Package org.vietspider.html

Examples of org.vietspider.html.HTMLNode

41
42
43
44
45
46
47
48
49
    }
  }

  public void searchNodes(NodeIterator iterator, List<HTMLNode> nodes, Name name) {
    while(iterator.hasNext()) {
      HTMLNode n = iterator.next();
      if(n.isNode(name)) nodes.add(n);
    }
  } 
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
  }


  public void autoSelect(HTMLDocument document, String url) throws Exception {
    ContentRegionSearcher2 searcher = new ContentRegionSearcher2();
    HTMLNode nodes = searcher.extractContent(document, url, false);

    NodePathParser pathParser = new NodePathParser();
    //    for(int i = 0; i < nodes.size(); i++) {
    NodePath path = pathParser.toPath(nodes);  
    if(path == null) return;
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
129
       
        if(paths.length < 1) {
          HTMLExtractor extractor  = new HTMLExtractor();
          NodePathParser pathParser = new NodePathParser();
          if(hyperlinkUtil == null) hyperlinkUtil = new HyperLinkUtil();
          HTMLNode header = null;
          HTMLNode body = null;
          try {
            NodePath nodePath  = pathParser.toPath("HEAD");
            header = extractor.lookNode(document.getRoot(), nodePath);
            nodePath  = pathParser.toPath("BODY");
            body = extractor.lookNode(document.getRoot(), nodePath);
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();
   
    try {
      NodePath nodePath  = pathParser.toPath(txt);
      HTMLNode node = extractor.lookNode(document.getRoot(), nodePath);
      if(node == null) return;
      if(node.isNode(Name.CONTENT)
          || node.isNode(Name.COMMENT)
          || node.isNode(Name.UNKNOWN)) {
        browser.setText(node.getTextValue());
        return;
      }
     
      NodePath headerPath  = pathParser.toPath("HEAD");
      HTMLNode header = extractor.lookNode(document.getRoot(), headerPath);
   
      if(toolbar.isShowAll()) {
        if(hyperlinkUtil == null) hyperlinkUtil = new HyperLinkUtil();
        try {
          String address = toolbar.getText();
          URL home = new URL(address);
         
          hyperlinkUtil.createFullNormalLink(node, home);
          hyperlinkUtil.createFullImageLink(node, home);
          HashMap<String, String> map = new HashMap<String,String>();
          map.put("link","href");
          map.put("script","src");
          hyperlinkUtil.createFullLink(header, map, home, null);
        } catch(MalformedURLException me) {
        } catch (Exception e) {
          ClientLog.getInstance().setException(getShell(), e);
        }
      }
     
      StringBuilder builder = new StringBuilder();
      builder.append("<html>");
      builder.append("<head>");
      if(toolbar.isShowAll() && header != null && header.getChildren() != null) {
        for(HTMLNode ele : header.getChildren()){
          builder.append(ele.getTextValue()).append('\n');
        }
      }
//      String baseHref = HTMLExplorer.class.getResource("").toString();
//      builder.append("<base href=\""+baseHref+"\">");
      if(node.isNode(Name.BODY)) {
        HTMLNode body = null;
        try {
          nodePath  = pathParser.toPath("BODY");
          body = extractor.lookNode(document.getRoot(), nodePath);
        } catch (Exception e) {
          ClientLog.getInstance().setException(getShell(), e);
View Full Code Here
305
306
307
308
309
310
311
312
313
314
315
    for(TreeItem item : items) {
      String pathIndex = handler.getConfig(item);
      try {
        NodeInfoViewer viewer = new NodeInfoViewer(getShell(), x, y);
        NodePath nodePath = pathParser.toPath(pathIndex);
        HTMLNode node = extractor.lookNode(document.getRoot(), nodePath);
        viewer.setNode(node);  
        x += 10;
        y += 10;
        nodeViewers.add(viewer);
      } catch(Exception exp) {
View Full Code Here
28
29
30
31
32
33
34
35
36
37
//    System.out.println("==================");
//    System.out.println(value.indexOf(txt));
    if(value.indexOf(txt) < 0)  return null;
    List<HTMLNode> children  = node.getChildrenNode();
    for(HTMLNode ele : children){
      HTMLNode newNode = findByText(ele, txt, decoder);
      if(newNode != null) return newNode;
    }
    return node;
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
50
  public StringBuilder getTextContent(HTMLNode node){
    StringBuilder value = new StringBuilder();
    NodeIterator iterator = node.iterator();
    while(iterator.hasNext()) {
      HTMLNode n = iterator.next();
      if(n.isNode(Name.CONTENT)) {
        value.append(n.getValue());   
      }   
    }
    /*if(node.getConfig().name() == Name.CONTENT){
      value.append(node.getValue());   
    }   
View Full Code Here
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
    URL url = new URL("http://java.sun.com/");
    HTMLDocument document = new HTMLParser2().createDocument(url.openStream(), "utf-8");
   
    NodeIterator iterator =  document.getRoot().iterator();
    while(iterator.hasNext()) {
      HTMLNode node = iterator.next();
      if(node.isNode(Name.SCRIPT)) {
        if(node.hasChildren() && node.getChildren().size() > 0) {
          System.out.println("===================================================");
          System.out.println(node.getChild(0).getTextValue());
        }
        continue;
      }
      Attributes attributes = node.getAttributes();
      for(int i = 0; i < attributes.size(); i++) {
        String value = attributes.get(i).getValue();
        if(attributes.get(i).getName().startsWith("on")
            || value.toLowerCase().startsWith("javascript")) {
          System.out.println("===================================================");
View Full Code Here
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
 
  public static synchronized void updateDocument(
      HTMLDocument document, List<String> jsDocWriters) throws Exception {

    List<HTMLNode> jsScripts = new ArrayList<HTMLNode>();
    HTMLNode root = document.getRoot();
    if(root.isNode(Name.SCRIPT)) {
      jsScripts.add(root);
    } else {
      searchScriptNode(root.iterator(), jsScripts);
    }
   
    for(int i = 0 ; i < jsScripts.size(); i++) {
      List<HTMLNode> childen = jsScripts.get(i).getChildren();
      if(childen.size() < 1) continue;
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
      replace(jsScripts.get(i), new HTMLParser2().createDocument(builder.toString()));
    }
  }
 
  private static void replace(HTMLNode script, HTMLDocument doc) {
    HTMLNode parent = script.getParent();
    if(parent == null) return;
    List<HTMLNode> childen = parent.getChildren();
    if(childen ==  null) return;
    for(int i = 0; i < childen.size(); i++) {
      if(childen.get(i) != script) continue;
      List<HTMLNode> values = getNodes(doc);
      if(values.size() > 0) {
        parent.setChild(i, values.get(0));
//        childen.set(i, values.get(0));
        for(int k = 1; k < values.size(); k++) {
          parent.addChild(i+k, values.get(k));
//          childen.add(i+k, values.get(k));
        }
      }
     
      return;
View Full Code Here
TOP

Related Classes of org.vietspider.html.HTMLNode

  • AttributeExplorer
  • ExtractForum
  • HTMLNodeExplorer
  • JavascriptExtractor
  • org.vietspider.browser.LoginUtils
  • org.vietspider.browser.LoginWebsiteHandler
  • org.vietspider.browser.VirtualFormPost
  • org.vietspider.browser.VirtualFormPostBak
  • org.vietspider.document.util.ImageDescRemover
  • org.vietspider.document.util.NodeRemover
    • 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.