java 爬虫



参考罗刚 王振东编著的 《自己动手写网络爬虫》

package a;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;

import org.apache.http.HttpEntity;
import org.apache.http.HttpStatus;
import org.apache.http.StatusLine;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;

public class CopyHtmlPage {
 
 public boolean download(String path) throws ClientProtocolException, IOException{
  CloseableHttpClient httpclient = HttpClients.createDefault();
  InputStream input = null;
  OutputStream output = null;

  HttpGet get = new HttpGet(path);
  CloseableHttpResponse response = httpclient.execute(get);
  StatusLine sl =  response.getStatusLine();
  int statusCode = sl.getStatusCode();
  if(statusCode == HttpStatus.SC_OK){
   HttpEntity entity = response.getEntity();

   input = entity.getContent();
   output = new FileOutputStream("E://git-guide.html");
   int b = -1;
   while((b = input.read())>0){
    output.write(b);
   }
   output.flush();
   if(input != null){
    input.close();
   }
   if(output != null){
    output.close();
   }
   return true;
  }
  return false;
 }
 
 public static void main(String[] args) {
  try {
   CopyHtmlPage copy = new  CopyHtmlPage();
   boolean b = copy.download("http://www.bootcss.com/p/git-guide/");
   System.out.println(b);
  } catch (IOException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
 }
 

}