javatools.wget
Class Wget

java.lang.Object
  |
  +--javatools.wget.Wget

public class Wget

extends java.lang.Object

Nested Class Summary

static class

Wget.El

Field Summary

static Wget.El	A_HREF
(package private) java.util.Set	alreadyProcessedURLs
static Wget.El	APPLET_CODE
static Wget.El	AREA_HREF
static Wget.El	BGSOUND_SRC
static Wget.El	BODY_BACKGROUND
static Wget.El	EMBED_HREF
static Wget.El	EMBED_SRC
(package private) java.util.List	errorListeners
static Wget.El	FIG_SRC
java.util.Map	followTags
static Wget.El	FRAME_SRC
static java.lang.String	HTML_TYPE
static Wget.El	IFRAME_SRC
static Wget.El	IMG_HREF
static Wget.El	IMG_LOWSRC
static Wget.El	IMG_SRC
static Wget.El	INPUT_SRC
static Wget.El	LAYER_SRC
protected static java.util.regex.Pattern	metaRefresh
static Wget.El	OVERLAY_SRC
(package private) WgetProcessUrl	processUrl
static Wget.El	SCRIPT_SRC
(package private) boolean	spiderURLs
static Wget.El	TABLE_BACKGROUND
static Wget.El	TD_BACKGROUND
static Wget.El	TH_BACKGROUND
(package private) WgetURLValidator	urlValidator

Constructor Summary

Wget(WgetProcessUrl processUrl)

Method Summary

void	addAllTags()
static void	addAllTags(java.util.Map followTags)
(package private) void	addAlreadyProcessed(java.net.URL url)
void	addErrorListener(WgetErrorListener listener)
void	addFollowTag(Wget.El el)
static void	addFollowTag(Wget.El el, java.util.Map followTags)
(package private) java.lang.String	connectionToMimeType(java.net.HttpURLConnection hconnect)
void	doProcessUrl(java.net.URLConnection connection)
void	doSpiderURLs(java.net.HttpURLConnection connection)
(package private) void	error(java.net.URL url, java.lang.String urlString, java.lang.Exception e)
(package private) java.util.List	followURL(org.jdom.Element element)
(package private) java.util.List	getListOfLinks(org.jdom.Element element) given a tree of xhtml, return a list of URLs as Strings contained in the entire XML tree.
(package private) void	getListOfLinksHelper(org.jdom.Element element, java.util.List rtn) Recursive Helper function for getListOfLinks
static java.lang.String	getMetaRefreshHeader(org.jdom.Element element)
static java.lang.String	getMetaRefreshUrl(org.jdom.Element element)
WgetURLValidator	getUrlValidator()
(package private) boolean	isAlreadyProcessed(java.net.URL url)
static boolean	isMetaRefresh(org.jdom.Element element)
static boolean	isRedirected(java.net.URLConnection connection)
boolean	isSpiderURLs()
static void	main(java.lang.String[] args)
java.net.URLConnection	openConnection(java.net.URL url)
void	recursiveGet(java.net.URL url)
void	removeAllTags()
void	removeFollowTag(Wget.El el)
void	setSpiderURLs(boolean v)
void	setUrlValidator(WgetURLValidator urlValidator)
(package private) org.jdom.Element	streamToElement(java.io.InputStream is) Convert an InputStream into a jdom tree of xhtml.

Methods inherited from class java.lang.Object

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

Field Detail

HTML_TYPE

public static final java.lang.String HTML_TYPE

See Also:

