Package org.vietspider.html.path2

Examples of org.vietspider.html.path2.NodePath

106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
        document : new HTMLAnchorUtil().searchDocument(document, ref);
  }
 
  public NodePath findNodeByText(HTMLNode node, String start, String end) throws Exception {
    RefsDecoder decoder = new RefsDecoder();
    NodePathParser pathParser = new NodePathParser();
    TextHandler textHandler = new TextHandler();
    if(start == null || start.trim().length() == 0) return pathParser.toPath(node);
    start = textHandler.trim(start);
    HTMLNode startNode = textHandler.findByText(node, start, decoder);
    if(end == null || end.trim().length() == 0) {
      return startNode != null ?  pathParser.toPath(startNode) : pathParser.toPath(node);
    }
    end = textHandler.trim(end);
   
    HTMLNode endNode = textHandler.findByText(node, end, decoder);   
    if(endNode == null)
      return startNode != null ? pathParser.toPath(startNode) : pathParser.toPath(node);
    if(startNode  == null) 
      return endNode != null  ?  pathParser.toPath(endNode) : pathParser.toPath(node);
    HTMLNodeUtil nodeUtil = new HTMLNodeUtil(); 
    String indexPath = nodeUtil.getCommonIndexPath(startNode, endNode);
    return pathParser.toPath(nodeUtil.getNodeByIndex(node, indexPath));
  }
View Full Code Here
47
48
49
50
51
52
53
54
    } 
    return txt;
  } 
 
  public short traverseTree(Tree tree, String path, int style, short type) throws Exception {
    NodePath nodePath = new NodePathParser().toPath(path);
    return traverseTree(tree, nodePath, path, style, type);
  }
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
    }
  }
 
  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
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
102
103
104
105
106
107
108
109
110
111
112
113
114
  }
 
  private void autoSelect() {
    if(type == HTMLExplorer.NONE) return;
    NodePath bodyPath = null;
    NodePathParser pathParser = new NodePathParser();
    try {
      bodyPath  = pathParser.toPath("BODY");
    }catch (Exception e) {
      ClientLog.getInstance().setException(tree.getShell(), e);
    }
   
    if(bodyPath == null || document == null) return;
    HTMLNode body = new HTMLExtractor().lookNode(document.getRoot(), bodyPath);
    List<HTMLNode> list = new ArrayList<HTMLNode>();
    List<HTMLNode> commons = new ArrayList<HTMLNode>();
    if(HTMLExplorer.SECTION == type) {
      searchSectionCSS(commons, list, body);

      short selectType = PathConfirmDialog.YES;
      for(HTMLNode ele : commons) {
        try {
          NodePath path = pathParser.toPath(ele);  
          if(path == null) continue;
          selectType = handler.traverseTree(tree, path, TreeHandler.MARK, selectType);     
        } catch(Exception exp){
          ClientLog.getInstance().setMessage(tree.getShell(), exp);
        } 
      }

      return;
    }

    searchContentCSS(commons, list, body);

    int maxCountContent = 0;
    HTMLNode maxNodeContent = null;

    List<HTMLNode> contents = new ArrayList<HTMLNode>();
    CharacterUtil characterUtil = new CharacterUtil();
   
    HTMLText htmlText = new HTMLText();
   
    short selectType = PathConfirmDialog.YES;
    boolean traverse = false;
    for(HTMLNode ele : commons) {
      contents.clear();
      htmlText.searchText(contents, ele);
      int count = countText(characterUtil, contents);

      if(count > maxCountContent) {
        maxCountContent = count;
        maxNodeContent = ele;
      }

      if(count < 100) continue;

      NodePath path = pathParser.toPath(ele);  
      if(path == null) continue;
      handler.traverseTree(tree, path, TreeHandler.MARK, selectType);
      if(!traverse) traverse = true;
    }
   
    if(traverse || maxNodeContent == null) return;
    try {       
      NodePath path = pathParser.toPath(maxNodeContent);  
      if(path == null) return;
      handler.traverseTree(tree, path, TreeHandler.MARK, selectType);     
    }catch(Exception exp){
      ClientLog.getInstance().setMessage(tree.getShell(), exp);
    } 
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
  public HTMLDocument searchDocument(HTMLDocument document, String name) {
    HTMLNode root = document.getRoot();
    HTMLNode newRoot = searchDocument(root, name);
    if (root == newRoot) return document;
    NodePathParser pathParser = new NodePathParser();
    HTMLExtractor extractor = new HTMLExtractor();
    try {
      HTMLNode body = extractor.lookNode(root, pathParser.toPath("BODY"));
      body.clearChildren();
      body.addChild(newRoot);
    } catch (Exception e) {
      LogService.getInstance().setThrowable(e);
    }
View Full Code Here
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
    URL url = new URL("http://news.google.com.vn/");
   
