Package com.norconex.collector.http.crawler

Class HttpCrawler

java.lang.Object

com.norconex.collector.core.crawler.Crawler

com.norconex.collector.http.crawler.HttpCrawler

public class HttpCrawler
extends Crawler

The HTTP Crawler.

Author:

Pascal Essiembre

See Also:

HttpCrawlerConfig

Nested Class Summary

Nested classes/interfaces inherited from class com.norconex.collector.core.crawler.Crawler

Crawler.ReferenceProcessStatus

Constructor Summary

Constructors

Constructor	Description
HttpCrawler(HttpCrawlerConfig crawlerConfig, HttpCollector collector)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected void	afterCrawlerExecution()
protected void	beforeCrawlerExecution(boolean resume)
protected void	beforeFinalizeDocumentProcessing(CrawlDoc doc)
protected CrawlDocInfo	createChildDocInfo(String embeddedReference, CrawlDocInfo parentCrawlData)
protected void	executeCommitterPipeline(Crawler crawler, CrawlDoc doc)
protected ImporterResponse	executeImporterPipeline(ImporterPipelineContext importerContext)
protected void	executeQueuePipeline(CrawlDocInfo crawlRef)
protected Class<? extends CrawlDocInfo>	getCrawlDocInfoType()
HttpCrawlerConfig	getCrawlerConfig()
IDataStore<String>	getDedupDocumentStore()
IDataStore<String>	getDedupMetadataStore()
HttpFetchClient	getHttpFetchClient()
ISitemapResolver	getSitemapResolver()
protected void	initCrawlDoc(CrawlDoc doc)
protected boolean	isQueueInitialized()
protected void	markReferenceVariationsAsProcessed(CrawlDocInfo crawlRef)

Methods inherited from class com.norconex.collector.core.crawler.Crawler

clean, deleteCacheOrphans, destroyCrawler, doExecute, exportDataStore, getCollector, getCommitterService, getDataStoreEngine, getDocInfoService, getDownloadDir, getEventManager, getId, getImporter, getMonitor, getStreamFactory, getTempDir, getWorkDir, handleOrphans, importDataStore, initCrawler, isMaxDocuments, isStopped, processNextReference, processReferences, reprocessCacheOrphans, start, stop, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

HttpCrawler

public HttpCrawler(HttpCrawlerConfig crawlerConfig,
                   HttpCollector collector)

Constructor.

Parameters:

crawlerConfig - HTTP crawler configuration

collector - http collector this crawler belongs to

Method Detail

getCrawlerConfig

public HttpCrawlerConfig getCrawlerConfig()

Overrides:

getCrawlerConfig in class Crawler

getHttpFetchClient

public HttpFetchClient getHttpFetchClient()

getSitemapResolver

public ISitemapResolver getSitemapResolver()

Returns:

the sitemapResolver

getDedupMetadataStore

public IDataStore<String> getDedupMetadataStore()

getDedupDocumentStore

public IDataStore<String> getDedupDocumentStore()

isQueueInitialized

protected boolean isQueueInitialized()

Overrides:

isQueueInitialized in class Crawler

beforeCrawlerExecution

protected void beforeCrawlerExecution(boolean resume)

Specified by:

beforeCrawlerExecution in class Crawler

afterCrawlerExecution

protected void afterCrawlerExecution()

Specified by:

afterCrawlerExecution in class Crawler

executeQueuePipeline

protected void executeQueuePipeline(CrawlDocInfo crawlRef)

Specified by:

executeQueuePipeline in class Crawler

getCrawlDocInfoType

protected Class<? extends CrawlDocInfo> getCrawlDocInfoType()

Overrides:

getCrawlDocInfoType in class Crawler

initCrawlDoc

protected void initCrawlDoc(CrawlDoc doc)

Overrides:

initCrawlDoc in class Crawler

executeImporterPipeline

protected ImporterResponse executeImporterPipeline(ImporterPipelineContext importerContext)

Specified by:

executeImporterPipeline in class Crawler

createChildDocInfo

protected CrawlDocInfo createChildDocInfo(String embeddedReference,
                                          CrawlDocInfo parentCrawlData)

Specified by:

createChildDocInfo in class Crawler

executeCommitterPipeline

protected void executeCommitterPipeline(Crawler crawler,
                                        CrawlDoc doc)

Specified by:

executeCommitterPipeline in class Crawler

beforeFinalizeDocumentProcessing

protected void beforeFinalizeDocumentProcessing(CrawlDoc doc)

Overrides:

beforeFinalizeDocumentProcessing in class Crawler

markReferenceVariationsAsProcessed

protected void markReferenceVariationsAsProcessed(CrawlDocInfo crawlRef)

Specified by:

markReferenceVariationsAsProcessed in class Crawler