Examples of HtmlExtractor

Examples of org.vietspider.html.path2.HTMLExtractor

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
   
    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());
   
    File file = new File("a.html");
    byte[] data = doc.getTextValue().getBytes();
View Full Code Here

Examples of org.vietspider.html.path2.HTMLExtractor

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

Examples of org.vietspider.html.path2.HTMLExtractor

50
51
52
53
54
55
56
57
58
59
60
61
      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());

      System.out.println("=================================================================");
View Full Code Here

Examples of org.vietspider.html.path2.HTMLExtractor

76
77
78
79
80
81
82
83
84
85
86
87
   
    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();
   
    //print header
    List<String> headers = new ArrayList<String>();
View Full Code Here

Examples of org.vietspider.html.path2.HTMLExtractor

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
    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
Copyright © 2018 www.massapi.com. 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.