public class HSFeedExtractor extends AbstractExtractor
Modifier and Type | Class and Description |
---|---|
private static class |
HSFeedExtractor.HSFeedParser |
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 |
---|
HSFeedExtractor()
Creates a new instance of HSFeedExtractor
|
Modifier and Type | Method and Description |
---|---|
boolean |
_extractTopicsFrom(java.io.File file,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.io.InputStream in,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.lang.String str,
TopicMap topicMap) |
boolean |
_extractTopicsFrom(java.net.URL url,
TopicMap topicMap) |
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.
|
java.lang.String |
getName()
Tools name represent the tool in UI unless the tool has been given
explicitly another GUI name.
|
boolean |
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, getIcon, 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
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 HSFeedExtractor()
public boolean useURLCrawler()
useURLCrawler
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 java.lang.String[] getContentTypes()
Handler
ContentHandler
can process.getContentTypes
in interface Handler
getContentTypes
in class AbstractExtractor
public boolean _extractTopicsFrom(java.net.URL url, 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.lang.String str, TopicMap topicMap) throws java.lang.Exception
_extractTopicsFrom
in class AbstractExtractor
java.lang.Exception
public boolean _extractTopicsFrom(java.io.InputStream in, TopicMap topicMap) throws java.lang.Exception
java.lang.Exception
Copyright 2004-2015 Wandora Team