Package org.vietspider.html.path2

Examples of org.vietspider.html.path2.INode

116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
        if(document != null) handler.createTreeItem(tree, document);
        new AutoSelectDataNode2(document, url, handler, tree);
       
        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);
          } catch (Exception e) {
            ClientLog.getInstance().setException(getShell(), e);
          }
         
View Full Code Here
188
189
190
191
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
244
245
    txtPath.setText(txt);
   
    treeAddButton.computeShowArea(item);
   
    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
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
  void viewItem(){
    TreeItem[] items = tree.getSelection();
    if( items == null || items.length  < 1) return;
    int x = getShell().getLocation().x+120, y = getShell().getLocation().y +130;
    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();
    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);
View Full Code Here
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334

  public List<String> traverseTree(int style, String[] paths) throws Exception {
//    String [] paths = cboPath.getItems();
    List<String> removePaths = new ArrayList<String>();
    NodePathParser pathParser = new NodePathParser();
    if(paths != null) {
      short selectType = PathConfirmDialog.YES;
      for(String path : paths) {
        NodePath nodePath = pathParser.toPath(path);
        selectType = handler.traverseTree(tree, nodePath, path, style, selectType);
        if(selectType == PathConfirmDialog.YES
            || selectType == PathConfirmDialog.YES_TO_ALL) {
          removePaths.add(path);
        }
View Full Code Here
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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
      extractPaths.add(pathParser.toPath(list.get(i)).toString());
    }
  }
 
  private void searchDataNode(HTMLNode root) {*/
    NodePathParser pathParser = new NodePathParser();
    NodeIterator iterator = root.iterator();
  
    while(iterator.hasNext()) {
      HTMLNode node = iterator.next();
      if(!node.isNode(Name.DIV)) continue;
      Attributes attributes = node.getAttributes();
      Attribute attribute = attributes.get("id");
      if(attribute == null) continue;
      String value = attribute.getValue();
      if(value == null) continue;
     
      if("posts".equalsIgnoreCase(value)) {
        HTMLNode titleNode = searchTitleNode(root, node);
        if(titleNode != null) {
          titlePath = titleNode.getName()+"[0]";
          extractPaths.add(pathParser.toPath(titleNode).toString());
        }
       
        HTMLNode pageNode = searchPageNode(node);
        if(pageNode == null) pageNode = searchPageNode2(root);
        if(pageNode != null) {
          pagePath = "TABLE[0]";
          extractPaths.add(pathParser.toPath(pageNode).toString());
        }
       
        String threadPath = pathParser.toPath(node).toString();
       
        HTMLNode userNode = searchUserNode(node);
        if(userNode != null) {
          userPath = pathParser.toPath(userNode).toString();
         
          String path = userPath.substring(threadPath.length());
          int index = path.indexOf('[');
          if(index > -1) {
            path = path.substring(0, index+1) + "*" + path.substring(index+2, path.length());
          }
          if(titleNode != null && titleNode.isNode(Name.DIV)) {
            userPath = "DIV[1]" + path;
          } else {
            userPath = "DIV[0]" + path;
          }
          index = userPath.lastIndexOf("TD[");
          if(index > 0) {
            int end = userPath.indexOf(']', index);
            if(end > 0) {
              userPath = userPath.substring(0, index+3) + "i<2"+ userPath.substring(end);
            }
          }
        }
        if(userPath == null) return;
       
       
        HTMLNode postNode = searchContentNode(node, "post_message");
        if(postNode != null) {
          postPath = pathParser.toPath(postNode).toString();
         
          String path = postPath.substring(threadPath.length());
          int index = path.indexOf('[');
          if(index > -1) {
            path = path.substring(0, index+1) + "*" + path.substring(index+2, path.length());
View Full Code Here
234
235
236
237
238
239
240
241
242
243
244
245
246
247
    return upParent(node.getParent(), names);
  }
 
  private HTMLNode searchTitleNode(HTMLNode root, HTMLNode node) {
    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();
    String title = "title";
    try {
      NodePath nodePath  = pathParser.toPath("HEAD.TITLE");
      HTMLNode titleNode = extractor.lookNode(root, nodePath);
      if(titleNode.hasChildren()) {
        title  = titleNode.getChild(0).getTextValue();
      }
    } catch (Exception e) {
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
    afters = build(tokens);
  }
 
  private String [] build(List<NodeImpl> tokens) throws Exception {
    HTMLDocument doc = new HTMLParser2().createDocument(tokens);
    NodePathParser pathParser = new NodePathParser();
    HTMLExtractor extractor  = new HTMLExtractor();
   
    NodePath nodePath  = pathParser.toPath("BODY");
    HTMLNode body = extractor.lookNode(doc.getRoot(), nodePath);
   
    TextRenderer renderer = new TextRenderer(body, TextRenderer.HANDLER);
    String value = renderer.getTextValue().toString();
    return value.trim().split("\n");
View Full Code Here
233
234
235
236
237
238
239
240
241
242
      chars =  java.text.Normalizer.normalize(new String(chars), Normalizer.Form.NFC).toCharArray();
      node.setValue(chars);             
    } 

    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();

    NodePath nodePath  = pathParser.toPath("BODY");
    return extractor.lookNode(document.getRoot(), nodePath);
  }
View Full Code Here
111
112
113
114
115
116
117
118
119
120
      chars =  java.text.Normalizer.normalize(new String(chars), Normalizer.Form.NFC).toCharArray();
      node.setValue(chars);             
    } 

    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();

    NodePath nodePath  = pathParser.toPath("BODY");
    return extractor.lookNode(document.getRoot(), nodePath);
  }
View Full Code Here
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
    if(popup != null) popup.dispose();
  }*/
 
  private HTMLNode createNode(String path) {
    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();
    if(path.endsWith("[.")) {
      path  = path.substring(0, path.length() - 2);
    } else  if(path.endsWith("[")) {
      path  = path.substring(0, path.length() - 1);
    }
    try {
      NodePath nodePath = pathParser.toPath(path);
      return extractor.lookNode(explorer.getDocument().getRoot(), nodePath);
    } catch (Exception e) {
    }
    return null;
  }
View Full Code Here
TOP

Related Classes of org.vietspider.html.path2.INode

  • ExtractForum
  • HASTCIndexEx
  • HTMLNodeExplorer
  • NewsComExtractor
  • org.apache.hadoop.fs.Path
  • org.apache.hadoop.fs.s3.Block
  • org.apache.tajo.storage.s3.S3OutputStream
  • org.apache.tajo.storage.s3.SmallBlockS3FileSystem
  • org.jnode.fs.ext4.ExtentHeader
  • org.vietspider.browser.LoginUtils
    • 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.