Package org.apache.html.dom

Examples of org.apache.html.dom.HTMLDocumentImpl

104
105
106
107
108
109
110
111
112
113
114
115
116
    LOG.debug("Using Tika parser " + parser.getClass().getName() + " for mime-type "
        + mimeType);

    Metadata tikamd = new Metadata();

    HTMLDocumentImpl doc = new HTMLDocumentImpl();
    doc.setErrorChecking(false);
    DocumentFragment root = doc.createDocumentFragment();
    DOMBuilder domhandler = new DOMBuilder(doc, root);
    ParseContext context = new ParseContext();
    // to add once available in Tika
    // context.set(HtmlMapper.class, IdentityHtmlMapper.INSTANCE);
    try {
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
248
      return parseTagSoup(input);
    else return parseNeko(input);
  }

  private DocumentFragment parseTagSoup(InputSource input) throws Exception {
    HTMLDocumentImpl doc = new HTMLDocumentImpl();
    DocumentFragment frag = doc.createDocumentFragment();
    DOMBuilder builder = new DOMBuilder(doc, frag);
    org.ccil.cowan.tagsoup.Parser reader = new org.ccil.cowan.tagsoup.Parser();
    reader.setContentHandler(builder);
    reader.setFeature(org.ccil.cowan.tagsoup.Parser.ignoreBogonsFeature, true);
    reader.setFeature(org.ccil.cowan.tagsoup.Parser.bogonsEmptyFeature, false);
View Full Code Here
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
          true);
      parser.setFeature("http://cyberneko.org/html/features/report-errors",
          LOG.isTraceEnabled());
    } catch (SAXException e) {}
    // convert Document to DocumentFragment
    HTMLDocumentImpl doc = new HTMLDocumentImpl();
    doc.setErrorChecking(false);
    DocumentFragment res = doc.createDocumentFragment();
    DocumentFragment frag = doc.createDocumentFragment();
    parser.parse(input, frag);
    res.appendChild(frag);

    try {
      while(true) {
        frag = doc.createDocumentFragment();
        parser.parse(input, frag);
        if (!frag.hasChildNodes()) break;
        if (LOG.isInfoEnabled()) {
          LOG.info(" - new frag, " + frag.getChildNodes().getLength() + " nodes.");
        }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
    }
  }

  public SeleniumScript(String scriptUrl, String url) throws IOException, SAXException, XPathExpressionException {
    DOMFragmentParser parser = new DOMFragmentParser();
    HTMLDocument document = new HTMLDocumentImpl();
    DocumentFragment fragment = document.createDocumentFragment();
    try {
      parser.parse(scriptUrl, fragment);
      // not nice, it seems that parse also throws a FileNotFoundException sometimes.
      // XXX I don't know why
      if (fragment.getTextContent().contains("The page was not found!")) {
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
            throws DiscoveryException
    {
        if (DEBUG)
            _log.debug("Parsing HTML data:\n" + htmlData);

        HTMLDocumentImpl doc = this.parseDocument(htmlData);

        NodeList heads = doc.getElementsByTagName("head");
        if (heads.getLength() != 1)
            throw new DiscoveryException(
                    "HTML response must have exactly one HEAD element, "
                            + "found " + heads.getLength() + " : "
                            + heads.toString(),
                    OpenIDException.DISCOVERY_HTML_PARSE_ERROR);

        HTMLHeadElement head = (HTMLHeadElement) doc.getHead();
        NodeList linkElements = head.getElementsByTagName("LINK");
        for (int i = 0, len = linkElements.getLength(); i < len; i++)
        {
            HTMLLinkElement linkElement = (HTMLLinkElement) linkElements.item(i);
            setResult(linkElement.getRel(), linkElement.getHref(), result);
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
     */
    public String getHtmlMeta(String input) throws YadisException
    {
        String xrdsLocation = null;

        HTMLDocumentImpl doc = this.parseDocument(input);
        if (DEBUG)
        {
            try
            {
                _log.debug("document:\n" + OpenID4JavaDOMParser.toXmlString(doc));
            } catch (TransformerException e)
            {
                _log.debug("An exception occurs while transforming the document to string in debugging.", e);
            }
        }

        NodeList heads = doc.getElementsByTagName("head");
        if (heads.getLength() != 1)
            throw new YadisException(
                    "HTML response must have exactly one HEAD element, "
                            + "found " + heads.getLength() + " : "
                            + heads.toString(),
                    OpenIDException.YADIS_HTMLMETA_INVALID_RESPONSE);

        HTMLHeadElement head = (HTMLHeadElement) doc.getHead();
        NodeList metaElements = head.getElementsByTagName("META");
        if (metaElements == null || metaElements.getLength() == 0)
        {
            if (DEBUG)
                _log.debug("No <meta> element found under <html><head>. " +
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
          .newInstance();
      // Create Document Builder
      DocumentBuilder docBuilder = docFactory.newDocumentBuilder();
      viewStateDocument = docBuilder.newDocument();
    } catch (ParserConfigurationException e) {
      viewStateDocument = new HTMLDocumentImpl();
      _log
          .error(
              "Error on create DOM Document by JAXP, use Xerxes implementation. Check JAXP configuration ",
              e);
    }
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
          .newInstance();
      // Create Document Builder
      DocumentBuilder docBuilder = docFactory.newDocumentBuilder();
      viewStateDocument = docBuilder.newDocument();
    } catch (ParserConfigurationException e) {
      viewStateDocument = new HTMLDocumentImpl();
      _log
          .error(
              "Error on create DOM Document by JAXP, use Xerxes implementation. Check JAXP configuration ",
              e);
    }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
    LOG.debug("Using Tika parser " + parser.getClass().getName() + " for mime-type "
        + mimeType);

    Metadata tikamd = new Metadata();

    HTMLDocumentImpl doc = new HTMLDocumentImpl();
    doc.setErrorChecking(false);
    DocumentFragment root = doc.createDocumentFragment();
    DOMBuilder domhandler = new DOMBuilder(doc, root);
    ParseContext context = new ParseContext();
    // to add once available in Tika
    // context.set(HtmlMapper.class, IdentityHtmlMapper.INSTANCE);
    try {
View Full Code Here
211
212
213
214
215
216
217
218
219
220
221
222
223
    tikaParser.setConf(conf);
    Parser parser = tikaParser.getTikaConfig().getParser("text/html");
    for (int i = 0; i < testPages.length; i++) {
      Metadata tikamd = new Metadata();

      HTMLDocumentImpl doc = new HTMLDocumentImpl();
      doc.setErrorChecking(false);
      DocumentFragment root = doc.createDocumentFragment();
      DOMBuilder domhandler = new DOMBuilder(doc, root);
      ParseContext context = new ParseContext();
      // to add once available in Tika
      //context.set(HtmlMapper.class, IdentityHtmlMapper.INSTANCE);
      try {
View Full Code Here
TOP

Related Classes of org.apache.html.dom.HTMLDocumentImpl

  • org.ajax4jsf.webapp.nekko.NekkoParser
  • org.apache.myfaces.tobago.example.test.SeleniumScript
  • org.apache.nutch.parse.html.HtmlParser
  • org.apache.nutch.parse.tika.DOMContentUtilsTest
  • org.apache.nutch.parse.tika.TikaParser
  • org.apache.xerces.dom.NodeImpl
  • org.cyberneko.html.DOMFragmentParserTest
  • org.openid4java.discovery.html.CyberNekoDOMHtmlParser
  • org.openid4java.discovery.yadis.CyberNekoDOMYadisHtmlParser
  • org.ryu22e.nico2cal.util.HtmlRemoveUtil
    • 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.