Package org.htmlcleaner

Examples of org.htmlcleaner.HtmlCleaner$OpenTags

159
160
161
162
163
164
165
166
167
168
169
170
171
    props.setTranslateSpecialEntities(true);
    props.setTransResCharsToNCR(true);
    props.setTransSpecialEntitiesToNCR(true);
    props.setOmitComments(true);
     
    HtmlCleaner cleaner = new HtmlCleaner(props);

    TagNode node = cleaner.clean(new URL(lien));
   
    for (Object o : node.evaluateXPath("//div[@id='retour_accueil']/a/img"))
    {
      //System.out.println(((TagNode)(o)).getAllChildren());
      lien_logo = ((TagNode)(o)).getAttributeByName("src");
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
214
215
216
    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));
   
    for (Object o : node.evaluateXPath("//div[@class='encadre_fiche firstencadre']/div/div/a"))
    {
      lien_site_spe = ((TagNode)(o)).getAttributeByName("href");
      //System.out.println("lien spe "+lien_site_spe);
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
  }
 
 
  public boolean recherche(String mot, String lien) throws MalformedURLException, IOException, XPatherException
  {
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode node = cleaner.clean(new URL(lien));
    boolean bool = false;

    String[] decoupage = mot.split(" ");
    if(decoupage.length == 1)
    {
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
    }
    return new Template(mapping);
  }
 
  private static HtmlCleaner getCleaner() {
    HtmlCleaner cleaner = new HtmlCleaner();
    cleaner.getProperties().setTranslateSpecialEntities(false);
    cleaner.getProperties().setRecognizeUnicodeChars(false);
    cleaner.getProperties().setUseEmptyElementTags(false);
    return cleaner;
  }
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
    return getError(response);
  }
 
  private static String getError(String response) throws IOException{
    String error = null;
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode html = cleaner.clean(response);
    TagNode errortag = html.findElementByAttValue("id", "error", true, true);
    if (errortag != null){
      error = errortag.getAttributeByName("title");
    }
    return error;
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
    private CleanerProperties parserProps;
    private DomSerializer2 domCreator;


    public HtmlParser() {
        this.htmlToXmlParser = new HtmlCleaner();
        this.parserProps = this.htmlToXmlParser.getProperties();
        this.parserProps.setRecognizeUnicodeChars(true);
        this.parserProps.setUseEmptyElementTags(true);
        this.parserProps.setAdvancedXmlEscape(true);
        this.parserProps.setTranslateSpecialEntities(true);
View Full Code Here
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
      String charset = get.getRequestCharSet();

      //
      // Check for charset overrides in the HTML start page
      //
      HtmlCleaner cleaner = new HtmlCleaner();
      TagNode httpEquivNode = cleaner.clean(get.getResponseBodyAsStream()).findElementByAttValue("http-equiv", "content-type", true, false);
      if (httpEquivNode != null && httpEquivNode.hasAttribute("content")){
        String value = httpEquivNode.getAttributeByName("content");
        int offset = value.indexOf("charset=");
        if (offset >= -1){
            charset = value.substring(offset+8).toUpperCase();
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
    }

    @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) {
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
152
    @Override
    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) {
View Full Code Here
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
    @Ignore("take long time")
    @Test
    public void parserPerformanceTest() throws XPatherException {
        System.out.println(html.length());

        HtmlCleaner htmlCleaner = new HtmlCleaner();
        TagNode tagNode = htmlCleaner.clean(html);
        Document document = Jsoup.parse(html);

        long time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            htmlCleaner.clean(html);
        }
        System.out.println(System.currentTimeMillis()-time);

        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            tagNode.evaluateXPath("//a");
        }
        System.out.println(System.currentTimeMillis()-time);

        System.out.println("=============");

        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            Jsoup.parse(html);
        }
        System.out.println(System.currentTimeMillis()-time);

        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            document.select("a");
        }
        System.out.println(System.currentTimeMillis()-time);

        System.out.println("=============");

        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
            htmlCleaner.clean(html);
        }
        System.out.println(System.currentTimeMillis()-time);

        time =System.currentTimeMillis();
        for (int i = 0; i < 2000; i++) {
View Full Code Here
TOP

Related Classes of org.htmlcleaner.HtmlCleaner$OpenTags

  • at.newmedialab.ldpath.model.functions.CleanHtmlFunction
  • ch.entwine.weblounge.preview.xhtmlrenderer.XhtmlRendererPagePreviewGenerator
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilter
  • com.cubusmail.mail.text.MessageTextUtil
  • com.cubusmail.mail.text.test.HtmlParserTest
  • com.cubusmail.server.mail.text.MessageTextUtil
  • com.ikanow.infinit.e.harvest.enrichment.custom.UnstructuredAnalysisHarvester
  • com.jeck.microblogging.utils.HtmlUtils
  • com.netfever.site.dynovisz.tools.utils.XmlUtils
  • com.skrul.greasefire.DownloadScripts
    • 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.