java 网络爬虫教程_Java 简单网络爬虫
在类里写实现代码:
package com.baidu;import java.io.BufferedReader;import java.io.IOException;import java.io.InputStreamReader;import org.apache.http.HttpEntity;import org.apache.http.HttpStatus;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 HttpGetUtils { public static void main(String[] args) { // TODO Auto-generated method stub //https://v.qq.com/ http://www.youku.com/ http://m.sunlands.com String str=get("http://m.sunlands.com"); System.out.println(str); } private static String get(String url) { String result = ""; try { //获取httpclient实例 CloseableHttpClient httpclient = HttpClients.createDefault(); //获取方法实例。GET HttpGet httpGet = new HttpGet(url); //执行方法得到响应 CloseableHttpResponse response = httpclient.execute(httpGet); try { //如果正确执行而且返回值正确,即可解析 if (response != null && response.getStatusLine().getStatusCode() == HttpStatus.SC_OK) { System.out.println(response.getStatusLine()); HttpEntity entity = response.getEntity(); //从输入流中解析结果 result = readResponse(entity, "utf-8"); } } finally { httpclient.close(); response.close(); } }catch (Exception e){ e.printStackTrace(); } return result; } private static String readResponse(HttpEntity resEntity, String charset) { StringBuffer res = new StringBuffer(); BufferedReader reader = null; try { if (resEntity == null) { return null; } reader = new BufferedReader(new InputStreamReader( resEntity.getContent(), charset)); String line = null; while ((line = reader.readLine()) != null) { res.append(line); } } catch (Exception e) { e.printStackTrace(); } finally { try { if (reader != null) { reader.close(); } } catch (IOException e) { } } return res.toString(); }}
本文来自互联网用户投稿,文章观点仅代表作者本人,不代表本站立场,不承担相关法律责任。如若转载,请注明出处。 如若内容造成侵权/违法违规/事实不符,请点击【内容举报】进行投诉反馈!
