Package org.vietspider.html

Examples of org.vietspider.html.HTMLDocument

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
   
    String address = "http://forums.java.net/jive/thread.jspa?threadID=40523&tstart=0";
    byte  [] bytes = download(homepage, address);
   
    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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
   
    String address = "http://www.hastc.org.vn/Ketqua_giaodich.asp?stocktype=2&menuid=103120";
    byte  [] bytes = download(homepage, address);
   
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(bytes, "utf-8");
   
    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();
   
    //print header
    List<String> headers = new ArrayList<String>();
    headers.add("STT");
    headers.add("MaCK");
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
  }

  public static void main(String[] args) {
    try{
      URL url = new URL("http://www.java.net");
      HTMLDocument document = new HTMLParser2().createDocument(url.openStream(), "utf-8");
      testGetLink(document.getRoot());
      System.out.println("\n\n\n\n*********************************************************************\n\n\n\n");
      testCreateFullLink(document.getRoot(), url);
      System.out.println("\n\n\n\n*********************************************************************\n\n\n\n");
      testCreateImageLink(document.getRoot(), url);
    }catch(Exception exp){
      exp.printStackTrace();
    }
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
    }
  }

  public static void main(String[] args)  throws Exception {
    URL url = new URL("http://vnexpress.net/Vietnam/Xa-hoi/2006/10/3B9EFB66/");
    HTMLDocument document = new HTMLParser2().createDocument(url.openStream(), null);
    StringBuilder builder = new StringBuilder();
    build(builder, document.getRoot());
    File file = new File("E:\\Temp\\a.txt");
    if(!file.exists()) file.createNewFile();
    FileOutputStream stream = new FileOutputStream(file);
    stream.write(builder.toString().getBytes("utf-8"));
    stream.close();
View Full Code Here
TOP

Related Classes of org.vietspider.html.HTMLDocument

  • AttributeExplorer
  • CrawlerService
  • DecodeHTMLRef
  • ExtractForum
  • HASTCIndexEx
  • HTMLNodeExplorer
  • JavascriptExtractor
  • LinkUtilExample
  • NewsComExtractor
  • 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.