com.github.vector4wang

类 VWCrawler

java.lang.Object

com.github.vector4wang.VWCrawler

public class VWCrawler
extends Object

vw爬虫的简单配置中心

作者:

vector

嵌套类概要

嵌套类

限定符和类型	类和说明
static class	VWCrawler.Builder

构造器概要

构造器

构造器和说明
VWCrawler()

方法概要

限定符和类型	方法和说明
Set<String>	getCrawledUrls()
CrawlerService	getCrawlerService()
Proxy	getCurrentProxy()
AbstractDownloader	getDownloader()
Map<String,String>	getHeaderMap()
List<Proxy>	getProxys()
ProxyBuilder.Type	getProxyType()
Set<String>	getSeedsPageUrlRex()
Set<String>	getTargetUrlRex()
int	getThreadCount()
int	getTimeout()
String	getUrl()
LinkedBlockingQueue<String>	getWaitCrawlerUrls()
boolean	isTargetUrl(String url)
void	setCrawledUrls(Set<String> crawledUrls)
void	setCrawlerService(CrawlerService crawlerService)
void	setCurrentProxy(Proxy currentProxy)
void	setDownloader(AbstractDownloader downloader)
void	setHeaderMap(Map<String,String> headerMap)
void	setProxys(List<Proxy> proxys)
void	setProxyType(ProxyBuilder.Type proxyType)
void	setSeedsPageUrlRex(Set<String> seedsPageUrlRex)
void	setTargetUrlRex(Set<String> targetUrlRex)
void	setThreadCount(int threadCount)
void	setTimeout(int timeout)
void	setUrl(String url)
void	setWaitCrawlerUrls(LinkedBlockingQueue<String> waitCrawlerUrls)
void	start()

从类继承的方法 java.lang.Object

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

构造器详细资料

VWCrawler

public VWCrawler()

方法详细资料

getUrl

public String getUrl()

setUrl

public void setUrl(String url)

getTimeout

public int getTimeout()

setTimeout

public void setTimeout(int timeout)

getThreadCount

public int getThreadCount()

setThreadCount

public void setThreadCount(int threadCount)

getWaitCrawlerUrls

public LinkedBlockingQueue<String> getWaitCrawlerUrls()

setWaitCrawlerUrls

public void setWaitCrawlerUrls(LinkedBlockingQueue<String> waitCrawlerUrls)

getCrawledUrls

public Set<String> getCrawledUrls()

setCrawledUrls

public void setCrawledUrls(Set<String> crawledUrls)

getTargetUrlRex

public Set<String> getTargetUrlRex()

setTargetUrlRex

public void setTargetUrlRex(Set<String> targetUrlRex)

getSeedsPageUrlRex

public Set<String> getSeedsPageUrlRex()

setSeedsPageUrlRex

public void setSeedsPageUrlRex(Set<String> seedsPageUrlRex)

getCrawlerService

public CrawlerService getCrawlerService()

setCrawlerService

public void setCrawlerService(CrawlerService crawlerService)

getProxys

public List<Proxy> getProxys()

setProxys

public void setProxys(List<Proxy> proxys)

getProxyType

public ProxyBuilder.Type getProxyType()

setProxyType

public void setProxyType(ProxyBuilder.Type proxyType)

getCurrentProxy

public Proxy getCurrentProxy()

setCurrentProxy

public void setCurrentProxy(Proxy currentProxy)

getHeaderMap

public Map<String,String> getHeaderMap()

setHeaderMap

public void setHeaderMap(Map<String,String> headerMap)

getDownloader

public AbstractDownloader getDownloader()

setDownloader

public void setDownloader(AbstractDownloader downloader)

start

public void start()

isTargetUrl

public boolean isTargetUrl(String url)