java - XML读取具有不同段的相同标签

以下是xml文件

<maindata>
        <publication-reference>
          <document-id document-id-type="docdb">
            <country>US</country>
            <doc-number>9820394ASD</doc-number>
            <date>20111101</date>
          </document-id>
          <document-id document-id-type="docmain">
            <doc-number>9820394</doc-number>
            <date>20111101</date>
          </document-id>
        </publication-reference>
</maindata>

我想提取类型=“ <doc-number>”下的docmain标记值
下面是我的Java代码，在执行其提取9829394ASD而不是9820394时

public static void main(String[] args) {
        String filePath ="D:/bs.xml";
        File xmlFile = new File(filePath);
        DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
        DocumentBuilder dBuilder;
        try {
            dBuilder = dbFactory.newDocumentBuilder();
            Document doc = dBuilder.parse(xmlFile);
            doc.getDocumentElement().normalize();
            System.out.println("Root element :" + doc.getDocumentElement().getNodeName());
            NodeList nodeList = doc.getElementsByTagName("publication-reference");
            List<Biblio> docList = new ArrayList<Biblio>();
            for (int i = 0; i < nodeList.getLength(); i++) {
                docList.add(getdoc(nodeList.item(i)));
            }

        } catch (SAXException | ParserConfigurationException | IOException e1) {
            e1.printStackTrace();
        }
    }
    private static Biblio getdoc(Node node) {
           Biblio bib = new Biblio();
        if (node.getNodeType() == Node.ELEMENT_NODE) {
            Element element = (Element) node;
            bib.setCountry(getTagValue("country",element));
            bib.setDocnumber(getTagValue("doc-number",element));
            bib.setDate(getTagValue("date",element));
        }
        return bib;
    }

让我知道如何检查Type的docmain或doctype，仅当类型为docmain时才应提取，否则应保留元素

添加了getTagValue方法

private static String getTagValue(String tag, Element element) {
        NodeList nodeList = element.getElementsByTagName(tag).item(0).getChildNodes();
        Node node = (Node) nodeList.item(0);
        return node.getNodeValue();
    }

最佳答案

可以使用following使用DOM and XPath API XPath检索该值。

    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    DocumentBuilder builder = factory.newDocumentBuilder();
    Document doc = builder.parse(new File(...) );
    XPathFactory xPathfactory = XPathFactory.newInstance();
    XPath xpath = xPathfactory.newXPath();
    XPathExpression expr = xpath.compile("//document-id[@document-id-type=\"docmain\"]/doc-number/text()");
    String value = expr.evaluate(doc);