HttpClient 3.x,4.x都提供http连接池管理器,当使用了请求连接池管理器(比如PoolingHttpClientConnectionManager)后,HttpClient就可以同时执行多个线程的请求了。
hc3.x和4.x的早期版本,提供了PoolingClientConnectionManager,DefaultHttpClient等类来实现http连接池,但这些类在4.3.x版本之后大部分就已经过时,本文使用4.3.x提供的最新的PoolingHttpClientConnectionManager等类进行http连接池的实现.
废话不多说,下面是全部代码:
public class PoolTest { private static void config(HttpRequestBase httpRequestBase) { httpRequestBase.setHeader("User-Agent", "Mozilla/5.0"); httpRequestBase.setHeader("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"); httpRequestBase.setHeader("Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3");//"en-US,en;q=0.5"); httpRequestBase.setHeader("Accept-Charset", "ISO-8859-1,utf-8,gbk,gb2312;q=0.7,*;q=0.7"); // 配置请求的超时设置 RequestConfig requestConfig = RequestConfig.custom() .setConnectionRequestTimeout(3000) .setConnectTimeout(3000) .setSocketTimeout(3000) .build(); httpRequestBase.setConfig(requestConfig); } public static void main(String[] args) { ConnectionSocketFactory plainsf = PlainConnectionSocketFactory.getSocketFactory(); LayeredConnectionSocketFactory sslsf = SSLConnectionSocketFactory.getSocketFactory(); Registry<ConnectionSocketFactory> registry = RegistryBuilder.<ConnectionSocketFactory>create() .register("http", plainsf) .register("https", sslsf) .build(); PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager(registry); // 将最大连接数增加到200 cm.setMaxTotal(200); // 将每个路由基础的连接增加到20 cm.setDefaultMaxPerRoute(20); // 将目标主机的最大连接数增加到50 HttpHost localhost = new HttpHost("http://blog.csdn.net/gaolu",80); cm.setMaxPerRoute(new HttpRoute(localhost), 50); //请求重试处理 HttpRequestRetryHandler httpRequestRetryHandler = new HttpRequestRetryHandler() { public boolean retryRequest(IOException exception,int executionCount, HttpContext context) { if (executionCount >= 5) {// 如果已经重试了5次,就放弃 return false; } if (exception instanceof NoHttpResponseException) {// 如果服务器丢掉了连接,那么就重试 return true; } if (exception instanceof SSLHandshakeException) {// 不要重试SSL握手异常 return false; } if (exception instanceof InterruptedIOException) {// 超时 return false; } if (exception instanceof UnknownHostException) {// 目标服务器不可达 return false; } if (exception instanceof ConnectTimeoutException) {// 连接被拒绝 return false; } if (exception instanceof SSLException) {// ssl握手异常 return false; } HttpClientContext clientContext = HttpClientContext.adapt(context); HttpRequest request = clientContext.getRequest(); // 如果请求是幂等的,就再次尝试 if (!(request instanceof HttpEntityEnclosingRequest)) { return true; } return false; } }; CloseableHttpClient httpClient = HttpClients.custom() .setConnectionManager(cm) .setRetryHandler(httpRequestRetryHandler) .build(); // URL列表数组 String[] urisToGet = { "http://blog.csdn.net/gaolu/article/details/48466059", "http://blog.csdn.net/gaolu/article/details/48243103", "http://blog.csdn.net/gaolu/article/details/47656987", "http://blog.csdn.net/gaolu/article/details/47055029", "http://blog.csdn.net/gaolu/article/details/46400883", "http://blog.csdn.net/gaolu/article/details/46359127", "http://blog.csdn.net/gaolu/article/details/46224821", "http://blog.csdn.net/gaolu/article/details/45305769", "http://blog.csdn.net/gaolu/article/details/43701763", "http://blog.csdn.net/gaolu/article/details/43195449", "http://blog.csdn.net/gaolu/article/details/42915521", "http://blog.csdn.net/gaolu/article/details/41802319", "http://blog.csdn.net/gaolu/article/details/41045233", "http://blog.csdn.net/gaolu/article/details/40395425", "http://blog.csdn.net/gaolu/article/details/40047065", "http://blog.csdn.net/gaolu/article/details/39891877", "http://blog.csdn.net/gaolu/article/details/39499073", "http://blog.csdn.net/gaolu/article/details/39314327", "http://blog.csdn.net/gaolu/article/details/38820809", "http://blog.csdn.net/gaolu/article/details/38439375", }; long start = System.currentTimeMillis(); try { int pagecount = urisToGet.length; ExecutorService executors = Executors.newFixedThreadPool(pagecount); CountDownLatch countDownLatch = new CountDownLatch(pagecount); for(int i = 0; i< pagecount;i++){ HttpGet httpget = new HttpGet(urisToGet[i]); config(httpget); //启动线程抓取 executors.execute(new GetRunnable(httpClient,httpget,countDownLatch)); } countDownLatch.await(); executors.shutdown(); } catch (InterruptedException e) { e.printStackTrace(); } finally { System.out.println("线程" + Thread.currentThread().getName() + "," + System.currentTimeMillis() + ", 所有线程已完成,开始进入下一步!"); } long end = System.currentTimeMillis(); System.out.println("consume -> " + (end - start)); } static class GetRunnable implements Runnable { private CountDownLatch countDownLatch; private final CloseableHttpClient httpClient; private final HttpGet httpget; public GetRunnable(CloseableHttpClient httpClient, HttpGet httpget, CountDownLatch countDownLatch){ this.httpClient = httpClient; this.httpget = httpget; this.countDownLatch = countDownLatch; } @Override public void run() { CloseableHttpResponse response = null; try { response = httpClient.execute(httpget,HttpClientContext.create()); HttpEntity entity = response.getEntity(); System.out.println(EntityUtils.toString(entity, "utf-8")) ; EntityUtils.consume(entity); } catch (IOException e) { e.printStackTrace(); } finally { countDownLatch.countDown(); try { if(response != null) response.close(); } catch (IOException e) { e.printStackTrace(); } } } } }
主要参考文档:
http://free0007.iteye.com/blog/2012308