List of usage examples for org.apache.http.conn.params ConnPerRouteBean setDefaultMaxPerRoute
public void setDefaultMaxPerRoute(final int max)
From source file:org.apache.droids.examples.cli.SimpleRuntime.java
public static void main(String[] args) throws Exception { if (args.length < 1) { System.out.println("Please specify a URL to crawl"); System.exit(-1);//w w w .jav a2 s. c om } String targetURL = args[0]; // Create parser factory. Support basic HTML markup only ParserFactory parserFactory = new ParserFactory(); TikaDocumentParser tikaParser = new TikaDocumentParser(); parserFactory.getMap().put("text/html", tikaParser); // Create protocol factory. Support HTTP/S only. ProtocolFactory protocolFactory = new ProtocolFactory(); // Create and configure HTTP client HttpParams params = new BasicHttpParams(); HttpProtocolParamBean hppb = new HttpProtocolParamBean(params); HttpConnectionParamBean hcpb = new HttpConnectionParamBean(params); ConnManagerParamBean cmpb = new ConnManagerParamBean(params); // Set protocol parametes hppb.setVersion(HttpVersion.HTTP_1_1); hppb.setContentCharset(HTTP.ISO_8859_1); hppb.setUseExpectContinue(true); // Set connection parameters hcpb.setStaleCheckingEnabled(false); // Set connection manager parameters ConnPerRouteBean connPerRouteBean = new ConnPerRouteBean(); connPerRouteBean.setDefaultMaxPerRoute(2); cmpb.setConnectionsPerRoute(connPerRouteBean); DroidsHttpClient httpclient = new DroidsHttpClient(params); HttpProtocol httpProtocol = new HttpProtocol(httpclient); protocolFactory.getMap().put("http", httpProtocol); protocolFactory.getMap().put("https", httpProtocol); // Create URL filter factory. URLFiltersFactory filtersFactory = new URLFiltersFactory(); RegexURLFilter defaultURLFilter = new RegexURLFilter(); defaultURLFilter.setFile("classpath:/regex-urlfilter.txt"); filtersFactory.getMap().put("default", defaultURLFilter); // Create handler factory. Provide sysout handler only. HandlerFactory handlerFactory = new HandlerFactory(); SysoutHandler defaultHandler = new SysoutHandler(); handlerFactory.getMap().put("default", defaultHandler); // Create droid factory. Leave it empty for now. DroidFactory<Link> droidFactory = new DroidFactory<Link>(); // Create default droid SimpleDelayTimer simpleDelayTimer = new SimpleDelayTimer(); simpleDelayTimer.setDelayMillis(100); Queue<Link> simpleQueue = new LinkedList<Link>(); SequentialTaskMaster<Link> taskMaster = new SequentialTaskMaster<Link>(); taskMaster.setDelayTimer(simpleDelayTimer); taskMaster.setExceptionHandler(new DefaultTaskExceptionHandler()); CrawlingDroid helloCrawler = new SysoutCrawlingDroid(simpleQueue, taskMaster); helloCrawler.setFiltersFactory(filtersFactory); helloCrawler.setParserFactory(parserFactory); helloCrawler.setProtocolFactory(protocolFactory); Collection<String> initialLocations = new ArrayList<String>(); initialLocations.add(targetURL); helloCrawler.setInitialLocations(initialLocations); // Initialize and start the crawler helloCrawler.init(); helloCrawler.start(); // Await termination helloCrawler.getTaskMaster().awaitTermination(0, TimeUnit.MILLISECONDS); // Shut down the HTTP connection manager httpclient.getConnectionManager().shutdown(); }
From source file:eu.sisob.uma.api.crawler4j.crawler.PageFetcher.java
public synchronized static void startConnectionMonitorThread() { if (connectionMonitorThread == null) { HttpParams params = new BasicHttpParams(); HttpProtocolParamBean paramsBean = new HttpProtocolParamBean(params); paramsBean.setVersion(HttpVersion.HTTP_1_1); paramsBean.setContentCharset("UTF-8"); paramsBean.setUseExpectContinue(false); params.setParameter("http.useragent", Configurations.getStringProperty("fetcher.user_agent", "crawler4j (http://code.google.com/p/crawler4j/)")); params.setIntParameter("http.socket.timeout", Configurations.getIntProperty("fetcher.socket_timeout", 20000)); params.setIntParameter("http.connection.timeout", Configurations.getIntProperty("fetcher.connection_timeout", 30000)); params.setBooleanParameter("http.protocol.handle-redirects", false); ConnPerRouteBean connPerRouteBean = new ConnPerRouteBean(); connPerRouteBean .setDefaultMaxPerRoute(Configurations.getIntProperty("fetcher.max_connections_per_host", 100)); ConnManagerParams.setMaxConnectionsPerRoute(params, connPerRouteBean); ConnManagerParams.setMaxTotalConnections(params, Configurations.getIntProperty("fetcher.max_total_connections", 100)); SchemeRegistry schemeRegistry = new SchemeRegistry(); schemeRegistry.register(new Scheme("http", PlainSocketFactory.getSocketFactory(), 80)); if (Configurations.getBooleanProperty("fetcher.crawl_https", false)) { schemeRegistry.register(new Scheme("https", SSLSocketFactory.getSocketFactory(), 443)); }//w w w. j av a 2 s .co m connectionManager = new ThreadSafeClientConnManager(params, schemeRegistry); ProjectLogger.LOGGER.setLevel(Level.INFO); httpclient = new DefaultHttpClient(connectionManager, params); connectionMonitorThread = new IdleConnectionMonitorThread(connectionManager); } connectionMonitorThread.start(); }
From source file:it.av.youeat.web.pubsubhubbub.Publisher.java
/** * Constructor//from ww w.j a v a 2 s . co m */ public Publisher() { HttpParams params = new BasicHttpParams(); ConnManagerParams.setMaxTotalConnections(params, 200); ConnPerRouteBean connPerRoute = new ConnPerRouteBean(20); connPerRoute.setDefaultMaxPerRoute(50); ConnManagerParams.setMaxConnectionsPerRoute(params, connPerRoute); SchemeRegistry schemeRegistry = new SchemeRegistry(); schemeRegistry.register(new Scheme("http", PlainSocketFactory.getSocketFactory(), 80)); ClientConnectionManager cm = new ThreadSafeClientConnManager(params, schemeRegistry); httpClient = new DefaultHttpClient(cm, params); httpClient.setKeepAliveStrategy(new ConnectionKeepAliveStrategy() { public long getKeepAliveDuration(HttpResponse response, HttpContext context) { HeaderElementIterator it = new BasicHeaderElementIterator( response.headerIterator(HTTP.CONN_KEEP_ALIVE)); while (it.hasNext()) { HeaderElement he = it.nextElement(); String param = he.getName(); String value = he.getValue(); if (value != null && param.equalsIgnoreCase("timeout")) { try { return Long.parseLong(value) * 1000; } catch (NumberFormatException ignore) { } } } // default keepalive is 60 seconds. This is higher than usual // since the number of hubs it should be talking to should be // small return 30 * 1000; } }); }