org.archive.resource.html

Class ExtractingParseObserver

java.lang.Object

org.archive.resource.html.ExtractingParseObserver

All Implemented Interfaces:

ParseObserver

public class ExtractingParseObserver
extends java.lang.Object
implements ParseObserver

Field Summary

Fields

Modifier and Type	Field and Description
protected static java.lang.String	cssImportNoUrlPatString
protected static java.util.regex.Pattern	cssImportNoUrlPattern
protected static java.lang.String	cssUrlPatString
protected static java.util.regex.Pattern	cssUrlPattern
protected static java.lang.String	cssUrlTrimPatString
protected static java.util.regex.Pattern	cssUrlTrimPattern

Constructor Summary

Constructors

Constructor and Description
ExtractingParseObserver(HTMLMetaData data)

Method Summary

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 java.lang.String cssUrlPatString

cssUrlTrimPatString

protected static java.lang.String cssUrlTrimPatString

cssImportNoUrlPatString

protected static java.lang.String cssImportNoUrlPatString

cssImportNoUrlPattern

protected static java.util.regex.Pattern cssImportNoUrlPattern

cssUrlPattern

protected static java.util.regex.Pattern cssUrlPattern

cssUrlTrimPattern

protected static java.util.regex.Pattern cssUrlTrimPattern

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