Files
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

66 lines
2.5 KiB
C#

using BomLocalService.Services.Interfaces;
using BomLocalService.Services.Scraping;
using Microsoft.Playwright;
namespace BomLocalService.Services.Scraping.Steps.Navigation;
public class ClickSearchButtonStep : BaseScrapingStep
{
public override string Name => "ClickSearchButton";
public override string[] Prerequisites => new[] { "NavigateHomepage" };
public ClickSearchButtonStep(
ILogger<ClickSearchButtonStep> logger,
ISelectorService selectorService,
IDebugService debugService,
IConfiguration configuration)
: base(logger, selectorService, debugService, configuration)
{
}
public override bool CanExecute(ScrapingContext context)
{
return context.IsHomepageLoaded;
}
public override async Task<ScrapingStepResult> ExecuteAsync(ScrapingContext context, CancellationToken cancellationToken)
{
try
{
Logger.LogInformation("Step {Step}: Clicking 'Search for a location' button", Name);
var searchButton = await SelectorService.FindElementAsync(context.Page, Selectors.SearchButton, cancellationToken);
if (searchButton == null)
{
var errorMsg = Selectors.SearchButton.ErrorMessage ?? "Could not find 'Search for a location' button on BOM homepage.";
await SaveErrorDebugAsync(context, errorMsg, cancellationToken);
return ScrapingStepResult.Failed(errorMsg);
}
context.SearchButton = searchButton;
await searchButton.ClickAsync();
// Wait for search input to appear
var searchInputReady = SelectorService.GetLocator(context.Page, Selectors.SearchInput);
await searchInputReady.WaitForAsync(new LocatorWaitForOptions
{
Timeout = Selectors.SearchInput.TimeoutMs,
State = WaitForSelectorState.Visible
});
await SaveDebugAsync(context, 2, "search_button_clicked", cancellationToken);
context.CurrentState = PageState.SearchModalOpen;
return ScrapingStepResult.Successful();
}
catch (Exception ex)
{
Logger.LogError(ex, "Step {Step} failed", Name);
await SaveErrorDebugAsync(context, $"Failed to click search button: {ex.Message}", cancellationToken);
return ScrapingStepResult.Failed($"Failed to click search button: {ex.Message}");
}
}
}