程序员社区

java 爬取网页代码

package text;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.nio.charset.MalformedInputException;

public class GetHtml {
	
	/**java项目源www.fhadmin.org
	 * @param url 网址
	 * @param encoding 编码
	 * @return 返回string
	 */
	public static String getHtmlResouceUrl(String url,String encoding){
		StringBuffer buffer= new StringBuffer();
		URL urlObj=null;
		URLConnection uc=null;
		InputStreamReader isr=null;
		BufferedReader reader=null;
		String line=null;
		try {
			urlObj=new URL(url);
			uc = urlObj.openConnection();
			isr=new InputStreamReader(uc.getInputStream(), encoding);
			reader=new BufferedReader(isr);
			while((line=reader.readLine())!=null){
				buffer.append(line+"\n");
			}
		}catch (MalformedInputException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			System.out.println("网络打开失败");
		}catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			System.out.println("网络连接失败");
			 }finally{
				 if(isr!=null){
					 try {
						isr.close();
					} catch (IOException e) {
						// TODO Auto-generated catch block
						e.printStackTrace();
					}
				 }
			 }
		return buffer.toString();
		
	}
	public static void main(String[] args) {
		
		String url="http://www.1b23.com";
		String econding="utf-8";
		String html=getHtmlResouceUrl(url,econding);
		System.out.println(html);
	}

}

 

赞(0) 打赏
未经允许不得转载:IDEA激活码 » java 爬取网页代码

相关推荐

  • 暂无文章

一个分享Java & Python知识的社区