HttpClient 实现 socks 代理

httpclient 实现 socks 代理

使用的环境

<dependency><groupId>org.apache.httpcomponents</groupId><artifactId>httpclient</artifactId><version>4.4.1</version></dependency><dependency><groupId>org.apache.httpcomponents</groupId><artifactId>httpcore</artifactId><version>4.4.1</version></dependency>

代码及 ConnectionSocketFactory 实现类

package xxx;import com.lucas.admin.util.HttpClientUtil;
import org.apache.http.HttpEntity;
import org.apache.http.HttpHost;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.config.Registry;
import org.apache.http.config.RegistryBuilder;
import org.apache.http.conn.socket.ConnectionSocketFactory;
import org.apache.http.conn.socket.PlainConnectionSocketFactory;
import org.apache.http.conn.ssl.SSLConnectionSocketFactory;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
import org.apache.http.protocol.HttpContext;
import org.apache.http.ssl.SSLContexts;
import org.apache.http.util.EntityUtils;import java.io.IOException;
import java.net.InetSocketAddress;
import java.net.Proxy;
import java.net.Socket;/*** @author kzcming* @since 2020/11/19 15:51*/public class Test {public static void main(String[] args) throws Exception {test("https://www.cnblogs.com/");}public static void test(String url) throws Exception{// ConnectionSocketFactory注册Registry<ConnectionSocketFactory> reg = RegistryBuilder.<ConnectionSocketFactory>create().register("http", new MyConnectionSocketFactory()).register("https",new MySSLConnectionSocketFactory()).build();// HTTP客户端连接管理池PoolingHttpClientConnectionManager connManager = new PoolingHttpClientConnectionManager(reg);CloseableHttpClient httpclient = HttpClients.custom().setConnectionManager(connManager).build();try {// socks代理地址 , socks 地址和端口,这里随便写了一个1008InetSocketAddress socksaddr = new InetSocketAddress("你的地址", 1008);HttpClientContext context = HttpClientContext.create();context.setAttribute("socks.address", socksaddr);// 请求目标HttpGet request = new HttpGet(url);System.out.println("----------------------------------------");System.out.println("执行请求 ：" + request.getRequestLine());System.out.println("通过代理： " + socksaddr);System.out.println("----------------------------------------");CloseableHttpResponse response = httpclient.execute(request, context);try {HttpEntity entity = response.getEntity();System.out.println("----------------------------------------");System.out.println("返回响应：" + response.getStatusLine());System.out.println("响应内容：" + EntityUtils.toString(entity));System.out.println("----------------------------------------");} finally {response.close();}} finally {httpclient.close();}}/*** 实现 http 链接的socket 工厂*/static class MyConnectionSocketFactory extends PlainConnectionSocketFactory {@Overridepublic Socket createSocket(final HttpContext context) throws IOException {InetSocketAddress socksaddr = (InetSocketAddress) context.getAttribute("socks.address");// socket代理Proxy proxy = new Proxy(Proxy.Type.SOCKS, socksaddr);return new Socket(proxy);}}/*** 实现 https 链接的socket 工厂*/static class MySSLConnectionSocketFactory extends SSLConnectionSocketFactory {public MySSLConnectionSocketFactory() {super(SSLContexts.createDefault(), getDefaultHostnameVerifier());}@Overridepublic Socket createSocket(final HttpContext context) throws IOException {InetSocketAddress socksaddr = (InetSocketAddress) context.getAttribute("socks.address");
//            // socket代理Proxy proxy = new Proxy(Proxy.Type.SOCKS, socksaddr);return new Socket(proxy);}}}

说明

为什么非得实现一个ConnectionSocketFactory 类,因为这个类,可以看出来这个类就是底层socket请求的时候,创建socket,请求套接字,指定请求ip和端口的,而 socks 协议是通过 socket 实现的协议,

如果不实现一个 ConnectionSocketFactory 实现类,最后在请求的时候,会直接访问原来网址绑定的ip和端口,实现了这个接口,在请求的时候就相当于在待请求的目标地址外,包了一层外壳,会先去请求 socks 代理地址和端口,

