org.archive.resource.html

Class ExtractingParseObserver

java.lang.Object

org.archive.resource.html.ExtractingParseObserver

All Implemented Interfaces:

ParseObserver

public class ExtractingParseObserver
extends Object
implements ParseObserver

Field Summary

Fields

Modifier and Type	Field and Description
protected static String	cssImportNoUrlPatString
protected static Pattern	cssImportNoUrlPattern
protected static String	cssUrlPatString
protected static Pattern	cssUrlPattern

Constructor Summary

Constructors

Constructor and Description
ExtractingParseObserver(HTMLMetaData data)

Method Summary

Methods

Modifier and Type	Method and Description
void	handleDocumentComplete()
void	handleDocumentStart()
void	handleRemarkNode(org.htmlparser.nodes.RemarkNode remark)
void	handleScriptNode(org.htmlparser.nodes.TextNode text)
void	handleStyleNode(org.htmlparser.nodes.TextNode text)
void	handleTagClose(org.htmlparser.nodes.TagNode tag)
void	handleTagEmpty(org.htmlparser.nodes.TagNode tag)
void	handleTagOpen(org.htmlparser.nodes.TagNode tag)
void	handleTextNode(org.htmlparser.nodes.TextNode text)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

cssUrlPatString

protected static String cssUrlPatString

cssImportNoUrlPatString

protected static String cssImportNoUrlPatString

cssImportNoUrlPattern

protected static Pattern cssImportNoUrlPattern

cssUrlPattern

protected static Pattern cssUrlPattern

Constructor Detail

ExtractingParseObserver

public ExtractingParseObserver(HTMLMetaData data)

Method Detail

handleDocumentStart

public void handleDocumentStart()

Specified by:

handleDocumentStart in interface ParseObserver

handleDocumentComplete

public void handleDocumentComplete()

Specified by:

handleDocumentComplete in interface ParseObserver

handleTagEmpty

public void handleTagEmpty(org.htmlparser.nodes.TagNode tag)

Specified by:

handleTagEmpty in interface ParseObserver

handleTagOpen

public void handleTagOpen(org.htmlparser.nodes.TagNode tag)

Specified by:

handleTagOpen in interface ParseObserver

handleTagClose

public void handleTagClose(org.htmlparser.nodes.TagNode tag)

Specified by:

handleTagClose in interface ParseObserver

handleTextNode

public void handleTextNode(org.htmlparser.nodes.TextNode text)

Specified by:

handleTextNode in interface ParseObserver

handleScriptNode

public void handleScriptNode(org.htmlparser.nodes.TextNode text)

Specified by:

handleScriptNode in interface ParseObserver

handleStyleNode

public void handleStyleNode(org.htmlparser.nodes.TextNode text)

Specified by:

handleStyleNode in interface ParseObserver

handleRemarkNode

public void handleRemarkNode(org.htmlparser.nodes.RemarkNode remark)

Specified by:

handleRemarkNode in interface ParseObserver