java實現的簡單爬蟲

終於寫了個小的爬蟲程式，mark一下。只是實現根據url擷取網頁資訊的功能。

mport org.apache.http.HttpEntity;import org.apache.http.HttpResponse;import org.apache.http.client.HttpClient;import org.apache.http.client.methods.HttpGet;import org.apache.http.impl.client.DefaultHttpClient;import org.apache.http.params.HttpConnectionParams;import org.apache.http.util.EntityUtils;import org.apache.log4j.Logger;/* * 擷取網頁資訊 */public class DownloadPage{  public String getContentFormUrl(String url,Logger log)      {                     /* 執行個體化一個HttpClient用戶端 */         HttpClient client = new DefaultHttpClient();     HttpGet getHttp = new HttpGet(url);           String content = null;       HttpResponse response;   int i=0;  for(i=0;i<3;i++)  {  try          {         /*逾時設定*/  client.getParams().setIntParameter(HttpConnectionParams.SO_TIMEOUT,3000); //逾時設定       client.getParams().setIntParameter(HttpConnectionParams.CONNECTION_TIMEOUT, 3000);//連線逾時   /*獲得資訊載體*/        response = client.execute(getHttp);      HttpEntity entity = response.getEntity();    if(entity!=null)  {  /* 轉化為文本資訊 */              content = EntityUtils.toString(entity);       //System.out.print(content);       log.info("擷取"+url+"資訊！");      //log.info(content);      client.getConnectionManager().shutdown();       return content;  }   } catch (Exception e)     {               log.error("Exception 訪問"+url+ e.toString());      } finally          {              client.getConnectionManager().shutdown();      }    }  return content;    } }