一个简单的爬虫程序
import org.apache.commons.httpclient.HttpClient; import org.apache.commons.httpclient.HttpStatus; import org.apache.commons.httpclient.methods.GetMethod; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; public class Test1 { public static void main(String[] args)throws Exception { //String url="http://www.baidu.com"; String url="http://10.137.13.61:9000/dashboard/index/1"; HttpClient client=new HttpClient(); //PostMethod method=new PostMethod(url); GetMethod method=new GetMethod(url); int status=client.executeMethod(method); if(status==HttpStatus.SC_OK){ String html=method.getResponseBodyAsString(); Document doc=Jsoup.parse(html); System.out.println(doc.toString()); }else{ System.err.println("URL Exception"); } } }
commons-httpclient-3.1.zip : http://mirrors.hust.edu.cn/apache/httpcomponents/commons-httpclient/binary/
另外需要commons-logging-1.1.3.jar commons-codec-1.6.jar jsoup-1.7.2.jar 网上下