    WebClient webClient = new WebClient();
    webClient.setURL(null, url);
   
    NodePathParser pathParser = new NodePathParser();
    HTMLExtractor htmlExtractor = new HTMLExtractor();
   
    byte  [] bytes = download(webClient, "http://news.google.com.vn/");
   
    HTMLDocument document = new HTMLParser2().createDocument(bytes, null);
   
    String [] paths = {
        "BODY[0].TABLE[2].TBODY[0].TR[0].TD[3].TABLE[1].TBODY[0].TR[0].TD[0].TABLE[0].TBODY[0].TR[0].TD[0].DIV[0].TABLE[0].TBODY[0].TR[0].TD[0].DIV[*]"
    };
   
    NodePath [] nodePaths = new NodePath[paths.length];
    for(int i=0; i<paths.length; i++){
      nodePaths[i] = pathParser.toPath(paths[i]);
    }
   
    HTMLDocument doc = htmlExtractor.extract(document, nodePaths);
    System.out.println(doc.getTextValue());
   
    paths = new String[]{
        "DIV[*].BR[*]",
    };
   
    nodePaths = new NodePath[paths.length];
    for(int i=0; i<paths.length; i++){
      nodePaths[i] = pathParser.toPath(paths[i]);
    }
   
    htmlExtractor.remove(doc.getRoot(), nodePaths);
   
    System.out.println(doc.getRoot().getTextValue());
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
  }

  public void viewNode(String path) throws Exception {
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(file, null);
    NodePathParser pathParser = new NodePathParser();
    NodePath nodePath = pathParser.toPath(path);
    HTMLExtractor htmlExtractor = new HTMLExtractor();
    HTMLNode node = htmlExtractor.extract(document, new NodePath[]{nodePath}).getRoot();
    System.out.println(node.getTextValue());
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
      URL url = new URL("http://www.java.net");
//      System.out.println(URLDecoder.decode("video_id=http%3A%2F%2Fliveu-80.vo.llnwd.net%2Fflurl%2Fmb53%2Fnew_media3%2F2006%2F8%2F29%2F174380_media_flash8.flv&homeurl=http%3A%2F%2Fwww.flurl.com%2F&endmovies=http%3A%2F%2Fwww.flurl.com%2Fthumbs.php%3Fid%3D174380&embed=%3Ctable%20border%3D%270%27%20bgcolor%3D%27ffffff%27%20cellpadding%3D%270%27%20cellspacing%3D%270%27%3E%3Ctr%3E%3Ctd%3E%3Cembed%20id%3D%27flurl_media%27%20name%3D%27flurl_media%27%20width%3D%27519%27%20height%3D%27438%27%20src%3D%27http%3A%2F%2Fwww.flurl.com%2Fflvplayer2.swf%3Fvideo%3Dhttp%3A%2F%2Fwww.flurl.com%2Fflash_player_info.php%3Fid%3D174380%26flash%3D8%27%20quality%3D%27high%27%20bgcolor%3D%27white%27%20play%3D%27true%27%20loop%3D%27false%27%20allowScriptAccess%3D%27sameDomain%27%20type%3D%27application%2Fx-shockwave-flash%27%20pluginspage%3D%27http%3A%2F%2Fwww.macromedia.com%2Fgo%2Fgetflashplayer%27%3E%3C%2Fembed%3E%3C%2Ftd%3E%3C%2Ftr%3E%3Ctr%3E%3Ctd%20align%3D%27right%27%3E%3Cstrong%3E%3Ca%20href%3D%27http%3A%2F%2Fwww.flurl.com%2F%27%3EHosted%20on%20Flurl%20Video%20Search%3C%2Fa%3E%20-%20%3Ca%20href%3D%27http%3A%2F%2Fwww.flurl.com%2Fmedia%27%3EWatch%20More%20Videos%3C%2Fa%3E%20%3C%2Fstrong%3E%3C%2Ftd%3E%3C%2Ftr%3E%3C%2Ftable%3E"));
      HTMLParser2 parser2 = new HTMLParser2();
      HTMLDocument document = parser2.createDocument(url.openStream(), "utf-8");

