|
||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object javax.swing.text.html.HTMLEditorKit.ParserCallback org.apache.lenya.search.crawler.HTMLHandler
public final class HTMLHandler
DOCUMENT ME!
Field Summary |
---|
Fields inherited from class javax.swing.text.html.HTMLEditorKit.ParserCallback |
---|
IMPLIED |
Constructor Summary | |
---|---|
HTMLHandler()
Constructor - initializes variables |
Method Summary | |
---|---|
java.lang.String |
getAuthor()
Parse Content. [24] 320:1 |
java.lang.String |
getCategories()
Return categories (from META tags) |
java.lang.String |
getContents()
Return contents |
java.lang.String |
getDescription()
Return description (from META tags) |
java.lang.String |
getHREF()
Return META HREF |
java.lang.String |
getKeywords()
Return keywords (from META tags) |
java.util.List |
getLinks()
Return links |
long |
getPublished()
Return published date (from META tag) |
boolean |
getRobotFollow()
Return boolean true if links are to be followed |
boolean |
getRobotIndex()
Return boolean true if this is to be indexed |
java.lang.String |
getTitle()
Return page title |
void |
handleAnchor(javax.swing.text.MutableAttributeSet attribs)
Handle Anchor tags |
void |
handleEndTag(javax.swing.text.html.HTML.Tag tag,
int pos)
Closing tag |
void |
handleMeta(javax.swing.text.MutableAttributeSet attribs)
Handle META tags |
void |
handleSimpleTag(javax.swing.text.html.HTML.Tag tag,
javax.swing.text.MutableAttributeSet attribs,
int pos)
Handle standalone tags |
void |
handleStartTag(javax.swing.text.html.HTML.Tag tag,
javax.swing.text.MutableAttributeSet attribs,
int pos)
Opening tag |
void |
handleText(char[] text,
int pos)
Handle page text |
void |
parse(java.io.InputStream in)
Parse Content. |
Methods inherited from class javax.swing.text.html.HTMLEditorKit.ParserCallback |
---|
flush, handleComment, handleEndOfLineString, handleError |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
public HTMLHandler()
Method Detail |
---|
public java.lang.String getAuthor()
getAuthor
in interface ContentHandler
public java.lang.String getCategories()
getCategories
in interface ContentHandler
public java.lang.String getContents()
getContents
in interface ContentHandler
public java.lang.String getDescription()
getDescription
in interface ContentHandler
public java.lang.String getHREF()
getHREF
in interface ContentHandler
public java.lang.String getKeywords()
getKeywords
in interface ContentHandler
public java.util.List getLinks()
getLinks
in interface ContentHandler
public long getPublished()
getPublished
in interface ContentHandler
public boolean getRobotFollow()
getRobotFollow
in interface ContentHandler
public boolean getRobotIndex()
getRobotIndex
in interface ContentHandler
public java.lang.String getTitle()
getTitle
in interface ContentHandler
public void handleAnchor(javax.swing.text.MutableAttributeSet attribs)
attribs
- DOCUMENT ME!public void handleEndTag(javax.swing.text.html.HTML.Tag tag, int pos)
handleEndTag
in class javax.swing.text.html.HTMLEditorKit.ParserCallback
tag
- DOCUMENT ME!pos
- DOCUMENT ME!public void handleMeta(javax.swing.text.MutableAttributeSet attribs)
attribs
- DOCUMENT ME!public void handleSimpleTag(javax.swing.text.html.HTML.Tag tag, javax.swing.text.MutableAttributeSet attribs, int pos)
handleSimpleTag
in class javax.swing.text.html.HTMLEditorKit.ParserCallback
tag
- DOCUMENT ME!attribs
- DOCUMENT ME!pos
- DOCUMENT ME!public void handleStartTag(javax.swing.text.html.HTML.Tag tag, javax.swing.text.MutableAttributeSet attribs, int pos)
handleStartTag
in class javax.swing.text.html.HTMLEditorKit.ParserCallback
tag
- DOCUMENT ME!attribs
- DOCUMENT ME!pos
- DOCUMENT ME!public void handleText(char[] text, int pos)
handleText
in class javax.swing.text.html.HTMLEditorKit.ParserCallback
text
- DOCUMENT ME!pos
- DOCUMENT ME!public void parse(java.io.InputStream in)
parse
in interface ContentHandler
in
- DOCUMENT ME!
|
||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |