使用 Java Jsoup获取网页Title和Meta, 包括description, keywords

使用 Java Jsoup获取网页Title和Meta, 包括description, keywords

import java.io.IOException;
     
    import org.jsoup.Jsoup;
    import org.jsoup.nodes.Document;
    import org.jsoup.nodes.Element;
    import org.jsoup.select.Elements;
     
    public class SemanticCrawl{
        public static void main(String[] args){
            Document doc = null;
            try {
                doc = Jsoup.connect("http://www.qq.com/").get();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
            String title = doc.title();
            Elements metas = doc.head().select("meta");  
            for (Element meta : metas) {  
                String content = meta.attr("content");  
                if ("keywords".equalsIgnoreCase(meta.attr("name"))) {  
                    System.out.println(content);  
                }  
                if ("description".equalsIgnoreCase(meta.attr("name"))) {  
                    System.out.println(content);  
                }  
            }  
     
            Elements keywords = doc.getElementsByTag("meta");
            System.out.println(title);
        }
    }