Package org.htmlcleaner

Examples of org.htmlcleaner.CleanerProperties

17
18
19
20
21
22
23
24
25
26
27
28
        // 1. get standard map
        // 2. goto (x,y)
//        String page = HttpServer.getHttpServer().getMapPage( coordX, coordY);
       
        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setRecognizeUnicodeChars( true);
        TagNode node = cleaner.clean( new File("tests/karte.htm"));
//        TagNode node = cleaner.clean( page);

        return getSquareUrl2( node);
    }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
        // 1. get overview/innerview pantalla actual
//        String page =  HttpServer.getHttpServer().httpGetPage( url.toString().replace( "&", "&"));
        Thread.sleep( (long) (1000 + 2000*Math.random()));
       
        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setRecognizeUnicodeChars( true);
        TagNode node = cleaner.clean( new File("tests/karte_village.htm"));
//        TagNode node = cleaner.clean( page);

        return getSquareType2( node);

View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
  {   
    FileWriter writer = null;
    writer = new FileWriter("resultats", false);
    String ajout = new String();
     
    CleanerProperties props = new CleanerProperties();
    props.setAdvancedXmlEscape(true);
    props.setTransResCharsToNCR(true);
    props.setTranslateSpecialEntities(true);
    props.setTransSpecialEntitiesToNCR(true);
   
    HtmlCleaner cleaner = new HtmlCleaner(props);
     
    TagNode node = cleaner.clean(new URL(lien));
    //System.out.println("Title: " + ((TagNode)(node.evaluateXPath("//title")[0])).getText());
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
    }
  }
 
  public static void parser_site_spe(String lien) throws MalformedURLException, IOException, XPatherException
  {
    CleanerProperties props = new CleanerProperties();
    props.setTranslateSpecialEntities(true);
    props.setTransResCharsToNCR(true);
    props.setTransSpecialEntitiesToNCR(true);
    props.setOmitComments(true);
     
    HtmlCleaner cleaner = new HtmlCleaner(props);

    TagNode node = cleaner.clean(new URL(lien));
   
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
  public static void parser_final (String lien) throws MalformedURLException, IOException, XPatherException
  {       
    FileWriter writer = null;
    writer = new FileWriter("resultats_final", false);
     
    CleanerProperties props = new CleanerProperties();
    props.setTranslateSpecialEntities(true);
    props.setTransResCharsToNCR(true);
    props.setTransSpecialEntitiesToNCR(true);
    props.setOmitComments(true);
     
    HtmlCleaner cleaner = new HtmlCleaner(props);
     
    int i=0;
    TagNode node = cleaner.clean(new URL(lien));
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
    @Override
    public String select(String text) {
        try {
            HtmlCleaner htmlCleaner = new HtmlCleaner();
            TagNode tagNode = htmlCleaner.clean(text);
            Document document = new DomSerializer(new CleanerProperties()).createDOM(tagNode);
            Object result;
            try {
                result = xPathExpression.evaluate(document, XPathConstants.NODESET);
            } catch (XPathExpressionException e) {
                result = xPathExpression.evaluate(document, XPathConstants.STRING);
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
    public List<String> selectList(String text) {
        List<String> results = new ArrayList<String>();
        try {
            HtmlCleaner htmlCleaner = new HtmlCleaner();
            TagNode tagNode = htmlCleaner.clean(text);
            Document document = new DomSerializer(new CleanerProperties()).createDOM(tagNode);
            Object result;
            try {
                result = xPathExpression.evaluate(document, XPathConstants.NODESET);
            } catch (XPathExpressionException e) {
                result = xPathExpression.evaluate(document, XPathConstants.STRING);
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
  public static final String DEFAULT_HTML_INPUT_ENCODING = "Windows-1251";
 
  public static List<TOCReference> parseHhc(InputStream hhcFile, Resources resources) throws IOException, ParserConfigurationException,  XPathExpressionException {
    HtmlCleaner htmlCleaner = new HtmlCleaner();
    CleanerProperties props = htmlCleaner.getProperties();
    TagNode node = htmlCleaner.clean(hhcFile);
    Document hhcDocument = new DomSerializer(props).createDOM(node);
    XPath xpath = XPathFactory.newInstance().newXPath();
    Node ulNode = (Node) xpath.evaluate("body/ul", hhcDocument
        .getDocumentElement(), XPathConstants.NODE);
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
    this.htmlCleaner = createHtmlCleaner();
  }

  private static HtmlCleaner createHtmlCleaner() {
    HtmlCleaner result = new HtmlCleaner();
    CleanerProperties cleanerProperties = result.getProperties();
    cleanerProperties.setOmitXmlDeclaration(true);
    cleanerProperties.setOmitDoctypeDeclaration(false);
    cleanerProperties.setRecognizeUnicodeChars(true);
    cleanerProperties.setTranslateSpecialEntities(false);
    cleanerProperties.setIgnoreQuestAndExclam(true);
    cleanerProperties.setUseEmptyElementTags(false);
    return result;
  }
View Full Code Here
950
951
952
953
954
955
956
957
958
959
960
         
          TagNode node = cleaner.clean(new ByteArrayInputStream(text.getBytes()));
         
          //NewCode : Only use html cleaner for cleansing
          //use JAXP for full Xpath lib
          Document doc = new DomSerializer(new CleanerProperties()).createDOM(node);
         
 
          String extraRegex = extractRegexFromXpath(xpath);
 
          if (extraRegex != null)
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.