Package org.htmlcleaner

Examples of org.htmlcleaner.TagNode

33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
 
  public static Collection<String> findAllLinkHref(String html, String hostUrl) throws Exception{
    Collection<String> urls = new ArrayList<String>();
   
    HtmlCleaner cleaner = new HtmlCleaner();
    TagNode node = cleaner.clean(html);
    Object[] ns = node.evaluateXPath("//a[@href]");
    for (Object object : ns) {
      TagNode node2=(TagNode) object;
      String href = node2.getAttributeByName("href");
      if (href == null || href.trim().length() == 0)
        continue;
     
      if (!href.startsWith("https://") && !href.startsWith("http://")){
        StringBuilder sb = new StringBuilder("http://").append(new URL(hostUrl).getHost());
View Full Code Here
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
 
  private List<Map<String, Object>> parseHtml(Page page) throws Exception{
    HtmlCleaner cleaner = new HtmlCleaner();
    cleaner.getProperties().setTreatUnknownTagsAsContent(true);
    String html = page.getContent();
    TagNode rootNode = cleaner.clean(html);
    fel.getContext().set("$page_content", html);
        final List<Field> fields = target.getModel().getField();
    String isModelArray = target.getModel().getIsArray();
    String modelXpath = target.getModel().getXpath();
    List<Map<String, Object>> list = new ArrayList<Map<String, Object>>();
    if ("1".equals(isModelArray) || "tre".equals(isModelArray)){
      Object[] nodeVals = rootNode.evaluateXPath(modelXpath);
          if (nodeVals != null && nodeVals.length > 0){
            for (int i = 0; i < nodeVals.length; i++) {
          list.add(parseHtmlMap(nodeVals[i], fields));
            }
          }
View Full Code Here
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
        String exp = parser.getExp();
        String regex = parser.getRegex();
        String skipRgxFail = parser.getSkipRgxFail();
        try {
          if (xpath != null && xpath.trim().length() > 0) {
            TagNode tag = (TagNode)item;
            Object[] nodeVals = tag.evaluateXPath(xpath);
            if (nodeVals == null || nodeVals.length == 0)
              continue;
           
            if (attribute != null && attribute.trim().length() > 0){
              for (Object nodeVal : nodeVals){
                TagNode node = (TagNode)nodeVal;
                String attrVal = node.getAttributeByName(attribute);
                values.add(attrVal);
              }
              //正则
              parseByRegex(regex, skipRgxFail, values);
              // EXP表达式
              parseByExp(exp, values);
            }else if (xpath.endsWith("/text()")){
              for (Object nodeVal : nodeVals){
                values.add(nodeVal.toString());
              }
             
              //正则
              parseByRegex(regex, skipRgxFail, values);
             
              // EXP表达式
              parseByExp(exp, values);
            }else {
              for (Object nodeVal : nodeVals){
                TagNode node = (TagNode)nodeVal;
                values.add(node);
              }
             
              // 此种方式获取到的Node节点大部分都不是字符串，因此先执行表达式后执行正则
              // EXP表达式
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
 
  public static Object evalXpath(String html, String xpath, String attribute){
    List<Object> result = new ArrayList<Object>();
    HtmlCleaner cleaner = new HtmlCleaner();
    try {
      TagNode tagNode = cleaner.clean(html);
      Object[] nodeVals = tagNode.evaluateXPath(xpath);
      for (Object tag : nodeVals){
        TagNode _tag = (TagNode)tag;
        Object val = null;
        if (attribute != null)
          val = _tag.getAttributeByName(attribute);
        else if (xpath.endsWith("/text()")){
          result.add(tag.toString());
        }else
          val = tag;
       
