Files
bom-local-service/Services/Scraping/Steps/Metadata/ExtractMetadataStep.cs
T
alex 12dd0eedad Refactor scraping system to workflow-based architecture
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
2025-12-18 00:54:57 +10:00

69 lines
2.5 KiB
C#

using BomLocalService.Services.Interfaces;
using BomLocalService.Services.Scraping;
namespace BomLocalService.Services.Scraping.Steps.Metadata;
public class ExtractMetadataStep : BaseScrapingStep
{
private readonly ITimeParsingService _timeParsingService;
public override string Name => "ExtractMetadata";
public override string[] Prerequisites => new[] { "ResetToFirstFrame" };
public ExtractMetadataStep(
ILogger<ExtractMetadataStep> logger,
ISelectorService selectorService,
IDebugService debugService,
IConfiguration configuration,
ITimeParsingService timeParsingService)
: base(logger, selectorService, debugService, configuration)
{
_timeParsingService = timeParsingService;
}
public override bool CanExecute(ScrapingContext context)
{
return context.IsMapReady;
}
public override async Task<ScrapingStepResult> ExecuteAsync(ScrapingContext context, CancellationToken cancellationToken)
{
try
{
Logger.LogInformation("Step {Step}: Extracting metadata and frame information", Name);
var lastUpdatedInfo = await _timeParsingService.ExtractLastUpdatedInfoAsync(context.Page);
context.LastUpdatedInfo = lastUpdatedInfo;
// Extract frame info
try
{
var frameInfo = await context.Page.EvaluateAsync<object[]>(JavaScriptTemplates.ExtractFrameInfo);
var result = new List<(int index, int minutesAgo)>();
for (int i = 0; i < 7; i++)
{
var minutesAgo = 40 - (i * 5);
result.Add((i, minutesAgo));
}
context.FrameInfo = result;
}
catch (Exception ex)
{
Logger.LogWarning(ex, "Step {Step}: Failed to extract frame info, using defaults", Name);
context.FrameInfo = Enumerable.Range(0, 7)
.Select(i => (i, 40 - (i * 5)))
.ToList();
}
return ScrapingStepResult.Successful();
}
catch (Exception ex)
{
Logger.LogError(ex, "Step {Step} failed", Name);
await SaveErrorDebugAsync(context, $"Failed to extract metadata: {ex.Message}", cancellationToken);
return ScrapingStepResult.Failed($"Failed to extract metadata: {ex.Message}");
}
}
}