# 1
hi there
first I'm not really understand you meaning, sorry for my bad english, anyway if the key word "water" is what you want, you could first make the query request, then with response return by the server, you search for a particular line or words that can uniquely identify the key word "water", eg. the google search input text box, but unfortunately you can't do this by the URL Class, as google will alway return you a 403 error, to do this you need to implement your own socket program to make the http request, this is exactly what I'm doing, and now I'm stucking on the session problem, anyway if you want here is am example, just copyand run it and you will get your "water" :-)
import java.net.*;
import java.io.*;
import java.util.Properties;
import java.util.Enumeration;
import java.util.regex.Pattern;
import java.util.regex.Matcher;
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);
}
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;
}
}
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;
}
}
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("\u8FD9\u4E0D\u662FHTTP\u534F\u8BAE");
}
this.target=target;
}
catch(MalformedURLException m)
{
throw new ProtocolException("\u534F\u8BAE\u683C\u5F0F\u9519\u8BEF");
}
}
protected void openServer(String host, int port) throws UnknownHostException,
IOException
{
header.clear();
responseMessage="";
responseCode=-1;
if(client!=null)
{
closeServer();
}
if(byteStream!=null)
{
byteStream.close();
byteStream=null;
}
InetAddress address=InetAddress.getByName(host);
client=new Socket(address, port==-1?80:port);
client.setSoTimeout(5000);
sender=new BufferedOutputStream(client.getOutputStream());
receiver=new BufferedInputStream(client.getInputStream());
}
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();
}
protected void sendMessage(String data) throws IOException
{
sender.write(data.getBytes(), 0, data.length());
sender.flush();
}
protected void receiveMessage() throws IOException
{
byte data[]=new byte[1024];
int count=0;
int word=-1;
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();
switch(responseCode)
{
case 400:
throw new IOException("\u9519\u8BEF\u8BF7\u6C42");
case 404:
throw new FileNotFoundException(getURLFormat(target));
case 503:
throw new IOException("\u670D\u52A1\u5668\u4E0D\u53EF\u7528");
}
if(word==-1)
{
throw new ProtocolException("\u4FE1\u606F\u63A5\u6536\u5F02\u5E38\u7EC8\u6B62");
}
int symbol=-1;
count=0;
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;
}
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 enumss=header.propertyNames();
String key=null;
for(int j=0; j<=i; j++)
{
key=(String)enumss.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: ZealHttp/1.0\r\nAccept: 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;
}
public static void main(String[] arg)
{
try
{
Http http=new Http();
String rep="";
http.GET("http://www.google.com/search?hl=zh-TW&q=water");
BufferedReader br=new BufferedReader(new InputStreamReader(http.getInputStream()));
String html="";
Pattern pat=Pattern.compile("<input type=text name=q size=41 maxlength=2048 value=[^\n]* title=");
Matcher match=null;
while((rep=br.readLine())!=null)
{
match=pat.matcher(rep);
if(match.find())
{
html=match.group();
break;
}
}
System.out.println(html.substring(html.indexOf("\"")+1, html.lastIndexOf("\"")));
br.close();
http.closeServer();
}
catch(Exception e)
{
e.printStackTrace();
}
}
}