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
      for( int i=0 ; i<lElements.size() ; i++ )
      {
        try
        {
          HtmlCleaner cleaner = new HtmlCleaner();
          TagNode rootNode = cleaner.clean(new URL(url));
          TagNode tagElements[] = rootNode.getElementsByName( lElements.get(i).getTag(), true );
          for( int j=0 ; j<tagElements.length ; j++ )
            if( lElements.get(i).getClas().equalsIgnoreCase("*") || tagElements[j].getAttributeByName("class").equals(lElements.get(i).getClas()) )
              lElements.get(i).add( tagElements[j].getText().toString() );
        }
        catch( Exception e )
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
    return result;
  }

  public void buildEditLinkUrl(int section) {
    if (fParserInput.getAllowSectionEdit()) {
      TagNode divTagNode = new TagNode("div");
      divTagNode.addAttribute("style", "font-size:90%;float:right;margin-left:5px;", false);
      divTagNode.addChild(new ContentToken("["));
      append(divTagNode);

      String url = "";
      try {
        url = LinkUtil.buildEditLinkUrl(fParserInput.getContext(), fParserInput.getVirtualWiki(), fParserInput.getTopicName(),
            null, section);
      } catch (Exception e) {
        logger.severe("Failure while building link for topic " + fParserInput.getVirtualWiki() + " / "
            + fParserInput.getTopicName(), e);
      }
      TagNode aTagNode = new TagNode("a");
      aTagNode.addAttribute("href", url, false);
      aTagNode.addChild(new ContentToken(Utilities.formatMessage("common.sectionedit", fParserInput.getLocale())));
      divTagNode.addChild(aTagNode);
      divTagNode.addChild(new ContentToken("]"));
    }
  }
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
      HtmlCleaner cleaner = new HtmlCleaner();
     
      CleanerProperties props = cleaner.getProperties();
      props.setUseEmptyElementTags(false);
     
      TagNode node = cleaner.clean(sb.toString());
      Document myJDom = new JDomSerializer(props, true).createJDom(node);
      XMLOutputter outputter = new XMLOutputter(Format.getPrettyFormat());
      sbResult.append(outputter.outputString(myJDom));
    }
    catch (IOException e) {logger.error(e);}
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
  public List<String> readByXPath(String xPath) throws XPatherException {
    Object[] nodes = root.evaluateXPath(xPath);
    List<String> rsList = new ArrayList<String>();
    if (null != nodes) {
      for (Object object : nodes) {
        TagNode node = (TagNode) object;
        rsList.add(node.getText().toString());
      }
    }
    return rsList;
  }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
  public List<String> readByAttrValue(String attrName,String value) throws XPatherException {
    Object[] nodes = root.getElementsByAttValue(attrName, value, true, true);
    List<String> rsList = new ArrayList<String>();
    if (null != nodes) {
      for (Object object : nodes) {
        TagNode node = (TagNode) object;
        rsList.add(node.getText().toString());
      }
    }
    return rsList;
  }
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
    // input source or reader. Result is root node of created
    // tree-like structure. Single cleaner instance may be safely used
    // multiple times.
//    TagNode node = cleaner.clean( new File("tests/accept.html"));

    TagNode node = cleaner.clean( new File("tests/rallypoint.htm"));


    Object[] myNodes;
       


        myNodes = node.evaluateXPath( "//div[@id='content']//h1/text( )");

    String[] data = Util.patternExtract( "([^(]+)"+Translator.get(Translator.LEVEL)+" (\\d+)", myNodes[0].toString(), 2);
        String currentLocation = Translator.translate( data[0].trim());
        int    level    = Integer.parseInt( data[1].trim());
    System.out.printf( "currentLocation=%s, level=%d\n\n", currentLocation, level);

    int  numNode = 0;
        Object[] domTroops = node.evaluateXPath( "//div[@id='content']//table");
        for( Object t : domTroops) {
          if( t instanceof TagNode) {
            TagNode domTroop = (TagNode) t;
           
                Object[] domTroopTypes = domTroop.evaluateXPath( ".//tbody[@class='units']/tr[position()=1]/td/img/@title");
                Object[] domTroopQuantities = node.evaluateXPath( ".//tbody[@class='units']/tr[position()=2]/td/text()");
                Object[] domLocations = node.evaluateXPath( "//div[@id='content']//table/thead/tr/td[2]/a/@href");

              String codLocation = "<local>";
              if( numNode > 0) { // Other villages
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.