Package bixo.datum

Examples of bixo.datum.Outlink

58
59
60
61
62
63
64
65
66
67
68
    }

    @Override
    public void operate(FlowProcess process, FunctionCall<NullContext> funcCall) {
        ParsedDatum datum = new ParsedDatum(funcCall.getArguments());
        Outlink outlinks[] = datum.getOutlinks();

        // Bump the crawl depth value only on a successful parse
        int crawlDepth = (Integer) datum.getPayloadValue(CrawlDbDatum.CRAWL_DEPTH);
        datum.setPayloadValue(CrawlDbDatum.CRAWL_DEPTH, crawlDepth + 1);
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    @SuppressWarnings("rawtypes")
    @Override
    public void operate(FlowProcess process, FunctionCall<NullContext> funcCall) {
       
        AnalyzedDatum datum = new AnalyzedDatum(funcCall.getArguments().getTuple());
        Outlink outlinks[] = datum.getOutlinks();

        TupleEntryCollector collector = funcCall.getOutputCollector();

        if (outlinks.length > 0) {
            float pageScore = datum.getPageScore();
View Full Code Here
120
121
122
123
124
125
126
127
128
129
130
       
        for (Node node : aNodes) {
            String url = getAttributeFromNode(node, "href");
            String anchor = getAttributeFromNode(node, "name");
            String rel = getAttributeFromNode(node, "rel");
            Outlink link = new Outlink(url, anchor, rel);
            outlinkList.add(link);
        }
   
        return outlinkList.toArray(new Outlink[outlinkList.size()]);
    }
View Full Code Here
143
144
145
146
147
148
149
150
151
    @Override
    public void endElement(String uri, String localName, String name) throws SAXException {
        super.endElement(uri, localName, name);

        if (localName.equalsIgnoreCase(_inAnchorTag)) {
            addLink(new Outlink(_curUrl, _curAnchor.toString(), _curRelAttributes));
            _inAnchorTag = null;
        }
    }
View Full Code Here
TOP

Related Classes of bixo.datum.Outlink

  • bixo.examples.crawl.CreateUrlDatumFromOutlinksFunction
  • bixo.examples.webmining.AnalyzeHtml
  • bixo.examples.webmining.CreateLinkDatumFromOutlinksFunction
  • bixo.parser.BaseLinkExtractor
    • 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.