扫描的网站链接给定的格式Jsoup的Java

Question

我尽量尝试根据给定

这是我发言的选择level.I've扫描所有链接在网页中，我已阅读选择一定的方式固定，我想读它在循环较多，递归或任何事情来帮助我成为电平选择更灵活的命令我将来可能会大于2

public static void main(String[] args) { 
     String website = website("http://www.java2s.com/"); 
     System.out.println(website); 
    } 

    private static String website(String url) { 
     String lstLink = ""; 
     try { 
      String level[] = {"div.col-md-9 li a", "div#sidebar ul li a"}; 
      //Level 1 
      Document connect = Jsoup.connect(url).get(); 
      Elements selectLevel1 = connect.select(level[0]); 
      for (Element level1 : selectLevel1) { 
       lstLink += level1.attr("href") + "\n"; 

       //Level2 
       Document connect2 = Jsoup.connect(level1.attr("href")).get(); 
       Elements selectLevel2 = connect2.select(level[1]); 
       for (Element level2 : selectLevel2) { 
        lstLink += level2.attr("href") + "\n"; 
       } 
      } 
     } catch (IOException ex) { 
      Logger.getLogger(AWebsite.class.getName()).log(Level.SEVERE, null, ex); 
     } 
     return lstLink; 

    } 

Answer 1

请检查一下。

static String levels[] = {"div.col-md-9 li a", "div#sidebar ul li a"}; 

    private static String getRecursive(String href, int level) { 

     String links = ""; 

     if (level > levels.length-1) { 
      return ""; 
     } 

     Document doc; 
     try { 
      doc = Jsoup.connect(href).get(); 
      Elements elements = doc.select(levels[level]); 

      level++; 

      for (Element element : elements) { 
       if(!element.attr("href").isEmpty()) 
       { 
        links += element.attr("abs:href") + "\n"; 
        links += getRecursive(element.attr("abs:href"), level); 
       } 
      } 
     } catch (IOException e1) { 
      e1.printStackTrace(); 
     } 
     return links; 
    } 



public static void main(String[] args) { 
    String website = getRecursive("http://www.java2s.com/", 0); 
    System.out.println(website); 
}