mirror of
https://github.com/alexhopeoconnor/bom-local-service.git
synced 2026-10-03 21:21:59 +10:00
alex
12dd0eedad
Major architectural changes: - Replace monolithic ScrapingService with workflow-based system - Extract scraping logic into discrete, testable steps - Add configuration-driven selectors, JavaScript templates, and text patterns - Implement step registry and workflow factory for extensibility - Add PageState tracking and step dependencies - Make IWorkflow generic to support different response types New components: - Scraping steps organized by category (Navigation, Search, Map, Metadata, Capture) - BaseScrapingStep base class with common dependencies - ScrapingContext for shared state between steps - RadarScrapingWorkflow orchestrating step execution - SelectorService for configurable element selection - Configuration models (SelectorConfig, TextPatternsConfig, JavaScriptTemplatesConfig) Performance and monitoring: - Add step-level timing metrics with historical tracking - Log step durations and compare to averages - Warn on slow steps/workflows (50%+ slower than average) - Integrate metrics with CacheService Configuration improvements: - Externalize all selectors to appsettings.json - Externalize JavaScript templates to appsettings.json - Externalize text patterns to appsettings.json - Support Docker configuration via mounted appsettings.json - Remove hardcoded waits, use configurable timeouts Bug fixes: - Fix DebugService collection modification exception - Fix ResetToFirstFrameStep click interception with JavaScript fallback - Remove minutes ago fallback, use timestamp parsing only - Update timestamp parsing for new BOM website format Documentation: - Update README with new architecture details - Add configuration section with Docker guidance - Add development guidelines for extending scraping system - Add performance monitoring documentation
34 lines
905 B
C#
34 lines
905 B
C#
namespace BomLocalService.Services.Scraping;
|
|
|
|
public class ScrapingStepRegistry : IScrapingStepRegistry
|
|
{
|
|
private readonly Dictionary<string, IScrapingStep> _steps = new();
|
|
private readonly ILogger<ScrapingStepRegistry> _logger;
|
|
|
|
public ScrapingStepRegistry(ILogger<ScrapingStepRegistry> logger)
|
|
{
|
|
_logger = logger;
|
|
}
|
|
|
|
public void RegisterStep(IScrapingStep step)
|
|
{
|
|
if (_steps.ContainsKey(step.Name))
|
|
{
|
|
_logger.LogWarning("Step {Name} is already registered, overwriting", step.Name);
|
|
}
|
|
_steps[step.Name] = step;
|
|
_logger.LogDebug("Registered step: {Name}", step.Name);
|
|
}
|
|
|
|
public IScrapingStep? GetStep(string name)
|
|
{
|
|
return _steps.TryGetValue(name, out var step) ? step : null;
|
|
}
|
|
|
|
public IEnumerable<IScrapingStep> GetAllSteps()
|
|
{
|
|
return _steps.Values;
|
|
}
|
|
}
|
|
|