xpath的问题

2009-01-08 05:41:43 158 阅读 AI 写同款 · GEO 优化AI 选题数据监测一键分发 ›

解决xpath提取不规则网页的问题在数据采集过程中，面对不规范的HTML页面，xpath解析经常遇到困难。通过引入PyTidyLib库，可以有效解决这个问题。以慧聪网为例，应用PyTidyLib进行数据抓取，确保正确匹配和提取所需信息。阅读详情

我想得到leaf='true'的所有属于id的值。我用如下代码会出错。



	    DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();

	    domFactory.setNamespaceAware(true); // never forget this!

//	    String str = "<?xml version='1.0' encoding='UTF-8'?><tree><node text='君实软件' draggable='false' id='0'><node id='000000000003' text='测试1部' leaf='false' loader='[object Object]'/><node id='S0003' text='刘备' leaf='true' loader='[object Object]'/></node></tree>";//假设这个 str 中已经是一个xml格式的字符串了

	    String str="<?xml version='1.0'?><tree><node text='test' draggable='false' id='200826' searchParam='200826'><node id='200826000001' text='总兵都' leaf='false'><node id='A01' text='宋江' leaf='true'/><node id='200826000002' text='军机部' leaf='false' loader='[object Object]' searchParam='200826'><node id='A03' text='吴用' leaf='true' loader='[object Object]'/><node id='A04' text='公孙胜' leaf='true' loader='[object Object]'/><node id='A05' text='戴宗' leaf='true' loader='[object Object]'/><node id='A06' text='时迁' leaf='true' loader='[object Object]'/></node></node></node></tree>";

	    str=new   String(str.getBytes("ISO8859_1"),   "UTF-8");//把字符串转换为utf-8格式。

	    //StringBufferInputStream 继承自 InputStream 类

	    StringBufferInputStream in = new StringBufferInputStream(str);

	    DocumentBuilder builder = domFactory.newDocumentBuilder();

	    Document doc = builder.parse(in);

	    XPathFactory factory = XPathFactory.newInstance();

	    XPath xpath = factory.newXPath();

	    //编译XPath表达式供以后计算使用。//BBB[@id='b1']

	    //xpath   =   "//RES[(@name   =   'Count')   and   not(@parmType   =   'DbField')]";

//	    XPathExpression expr = xpath.compile("//@id");

	    XPathExpression expr = xpath.compile("//node[(@id) and (@leaf='true')]");

	    //计算指定上下文中的 XPath 表达式并返回指定类型的结果。

	    Object result = expr.evaluate(doc, XPathConstants.NODESET);

	    NodeList nodes = (NodeList) result;

	    for (int i = 0; i < nodes.getLength(); i++) {

	        System.out.println(nodes.item(i).getNodeValue());

	    }