Package org.cyberneko.html.parsers

Examples of org.cyberneko.html.parsers.DOMFragmentParser

43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
            IOException {
        if (html == null) {
            return null;
        }

        DOMFragmentParser parser = new DOMFragmentParser();

        // フィルターの設定
        ElementRemover remover = new ElementRemover();
        XMLDocumentFilter[] filters = { remover };
        parser.setProperty(
            "http://cyberneko.org/html/properties/filters",
            filters);
        HTMLDocument document = new HTMLDocumentImpl();
        DocumentFragment fragment = document.createDocumentFragment();

        InputSource inputSource = new InputSource(new StringReader(html));
        parser.parse(inputSource, fragment);
        StringWriter writer = new StringWriter();
        OutputFormat format = new OutputFormat();

        format.setOmitXMLDeclaration(true);
        XMLSerializer serializer = new XMLSerializer();
View Full Code Here
133
134
135
136
137
138
139
140
141
142
143
    properties = OutputPropertiesFactory.getDefaultMethodProperties(Method.HTML);
    _HTMLserialiser = SerializerFactory.getSerializer(properties);
    _serializer = _HTMLserialiser;
    // serializer.setOutputStream(output);
    // _parser.setContentHandler(serializer.asContentHandler());
    viewStateParser = new DOMFragmentParser();
    // Set parser features
    try {
      viewStateParser
          .setProperty(
              "http://cyberneko.org/html/properties/names/elems",
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
    // MAIN
    //

    /** Main. */
    public static void main(String[] argv) throws Exception {
        DOMFragmentParser parser = new DOMFragmentParser();
        HTMLDocument document = new HTMLDocumentImpl();
        for (int i = 0; i < argv.length; i++) {
            DocumentFragment fragment = document.createDocumentFragment();
            parser.parse(argv[i], fragment);
            print(fragment, "");
        }
    } // main(String[])
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
40
41
    // MAIN
    //

    /** Main. */
    public static void main(String[] argv) throws Exception {
        DOMFragmentParser parser = new DOMFragmentParser();
        HTMLDocument document = new HTMLDocumentImpl();
        for (int i = 0; i < argv.length; i++) {
            DocumentFragment fragment = document.createDocumentFragment();
            parser.parse(argv[i], fragment);
            print(fragment, "");
        }
    } // main(String[])
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
      return parser.getDocument();
    } else {
      Document htmlDoc = documentProvider.createDocument(null, null, null);
      // Workaround for error check failure adding text node to entity ref as a child
      htmlDoc.setStrictErrorChecking(false);
      DOMFragmentParser parser = new DOMFragmentParser();
      parser.setProperty("http://cyberneko.org/html/properties/names/elems", "default");
      parser.setFeature("http://cyberneko.org/html/features/document-fragment", true);
      parser.setProperty("http://cyberneko.org/html/properties/names/attrs", "no-change");
      parser.setFeature("http://apache.org/xml/features/scanner/notify-char-refs", true);
      parser.setFeature("http://cyberneko.org/html/features/scanner/notify-builtin-refs", true);
      DocumentFragment fragment = htmlDoc.createDocumentFragment();
      parser.parse(input, fragment);
      normalizeFragment(htmlDoc, fragment);
      return htmlDoc;
    }
  }
View Full Code Here
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
    reader.parse(input);
    return frag;
  }

  private DocumentFragment parseNeko(InputSource input) throws Exception {
    DOMFragmentParser parser = new DOMFragmentParser();
    try {
      parser.setFeature("http://cyberneko.org/html/features/augmentations",
          true);
      parser.setProperty("http://cyberneko.org/html/properties/default-encoding",
          defaultCharEncoding);
      parser.setFeature("http://cyberneko.org/html/features/scanner/ignore-specified-charset",
          true);
      parser.setFeature("http://cyberneko.org/html/features/balance-tags/ignore-outside-content",
          false);
      parser.setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment",
          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.");
        }
        res.appendChild(frag);
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
      throw new RuntimeException(e);
    }
  }

  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!")) {
        throw new FileNotFoundException(scriptUrl);
      }
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
    // OutputPropertiesFactory.getDefaultMethodProperties(Method.XML);
    // properties.put("encoding",_encoding);
    _serializer = SerializerFactory.getSerializer(properties);
    // serializer.setOutputStream(output);
    // _parser.setContentHandler(serializer.asContentHandler());
    viewStateParser = new DOMFragmentParser();
    // Set parser features
    try {
      viewStateParser
          .setProperty(
              "http://cyberneko.org/html/properties/names/elems",
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
    properties = OutputPropertiesFactory.getDefaultMethodProperties(Method.HTML);
    _HTMLserialiser = SerializerFactory.getSerializer(properties);
    _serializer = _HTMLserialiser;
    // serializer.setOutputStream(output);
    // _parser.setContentHandler(serializer.asContentHandler());
    viewStateParser = new DOMFragmentParser();
    // Set parser features
    try {
      viewStateParser
          .setProperty(
              "http://cyberneko.org/html/properties/names/elems",
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
  private static void setup() throws Exception {
    conf = NutchConfiguration.create();
    conf.setBoolean("parser.html.form.use_action", true);
    utils = new DOMContentUtils(conf);
    DOMFragmentParser parser = new DOMFragmentParser();
    for (int i = 0; i < testPages.length; i++) {
      DocumentFragment node = new HTMLDocumentImpl().createDocumentFragment();
      try {
        parser.parse(
            new InputSource(new ByteArrayInputStream(testPages[i].getBytes())),
            node);
        testBaseHrefURLs[i] = new URL(testBaseHrefs[i]);
      } catch (Exception e) {
        assertTrue("caught exception: " + e, false);
View Full Code Here
TOP

Related Classes of org.cyberneko.html.parsers.DOMFragmentParser

  • org.ajax4jsf.webapp.nekko.NekkoParser
  • org.apache.kato.anttasks.xmlgen.XMLWriter
  • org.apache.myfaces.tobago.example.test.SeleniumScript
  • org.apache.nutch.parse.html.HtmlParser
  • org.apache.nutch.tika.TestDOMContentUtils
  • org.apache.nutch.tika.TestRobotsMetaProcessor
  • org.apache.shindig.gadgets.parse.nekohtml.NekoHtmlParser
  • org.apache.xerces.util.ErrorHandlerWrapper
  • org.apache.xerces.xni.parser.XMLErrorHandler
  • org.apache.xerces.xni.parser.XMLInputSource
    • 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.