Http客戶端程序已集成在Java語言中,可以通過URLConnection類調用。遺憾的是,由於SUN沒有公布Http客戶程序的源碼,它實現的細節仍是一個謎。本文根據HTTP協議規范,用Java.net.Socket類實現一個HTTP協議客戶端程序。
1.Socket類:
了解TCP/IP協議集通信的讀者知道,協議間的通信是通過Socket完成的。在Java.net包中,Socket類就是對Socket的具體實現。它通過連接到主機後,返回一個I/O流,實現協議間的信息交換。
2 . HTTP協議
HTTP協議同其它TCP/IP協議集中的協議一樣,是遵循客戶/服務器模型工作的。客戶端發往服務端的信息格式如下:
請求方法 URL HTTP協議的版本號
提交的元信息
**空行**
實體
請求方法是對這次連接工作的說明,目前HTTP協議已經發展到1.1版,它包括GET、HEAD、POST、DELETE、OPTIONS、TRACE、PUT七種。元信息是關於當前請求的信息。通過分析元信息,可以檢查實體數據是否完整,接收過程是否出錯,類型是否匹配等。元信息的引入使HTTP協議通信更加穩妥可靠。實體是請求的具體內容。
將上述報文發往Web服務器,如果成功,應答格式如下:
HTTP協議的版本號 應答狀態碼 應答狀態碼說明
接收的元信息
**空行**
實體
以上報文發向客戶端,並且接收成功,彼此間關閉連接,完成一次握手。下面用最常用的GET方法,來說明具體的報文應用:
GET http://www.youhost.com HTTP/1.0
accept: www/source; text/html; image/gif; image/jpeg; */*
User_Agent: myAgent
**空行**
這個報文是向www.youhost.com主機請求一個缺省HTML文檔。客戶端HTTP協議版本號是1.0版,元信息包括可接收的文件格式,用戶代理,每一段之間用回車換行符分隔,最後以一個空行結束。發向服務器後,如果執行過程正常,服務器返回以下代碼:
HTTP/1.1 200 OK
Date: Tue, 14 Sep 1999 02:19:57 GMT
Server: Apache/1.2.6
Connection: close
Content-Type: text/html
**空行**
<html><head>...</head><body>...</body></html>
HTTP/1.1表示這個HTTP服務器是1.1版,200是服務器對客戶請求的應答狀態碼,OK是對應答狀態碼的解釋,之後是這個文檔的元信息和文檔正文。(相關應答狀態碼和元信息的解釋請參閱Inetrnet標准草案:RFC2616)。
3. HTTP客戶端程序:
import java.net.*;
import java.io.*;
import java.util.Properties;
import java.util.Enumeration;
public class Http {
protected Socket client;
protected BufferedOutputStream sender;
protected BufferedInputStream receiver;
protected ByteArrayInputStream byteStream;
protected URL target;
private int responseCode=-1;
private String responseMessage="";
private String serverVersion="";
private Properties header = new Properties();
public Http() { }
public Http(String url) {
GET(url) ;
}
/* GET方法根據URL,會請求文件、數據庫查詢結果、程序運行結果等多種內容 */
public void GET(String url) {
try {
checkHTTP(url);
openServer(target.getHost(),target.getPort() );
String cmd = "GET "+ getURLFormat(target) +" HTTP/1.0\r\n"
+ getBaseHeads()+"\r\n";
sendMessage(cmd);
receiveMessage();
}catch(ProtocolException p) {
p.printStackTrace();
return;
}catch(UnknownHostException e) {
e.printStackTrace();
return;
}catch(IOException i)
i.printStackTrace();
return;
}
}
/*
* HEAD方法只請求URL的元信息,不包括URL本身。若懷疑本機和服務器上的
* 文件相同,用這個方法檢查最快捷有效。
*/
public void HEAD(String url) {
try {
checkHTTP(url);
openServer(target.getHost(),target.getPort() );
String cmd = "HEAD "+getURLFormat(target)+" HTTP/1.0\r\n"
+getBaseHeads()+"\r\n";
sendMessage(cmd);
receiveMessage();
}catch(ProtocolException p) {
p.printStackTrace();
return;
}catch(UnknownHostException e) {
e.printStackTrace();
return;
}catch(IOException i)
i.printStackTrace();
return;
}
}
/*
* POST方法是向服務器傳送數據,以便服務器做出相應的處理。例如網頁上常用的
* 提交表格。
*/
public void POST(String url,String content) {
try {
checkHTTP(url);
openServer(target.getHost(),target.getPort() );
String cmd = "POST "+ getURLFormat(target) +"
HTTP/1.0\r\n"+getBaseHeads();
cmd += "Content-type: application/x-www-form-urlencoded\r\n";
cmd += "Content-length: " + content.length() + "\r\n\r\n";
cmd += content+"\r\n";
sendMessage(cmd);
receiveMessage();
}catch(ProtocolException p) {
p.printStackTrace();
return;
}catch(UnknownHostException e) {
e.printStackTrace();
return;
}catch(IOException i)
i.printStackTrace();
return;
}
}
protected void checkHTTP(String url) throws ProtocolException {
try {
URL target = new URL(url);
if(target==null || !target.getProtocol().toUpperCase().equals("HTTP") )
throw new ProtocolException("這不是HTTP協議");
this.target = target;
}catch(MalformedURLException m) {
throw new ProtocolException("協議格式錯誤");
}
}
/*
* 與Web服務器連接。若找不到Web服務器,InetAddress會引發UnknownHostException
* 異常。若Socket連接失敗,會引發IOException異常。
*/
protected void openServer(String host,int port) throws
UnknownHostException,IOException {
header.clear();
responseMessage=""; responseCode=-1;
try {
if(client!=null) closeServer();
if(byteStream != null) {
byteStream.close(); byteStream=null;
}
InetAddress address = InetAddress.getByName(host);
