/apache/any23/prefixes/prefixes.properties ---------------------------------------------------------------------- diff --git a/core/src/main/resources/org/apache/any23/prefixes/prefixes.properties b/core/src/main/resources/org/apache/any23/prefixes/prefixes.properties index 1151056..58516ec 100644 --- a/core/src/main/resources/org/apache/any23/prefixes/prefixes.properties +++ b/core/src/main/resources/org/apache/any23/prefixes/prefixes.properties @@ -35,3 +35,4 @@ hrecipe=http://sindice.com/hrecipe/ sindice=http://vocab.sindice.net/ og=http://opengraphprotocol.org/schema/ fb=http://www.facebook.com/2008/fbml# +jsonld=http://www.w3.org/ns/json-ld# http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/core/src/test/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorTest.java ---------------------------------------------------------------------- diff --git a/core/src/test/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorTest.java b/core/src/test/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorTest.java new file mode 100644 index 0000000..b30840c --- /dev/null +++ b/core/src/test/java/org/apache/any23/extractor/html/EmbeddedJSONLDExtractorTest.java @@ -0,0 +1,50 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.any23.extractor.html; + +import static org.junit.Assert.*; + +import org.apache.any23.extractor.ExtractorFactory; +import org.junit.Test; +import org.openrdf.repository.RepositoryException; + +/** + * @author lmcgibbn + * + */ +public class EmbeddedJSONLDExtractorTest extends AbstractExtractorTestCase { + + @Test + public void testEmbeddedJSONLDInHead() throws RepositoryException { + assertExtract("/html/html-embedded-jsonld-extractor.html"); + assertModelNotEmpty(); + assertStatementsSize(null, null, null, 7); + } + + @Test + public void testSeveralEmbeddedJSONLDInHead() throws RepositoryException { + assertExtract("/html/html-embedded-jsonld-extractor.html"); + assertModelNotEmpty(); + assertStatementsSize(null, null, null, 7); + } + + @Override + protected ExtractorFactory<?> getExtractorFactory() { + return new EmbeddedJSONLDExtractorFactory(); + } + +} http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/plugins/integration-test/src/test/java/org/apache/any23/plugin/PluginIT.java ---------------------------------------------------------------------- diff --git a/plugins/integration-test/src/test/java/org/apache/any23/plugin/PluginIT.java b/plugins/integration-test/src/test/java/org/apache/any23/plugin/PluginIT.java index cbb9c32..a3e5675 100644 --- a/plugins/integration-test/src/test/java/org/apache/any23/plugin/PluginIT.java +++ b/plugins/integration-test/src/test/java/org/apache/any23/plugin/PluginIT.java @@ -41,7 +41,7 @@ import static org.junit.Assert.assertTrue; */ public class PluginIT { - private static final int NUM_OF_EXTRACTORS = 30; + private static final int NUM_OF_EXTRACTORS = 31; private static final String PLUGIN_DIR = "target/plugins-build/"; http://git-wip-us.apache.org/repos/asf/any23/blob/1e3eb9c3/test-resources/src/test/resources/html/html-embedded-jsonld-extractor.html ---------------------------------------------------------------------- diff --git a/test-resources/src/test/resources/html/html-embedded-jsonld-extractor.html b/test-resources/src/test/resources/html/html-embedded-jsonld-extractor.html new file mode 100644 index 0000000..09859ff --- /dev/null +++ b/test-resources/src/test/resources/html/html-embedded-jsonld-extractor.html @@ -0,0 +1,34 @@ +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> +<html> + <head> + <title>Hello World!</title> + <meta name="title" content="Embedded JSONLD extractor"/> + <!-- As per spec in http://www.w3.org/TR/json-ld/#embedding-json-ld-in-html-documents --> + <script type="application/ld+json"> + { + "@context": "http://json-ld.org/contexts/person.jsonld";, + "@id": "http://dbpedia.org/resource/Robert_Millar";, + "name": "Robert Millar", + "born": "1958-09-13", + "birthPlace": "http://dbpedia.org/resource/Glasgow"; + } + </script> + </head> + <h1>Embedded JSONLD Extractor</h1> + <p>It extracts only the embedded JSON-LD elements. +</html> \ No newline at end of file
