HttpClient4.5使用RequestConfig配置连接信息

本文作者：合肥工业大学 管理学院 钱洋 email：1563178220@qq.com 内容可能有不到之处，欢迎交流。

未经本人允许禁止转载。

RequestConfig类

在构建网络爬虫时，经常需要配置很多信息，例如RequestTimeout（连接池获取到连接的超时时间）、ConnectTimeout（建立连接的超时）、SocketTimeout（获取数据的超时时间)、代理、是否允许重定向等信息。
在HttpClient，实现这些配置需要使用到RequestConfig类的一个内部类Builder。如下为Builder的源码：

    public static class Builder {

        private boolean expectContinueEnabled;
        private HttpHost proxy;
        private InetAddress localAddress;
        private boolean staleConnectionCheckEnabled;
        private String cookieSpec;
        private boolean redirectsEnabled;
        private boolean relativeRedirectsAllowed;
        private boolean circularRedirectsAllowed;
        private int maxRedirects;
        private boolean authenticationEnabled;
        private Collection<String> targetPreferredAuthSchemes;
        private Collection<String> proxyPreferredAuthSchemes;
        private int connectionRequestTimeout;
        private int connectTimeout;
        private int socketTimeout;
        private boolean contentCompressionEnabled;

        Builder() {
            super();
            this.staleConnectionCheckEnabled = false;
            this.redirectsEnabled = true;
            this.maxRedirects = 50;
            this.relativeRedirectsAllowed = true;
            this.authenticationEnabled = true;
            this.connectionRequestTimeout = -1;
            this.connectTimeout = -1;
            this.socketTimeout = -1;
            this.contentCompressionEnabled = true;
        }

        public Builder setExpectContinueEnabled(final boolean expectContinueEnabled) {
            this.expectContinueEnabled = expectContinueEnabled;
            return this;
        }

        public Builder setProxy(final HttpHost proxy) {
            this.proxy = proxy;
            return this;
        }

        public Builder setLocalAddress(final InetAddress localAddress) {
            this.localAddress = localAddress;
            return this;
        }

        /**
         * @deprecated (4.4) Use {@link
         *   org.apache.http.impl.conn.PoolingHttpClientConnectionManager#setValidateAfterInactivity(int)}
         */
        @Deprecated
        public Builder setStaleConnectionCheckEnabled(final boolean staleConnectionCheckEnabled) {
            this.staleConnectionCheckEnabled = staleConnectionCheckEnabled;
            return this;
        }

        public Builder setCookieSpec(final String cookieSpec) {
            this.cookieSpec = cookieSpec;
            return this;
        }

        public Builder setRedirectsEnabled(final boolean redirectsEnabled) {
            this.redirectsEnabled = redirectsEnabled;
            return this;
        }

        public Builder setRelativeRedirectsAllowed(final boolean relativeRedirectsAllowed) {
            this.relativeRedirectsAllowed = relativeRedirectsAllowed;
            return this;
        }

        public Builder setCircularRedirectsAllowed(final boolean circularRedirectsAllowed) {
            this.circularRedirectsAllowed = circularRedirectsAllowed;
            return this;
        }

        public Builder setMaxRedirects(final int maxRedirects) {
            this.maxRedirects = maxRedirects;
            return this;
        }

        public Builder setAuthenticationEnabled(final boolean authenticationEnabled) {
            this.authenticationEnabled = authenticationEnabled;
            return this;
        }

        public Builder setTargetPreferredAuthSchemes(final Collection<String> targetPreferredAuthSchemes) {
            this.targetPreferredAuthSchemes = targetPreferredAuthSchemes;
            return this;
        }

        public Builder setProxyPreferredAuthSchemes(final Collection<String> proxyPreferredAuthSchemes) {
            this.proxyPreferredAuthSchemes = proxyPreferredAuthSchemes;
            return this;
        }

        public Builder setConnectionRequestTimeout(final int connectionRequestTimeout) {
            this.connectionRequestTimeout = connectionRequestTimeout;
            return this;
        }

        public Builder setConnectTimeout(final int connectTimeout) {
            this.connectTimeout = connectTimeout;
            return this;
        }

        public Builder setSocketTimeout(final int socketTimeout) {
            this.socketTimeout = socketTimeout;
            return this;
        }

        /**
         * @deprecated (4.5) Set {@link #setContentCompressionEnabled(boolean)} to {@code false} and
         * add the {@code Accept-Encoding} request header.
         */
        @Deprecated
        public Builder setDecompressionEnabled(final boolean decompressionEnabled) {
            this.contentCompressionEnabled = decompressionEnabled;
            return this;
        }

        public Builder setContentCompressionEnabled(final boolean contentCompressionEnabled) {
            this.contentCompressionEnabled = contentCompressionEnabled;
            return this;
        }

        public RequestConfig build() {
            return new RequestConfig(
                    expectContinueEnabled,
                    proxy,
                    localAddress,
                    staleConnectionCheckEnabled,
                    cookieSpec,
                    redirectsEnabled,
                    relativeRedirectsAllowed,
                    circularRedirectsAllowed,
                    maxRedirects,
                    authenticationEnabled,
                    targetPreferredAuthSchemes,
                    proxyPreferredAuthSchemes,
                    connectionRequestTimeout,
                    connectTimeout,
                    socketTimeout,
                    contentCompressionEnabled);
        }

    }

超时相关配置

HttpClient中可设置三个超时：RequestTimeout（连接池获取到连接的超时时间）、ConnectTimeout（建立连接的超时）、SocketTimeout（获取数据的超时时间）。使用RequestConfig进行配置的示例程序如下：

		//全部设置为10秒
		RequestConfig requestConfig = RequestConfig.custom()
				.setSocketTimeout(10000)
				.setConnectTimeout(10000)
				.setConnectionRequestTimeout(10000)
				.build();
		//配置httpClient
		HttpClient httpClient = HttpClients.custom()
				.setDefaultRequestConfig(requestConfig)
				.build();

代理配置

		RequestConfig defaultRequestConfig = RequestConfig.custom()
				.setProxy(new HttpHost("171.97.67.160", 3128, null))
				.build();   //添加代理
		HttpClient httpClient = HttpClients.custom().
				setDefaultRequestConfig(defaultRequestConfig).build();  //配置httpClient