public static void main(String[] args) throws Exception{// 创建httpClient实例CloseableHttpClient httpClient = HttpClients.createDefault();// 创建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，得到文档对象/*** 1.根据tag获取元素*/Elements elements = document.getElementsByTag("title"); // 获取 tag为 title的DOM元素Element element = elements.get(0); // 获取第一个DOM元素String title = element.text();  // 返回元素的文本System.out.println("博客园的标题：" + title);/*** 2.根据 id获取元素*/Element element2 = document.getElementById("site_nav_top");String navTop = element2.text();System.out.println("座右铭：" + navTop);/*** 3.根据样式获取元素*/Elements elements3 = document.getElementsByClass("post_item");System.out.println("============根据样式获取元素=============");for(Element e : elements3){System.out.println(e.html());System.out.println("------------------------------");}/*** 4.根据属性名称来查询DOM*/Elements elements4 = document.getElementsByAttribute("width");System.out.println("============根据属性名称来查询DOM=============");for(Element e : elements4){System.out.println(e.toString());System.out.println("------------------------------");}/*** 5.根据属性名和属性值来查询DOM*/Elements elements5 = document.getElementsByAttributeValue("target", "_blank");System.out.println("============ 根据属性名和属性值来查询DOM=============");for(Element e : elements5){System.out.println(e.toString());System.out.println("------------------------------");}}if(response != null){response.close();}if(httpClient != null){httpClient.close();}}