Package org.htmlcleaner

Examples of org.htmlcleaner.TagNode

96
97
98
99
100
101
102
103
104
    node.serialize(serializer, writer);
    return writer.toString();
  }
 
  private static Set<Node> condense(String document) throws IOException {
    TagNode root = parse(document);
    Collector collector = Traverser.traverse(root, new Collector());
    return new HashSet<Node>(collector.getNodes());
  }
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
103
  }
 
  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
68
69
70
71
72
73
74
75
76
77
 
  /* (non-Javadoc)
   * @see org.apache.wookie.util.html.IHtmlProcessor#injectScript(java.lang.String)
   */
  public void injectScript(String script) {
    TagNode js = new TagNode(SCRIPT_TAG);
    js.addAttribute(TYPE_ATTRIBUTE, TYPE_ATTRIBUTE_VALUE);
    js.addAttribute(SRC_ATTRIBUTE, script);
    headNode.addChild(js);
  }
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
  /* (non-Javadoc)
   * @see org.apache.wookie.util.html.IHtmlProcessor#injectStylesheet(java.lang.String)
   */
  public void injectStylesheet(String stylesheet) {
    TagNode js = new TagNode(LINK_TAG);
    js.addAttribute(TYPE_ATTRIBUTE, CSS_TYPE_ATTRIBUTE_VALUE);
    js.addAttribute(REL_ATTRIBUTE, CSS_REL_ATTRIBUTE_VALUE);
    js.addAttribute(HREF_ATTRIBUTE, stylesheet);
    headNode.addChild(js);
  }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
          if (escapeXml && !specialCase) {
            content = escapeXml(content, props, true);
          }
          element.appendChild( specialCase ? document.createCDATASection(content) : document.createTextNode(content) );
        } else if (item instanceof TagNode) {
          TagNode subTagNode = (TagNode) item;
          Element subelement = document.createElement( subTagNode.getName() );;
         
          setAttributes(subTagNode, subelement);
         
          // recursively create subnodes
          createSubnodes(document, subelement, subTagNode.getChildren());
         
          element.appendChild(subelement);
        } else if (item instanceof List) {
          List sublist = (List) item;
          createSubnodes(document, element, sublist);
View Full Code Here
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
      //
      // 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
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
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
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
1457
1458
1459
1460
1461
1462
    @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++) {
            tagNode.evaluateXPath("//a");
        }
        System.out.println(System.currentTimeMillis()-time);

        System.out.println("=============");
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
  }

  public byte[] processHtml(Resource resource, Book book, String outputEncoding) throws IOException {
   
    // clean html
    TagNode node = htmlCleaner.clean(resource.getReader());

    // post-process cleaned html
    node.setAttribute("xmlns", Constants.NAMESPACE_XHTML);
    node.setDocType(createXHTMLDoctypeToken());
   
    // write result to output
    ByteArrayOutputStream out = new ByteArrayOutputStream();
    Writer writer = new OutputStreamWriter(out, outputEncoding);
    writer = new NoCloseWriter(writer);
View Full Code Here
TOP

Related Classes of org.htmlcleaner.TagNode

  • 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.