|
1 package org.enhydra.snapper.parsers;
2
3 import org.enhydra.snapper.api.Parser;
4 import java.io.File  ;
5 import java.io.InputStream ;
6
7 import org.htmlparser.beans.StringBean;
8 import org.htmlparser.tags.TitleTag;
9 import org.htmlparser.Node;
10
11 public class HTMLParser implements org.enhydra.snapper.api.Parser {
12
13 String title, parsedText, fileName;
14
15 public String parse(InputStream is) throws java.io.IOException { return "";}
16
17 public void parse(){
18
19
20 StringBean sb = new StringBean ();
21 sb.setLinks (false);
22 sb.setReplaceNonBreakingSpaces (false);
23 sb.setCollapse (true);
24 sb.setURL (fileName);
25 parsedText = sb.getStrings ();
26
27 try{
28
29 org.htmlparser.Parser parser = new org.htmlparser.Parser(fileName);
30
31 Node[] allTITLETags = parser.extractAllNodesThatAre(TitleTag.class);
32 TitleTag titleTag = (TitleTag) allTITLETags[0];
33 title = titleTag.getTitle();
34
35 }catch(Exception e)
36 {
37 title = fileName.substring(fileName.lastIndexOf(File.separator)+1);
38 title = title.substring(0,title.lastIndexOf("."));
39 }
40
41
42 if(parsedText==null)
43 {
44 parsedText="";
45 }
46 if(title==null)
47 {
48 title = fileName.substring(fileName.lastIndexOf(File.separator)+1);
49 title = title.substring(0,title.lastIndexOf("."));
50 }
51
52 }
53
54
55 public void setFileName(String fileName) {
56 this.fileName = fileName;
57 }
58
59 public String getParsedText() {
60 return parsedText;
61 }
62
63 public String getTitle() {
64 return title;
65 }
66
67
68 } |
Popular Tags |
Java API By Example, From Geeks To Geeks.