Demystifying XPath: The Complete Guide to Navigating Complex XML Documents

<?xml version="1.0" encoding="UTF-8"?>
<library>
  <section name="fiction">
    <book id="b001" available="true">
      <title lang="en">Dune</title>
      <author>Frank Herbert</author>
      <price currency="USD">14.99</price>
      <tags><tag>sci-fi</tag><tag>classic</tag></tags>
    </book>
    <book id="b002" available="false">
      <title lang="en">Foundation</title>
      <author>Isaac Asimov</author>
      <price currency="USD">12.50</price>
      <tags><tag>sci-fi</tag><tag>classic</tag></tags>
    </book>
  </section>
  <section name="technical">
    <book id="b003" available="true">
      <title lang="en">Clean Code</title>
      <author>Robert C. Martin</author>
      <price currency="USD">39.99</price>
      <tags><tag>programming</tag><tag>best-practices</tag></tags>
    </book>
  </section>
</library>

<catalog xmlns:bk="https://example.com/books"
         xmlns:inv="https://example.com/inventory">
  <bk:book id="001">
    <bk:title>Dune</bk:title>
    <inv:stock>42</inv:stock>
  </bk:book>
</catalog>

XPathFactory factory = XPathFactory.newInstance();
XPath xpath = factory.newXPath();

// Register namespace prefixes so XPath can resolve them
xpath.setNamespaceContext(new NamespaceContext() {
    @Override
    public String getNamespaceURI(String prefix) {
        return switch (prefix) {
            case "bk"  -> "https://example.com/books";
            case "inv" -> "https://example.com/inventory";
            default    -> XMLConstants.NULL_NS_URI;
        };
    }
    @Override public String getPrefix(String ns) { return null; }
    @Override public Iterator<String> getPrefixes(String ns) { return null; }
});

// Now use the registered prefixes in expressions
NodeList books = (NodeList) xpath.evaluate(
    "//bk:book[@id='001']/bk:title",
    document,
    XPathConstants.NODESET
);
System.out.println(books.item(0).getTextContent()); // → "Dune"

from lxml import etree

tree = etree.parse('library.xml')
root = tree.getroot()

# Simple path selection
books = root.xpath('//book')
print(f"Found {len(books)} books")

# Predicate filtering
expensive = root.xpath('//book[number(price) > 20]')
for book in expensive:
    title = book.findtext('title')
    price = book.findtext('price')
    print(f"{title}: ${price}")

# Attribute selection
available_ids = root.xpath('//book[@available="true"]/@id')
print("Available:", available_ids)

# String function
sci_fi = root.xpath('//book[tags/tag[contains(., "sci-fi")]]/title/text()')
print("Sci-fi books:", sci_fi)

# Aggregate
total = root.xpath('sum(//price)')
print(f"Total inventory value: ${total:.2f}")

// Browser XPath API: document.evaluate()
const xml = `<library><book id="b1"><title>Dune</title><price>14.99</price></book></library>`;
const parser = new DOMParser();
const doc = parser.parseFromString(xml, 'application/xml');

function xpathAll(expr, contextNode = doc) {
    const result = doc.evaluate(
        expr, contextNode,
        null,                  // namespace resolver (null = no namespaces)
        XPathResult.ANY_TYPE,
        null
    );
    const nodes = [];
    let node;
    while ((node = result.iterateNext())) nodes.push(node);
    return nodes;
}

function xpathString(expr, contextNode = doc) {
    return doc.evaluate(
        expr, contextNode, null,
        XPathResult.STRING_TYPE, null
    ).stringValue;
}

// Usage
const titles = xpathAll('//title').map(n => n.textContent);
console.log(titles); // ["Dune"]

const price = xpathString('string(//book[@id="b1"]/price)');
console.log(price); // "14.99"

var doc = new XmlDocument();
doc.Load("library.xml");

// Basic node selection
var books = doc.SelectNodes("//book");
Console.WriteLine($"Total books: {books.Count}");

// Filtered selection with predicate
var available = doc.SelectNodes("//book[@available='true']");
foreach (XmlNode book in available) {
    Console.WriteLine(book.SelectSingleNode("title")?.InnerText);
}

// Single node
var firstBook = doc.SelectSingleNode("//book[1]/title");
Console.WriteLine(firstBook?.InnerText); // → "Dune"

// With namespace manager for namespaced XML
var nsMgr = new XmlNamespaceManager(doc.NameTable);
nsMgr.AddNamespace("bk", "https://example.com/books");
var titleNode = doc.SelectSingleNode("//bk:title", nsMgr);