Parse XML

readme.md

.NET script to parse XML and count elements

Uses XPath

Prerequisites

• .NET 10

Usage

dotnet run parse.cs "<url>" "<xpath-query>"

dotnet run parse.cs "https://httpstatus.io/sitemap.xml" "//ns:url" 

parse.cs

#:package Spectre.Console@0.*
#:package Spectre.Console.Cli@0.*

#:property PublishAot=false

using System.ComponentModel;
using System.Diagnostics.CodeAnalysis;
using System.Xml;
using System.Xml.XPath;
using Spectre.Console;
using Spectre.Console.Cli;

CommandApp<ParseXmlCommand> app = new();
return await app.RunAsync(args);

internal sealed class ParseXmlCommand : AsyncCommand<ParseXmlCommand.Settings>
{
    public sealed class Settings : CommandSettings
    {
        [CommandArgument(0, "<URL>")]
        [Description("The URL of the XML document to parse")]
        public string Url { get; init; } = string.Empty;

        [CommandArgument(1, "<XPATH>")]
        [Description("The XPath query to execute against the XML document")]
        public string XPath { get; init; } = string.Empty;
    }

    public override async Task<int> ExecuteAsync([NotNull] CommandContext context, [NotNull] Settings settings, CancellationToken cancellationToken)
    {
        try
        {
            await AnsiConsole.Status()
                .Spinner(Spinner.Known.Dots)
                .StartAsync("Fetching XML...", async ctx =>
                {
                    using HttpClient httpClient = new();
                    string xmlContent = await httpClient.GetStringAsync(settings.Url, cancellationToken);

                    ctx.Status("Parsing XML...");
                    XmlDocument xmlDoc = new();
                    xmlDoc.LoadXml(xmlContent);

                    ctx.Status("Executing XPath query...");
                    XPathNavigator? navigator = xmlDoc.CreateNavigator();
                    
                    if (navigator == null)
                    {
                        AnsiConsole.MarkupLine("[red]Failed to create XML navigator[/]");
                        return;
                    }
                    
                    // Create namespace manager and auto-detect namespaces
                    XmlNamespaceManager namespaceManager = new(navigator.NameTable);
                    IDictionary<string, string> namespaces = navigator.GetNamespacesInScope(XmlNamespaceScope.All);
                    
                    if (namespaces != null)
                    {
                        foreach (var ns in namespaces)
                        {
                            if (!string.IsNullOrEmpty(ns.Key))
                            {
                                namespaceManager.AddNamespace(ns.Key, ns.Value);
                            }
                        }
                    }
                    
                    // If there's a default namespace, add it with a prefix
                    var defaultNamespace = xmlDoc.DocumentElement?.NamespaceURI;
                    if (!string.IsNullOrEmpty(defaultNamespace) && namespaces != null && !namespaces.Values.Contains(defaultNamespace))
                    {
                        namespaceManager.AddNamespace("ns", defaultNamespace);
                        AnsiConsole.MarkupLine($"[dim]Tip: Default namespace detected. Use 'ns:' prefix in XPath (e.g., //ns:url)[/]");
                    }
                    
                    XPathNodeIterator? nodes = navigator.Select(settings.XPath, namespaceManager);

                    var table = new Table();
                    table.Border(TableBorder.Rounded);
                    table.AddColumn(new TableColumn("[bold yellow]Property[/]"));
                    table.AddColumn(new TableColumn("[bold cyan]Value[/]"));

                    table.AddRow("[grey]URL[/]", $"[link]{settings.Url}[/]");
                    table.AddRow("[grey]XPath[/]", $"[green]{settings.XPath}[/]");
                    table.AddRow("[grey]Nodes Found[/]", $"[bold blue]{nodes?.Count ?? 0}[/]");

                    AnsiConsole.WriteLine();

                    if (nodes != null && nodes.Count > 0)
                    {
                        AnsiConsole.WriteLine();
                        AnsiConsole.MarkupLine("[bold]Results:[/]");
                        var panel = new Panel(string.Join(Environment.NewLine, 
                            nodes.Cast<XPathNavigator>().Select(n => n.Value)))
                        {
                            Border = BoxBorder.Rounded,
                            BorderStyle = new Style(Color.Green)
                        };
                        AnsiConsole.Write(panel);
                    }

                    AnsiConsole.WriteLine();
                    AnsiConsole.Write(table);
                });

            return 0;
        }
        catch (HttpRequestException ex)
        {
            AnsiConsole.MarkupLine($"[red bold]Error fetching URL:[/] {ex.Message}");
            return 1;
        }
        catch (XmlException ex)
        {
            AnsiConsole.MarkupLine($"[red bold]Error parsing XML:[/] {ex.Message}");
            return 1;
        }
        catch (XPathException ex)
        {
            AnsiConsole.MarkupLine($"[red bold]Error with XPath query:[/] {ex.Message}");
            return 1;
        }
        catch (Exception ex)
        {
            AnsiConsole.MarkupLine($"[red bold]Error:[/] {ex.Message}");
            return 1;
        }
    }
}