VWCrawler.Builder |
VWCrawler.Builder.setAbsProxyExtracter(AbstractProxyExtractor extracter) |
VWCrawler.Builder |
VWCrawler.Builder.setCookie(String key,
String value) |
VWCrawler.Builder |
VWCrawler.Builder.setCookies(Map<String,String> cookies) |
VWCrawler.Builder |
VWCrawler.Builder.setDownloader(AbstractDownloader downloader) |
VWCrawler.Builder |
VWCrawler.Builder.setHeader(String key,
String value) |
VWCrawler.Builder |
VWCrawler.Builder.setHeaders(HashMap<String,String> headerMap) |
VWCrawler.Builder |
VWCrawler.Builder.setPageParser(CrawlerService crawlerService) |
VWCrawler.Builder |
VWCrawler.Builder.setProxys(List<Proxy2> proxys) |
VWCrawler.Builder |
VWCrawler.Builder.setRetryCount(int retryCount) |
VWCrawler.Builder |
VWCrawler.Builder.setSeedsPage(String... seedsPage) |
VWCrawler.Builder |
VWCrawler.Builder.setSeedsPageUrlRex(String... seedsPageUrlRex)
设置种子页面URL的正则表达式
|
VWCrawler.Builder |
VWCrawler.Builder.setSeedUrl(String... targetUrl) |
VWCrawler.Builder |
VWCrawler.Builder.setTargetUrlRex(String... targetUrlRex)
设置目标页URL的正则表达式
|
VWCrawler.Builder |
VWCrawler.Builder.setThreadCount(int count) |
VWCrawler.Builder |
VWCrawler.Builder.setTimeOut(int timeOut) |
VWCrawler.Builder |
VWCrawler.Builder.setUrl(String url) |