网页解析

解析html文件，采用Jar包 htmlparser，filter组合应用。
1.获取新网页的链接。形如<a href ="xxx" target = "_blank">

点击(此处)折叠或打开

1. Parser parser = Parser.createParser(all,"charest");//all为文件，charest为编码
   
2. 
   
3. public String getlink(Parser parser) {
   
4.         String link="";
   
5.         try {
   
6.             AndFilter andFilter = new AndFilter(new TagNameFilter("a"),new HasAttributeFilter("target", "_blank"));
   
7.             NodeList nodeList = parser.extractAllNodesThatMatch(andFilter);
   
8.             for (int i = 0; i < nodeList.size(); i++) {
   
9.                 Node node = nodeList.elementAt(i);
   
10.                                 if (!node.toPlainTextString().equals("")) {
    
11.                     link+=node.toPlainTextString();
    
12.                     link+="@";
    
13.                 }
    
14.             }
    
15.         } catch (Exception e) {
    
16.             // TODO: handle exception
    
17. 
    
18.             return "";
    
19.         }
    
20.                 return link;
    
21.     }

2.获取图片

点击(此处)折叠或打开

1. public void pic(Parser parser,String num,String name,String category) {
   
2.         String src="";
   
3.         String alt="";
   
4.         String datasrc = "";
   
5.         try {
   
6.             TagNameFilter tagNameFilter = new TagNameFilter("img");
   
7.             NodeList nodeList=parser.extractAllNodesThatMatch(tagNameFilter);
   
8.             //System.out.println(nodeList.size());
   
9. 
   
10.             if (nodeList.size()>0) {
    
11.                 for (int i = 0; i < nodeList.size(); i++) {
    
12.                 Tag tagnode=(Tag)nodeList.elementAt(i);
    
13.                 src = tagnode.getAttribute("src");
    
14.                 //System.out.println("src :"+src+"e");
    
15. 
    
16.                 alt = tagnode.getAttribute("alt");
    
17.                 //System.out.println("alt :"+alt+"e");
    
18. 
    
19.                 datasrc = tagnode.getAttribute("data-src");
    
20.                 //System.out.println("data-src:"+datasrc+"e");
    
21. 
    
22.                             }
    
23.             }
    
24.             
    
25.         } catch (ParserException e) {
    
26.             // TODO Auto-generated catch block
    
27. 
    
28.             e.printStackTrace();
    
29.             return ;
    
30.         }
    
31.                 parser.reset();
    
32.     }

<script type=text/javascript charset=utf-8 src="http://static.bshare.cn/b/buttonLite.js#style=-1&uuid=&pophcol=3&lang=zh"></script> <script type=text/javascript charset=utf-8 src="http://static.bshare.cn/b/bshareC0.js"></script>

阅读(31) | 评论(0) | 转发(0) |

0

上一篇：IKanalyzer分词实例并统计词频

下一篇：图片抓取

相关热门文章

• 至尊体验 卡盟站、电子商务平...
• 解析linux根文件系统的挂载过...
• 企业建设网站的好处有哪些呢？...
• http://sx.baoxianzp.com 绍兴...
• 全新253个多ip站群服务器，续...

• JDK1.6官方下载_JDK6官方下载_...
• MyEclipse6.5下载及注册码...
• Eclipse+MyEclipse的配置
• Eclipse 插件安装、升级和卸载...
• 最新版SWT Designer 6.0 安装,...

• ChinaUnix & ITPUB社区12周年...
• ssh连接出现以下提示，求解...
• 如何扩展MYSQL
• 准备做一个大型门户,用户什么...
• gbk or utf8

给主人留下些什么吧！~~

评论热议