| 构造器和说明 |
|---|
Builder() |
| 限定符和类型 | 方法和说明 |
|---|---|
VWCrawler |
build() |
VWCrawler.Builder |
setAbsProxyExtracter(AbstractProxyExtractor extracter) |
VWCrawler.Builder |
setDownloader(AbstractDownloader downloader) |
VWCrawler.Builder |
setHeader(String key,
String value) |
VWCrawler.Builder |
setHeaders(HashMap<String,String> headerMap) |
VWCrawler.Builder |
setPageParser(CrawlerService crawlerService) |
VWCrawler.Builder |
setProxys(List<Proxy2> proxys) |
VWCrawler.Builder |
setRetryCount(int retryCount) |
VWCrawler.Builder |
setSeedsPage(String... seedsPage) |
VWCrawler.Builder |
setSeedsPageUrlRex(String... seedsPageUrlRex)
设置种子页面URL的正则表达式
|
VWCrawler.Builder |
setSeedUrl(String... targetUrl) |
VWCrawler.Builder |
setTargetUrlRex(String... targetUrlRex)
设置目标页URL的正则表达式
|
VWCrawler.Builder |
setThreadCount(int count) |
VWCrawler.Builder |
setTimeOut(int timeOut) |
VWCrawler.Builder |
setUrl(String url) |
public VWCrawler.Builder setUrl(String url)
public VWCrawler.Builder setTimeOut(int timeOut)
public VWCrawler.Builder setSeedUrl(String... targetUrl)
public VWCrawler.Builder setThreadCount(int count)
public VWCrawler.Builder setSeedsPage(String... seedsPage)
public VWCrawler.Builder setTargetUrlRex(String... targetUrlRex)
targetUrlRex - seed url正则表达式public VWCrawler.Builder setSeedsPageUrlRex(String... seedsPageUrlRex)
seedsPageUrlRex - seeds url 正则表达式public VWCrawler.Builder setPageParser(CrawlerService crawlerService)
public VWCrawler.Builder setDownloader(AbstractDownloader downloader)
public VWCrawler.Builder setHeaders(HashMap<String,String> headerMap)
public VWCrawler.Builder setHeader(String key, String value)
public VWCrawler.Builder setProxys(List<Proxy2> proxys)
public VWCrawler.Builder setAbsProxyExtracter(AbstractProxyExtractor extracter)
public VWCrawler.Builder setRetryCount(int retryCount)
public VWCrawler build()
Copyright © 2018. All rights reserved.