public class IcelandicExtractorJS extends org.archive.modules.extractor.ExtractorJS
Modifier and Type | Field and Description |
---|---|
protected static String[] |
EXTRACTOR_URI_EXCEPTIONS |
protected long |
numberOfCURIsHandled |
Constructor and Description |
---|
IcelandicExtractorJS()
Constructor.
|
Modifier and Type | Method and Description |
---|---|
long |
considerStrings(org.archive.modules.extractor.Extractor ext,
org.archive.modules.CrawlURI curi,
CharSequence cs,
boolean handlingJSFile) |
List<Pattern> |
getRejectRelativeMatchingRegexList() |
protected boolean |
innerExtract(org.archive.modules.CrawlURI curi) |
String |
report() |
void |
setRejectRelativeMatchingRegexList(List<Pattern> patterns) |
protected boolean |
shouldExtract(org.archive.modules.CrawlURI uri) |
considerString, considerStrings, considerStrings
add, addOutlink, addOutlink, addRelativeToBase, addRelativeToVia, fromCheckpointJson, getExtractorParameters, getLoggerModule, innerProcess, logUriError, setExtractorParameters, setLoggerModule, toCheckpointJson
doCheckpoint, finishCheckpoint, flattenVia, getBeanName, getEnabled, getKeyedProperties, getRecordedSize, getShouldProcessRule, getURICount, hasHttpAuthenticationCredential, innerProcessResult, innerRejectProcess, isRunning, isSuccess, process, setBeanName, setEnabled, setRecoveryCheckpoint, setShouldProcessRule, start, startCheckpoint, stop
protected long numberOfCURIsHandled
protected static final String[] EXTRACTOR_URI_EXCEPTIONS
public IcelandicExtractorJS()
public List<Pattern> getRejectRelativeMatchingRegexList()
public void setRejectRelativeMatchingRegexList(List<Pattern> patterns)
protected boolean shouldExtract(org.archive.modules.CrawlURI uri)
shouldExtract
in class org.archive.modules.extractor.ExtractorJS
protected boolean innerExtract(org.archive.modules.CrawlURI curi)
innerExtract
in class org.archive.modules.extractor.ExtractorJS
public long considerStrings(org.archive.modules.extractor.Extractor ext, org.archive.modules.CrawlURI curi, CharSequence cs, boolean handlingJSFile)
considerStrings
in class org.archive.modules.extractor.ExtractorJS
Copyright © 2005–2016 The Royal Danish Library, the Danish State and University Library, the National Library of France and the Austrian National Library.. All rights reserved.