public class HTMLLinkStructureExtractor extends AbstractExtractor implements WandoraTool, BrowserPluginExtractor
Modifier and Type | Field and Description |
---|---|
private java.lang.String[] |
contentTypes |
CUSTOM_EXTRACTOR, DONE_FAILED, DONE_MANY, DONE_ONE, EXACTLY_GIVEN_URLS, FILE_EXTRACTOR, FILE_PATTERN, GIVEN_URLS_AND_ALL_CRAWLED_DOCUMENTS, GIVEN_URLS_AND_CRAWLED_DOCUMENTS_IN_URL_DOMAIN, GIVEN_URLS_AND_LINKED_DOCUMENTS, GIVEN_URLS_AND_URL_BELOW, INFO_WAIT_WHILE_WORKING, LOG_TITLE, POINT_START_URL_TEXT, RAW_EXTRACTOR, SELECT_DIALOG_TITLE, STRING_EXTRACTOR_NOT_SUPPORTED_MESSAGE, URL_EXTRACTOR
CLOSE, EXECUTE, INVISIBLE, VISIBLE, WAIT
RETURN_ERROR, RETURN_INFO
Constructor and Description |
---|
HTMLLinkStructureExtractor()
Creates a new instance of HTMLLinkStructureExtractor
|
Modifier and Type | Method and Description |
---|---|
boolean |
_extractTopicsFrom(java.io.File file,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.lang.String str,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.net.URL url,
TopicMap topicMap) |
boolean |
acceptBrowserExtractRequest(BrowserExtractRequest request,
Wandora wandora) |
void |
associateUrls(java.lang.String url,
java.net.URL[] linkedUrls,
TopicMap topicMap) |
java.lang.String |
buildBaseName(java.io.File file) |
Locator |
buildSI(java.lang.String siend) |
java.lang.String |
doBrowserExtract(BrowserExtractRequest request,
Wandora wandora) |
java.lang.String[] |
getContentTypes()
Returns an array of String containing the content-types this
ContentHandler can process. |
java.lang.String |
getDescription()
AdminToolManager views tool descriptions while user browses available
tools and build user customizable GUI elements such as Tools menu.
|
int |
getExtractorType() |
java.lang.String |
getGUIText(int textType) |
javax.swing.Icon |
getIcon()
All tools may have identifying graphic icon used within tool GUI elements.
|
java.lang.String |
getName()
Tools name represent the tool in UI unless the tool has been given
explicitly another GUI name.
|
Topic |
getOrCreateTopic(TopicMap map,
java.lang.String si,
java.lang.String basename) |
addCrawlerUrl, browserExtractorConsumesPlainText, buildSL, clearMasterSubject, createAssociation, createAssociation, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, croppedFilename, croppedFilename, croppedUrlString, croppedUrlString, dropExtract, dropExtract, dropExtract, execute, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFromText, getBrowserExtractorName, getCrawlerMode, getForceContent, getForceFiles, getForceUrls, getGUIText, getInterruptsHandled, getMasterSubject, getType, getWandora, handle, handleContent, handleCustomType, handleFiles, handleForcedContent, handleInterrupt, handleStringContent, handleUrls, initializeCustomType, instantDropHandle, makeSubclassOfWandoraClass, runInOwnThread, setData, setDisplayName, setForceContent, setForceFiles, setForceUrls, setMasterSubject, setMasterSubject, setTopicMap, setupCrawler, setWandora, takeNap, urlEncode, useTempTopicMap, useURLCrawler
addUndoMarker, addUndoMarker, allowMultipleInvocations, clearAllThreads, clearThreads, clearThreads, clearToolLock, clearToolLock, clearToolLocks, configure, execute, execute, forceStop, forceStop, getContext, getCurrentLogger, getDefaultLogger, getHistory, getLastLogger, getState, getThreads, getThreads, getToolMenuItem, getToolMenuItem, getTopicName, hlog, initialize, interruptAllThreads, interruptThreads, interruptThreads, isConfigurable, isRunning, isRunning, lockLog, log, log, log, log, requiresRefresh, run, setContext, setDefaultLogger, setLogTitle, setProgress, setProgressMax, setState, setToolLogger, singleLog, singleLog, singleLog, solveContextTopicMap, solveNameForTopicMap, writeOptions
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
configure, execute, execute, execute, getContext, getToolMenuItem, getType, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptions
forceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setState
getBrowserExtractorName
public HTMLLinkStructureExtractor()
public int getExtractorType()
getExtractorType
in class AbstractExtractor
public java.lang.String getName()
AbstractWandoraTool
getName
in interface WandoraTool
getName
in class AbstractExtractor
public java.lang.String getDescription()
AbstractWandoraTool
getDescription
in interface WandoraTool
getDescription
in class AbstractExtractor
public javax.swing.Icon getIcon()
AbstractWandoraTool
getIcon
should return Icon
object of
the tool.getIcon
in interface WandoraTool
getIcon
in class AbstractExtractor
public java.lang.String getGUIText(int textType)
getGUIText
in class AbstractExtractor
public java.lang.String doBrowserExtract(BrowserExtractRequest request, Wandora wandora) throws TopicMapException
doBrowserExtract
in interface BrowserPluginExtractor
doBrowserExtract
in class AbstractExtractor
TopicMapException
public boolean acceptBrowserExtractRequest(BrowserExtractRequest request, Wandora wandora) throws TopicMapException
acceptBrowserExtractRequest
in interface BrowserPluginExtractor
acceptBrowserExtractRequest
in class AbstractExtractor
TopicMapException
public boolean _extractTopicsFrom(java.lang.String str, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.io.File file, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.net.URL url, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public void associateUrls(java.lang.String url, java.net.URL[] linkedUrls, TopicMap topicMap)
public Topic getOrCreateTopic(TopicMap map, java.lang.String si, java.lang.String basename)
public java.lang.String buildBaseName(java.io.File file)
public Locator buildSI(java.lang.String siend)
buildSI
in class AbstractExtractor
public java.lang.String[] getContentTypes()
Handler
ContentHandler
can process.getContentTypes
in interface Handler
getContentTypes
in class AbstractExtractor
Copyright 2004-2015 Wandora Team