Package org.vietspider.html

Examples of org.vietspider.html.HTMLDocument

16
17
18
19
20
21
22
public class CharsToken extends Factory<NodeImpl> {
 
  private HTMLDocument document;
 
  public CharsToken() {
    this.document = new HTMLDocument();
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
  public String detectCharset(byte [] bytes) {
    EncodingDetector encodingDetector = new EncodingDetector();
    String codeCharset = encodingDetector.detect(bytes);
    if(codeCharset == null) codeCharset = "utf-8";
    try {
      HTMLDocument document = createDocument(bytes, codeCharset);
      String docCharset = getCharset(document);
      if(docCharset == null
          || charset.equalsIgnoreCase(docCharset)) return codeCharset;
      return docCharset;
    } catch (Exception e) {
View Full Code Here
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
    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();
    new DataWriter().save(file, data);
  }
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
    System.out.println("*********************************************************");
  }

  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
41
42
43
44
45
46
47
48
49
    System.out.println(node.getTextValue());
  }

  public HTMLDocument removeNode(String name)  throws Exception {
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(file, null);
    removeNode(name, document.getRoot());
    return document;
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
    }
  }

  public List<HTMLNode> getAllNode(String name) throws Exception {
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(file, null);
    List<HTMLNode> list = new ArrayList<HTMLNode>();
    getAllNode(name, document.getRoot(), list);
    return list;
  }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
    System.out.println("\n"+list.get(15).getTextValue());
    System.out.println("\n"+list.get(15).getParent().getTextValue());
    System.out.println("\n"+list.get(15).getParent().getChildren().size());

    System.out.println("*********************************************************");
    HTMLDocument document = explorer.removeNode("a");
    list = new ArrayList<HTMLNode>();
    explorer.getAllNode("a", document.getRoot(), list);
    System.out.println(list.size());

  }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
  public static void main(String[] args) {
    try{
      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();
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
    System.out.println("*********************************************************");   
  }
 
  public List<String> getAttribute(String nodeName, String attrName) throws Exception { 
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(file, null);
   
    List<String> attrValues = new ArrayList<String>();
   
    NodeIterator iterator = document.getRoot().iterator();
    while(iterator.hasNext()) {
      HTMLNode node = iterator.next();
      if(node.isNode(nodeName)) {
        Attributes attributes = node.getAttributes();
        Attribute attribute = attributes.get(attrName);
View Full Code Here
50
51
52
53
54
55
56
57
58
    return attrValues;
  }
 
  public List<String> getLinks() throws Exception {
    HTMLParser2 parser2 = new HTMLParser2();
    HTMLDocument document  = parser2.createDocument(file, null);
    HyperLinkUtil linkUtil = new HyperLinkUtil() ;
    return linkUtil.scanSiteLink(document.getRoot());
  }
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.