package com.jd.cis;
import java.io.IOException;
import javax.script.ScriptEngineManager;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.ResponseHandler;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.BasicResponseHandler;
import org.apache.http.impl.client.DefaultHttpClient;
import org.python.util.PythonInterpreter;
public class UrlFetch {
/**
* @param args
* @throws IOException
* @throws ClientProtocolException
*/
public static void main(String[] args) throws ClientProtocolException, IOException {
// TODO Auto-generated method stub
// HttpClient httpclient = new DefaultHttpClient();
// try {
// String url="";
// url="http://www.yuncheng.com/searchcate.aspx?page=4&cate=%E5%9B%BE%E4%B9%A6&subcate=%E5%8E%9F%E5%88%9B%E6%96%87%E5%AD%A6&level3=%E7%8E%84%E5%B9%BB&level4=%E4%B8%9C%E6%96%B9%E7%8E%84%E5%B9%BB#hd";
// HttpGet httpget = new HttpGet(url);
// HttpClientParams.setCookiePolicy(httpclient.getParams(), CookiePolicy.BROWSER_COMPATIBILITY);
// System.out.println("executing request " + httpget.getURI());
//
// // Create a response handler
// ResponseHandler<String> responseHandler = new BasicResponseHandler();
// String responseBody = httpclient.execute(httpget, responseHandler);
// System.out.println("----------------------------------------");
// System.out.println(responseBody);
// System.out.println("----------------------------------------");
//
// } finally {
// // When HttpClient instance is no longer needed,
// // shut down the connection manager to ensure
// // immediate deallocation of all system resources
// httpclient.getConnectionManager().shutdown();
// }
PythonInterpreter interpreter = new PythonInterpreter();
String code="";
code="url='http://www.yuncheng.com/searchcate.aspx?page=4&cate=%E5%9B%BE%E4%B9%A6&subcate=%E5%8E%9F%E5%88%9B%E6%96%87%E5%AD%A6&level3=%E7%8E%84%E5%B9%BB&level4=%E4%B8%9C%E6%96%B9%E7%8E%84%E5%B9%BB#hd'\nimport urllib2\nfor i in xrange(2,30):\n print i\n html=urllib2.urlopen(url).read()\n f=open('c:/%s.txt'%i,'w')\n f.write(html)\n f.close()\n";
interpreter.exec(code);
}
}
original python script
#!/usr/bin/env python
#encoding=utf-8
url="http://www.yuncheng.com/searchcate.aspx?page=4&cate=%E5%9B%BE%E4%B9%A6&subcate=%E5%8E%9F%E5%88%9B%E6%96%87%E5%AD%A6&level3=%E7%8E%84%E5%B9%BB&level4=%E4%B8%9C%E6%96%B9%E7%8E%84%E5%B9%BB#hd "
url=url.strip()
import urllib2
for i in xrange(2,30):
print i
html=urllib2.urlopen(url).read()
f=open("c:/22/%s.txt"%i,"w")
f.write(html)
f.close()