public class MediaArticleExtractor extends AbstractElavaArkistoExtractor
Modifier and Type | Field and Description |
---|---|
static boolean |
EXTRACT_SERVICE |
ELAVA_ARKISTO_ARTICLE_ID_TYPE_SI, ELAVA_ARKISTO_ARTICLE_PUBLISHED_TYPE_SI, ELAVA_ARKISTO_ARTICLE_TYPE_SI, ELAVA_ARKISTO_DATE_TYPE_SI, ELAVA_ARKISTO_MEDIA_TYPE_SI, ELAVA_ARKISTO_SERVICE_TYPE_SI, ELAVA_ARKISTO_SI, ELAVA_ARKISTO_TAG_ARTICLE_RELATION_TYPE_SI, ELAVA_ARKISTO_TAG_TYPE_SI, ELAVA_ARKISTO_TIME_TYPE_SI
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 |
---|
MediaArticleExtractor() |
Modifier and Type | Method and Description |
---|---|
boolean |
_extractTopicsFrom(CSVParser.Table table,
TopicMap tm) |
boolean |
_extractTopicsFrom(java.io.File f,
TopicMap tm) |
boolean |
_extractTopicsFrom(java.lang.String str,
TopicMap tm) |
boolean |
_extractTopicsFrom(java.net.URL u,
TopicMap tm) |
java.lang.String |
getDescription()
AdminToolManager views tool descriptions while user browses available
tools and build user customizable GUI elements such as Tools menu.
|
java.lang.String |
getName()
Tools name represent the tool in UI unless the tool has been given
explicitly another GUI name.
|
getElavaArkistoArticleIdType, getElavaArkistoArticleTopic, getElavaArkistoArticleType, getElavaArkistoDateTopic, getElavaArkistoDateType, getElavaArkistoMediaTopic, getElavaArkistoMediaType, getElavaArkistoServiceTopic, getElavaArkistoServiceType, getElavaArkistoTagArticleRelationTopic, getElavaArkistoTagArticleRelationType, getElavaArkistoTagTopic, getElavaArkistoTagType, getElavaArkistoTimeTopic, getElavaArkistoTimeType, getElavaArkistoType, getIcon, getWandoraType, isValidData, stringify
acceptBrowserExtractRequest, addCrawlerUrl, browserExtractorConsumesPlainText, buildSI, buildSL, clearMasterSubject, createAssociation, createAssociation, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, createTopic, croppedFilename, croppedFilename, croppedUrlString, croppedUrlString, doBrowserExtract, dropExtract, dropExtract, dropExtract, execute, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFrom, extractTopicsFromText, getBrowserExtractorName, getContentTypes, getCrawlerMode, getExtractorType, getForceContent, getForceFiles, getForceUrls, getGUIText, 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, getContext, getToolMenuItem, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptions
forceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setState
public java.lang.String getName()
AbstractWandoraTool
getName
in interface WandoraTool
getName
in class AbstractElavaArkistoExtractor
public java.lang.String getDescription()
AbstractWandoraTool
getDescription
in interface WandoraTool
getDescription
in class AbstractElavaArkistoExtractor
public boolean _extractTopicsFrom(java.io.File f, TopicMap tm) throws java.lang.Exception
_extractTopicsFrom
in class AbstractElavaArkistoExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.net.URL u, TopicMap tm) throws java.lang.Exception
_extractTopicsFrom
in class AbstractElavaArkistoExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.lang.String str, TopicMap tm) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public boolean _extractTopicsFrom(CSVParser.Table table, TopicMap tm) throws java.lang.Exception
java.lang.Exception
Copyright 2004-2015 Wandora Team