httpclient学习抓取网页

最新推荐文章于 2024-08-06 17:13:24 发布

bug小雨

最新推荐文章于 2024-08-06 17:13:24 发布

阅读量413

点赞数

分类专栏： httpclient 文章标签： httpclient url

本文链接：https://blog.csdn.net/xiaoyu_bug/article/details/73927748

版权

httpclient 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

private final static CloseableHttpClient httpClient = HttpClients.createDefault();//模拟客户端,全局静态常量

//抓取网页
public static void testGetUrl(String url)throws IOException{
    HttpGet httpGet = new HttpGet(url);//请求方法
    CloseableHttpResponse httpResponse = httpClient.execute(httpGet);//客户端发生请求，并返回响应
    System.out.println(httpResponse.getStatusLine());//输出响应状态码
    HttpEntity entity = httpResponse.getEntity();//得到响应实体
    dump(entity);//抓取网页内容
}

private static void dump(HttpEntity entity){
    BufferedReader br = null;
    try {
        br = new BufferedReader(new InputStreamReader(entity.getContent(), "utf-8"));
        String str = null;
        while ((str = br.readLine()) != null){
            System.out.println(str);
        }
    }catch (IOException e){
        e.printStackTrace();
    }finally {
        try{
            if(br != null)
                br.close();
        }catch(IOException e){
            e.printStackTrace();
        }
    }
}