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

Parser parser = Parser.createParser(all,"charest");//all为文件，charest为编码

public String getlink(Parser parser) {
        String link="";
        try {
            AndFilter andFilter = new AndFilter(new TagNameFilter("a"),new HasAttributeFilter("target", "_blank"));
            NodeList nodeList = parser.extractAllNodesThatMatch(andFilter);
            for (int i = 0; i < nodeList.size(); i++) {
                Node node = nodeList.elementAt(i);
                                if (!node.toPlainTextString().equals("")) {
                    link+=node.toPlainTextString();
                    link+="@";
                }
            }
        } catch (Exception e) {
            // TODO: handle exception

            return "";
        }
                return link;
    }

2.获取图片

public void pic(Parser parser,String num,String name,String category) {
        String src="";
        String alt="";
        String datasrc = "";
        try {
            TagNameFilter tagNameFilter = new TagNameFilter("img");
            NodeList nodeList=parser.extractAllNodesThatMatch(tagNameFilter);
            //System.out.println(nodeList.size());

            if (nodeList.size()>0) {
                for (int i = 0; i < nodeList.size(); i++) {
                Tag tagnode=(Tag)nodeList.elementAt(i);
                src = tagnode.getAttribute("src");
                //System.out.println("src :"+src+"e");

                alt = tagnode.getAttribute("alt");
                //System.out.println("alt :"+alt+"e");

                datasrc = tagnode.getAttribute("data-src");
                //System.out.println("data-src:"+datasrc+"e");

                            }
            }

        } catch (ParserException e) {
            // TODO Auto-generated catch block

            e.printStackTrace();
            return ;
        }
                parser.reset();
    }