Jsoup(四)-- Jsoup获取DOM元素属性值

1.获取博客园的博客标题以及博客地址,获取友情连接html

   

2.代码实现:java

public static void main(String[] args) throws Exception{
        // 建立httpClient实例
        CloseableHttpClient httpClient = HttpClients.createDefault();
        // 建立httpGet实例
        HttpGet httpGet = new HttpGet("http://www.cnblogs.com");
        httpGet.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0");
        CloseableHttpResponse response = httpClient.execute(httpGet);
        String content = null;
        if(response != null){
            HttpEntity entity = response.getEntity();   
            content = EntityUtils.toString(entity, "UTF-8");  // 获取网页内容
            Document document = Jsoup.parse(content);  // 解析网页,获得文档对象
            
            // 1.经过选择器查找全部博客标题以及连接
            Elements ele = document.select("#post_list .post_item .post_item_body h3 a");
            for(Element e : ele){
                System.out.println("博客标题:" + e.text() + "---博客地址:" + e.attr("href"));
            }
            
            // 2.获取友情连接
            Element linkEle = document.select("#friend_link").first();
            System.out.println("友情连接纯文本:" + linkEle.text());
            System.out.println("友情连接HTML:" + linkEle.html());
        }
        if(response != null){
            response.close();
        }
        if(httpClient != null){
            httpClient.close();
        }
    }

3.Jsoup学习地址post

  开源博客系统-Jsoup学习

相关文章
相关标签/搜索