// 第一種方法
//這種方法是用apache提供的包,簡(jiǎn)單方便
//但是要用到以下包:commons-codec-1.4.jar
// commons-httpclient-3.1.jar
// commons-logging-1.0.4.jar
public static String createhttpClient(String url, String param) {
  HttpClient client = new HttpClient();
  String response = null;
  String keyword = null;
  PostMethod postMethod = new PostMethod(url);
//  try {
//   if (param != null)
//    keyword = new String(param.getBytes("gb2312"), "ISO-8859-1");
//  } catch (UnsupportedEncodingException e1) {
//   // TODO Auto-generated catch block
//   e1.printStackTrace();
//  }
  // NameValuePair[] data = { new NameValuePair("keyword", keyword) };
  // // 將表單的值放入postMethod中
  // postMethod.setRequestBody(data);
  // 以上部分是帶參數(shù)抓取,我自己把它注銷(xiāo)了．大家可以把注銷(xiāo)消掉研究下
  try {
   int statusCode = client.executeMethod(postMethod);
   response = new String(postMethod.getResponseBodyAsString()
     .getBytes("ISO-8859-1"), "gb2312");
     //這里要注意下 gb2312要和你抓取網(wǎng)頁(yè)的編碼要一樣
   String p = response.replaceAll("http://&[a-zA-Z]{1,10};", "")
     .replaceAll("<[^>]*>", "");//去掉網(wǎng)頁(yè)中帶有html語(yǔ)言的標(biāo)簽
   System.out.println(p);
  } catch (Exception e) {
   e.printStackTrace();
  }
  return response;
}
// 第二種方法
// 這種方法是JAVA自帶的URL來(lái)抓取網(wǎng)站內(nèi)容
public String getPageContent(String strUrl, String strPostRequest,
   int maxLength) {
  // 讀取結(jié)果網(wǎng)頁(yè)
  StringBuffer buffer = new StringBuffer();
  System.setProperty("sun.net.client.defaultConnectTimeout", "5000");
  System.setProperty("sun.net.client.defaultReadTimeout", "5000");
  try {
   URL newUrl = new URL(strUrl);
   HttpURLConnection hConnect = (HttpURLConnection) newUrl
     .openConnection();
   // POST方式的額外數(shù)據(jù)
   if (strPostRequest.length() > 0) {
    hConnect.setDoOutput(true);
    OutputStreamWriter out = new OutputStreamWriter(hConnect
      .getOutputStream());
    out.write(strPostRequest);
    out.flush();
    out.close();
   }
   // 讀取內(nèi)容
   BufferedReader rd = new BufferedReader(new InputStreamReader(
     hConnect.getInputStream()));
   int ch;
   for (int length = 0; (ch = rd.read()) > -1
     && (maxLength <= 0 || length < maxLength); length++)
    buffer.append((char) ch);
   String s = buffer.toString();
   s.replaceAll("http://&[a-zA-Z]{1,10};", "").replaceAll("<[^>]*>", "");
   System.out.println(s);
   rd.close();
   hConnect.disconnect();
   return buffer.toString().trim();
  } catch (Exception e) {
   // return "錯(cuò)誤:讀取網(wǎng)頁(yè)失??！";
   //
   return null;
  }
}

public static void main(String[] args) {
  String url = "http://www.dhdzp.com";
  String keyword = "腳本之家";
  createhttpClient p = new createhttpClient();
  String response = p.createhttpClient(url, keyword);
  // 第一種方法
  // p.getPageContent(url, "post", 100500);//第二種方法
}