java 解析网站的标题，简介，图片等

       这里用到了一个别人的jar包

 jsoup-1.6.1.jar

public static void jiexi(){
System.out.println("-------------------------------------------------");
try {
URL url = new URL("http://www.baidu.com");
Document doc = Jsoup.parse(url, 5000);


// 标题
String title = doc.title();
System.out.println("title " + title);


// 简介
String description = null;
Elements elements = doc.select("meta[name=description]");
if (elements != null && elements.size() > 0) {
description = elements.get(0).attr("content");
} else {
// 取不到简介时取文字内容前100位
description = doc.text();
if (description.length() > 100) {
description = description.substring(0, 100);
}
}


// 简介没设置,文字内容也没有时设为"无简介"
System.out.print("description "+ description);


// 图片
String image = null;
elements = doc.select("meta[name=thumbnail]");
if (elements != null && elements.size() > 0) {
image = elements.get(0).attr("content");
}
System.out.print("image " + image);




} catch (Exception e1) {
System.out.print("dddf " + e1);
}
System.out.println("-------------------------------------------------");
}