Examples of org.apache.any23.http.DefaultHTTPClient

org.apache.any23.source.DocumentSource
Opens an {@link InputStream} on an HTTP URI. Is configuredwith sane values for timeouts, default headers and so on. @author Paolo Capriotti @author Richard Cyganiak (richard@cyganiak.de)

        assumeOnlineAllowed();


        /*1*/ Any23 runner = new Any23();
        /*2*/ runner.setHTTPUserAgent("test-user-agent");
        /*3*/ HTTPClient httpClient = runner.getHTTPClient();
        /*4*/ DocumentSource source = new HTTPDocumentSource(
                 httpClient,
                 "http://dbpedia.org/resource/Trento"
              );
        /*5*/ ByteArrayOutputStream out = new ByteArrayOutputStream();
        /*6*/ TripleHandler handler = new NTriplesWriter(out);

View Full Code Here

        ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
        TripleHandler handler = new RDFXMLWriter(byteArrayOutputStream);
        TripleHandler rdfWriter = new IgnoreAccidentalRDFa(handler);
        ReportingTripleHandler reporting = new ReportingTripleHandler(rdfWriter);


        DocumentSource source = getDocumentSourceFromResource(
                    "/html/rdfa/ansa_2010-02-26_12645863.html",
                    "http://host.com/service");


        Assert.assertTrue( any23.extract(source, reporting).hasMatchingExtractors() );
        try {

View Full Code Here

        assumeOnlineAllowed();


        Any23 runner = new Any23();
        runner.setHTTPUserAgent("test-user-agent");
        HTTPClient httpClient = runner.getHTTPClient();
        DocumentSource source = new HTTPDocumentSource(
                httpClient,
                "http://products.semweb.bestbuy.com/y/products/7590289/"
        );
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        TripleHandler handler = new NTriplesWriter(out);

View Full Code Here


    @Test
    public void testExtractionParameters() throws IOException, ExtractionException, TripleHandlerException {
        final int EXPECTED_TRIPLES  = 6;
        Any23 runner = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/org/apache/any23/validator/missing-og-namespace.html",
                "http://www.test.com"
        );


        ByteArrayOutputStream baos = new ByteArrayOutputStream();

View Full Code Here

    @Test
    public void testExtractionParametersWithNestingDisabled()
    throws IOException, ExtractionException, TripleHandlerException {
        final int EXPECTED_TRIPLES = 19;
        Any23 runner = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/microformats/nested-microformats-a1.html",
                "http://www.test.com"
        );


        ByteArrayOutputStream baos = new ByteArrayOutputStream();

View Full Code Here

    }


    @Test
    public void testExceptionPropagation() throws IOException {
        Any23 any23 = new Any23();
        DocumentSource source = getDocumentSourceFromResource(
                "/application/turtle/geolinkeddata.ttl",
                "http://www.test.com"
        );
        CountingTripleHandler cth1 = new CountingTripleHandler();
        try {

View Full Code Here

    @Test
    public void testXMLMimeTypeManagement() throws IOException, ExtractionException {
        final String documentURI = "http://www.test.com/resource.xml";
        final String contentType = "application/xml";
        final String in = StreamUtils.asString( this.getClass().getResourceAsStream("any23-xml-mimetype.xml") );
        final DocumentSource doc = new StringDocumentSource(in, documentURI, contentType);
        final Any23 any23 = new Any23();
        final CountingTripleHandler cth = new CountingTripleHandler(false);
        final ReportingTripleHandler rth = new ReportingTripleHandler(cth);
        final ExtractionReport report = any23.extract(doc, rth);
        Assert.assertFalse(report.hasMatchingExtractors());

View Full Code Here


    @Test
    public void testAbstractMethodErrorIssue186_1() throws IOException, ExtractionException{
        final Any23 runner = new Any23();
        final String content = FileUtils.readResourceContent("/html/rdfa/rdfa-issue186-1.xhtml");
        final DocumentSource source = new StringDocumentSource(content, "http://base.com");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        runner.extract(source, handler);
        String n3 = out.toString("UTF-8");
        logger.debug(n3);

View Full Code Here


    @Test
    public void testAbstractMethodErrorIssue186_2() throws IOException, ExtractionException{
        final Any23 runner = new Any23();
        final String content = FileUtils.readResourceContent("/html/rdfa/rdfa-issue186-2.xhtml");
        final DocumentSource source = new StringDocumentSource(content, "http://richard.cyganiak.de/");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        runner.extract(source, handler);
        final String n3 = out.toString("UTF-8");
        logger.debug(n3);

View Full Code Here

        final ModifiableConfiguration modifiableConf = DefaultConfiguration.copy();
        modifiableConf.setProperty("any23.extraction.metadata.timesize", "off");
        final Any23 any23 = new Any23(modifiableConf);


        final String content = FileUtils.readResourceContent("/rdf/rdf-issue183.ttl");
        final DocumentSource source = new StringDocumentSource(content, "http://base.com");
        final ByteArrayOutputStream out = new ByteArrayOutputStream();
        final TripleHandler handler = new NTriplesWriter(out);
        any23.extract(source, handler);
        handler.close();
        final String n3 = out.toString("UTF-8");

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.any23.http.DefaultHTTPClient

org.apache.any23.AbstractAny23TestBase

org.apache.any23.Any23

org.apache.any23.Any23Test

org.apache.any23.cli.ExtractorDocumentation

org.apache.any23.cli.MicrodataParser

org.apache.any23.cli.MicrodataParser$MicrodataParserDocumentSourceConverter

org.apache.any23.cli.MimeDetector

org.apache.any23.cli.MimeDetector$MimeDetectorDocumentSourceConverter

org.apache.any23.cli.Rover

org.apache.any23.cli.Tool

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.