html文件的获取,获取html文件Java

有趣的是，我写的实用工具方法就是在另一周完成

/**

* Retrieves the file specified by fileUrl and writes it to

* out.

*

* Does not close out, but does flush.

* @param fileUrl The URL of the file.

* @param out An output stream to capture the contents of the file

* @param batchWriteSize The number of bytes to write to out

* at once (larger files than this will be written

* in several batches)

* @throws IOException If call to web server fails

* @throws FileNotFoundException If the call to the web server does not

* return status code 200.

*/

public static void getFileStream(String fileURL, OutputStream out, int batchWriteSize)

throws IOException{

GetMethod get = new GetMethod(fileURL);

HttpClient client = new HttpClient();

HttpClientParams params = client.getParams();

params.setSoTimeout(2000);

client.setParams(params);

try {

client.executeMethod(get);

} catch(ConnectException e){

// Add some context to the exception and rethrow

throw new IOException("ConnectionException trying to GET " +

fileURL,e);

}

if(get.getStatusCode()!=200){

throw new FileNotFoundException(

"Server returned " + get.getStatusCode());

}

// Get the input stream

BufferedInputStream bis =

new BufferedInputStream(get.getResponseBodyAsStream());

// Read the file and stream it out

byte[] b = new byte[batchWriteSize];

int bytesRead = bis.read(b,0,batchWriteSize);

long bytesTotal = 0;

while(bytesRead!=-1) {

bytesTotal += bytesRead;

out.write(b, 0, bytesRead);

bytesRead = bis.read(b,0,batchWriteSize);;

}

bis.close(); // Release the input stream.

out.flush();

}

使用Apache Commons库，即

import org.apache.commons.httpclient.HttpClient;

import org.apache.commons.httpclient.methods.GetMethod;

import org.apache.commons.httpclient.params.HttpClientParams;