具体详情请看 org.apache.http.impl.conn.DefaultHttpClientConnectionOperator 类的 connect 方法,部分代码如下

public void connect(final ManagedHttpClientConnection conn,final HttpHost host,final InetSocketAddress localAddress,final int connectTimeout,final SocketConfig socketConfig,final HttpContext context) throws IOException {final Lookup<ConnectionSocketFactory> registry = getSocketFactoryRegistry(context);final ConnectionSocketFactory sf = registry.lookup(host.getSchemeName());if (sf == null) {throw new UnsupportedSchemeException(host.getSchemeName() +" protocol is not supported");}final InetAddress[] addresses = host.getAddress() != null ?new InetAddress[] { host.getAddress() } : this.dnsResolver.resolve(host.getHostName());final int port = this.schemePortResolver.resolve(host);for (int i = 0; i < addresses.length; i++) {final InetAddress address = addresses[i];final boolean last = i == addresses.length - 1;Socket sock = sf.createSocket(context);sock.setSoTimeout(socketConfig.getSoTimeout());sock.setReuseAddress(socketConfig.isSoReuseAddress());sock.setTcpNoDelay(socketConfig.isTcpNoDelay());sock.setKeepAlive(socketConfig.isSoKeepAlive());if (socketConfig.getRcvBufSize() > 0) {sock.setReceiveBufferSize(socketConfig.getRcvBufSize());}if (socketConfig.getSndBufSize() > 0) {sock.setSendBufferSize(socketConfig.getSndBufSize());}final int linger = socketConfig.getSoLinger();if (linger >= 0) {sock.setSoLinger(true, linger);}conn.bind(sock);final InetSocketAddress remoteAddress = new InetSocketAddress(address, port);if (this.log.isDebugEnabled()) {this.log.debug("Connecting to " + remoteAddress);}try {sock = sf.connectSocket(connectTimeout, sock, host, remoteAddress, localAddress, context);conn.bind(sock);if (this.log.isDebugEnabled()) {this.log.debug("Connection established " + conn);}return;
........

如果是http协议的代理或者 https 协议的代理,则需要在创建 HttpClientBuilder 的时候在 setProxy 方法中指定一个代理,最后会在 build() 创建 HttpClient的时候,根据有无代理,

创建HttpRoutePlanner,创建部分代码如下

........
HttpRoutePlanner routePlannerCopy = this.routePlanner;if (routePlannerCopy == null) {SchemePortResolver schemePortResolverCopy = this.schemePortResolver;if (schemePortResolverCopy == null) {schemePortResolverCopy = DefaultSchemePortResolver.INSTANCE;}if (proxy != null) {routePlannerCopy = new DefaultProxyRoutePlanner(proxy, schemePortResolverCopy);} else if (systemProperties) {routePlannerCopy = new SystemDefaultRoutePlanner(schemePortResolverCopy, ProxySelector.getDefault());} else {routePlannerCopy = new DefaultRoutePlanner(schemePortResolverCopy);}}
........

最后会在 HttpClient 的实现类的doExecute 方法中,根据HttpRoutePlanner 的实现类的 determineRoute 去创建HttpRoute ,最后在由 ClientExecChain 的实现类,去执行 CloseableHttpResponse execute(
            HttpRoute route,
            HttpRequestWrapper request,
            HttpClientContext clientContext,
            HttpExecutionAware execAware) throws IOException, HttpException; 得到响应
以下是 DefaultRoutePlanner 的 determineRoute 方法代码

@Overridepublic HttpRoute determineRoute(final HttpHost host,final HttpRequest request,final HttpContext context) throws HttpException {Args.notNull(request, "Request");if (host == null) {throw new ProtocolException("Target host is not specified");}final HttpClientContext clientContext = HttpClientContext.adapt(context);final RequestConfig config = clientContext.getRequestConfig();final InetAddress local = config.getLocalAddress();HttpHost proxy = config.getProxy();if (proxy == null) {proxy = determineProxy(host, request, context);}final HttpHost target;if (host.getPort() <= 0) {try {target = new HttpHost(host.getHostName(),this.schemePortResolver.resolve(host),host.getSchemeName());} catch (final UnsupportedSchemeException ex) {throw new HttpException(ex.getMessage());}} else {target = host;}final boolean secure = target.getSchemeName().equalsIgnoreCase("https");if (proxy == null) {return new HttpRoute(target, local, secure);} else {return new HttpRoute(target, local, proxy, secure);}}