public class EuropeanaSearchExtractor extends AbstractEuropeanaExtractor
Modifier and Type | Field and Description |
---|---|
private static java.lang.String |
currentURL |
private static java.lang.String |
defaultEncoding |
private static java.lang.String |
defaultLang |
COLLECTION_NAME_SI, CONCEPT_LABEL_SI, COUNTRY_SI, DATA_PROVIDER_SI, DC_CREATOR_SI, EUROPEANA_SI, GUID_LINK_SI, ITEM_SI, LANG_SI, LANGUAGE_SI, PLACE_LABEL_SI, PREVIEW_LINK_SI, PROVIDER_SI, RIGHTS_LINK_SI, TITLE_SI, TYPE_SI, YEAR_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 |
---|
EuropeanaSearchExtractor() |
Modifier and Type | Method and Description |
---|---|
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 |
doUrl(java.net.URL url) |
java.lang.String |
getDescription()
AdminToolManager views tool descriptions while user browses available
tools and build user customizable GUI elements such as Tools menu.
|
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.
|
void |
parse(org.json.JSONObject json,
TopicMap tm) |
void |
parseResult(org.json.JSONObject result,
TopicMap tm) |
getCollectionNameTopic, getCollectionNameTypeTopic, getConceptLabelTypeTopic, getContentTypes, getCountryTopic, getCountryTypeTopic, getDataProviderTopic, getDataProviderTypeTopic, getDcCreatorTopic, getDcCreatorTypeTopic, getEuropeanaTypeTopic, getGuidLinkTypeTopic, getItemTypeTopic, getLangTopic, getLanguageTypeTopic, getOrCreateTopic, getOrCreateTopic, getPlaceLabelTypeTopic, getPreviewLinkTypeTopic, getProviderTopic, getProviderTypeTopic, getRightsLinkTopic, getRightsLinkTypeTopic, getTitleTypeTopic, getTypeTopic, getTypeTypeTopic, getWandoraClassTopic, getYearTopic, getYearTypeTopic, makeSubclassOf, runInOwnThread, useURLCrawler
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, getCrawlerMode, getExtractorType, getForceContent, getForceFiles, getForceUrls, getGUIText, getGUIText, getInterruptsHandled, getMasterSubject, getType, getWandora, handle, handleContent, handleCustomType, handleFiles, handleForcedContent, handleInterrupt, handleStringContent, handleUrls, initializeCustomType, instantDropHandle, makeSubclassOfWandoraClass, setData, setDisplayName, setForceContent, setForceFiles, setForceUrls, setMasterSubject, setMasterSubject, setTopicMap, setupCrawler, setWandora, takeNap, urlEncode, useTempTopicMap
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
private static java.lang.String defaultEncoding
private static java.lang.String defaultLang
private static java.lang.String currentURL
public java.lang.String getName()
AbstractWandoraTool
getName
in interface WandoraTool
getName
in class AbstractEuropeanaExtractor
public java.lang.String getDescription()
AbstractWandoraTool
getDescription
in interface WandoraTool
getDescription
in class AbstractEuropeanaExtractor
public javax.swing.Icon getIcon()
AbstractWandoraTool
getIcon
should return Icon
object of
the tool.getIcon
in interface WandoraTool
getIcon
in class AbstractEuropeanaExtractor
public boolean _extractTopicsFrom(java.io.File f, TopicMap tm) throws java.lang.Exception
_extractTopicsFrom
in class AbstractEuropeanaExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.net.URL u, TopicMap tm) throws java.lang.Exception
_extractTopicsFrom
in class AbstractEuropeanaExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.lang.String str, TopicMap tm) throws java.lang.Exception
_extractTopicsFrom
in class AbstractEuropeanaExtractor
java.lang.Exception
public java.lang.String doUrl(java.net.URL url) throws java.io.IOException
java.io.IOException
public void parse(org.json.JSONObject json, TopicMap tm) throws TopicMapException
TopicMapException
public void parseResult(org.json.JSONObject result, TopicMap tm) throws org.json.JSONException, TopicMapException
org.json.JSONException
TopicMapException
Copyright 2004-2015 Wandora Team