      NodePathParser pathParser = new NodePathParser();
      NodePath nodePath = pathParser.toPath("BODY[0].DIV[0].TABLE[0].TBODY[0].TR[1].TD[3].DIV[10]");
      HTMLExtractor htmlExtractor = new HTMLExtractor();
      HTMLNode node = htmlExtractor.extract(document, new NodePath[]{nodePath}).getRoot();

      System.out.println(node.getTextValue());
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
   
    String path = "BODY[0].TABLE[0].TBODY[0].TR[0].TD[0].TABLE[0].TBODY[0].TR[0].TD[0]";
    path += ".TABLE[0].TBODY[0].TR[1].TD[1].TABLE[0].TBODY[0].TR[0].TD[0].TABLE[1].TBODY[0].TR[1]";
    path += ".TD[0].TABLE[1].TBODY[0].TR[i>0]";
   
    NodePathParser pathParser = new NodePathParser();
   
    NodePath nodePath = pathParser.toPath(path);
   
    HTMLExtractor htmlExtractor = new HTMLExtractor();
    document = htmlExtractor.extract(document, new NodePath[]{nodePath});
   
    List<HTMLNode> children = document.getRoot().getChildren();
View Full Code Here
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
102
103
104
   
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(bytes, "utf-8");
    String titlePathValue  = "BODY[0].DIV[1].TABLE[0].TBODY[0].TR[0].TD[0].P[1]";
   
    NodePathParser pathParser = new NodePathParser();
    HTMLExtractor htmlExtractor = new HTMLExtractor();
   
    NodePath titlePath = pathParser.toPath(titlePathValue);
    HTMLNode titleNode = htmlExtractor.lookNode(document.getRoot(), titlePath);
    String titleThread =  buildText(titleNode);
   
    String [] postPathValues = {
        "BODY[0].DIV[1].TABLE[1].TBODY[0].TR[0].TD[0].DIV[1].DIV[0].DIV[0].TABLE[0]",
        "BODY[0].DIV[1].TABLE[1].TBODY[0].TR[0].TD[0].TABLE[*].TBODY[0].TR[0].TD[1].DIV[0].DIV[0].DIV[0].TABLE[0]"
    };
   
    NodePath [] postPaths = pathParser.toNodePath(postPathValues);
    HTMLDocument document2 = htmlExtractor.extract(document, postPaths);
   
    String userPathValue = "TABLE[*].TBODY[0].TR[0].TD[0].TABLE[0].TBODY[0].TR[0].TD[0].TABLE[0].TBODY[0].TR[0].TD[0].NOBR[0].A[0]";
    NodePath userPath = pathParser.toPath(userPathValue);
    List<HTMLNode> userNodes = htmlExtractor.matchNodes(document2.getRoot(), userPath);
   
    List<String> users = new ArrayList<String>();
    for(HTMLNode userNode : userNodes) {
      users.add(buildText(userNode));
    }
   
    String textPostPathValue = "TABLE[*].TBODY[0].TR[0].TD[1].TABLE[0].TBODY[0].TR[1]";
    NodePath textPostPath = pathParser.toPath(textPostPathValue);
    List<HTMLNode> textPostNodes = htmlExtractor.matchNodes(document2.getRoot(), textPostPath);

    List<String> posts = new ArrayList<String>();
    for(HTMLNode textPostNode : textPostNodes) {
      posts.add(buildText(textPostNode));
View Full Code Here
TOP

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

  • ExtractForum
  • HASTCIndexEx
  • HTMLNodeExplorer
  • NewsComExtractor
  • org.vietspider.browser.LoginUtils
  • org.vietspider.html.HTMLDocument
  • org.vietspider.html.HTMLNode
  • org.vietspider.html.Name
  • org.vietspider.html.renderer.ContentRegionSearcher
  • org.vietspider.html.renderer.ContentRendererFactory
    • 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.