client = new Socket(address,port==-1?80:port);
sender = new BufferedOutputStream(client.getOutputStream());
receiver = new BufferedInputStream(client.getInputStream());
}catch(UnknownHostException u) {
throw u;
}catch(IOException i) {
throw i;
}
}
/* 關閉與Web服務器的連接 */
protected void closeServer() throws IOException {
if(client==null) return;
try {
client.close(); sender.close(); receiver.close();
}catch(IOException i) {
throw i;
}
client=null; sender=null; receiver=null;
}
protected String getURLFormat(URL target) {
String spec = "http://"+target.getHost();
if(target.getPort()!=-1)
spec+=":"+target.getPort();
return spec+=target.getFile();
}
/* 向Web服務器傳送數據 */
protected void sendMessage(String data) throws IOException{
sender.write(data.getBytes(),0,data.length());
sender.flush();
}
/* 接收來自Web服務器的數據 */
protected void receiveMessage() throws IOException{
byte data[] = new byte[1024];
int count=0;
int word=-1;
// 解析第一行
while( (word=receiver.read())!=-1 ) {
if(word=='\r'||word=='\n') {
word=receiver.read();
if(word=='\n') word=receiver.read();
break;
}
if(count == data.length) data = addCapacity(data);
data[count++]=(byte)word;
}
String message = new String(data,0,count);
int mark = message.indexOf(32);
serverVersion = message.substring(0,mark);
while( mark<message.length() && message.charAt(mark+1)==32 ) mark++;
responseCode = Integer.parseInt(message.substring(mark+1,mark+=4));
responseMessage = message.substring(mark,message.length()).trim();
// 應答狀態碼和處理請讀者添加
switch(responseCode) {
case 400:
throw new IOException("錯誤請求");
case 404:
throw new FileNotFoundException( getURLFormat(target) );
case 503:
throw new IOException("服務器不可用" );
}
if(word==-1) throw new ProtocolException("信息接收異常終止");
int symbol=-1;
count=0;
// 解析元信息
while( word!='\r' && word!='\n' && word>-1) {
if(word=='\t') word=32;
if(count==data.length) data = addCapacity(data);
data[count++] = (byte)word;
parseLine: {
while( (symbol=receiver.read()) >-1 ) {
switch(symbol) {
case '\t':
symbol=32; break;
case '\r':
case '\n':
word = receiver.read();
if( symbol=='\r' && word=='\n') {
word=receiver.read();
if(word=='\r') word=receiver.read();
}
if( word=='\r' || word=='\n' || word>32) break parseLine;
symbol=32; break;
}
if(count==data.length) data = addCapacity(data);
data[count++] = (byte)symbol;
}
word=-1;
}
message = new String(data,0,count);
mark = message.indexOf(':');
String key = null;
if(mark>0) key = message.substring(0,mark);
mark++;
while( mark<message.length() && message.charAt(mark)<=32 ) mark++;
String value = message.substring(mark,message.length() );
header.put(key,value);
count=0;
}
// 獲得正文數據
while( (word=receiver.read())!=-1) {
if(count == data.length) data = addCapacity(data);
data[count++] = (byte)word;
}
if(count>0) byteStream = new ByteArrayInputStream(data,0,count);
data=null;
closeServer();
}
public String getResponseMessage() {
return responseMessage;
}
public int getResponseCode() {
return responseCode;
}
public String getServerVersion() {
return serverVersion;
}
public InputStream getInputStream() {
return byteStream;
}
public synchronized String getHeaderKey(int i) {
if(i>=header.size()) return null;
Enumeration enum = header.propertyNames();
String key = null;
for(int j=0; j<=i; j++)
key = (String)enum.nextElement();
return key;
}
public synchronized String getHeaderValue(int i) {
if(i>=header.size()) return null;
return header.getProperty(getHeaderKey(i));
}
public synchronized String getHeaderValue(String key) {
return header.getProperty(key);
}
protected String getBaseHeads() {
String inf = "User-Agent: myselfHttp/1.0\r\n"+
"Accept: www/source; text/html; image/gif; */*\r\n";
return inf;
}
private byte[] addCapacity(byte rece[]){
byte temp[] = new byte[rece.length+1024];
System.arraycopy(rece,0,temp,0,rece.length);
return temp;
}
}
注: 程序中只實現GET、HEAD、POST三種方法。其他幾種因不常使用,暫且忽略。