Java使用代理服務器

HTTP協議是基於TCP協議的,TCP協議在Java中的體現就是套接字.在了解HTTP協議的基礎上,完全可以通過TCP來實現一套HTTP庫,這個庫可以發起網絡請求和接受網絡請求.只要能用URLConnection能實現的事情,用Socket同樣能夠實現.

代理是"代理服務器",我不直接向百度發起請求,而是向代理服務器發起請求,然后代理服務器代替我向百度發起請求.這樣一來,我的IP地址就不會暴露.在編寫爬蟲時,同一個IP爬多了就會被要求輸入驗證碼,這時就可以通過代理來不停地換IP從而規避驗證碼.

本文提供四種方法,第一種方法通過設置環境變量,第二種方法通過URLConnection,第三種方法通過nio中的SocketChannel,第四種方法通過Socket.

public class TestProxy {
    static String host = "112.126.65.26";
    static int port = 12345;
    static String url = "http://1212.ip138.com/ic.asp";
    public static void main(String[] args) throws Exception {
        four();
    }
    static void one() throws MalformedURLException, IOException {
        // 沒有這句話是不行的
        System.setProperty("http.proxySet", "true");
        System.setProperty("http.proxyHost", host);
        System.setProperty("http.proxyPort", port + "");
        URLConnection connection = new URL(url).openConnection();
        show(connection.getInputStream());
    }
    static void two() throws MalformedURLException, IOException {
        SocketAddress addr = new InetSocketAddress(host, port);
        Proxy proxy = new Proxy(Proxy.Type.HTTP, addr);
        // 下面這個網址會告訴你你的ip地址
        URLConnection connection = new URL(url).openConnection(proxy);
        show(connection.getInputStream());
    }
    // 使用socket也是一樣
    static void three() throws IOException {
        SocketChannel sc = SocketChannel
                .open(new InetSocketAddress(host, port));
        sc.write(Charset.forName("utf8")
                .encode("GET " + url + " HTTP/1.1\r\n\r\n"));
        ByteBuffer buffer = ByteBuffer.allocate(1024);
        while (sc.read(buffer) != -1) {
            buffer.flip();
            System.out.println(Charset.forName("utf8").decode(buffer));
            buffer.clear();
        }
        sc.close();
    }
    static void four() throws IOException {
        // 以下地址是代理服務器的地址
        Socket socket = new Socket(host, port);
        // 寫與的內容就是遵循HTTP請求協議格式的內容，請求百度
        socket.getOutputStream().write(
                new String("GET " + url + " HTTP/1.1\r\n\r\n").getBytes());
        show(socket.getInputStream());
        socket.close();
    }
    static void show(InputStream in) throws IOException {
        Scanner cin = new Scanner(in);
        StringBuilder builder = new StringBuilder();
        while (cin.hasNext()) {
            builder.append(cin.nextLine());
        }
        cin.close();
        Pattern pattern = Pattern
                .compile("\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}");
        Matcher matcher = pattern.matcher(builder.toString());
        matcher.find();
        System.out.println(matcher.group());
    }
}