使用HtmlCleaner从指定网页中提取链接的例子，htmlcleaner例子,需要依赖 htmlcle

使用HtmlCleaner从指定网页中提取链接的例子，htmlcleaner例子,需要依赖 htmlcle

需要依赖 htmlcleaner-2.2.jar 或以上版本

package crawl;import java.net.URL;import org.htmlcleaner.HtmlCleaner;import org.htmlcleaner.TagNode;/** *  * @author Tobacco */public class Crawl{    public static void main(String[] args) throws Exception    {        try {            HtmlCleaner cleaner = new HtmlCleaner();            URL url = new URL("http://www.baidu.com");            TagNode node = cleaner.clean(url, "gbk");            Object[] tagNodes = node.evaluateXPath("//p[@id='nv']/a");            for (Object tagNode : tagNodes) {                System.out.println(((TagNode)tagNode).getText());                System.out.println(((TagNode)tagNode).getAttributeByName("href"));            }        }        catch (Exception exception) {            exception.printStackTrace();        }    }}//该片段来自于http://byrx.net