Package org.vietspider.html

Examples of org.vietspider.html.HTMLNode

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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
   
    List<HTMLNode> removes = new ArrayList<HTMLNode>();
    NodeIterator nodeIterator = root.iterator();
//    System.out.println(new String(first.getValue()));
    while(nodeIterator.hasNext()) {
      HTMLNode node = nodeIterator.next();
      switch (node.getName()) {
      case UL:
        if(isLinkContainer(node)) removes.add(node);
        break;
      case DIV:
      case TD:
        if(isLinkDiv(node)) removes.add(node);
        break;
      case CONTENT:
//        System.out.println(new String(iterNode.getValue()));
        if(node == first) remove = false;
        if(remove) {
          removes.add(node);
//          System.out.println(new String(node.getValue()));
        }
        if(node == last) remove = true;
        break;
      default:
        break;
      }
    }
//    System.out.println(new String(last.getValue()));
   
    for(int i = 0; i < removes.size(); i++) {
      HTMLNode node = removes.get(i);
      HTMLNode parent = node.getParent();
//      System.out.println(parent.getTextValue());
      while(parent != null) {
//        System.out.println(parent.getTextValue());
        node.setValue(new char[]{});
        parent.removeChild(node);
       
        int word = countWord(parent);
        if(word > 15) break;
        node = parent;
        parent = node.getParent();
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  private int countWord(HTMLNode node) {
    if(node == null) return 0;
    NodeIterator nodeIterator = node.iterator();
    int word = 0;
    while(nodeIterator.hasNext()) {
      HTMLNode iterNode = nodeIterator.next();
      if(getAncestor(iterNode, Name.A, 0, 5) != null) continue;
      if(iterNode.isNode(Name.CONTENT)) {
        String text = iterNode.getTextValue();
        word += textCounter.countWord(text, 0, text.length());
      }
    }
    return word;
  }
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
114
    if(children == null) return false;
    if(isListNode(children)) {
      NodeIterator nodeIterator = node.iterator();
      int counter = 0;
      while(nodeIterator.hasNext()) {
        HTMLNode iterNode = nodeIterator.next();
        if(iterNode.isNode(Name.A)) counter++;
      }
      return counter >= children.size() - 3;
    }
   
    for(int i = 0; i < children.size(); i++) {
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
    return false;
  }
 
  public boolean isListNode(List<HTMLNode> nodes) {
    if(nodes.size() < 1) return false;
    HTMLNode node = nodes.get(0);
    for(int i = 1;  i < nodes.size(); i++) {
      if(!equalsFormat(node, nodes.get(i))) return false;
    }
    return true;
  }
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
    if(node.getChildren() == null) return false;
   
    List<HTMLNode> ignores = new ArrayList<HTMLNode>();
    NodeIterator iterator = node.iterator();
    while(iterator.hasNext()) {
      HTMLNode n = iterator.next();
      if(n.isNode(Name.A)
          && !linkNodeChecker.isValid(new CheckModel(n), 0)) ignores.add(n);
    }
   
    int counter = 0;
    iterator = node.iterator(ignores);
    while(iterator.hasNext()) {
      HTMLNode n = iterator.next();
      if(n.isNode(Name.CONTENT)) {
        counter += countWord(n);
      }
    }
    return counter < 5 && ignores.size() > 1;
  }
View Full Code Here
224
225
226
227
228
229
230
231
232
233
234
  private static int countLink(HTMLNode node) {
    if(node == null) return 0;
    NodeIterator iterator = node.iterator();
    int counter = 0;
    while(iterator.hasNext()) {
      HTMLNode n = iterator.next();
      if(n.isNode(Name.A)) counter++;
    }
//    System.out.println(" thay co cai na "+ counter);
    return counter;
  }
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
    for(;i < tokens.size(); i++) {
      NodeImpl node = tokens.get(i);
      if(node.isNode(Name.FORM)) break;
    }

    HTMLNode form = null;
    List<HTMLNode> inputs = new ArrayList<HTMLNode>();

    for(; i < tokens.size(); i++) {
      NodeImpl node = tokens.get(i);
      if(node.isNode(Name.FORM)) {
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
      }

      Node node = (Node)inodes[i];
      for(HTMLNode htmlNode : htmlNodes) {
        if(htmlNode == null) continue;
        HTMLNode test = lookNode(htmlNode, node);
        if(test == null) {
          continue;
        }
        htmlValues.add(lookNode(htmlNode, node));
      }
View Full Code Here
116
117
118
119
120
121
122
123
124
125
      if(matchValues != null) nodes.addAll(matchValues);
    }

    for(HTMLNode node : nodes) {
      if(node == null) continue;
      HTMLNode parent  = node.getParent();
      if(parent == null) continue;
      parent.removeChild(node);
    }
  }
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
      parent.removeChild(node);
    }
  }

  public void removeFrom(HTMLNode root, NodePath path){
    HTMLNode element = lookupNode(root, path);
    if (element == null) return;
    java.util.Iterator<HTMLNode> iter =  element.getParent().getChildren().iterator();
    boolean remove = false;
    while(iter.hasNext()){
      HTMLNode ele = iter.next();
      if(!remove) remove = ele == element;
      if(remove) iter.remove();
    }
  }
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.