抓起页面的图片地址

package cracler;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.methods.GetMethod;

public class CrawOnePageImg {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		String url = "http://www.baidu.com/";
		
		GetMethod method = new GetMethod(url);
		HttpClient client = new HttpClient();
			try {
				client.executeMethod(method);
				InputStream in = method.getResponseBodyAsStream();
				BufferedReader reader = new BufferedReader(new InputStreamReader(in, method.getResponseCharSet()));
				StringBuilder sb = new StringBuilder();
				String line;
				while( (line = reader.readLine()) != null){
					sb.append(line);
				}

				String body = sb.toString();
				Pattern p = Pattern.compile("<img.*?src=\"(.*?)\"");  //() 捕获组
				Matcher m = p.matcher(body);
				while (m.find()){
					System.out.println(m.group(1));
				}
			} catch (Exception e) {
				e.printStackTrace();
			}
			method.releaseConnection();
	}

}