public class JsoupAdrExtractor extends AbstractJsoupMicroformatExtractor
Modifier and Type | Field and Description |
---|---|
private static java.lang.String |
SI_PREFIX |
private TopicMap |
tm |
private java.util.HashMap<java.lang.String,Topic> |
typeTopics |
ADR_PROPS, GEO_PROPS, NAME_PROPS, TYPE_STRINGS
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 |
---|
JsoupAdrExtractor() |
Modifier and Type | Method and Description |
---|---|
boolean |
extractTopicsFrom(org.jsoup.nodes.Document d,
java.lang.String u,
TopicMap t) |
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.
|
protected java.lang.String |
getSIPrefix() |
protected TopicMap |
getTopicMap() |
protected java.lang.String[][] |
getTypeStrings() |
protected java.util.HashMap<java.lang.String,Topic> |
getTypeTopics() |
addProp, addProp, getIcon, getType, parseAdr, parseGeo, parseName
_extractTopicsFrom, _extractTopicsFrom, _extractTopicsFrom, getContentTypes, getLangTopic, getOrCreateTopic, getOrCreateTopic, getWandoraClassTopic, makeSubclassOf
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, 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
private static final java.lang.String SI_PREFIX
private java.util.HashMap<java.lang.String,Topic> typeTopics
private TopicMap tm
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
protected java.lang.String[][] getTypeStrings()
getTypeStrings
in class AbstractJsoupMicroformatExtractor
protected java.util.HashMap<java.lang.String,Topic> getTypeTopics()
getTypeTopics
in class AbstractJsoupMicroformatExtractor
protected TopicMap getTopicMap()
getTopicMap
in class AbstractJsoupMicroformatExtractor
protected java.lang.String getSIPrefix()
getSIPrefix
in class AbstractJsoupMicroformatExtractor
public boolean extractTopicsFrom(org.jsoup.nodes.Document d, java.lang.String u, TopicMap t) throws java.lang.Exception
extractTopicsFrom
in class AbstractJsoupExtractor
java.lang.Exception
Copyright 2004-2015 Wandora Team