Package org.htmlcleaner

Examples of org.htmlcleaner.CleanerProperties

1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
      try {
        createHtmlCleanerIfNeeded();

        TagNode node = cleaner.clean(new ByteArrayInputStream(field.getBytes()));

        Document doc = new DomSerializer(new CleanerProperties()).createDOM(node);
        XPath xpa = XPathFactory.newInstance().newXPath();       
       
        NodeList res = (NodeList)xpa.evaluate(script, doc, XPathConstants.NODESET);

        if (0 == res.getLength()) { // No match, just return "", unlike regex we don't want anything if we don't match...
View Full Code Here
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
 
  private void createHtmlCleanerIfNeeded()
  {
    if (null == cleaner) {
      cleaner = new HtmlCleaner();
      CleanerProperties props = cleaner.getProperties();
      props.setAllowHtmlInsideAttributes(true);
      props.setAllowMultiWordAttributes(true);
      props.setRecognizeUnicodeChars(true);
      props.setOmitComments(true);
      props.setTreatUnknownTagsAsContent(false);
      props.setTranslateSpecialEntities(true);
      props.setTransResCharsToNCR(true);
      props.setNamespacesAware(false);
    }   
  }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
  private void init() {
   
    // Initialize HTMLCleaner
    cleaner = new HtmlCleaner();
    CleanerProperties props = cleaner.getProperties();
    props.setAllowHtmlInsideAttributes(true);
    props.setAllowMultiWordAttributes(true);
    props.setRecognizeUnicodeChars(true);
    props.setOmitComments(true);
    props.setNamespacesAware(false);
   
    // Initialize DomSerializer
    domSerializer = new DomSerializer(props);
   
    // Initialize xml parser   
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
    }
  }

  private static String htmlCleaner( String content ) {

    CleanerProperties props = new CleanerProperties();
    props.setUseCdataForScriptAndStyle( false );
    props.setAllowHtmlInsideAttributes( false );
    props.setPruneTags( "style, script" );

    HtmlCleaner cleaner = new HtmlCleaner( props );
    try {
      TagNode node = cleaner.clean( new StringReader( content ) );
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
   
    return res;
  }
 
  public static void processXml(final ContentHandler handler, final String xml) throws IOException {
    final CleanerProperties props = new CleanerProperties();
    
    props.setTranslateSpecialEntities(true);
    props.setTransResCharsToNCR(true);
    props.setOmitComments(true);
    
    final TagNode tagNode = new HtmlCleaner(props).clean(xml);
    final String cleansData = new CompactXmlSerializer(props).getAsString(tagNode);
    
    final SAXParserFactory spf = SAXParserFactory.newInstance();
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
     *
     * @return The root Node of the resulting DOM
     */
    public static Node markupAsDOM(WicketTester tester) throws ParserConfigurationException
    {
        CleanerProperties props = new CleanerProperties();
        props.setNamespacesAware(false);
       
        HtmlCleaner cleaner = new HtmlCleaner(props);
        return new DomSerializer(props, true).createDOM(cleaner.clean(document(tester)));
    }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
58
    private Logger log = LoggerFactory.getLogger(CleanHtmlFunction.class);

    public CleanHtmlFunction() {
        this.cleaner = new HtmlCleaner();
        CleanerProperties p = cleaner.getProperties();
        p.setOmitComments(true);
        p.setTranslateSpecialEntities(true);
        p.setTransResCharsToNCR(true);

        // remove all tags that contain uninteresting content
        p.setPruneTags("style,script,form,object,audio,video");
    }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
58
    private Logger log = LoggerFactory.getLogger(CleanHtmlFunction.class);

    public CleanHtmlFunction() {
        this.cleaner = new HtmlCleaner();
        CleanerProperties p = cleaner.getProperties();
        p.setOmitComments(true);
        p.setTranslateSpecialEntities(true);
        p.setTransResCharsToNCR(true);

        // remove all tags that contain uninteresting content
        p.setPruneTags("style,script,form,object,audio,video");
    }
View Full Code Here
239
240
241
242
243
244
245
246
247
248
249
      throw new IOException(e);
    }

    // Try to convert html to xhtml
    HtmlCleaner cleaner = new HtmlCleaner();
    CleanerProperties xhtmlProperties = cleaner.getProperties();
    TagNode xhtmlNode = cleaner.clean(html);
    if (xhtmlNode == null) {
      logger.warn("Error creating well-formed document from page {}", resource);
      return;
    }
View Full Code Here
TOP

Related Classes of org.htmlcleaner.CleanerProperties

  • at.newmedialab.ldpath.model.functions.CleanHtmlFunction
  • ch.entwine.weblounge.preview.xhtmlrenderer.XhtmlRendererPagePreviewGenerator
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilter
  • com.cubusmail.mail.text.test.HtmlParserTest
  • com.ikanow.infinit.e.harvest.enrichment.custom.UnstructuredAnalysisHarvester
  • com.jeck.microblogging.utils.HtmlUtils
  • com.netfever.site.dynovisz.tools.utils.XmlUtils
  • fiftyfive.wicket.test.WicketTestUtils
  • net.sf.jwan.servlet.util.JwanHtmlFormatter
  • net.traviangui.hostInterface.IOAlly
    • 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.