Constant Field Values

alreadyProcessedURLs

java.util.Set alreadyProcessedURLs

processUrl

WgetProcessUrl processUrl

urlValidator

WgetURLValidator urlValidator

errorListeners

java.util.List errorListeners

spiderURLs

boolean spiderURLs

followTags

public java.util.Map followTags

metaRefresh

protected static java.util.regex.Pattern metaRefresh

A_HREF

public static final Wget.El A_HREF

APPLET_CODE

public static final Wget.El APPLET_CODE

AREA_HREF

public static final Wget.El AREA_HREF

BGSOUND_SRC

public static final Wget.El BGSOUND_SRC

BODY_BACKGROUND

public static final Wget.El BODY_BACKGROUND

EMBED_HREF

public static final Wget.El EMBED_HREF

EMBED_SRC

public static final Wget.El EMBED_SRC

FIG_SRC

public static final Wget.El FIG_SRC

FRAME_SRC

public static final Wget.El FRAME_SRC

IFRAME_SRC

public static final Wget.El IFRAME_SRC

IMG_HREF

public static final Wget.El IMG_HREF

IMG_LOWSRC

public static final Wget.El IMG_LOWSRC

IMG_SRC

public static final Wget.El IMG_SRC

INPUT_SRC

public static final Wget.El INPUT_SRC

LAYER_SRC

public static final Wget.El LAYER_SRC

OVERLAY_SRC

public static final Wget.El OVERLAY_SRC

SCRIPT_SRC

public static final Wget.El SCRIPT_SRC

TABLE_BACKGROUND

public static final Wget.El TABLE_BACKGROUND

TD_BACKGROUND

public static final Wget.El TD_BACKGROUND

TH_BACKGROUND

public static final Wget.El TH_BACKGROUND

Constructor Detail

Wget

public Wget(WgetProcessUrl processUrl)

Method Detail

addAllTags

public void addAllTags()

addAllTags

public static void addAllTags(java.util.Map followTags)

removeAllTags

public void removeAllTags()

removeFollowTag

public void removeFollowTag(Wget.El el)

addFollowTag

public void addFollowTag(Wget.El el)

addFollowTag

public static void addFollowTag(Wget.El el,
                                java.util.Map followTags)

addErrorListener

public void addErrorListener(WgetErrorListener listener)

main

public static void main(java.lang.String[] args)
                 throws WgetException

WgetException

getListOfLinks

java.util.List getListOfLinks(org.jdom.Element element)

given a tree of xhtml, return a list of URLs as Strings contained in the entire XML tree.

Parameters:

element -

Returns:

List of urls as Strings

isMetaRefresh

public static boolean isMetaRefresh(org.jdom.Element element)

getMetaRefreshHeader

public static java.lang.String getMetaRefreshHeader(org.jdom.Element element)

getMetaRefreshUrl

public static java.lang.String getMetaRefreshUrl(org.jdom.Element element)

followURL

java.util.List followURL(org.jdom.Element element)

Parameters:

element -

Returns:

URL to follow

getListOfLinksHelper

void getListOfLinksHelper(org.jdom.Element element,
                          java.util.List rtn)

Recursive Helper function for getListOfLinks

Parameters:

element -

rtn -

See Also:

getListOfLinks

connectionToMimeType

java.lang.String connectionToMimeType(java.net.HttpURLConnection hconnect)

openConnection

public java.net.URLConnection openConnection(java.net.URL url)
                                      throws java.io.IOException

java.io.IOException

recursiveGet

public void recursiveGet(java.net.URL url)
                  throws WgetException,
                         java.io.IOException

WgetException

java.io.IOException

doSpiderURLs

public void doSpiderURLs(java.net.HttpURLConnection connection)
                  throws java.io.IOException,
                         WgetException

java.io.IOException

WgetException

doProcessUrl

public void doProcessUrl(java.net.URLConnection connection)
                  throws java.io.IOException,
                         WgetException

java.io.IOException

WgetException

error

void error(java.net.URL url,
           java.lang.String urlString,
           java.lang.Exception e)
     throws WgetException

WgetException

streamToElement

org.jdom.Element streamToElement(java.io.InputStream is)
                           throws java.io.IOException,
                                  java.io.FileNotFoundException,
                                  org.jdom.JDOMException,
                                  WgetException

Convert an InputStream into a jdom tree of xhtml.

Parameters:

is - An InputStream

Returns:

a jdom tree.

Throws:

java.io.IOException

java.io.FileNotFoundException

org.jdom.JDOMException

WgetException

isRedirected

public static boolean isRedirected(java.net.URLConnection connection)
                            throws java.io.IOException

java.io.IOException

isAlreadyProcessed

boolean isAlreadyProcessed(java.net.URL url)

addAlreadyProcessed

void addAlreadyProcessed(java.net.URL url)

getUrlValidator

public WgetURLValidator getUrlValidator()

setUrlValidator

public void setUrlValidator(WgetURLValidator urlValidator)

isSpiderURLs

public boolean isSpiderURLs()

setSpiderURLs

public void setSpiderURLs(boolean v)