abstract class AbstractJsoupMicroformatExtractor extends AbstractJsoupExtractor
| Modifier and Type | Field and Description |
|---|---|
protected static java.lang.String[] |
ADR_PROPS |
protected static java.lang.String[] |
GEO_PROPS |
private static java.lang.String |
MICROFORMAT_SI |
protected static java.lang.String[] |
NAME_PROPS |
protected static java.lang.String[][] |
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_EXTRACTORCLOSE, EXECUTE, INVISIBLE, VISIBLE, WAITRETURN_ERROR, RETURN_INFO| Constructor and Description |
|---|
AbstractJsoupMicroformatExtractor() |
| Modifier and Type | Method and Description |
|---|---|
protected void |
addProp(Topic topic,
java.lang.String propName,
org.jsoup.nodes.Element prop) |
protected void |
addProp(Topic topic,
Topic topicType,
java.lang.String propName,
org.jsoup.nodes.Element prop) |
javax.swing.Icon |
getIcon()
All tools may have identifying graphic icon used within tool GUI elements.
|
private Topic |
getMicroformatTopic(TopicMap tm) |
protected abstract java.lang.String |
getSIPrefix() |
protected abstract TopicMap |
getTopicMap() |
protected Topic |
getType(java.lang.String typeKey) |
protected abstract java.lang.String[][] |
getTypeStrings() |
protected abstract java.util.HashMap<java.lang.String,Topic> |
getTypeTopics() |
protected void |
parseAdr(Topic parent,
org.jsoup.nodes.Element element,
java.lang.String parentTypeName) |
protected void |
parseGeo(Topic card,
org.jsoup.nodes.Element element,
java.lang.String parentTypeName) |
protected void |
parseName(Topic card,
org.jsoup.nodes.Element element) |
_extractTopicsFrom, _extractTopicsFrom, _extractTopicsFrom, extractTopicsFrom, getContentTypes, getLangTopic, getOrCreateTopic, getOrCreateTopic, getWandoraClassTopic, makeSubclassOfacceptBrowserExtractRequest, 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, getDescription, getExtractorType, getForceContent, getForceFiles, getForceUrls, getGUIText, getGUIText, getInterruptsHandled, getMasterSubject, getName, 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, useURLCrawleraddUndoMarker, 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, writeOptionsclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitconfigure, execute, execute, getContext, getToolMenuItem, hlog, initialize, isConfigurable, isRunning, log, log, log, log, requiresRefresh, setContext, setToolLogger, writeOptionsforceStop, getHistory, getState, lockLog, setLogTitle, setProgress, setProgressMax, setStateprivate static final java.lang.String MICROFORMAT_SI
protected static final java.lang.String[][] TYPE_STRINGS
protected static final java.lang.String[] ADR_PROPS
protected static final java.lang.String[] NAME_PROPS
protected static final java.lang.String[] GEO_PROPS
public javax.swing.Icon getIcon()
AbstractWandoraToolgetIcon should return Icon object of
the tool.getIcon in interface WandoraToolgetIcon in class AbstractJsoupExtractorprivate Topic getMicroformatTopic(TopicMap tm) throws TopicMapException
TopicMapExceptionprotected Topic getType(java.lang.String typeKey) throws TopicMapException
TopicMapExceptionprotected void addProp(Topic topic, java.lang.String propName, org.jsoup.nodes.Element prop) throws TopicMapException
TopicMapExceptionprotected void addProp(Topic topic, Topic topicType, java.lang.String propName, org.jsoup.nodes.Element prop) throws TopicMapException
TopicMapExceptionprotected void parseName(Topic card, org.jsoup.nodes.Element element) throws TopicMapException
TopicMapExceptionprotected void parseAdr(Topic parent, org.jsoup.nodes.Element element, java.lang.String parentTypeName) throws TopicMapException
TopicMapExceptionprotected void parseGeo(Topic card, org.jsoup.nodes.Element element, java.lang.String parentTypeName) throws TopicMapException
TopicMapExceptionprotected abstract java.lang.String[][] getTypeStrings()
protected abstract java.util.HashMap<java.lang.String,Topic> getTypeTopics()
protected abstract TopicMap getTopicMap()
protected abstract java.lang.String getSIPrefix()
Copyright 2004-2015 Wandora Team