Package org.vietspider.html

Examples of org.vietspider.html.HTMLNode

33
34
35
36
37
38
39
40
41
 
  private Name [] ignores = {Name.A, Name.MARQUEE};

  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
55
56
57
58
59
60
61
62
63
64
65
    return new NodePath(toNodes(htmlNode));
  }
 
  public Node[] toNodes(HTMLNode htmlNode) {
    if(htmlNode == null) return new Node[0];
    HTMLNode htmlParent = htmlNode.getParent();
    List<Node> list = new ArrayList<Node>();
    while(htmlParent != null){
      list.add(toNode(htmlParent, htmlNode));
      htmlNode = htmlParent;
      htmlParent = htmlNode.getParent();
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
    }
    return isIgnoreTag(node.getParent(), level+1);
  }

  public HTMLNode searchParent(HTMLDocument document, int level) throws Exception  {
    HTMLNode  body = searchBody(document);
    ContentRenderer renderer = createContentRenderer(body);

    int length = renderer.getTextValue().length();
    List<HTMLNode> renderNodes = renderer.getNodePositions(0, length);
    NodeRenderer nodeRenderer = new NodeRenderer(renderer, renderNodes, 0, length);
View Full Code Here
181
182
183
184
185
186
187
188
189
190
191
  }
 
  public List<HTMLNode> searchNodes(HTMLDocument document, int level, int step) throws Exception  {
    List<HTMLNode> values = new ArrayList<HTMLNode>();
   
    HTMLNode body = searchBody(document);
    ContentRenderer renderer = createContentRenderer(body);

    int length = renderer.getTextValue().length();
    List<HTMLNode> renderNodes = renderer.getNodePositions(0, length);
    NodeRenderer nodeRenderer = new NodeRenderer(renderer, renderNodes, 0, length);
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
    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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
 
  protected HTMLNode searchBody(HTMLDocument document) throws Exception {
    RefsDecoder decoder = new RefsDecoder();
    NodeIterator iterator = document.getRoot().iterator();
    while(iterator.hasNext()) {
      HTMLNode node = iterator.next();
      if(!node.isNode(Name.CONTENT)) continue;
      char [] chars = node.getValue();
      chars = decoder.decode(chars);

      chars = CharsUtil.cutAndTrim(chars, 0, chars.length);
      chars =  java.text.Normalizer.normalize(new String(chars), Normalizer.Form.NFC).toCharArray();
      node.setValue(chars);             
    } 

    HTMLExtractor extractor  = new HTMLExtractor();
    NodePathParser pathParser = new NodePathParser();
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
33
34
35
    if(documents.length < 1) return null;
    return documents[0];
  }
 
  public HTMLDocument extract(HTMLDocument document, NodePath... nodePaths) {
    HTMLNode root = document.getRoot();
//    CharsToken tokens = document.getTokens();
   
    HTMLNode newRoot = HTMLParser2.clone(root);
    HTMLDocument newDocument  = new HTMLDocument();
//    CharsToken newTokens = new CharsToken(newDocument);
//    newTokens.push((NodeImpl)newRoot);

    LookupNode lookupNode = new LookupNode();
View Full Code Here
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
    return newDocument;
  }

  public HTMLDocument[] extractRow(HTMLDocument document, NodePath[] nodePaths) {
    List<List<HTMLNode>> nodeLists = new ArrayList<List<HTMLNode>>();
    HTMLNode root = document.getRoot();

    LookupNode lookupNode = new LookupNode();
   
    for(int i = 0; i < nodePaths.length; i++) {
      List<HTMLNode> matchValues = lookupNode.lookupNodes(root, nodePaths[i]);
      if(matchValues != null) nodeLists.add(matchValues);
    }

    if(nodeLists.size() == 0 || nodeLists.get(0) == null) return new HTMLDocument[0];

    List<HTMLNode> nodes = nodeLists.get(0);
    HTMLDocument [] newDocuments = new HTMLDocument[nodes.size()];

    for(int i = 0; i < nodes.size(); i++) {
      HTMLNode newRoot = HTMLParser2.clone(root);
      if(nodes.get(i) == null) continue;
      nodes.get(i).clone(newRoot);
      for(int j = 1; j < nodeLists.size(); j++) {
        List<HTMLNode> nextNodes = nodeLists.get(j);
        if(i > nextNodes.size()) break;
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
  public TextRenderer (HTMLNode root,
      final List<HTMLNode> contents, final int type, final boolean constain) {
    NodeIterator iterator = root.iterator();
    while(iterator.hasNext()) {
      HTMLNode node = iterator.next();
      switch (node.getName()) {
      case CONTENT:
        char [] chars = node.getValue();
        if(!isEmpty(chars)) {
          if(isValid(contents, node, constain)) {
            int start = builder.length();
            for(int k = 0; k < chars.length; k++) {
              builder.append(chars[k] == '\n' ? ' ' : chars[k]);
            }
            HTMLNode parent = node.getParent();
            if(parent != null && parent.isNode(Name.SPAN)) builder.append(' ');
           
            int end = builder.length();
            positions.add(new NodePosition(node, start, end));
          }
        }
View Full Code Here
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
    if(documents.length < 1) return null;
    return documents[0];
  }
 
  public HTMLDocument extract(HTMLDocument document, NodePath... nodePaths) {
    HTMLNode root = document.getRoot();
//    CharsToken tokens = document.getTokens();
   
    HTMLNode newRoot = HTMLParser2.clone(root);
    HTMLDocument newDocument  = new HTMLDocument();
//    CharsToken newTokens = new CharsToken(newDocument);
//    newTokens.push((NodeImpl)newRoot);

    for(int i = 0; i < nodePaths.length; i++) {
      List<HTMLNode> htmlNodes = matchNodes(root, nodePaths[i]);
      if(htmlNodes == null ) continue;
      for(HTMLNode htmlNode : htmlNodes) {
        if(htmlNode == null) continue;
//        extractTokens(tokens, newTokens, htmlNode);
        newRoot.addChild(htmlNode);
//        htmlNode.setParent(newRoot);
      }
    }
   
    newDocument.setRoot(newRoot);
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.