api/models.py

@@ -0,0 +1,53 @@
+"""
+Pydantic models for NFOGuard API
+"""
+from pydantic import BaseModel
+from typing import Optional, Dict, Any, List
+
+
+class SonarrWebhook(BaseModel):
+    """Sonarr webhook payload model"""
+    eventType: str
+    series: Optional[Dict[str, Any]] = None
+    episodes: Optional[list] = []
+    episodeFile: Optional[Dict[str, Any]] = None
+    isUpgrade: Optional[bool] = False
+
+    class Config:
+        extra = "allow"
+
+
+class RadarrWebhook(BaseModel):
+    """Radarr webhook payload model"""
+    eventType: str
+    movie: Optional[Dict[str, Any]] = None
+    movieFile: Optional[Dict[str, Any]] = None
+    isUpgrade: Optional[bool] = False
+    deletedFiles: Optional[list] = []
+    remoteMovie: Optional[Dict[str, Any]] = None
+    renamedMovieFiles: Optional[List[Dict[str, Any]]] = None
+
+    class Config:
+        extra = "allow"
+
+
+class HealthResponse(BaseModel):
+    """Health check response model"""
+    status: str
+    version: str
+    uptime: str
+    database_status: str
+    radarr_database: Optional[Dict[str, Any]] = None
+
+
+class TVSeasonRequest(BaseModel):
+    """TV season processing request model"""
+    series_path: str
+    season_name: str
+
+
+class TVEpisodeRequest(BaseModel):
+    """TV episode processing request model"""
+    series_path: str
+    season_name: str
+    episode_name: str

api/routes.py

@@ -0,0 +1,870 @@
+"""
+FastAPI routes for NFOGuard - extracted from main nfoguard.py for modular architecture
+"""
+import os
+import json
+from pathlib import Path
+from datetime import datetime, timezone
+from fastapi import HTTPException, BackgroundTasks, Request
+from typing import Optional
+
+# Import models
+from api.models import SonarrWebhook, RadarrWebhook, HealthResponse, TVSeasonRequest, TVEpisodeRequest
+
+
+# ---------------------------
+# Helper Functions
+# ---------------------------
+
+async def _read_payload(request: Request) -> dict:
+    """Read webhook payload from request"""
+    content_type = (request.headers.get("content-type") or "").lower()
+    try:
+        if "application/json" in content_type:
+            return await request.json()
+        form = await request.form()
+        if "payload" in form:
+            return json.loads(form["payload"])
+        return dict(form)
+    except Exception as e:
+        print(f"ERROR: Failed to read webhook payload: {e}")  # Using print since _log is not available
+        return {}
+
+
+# ---------------------------
+# Route Handlers
+# ---------------------------
+
+async def sonarr_webhook(request: Request, background_tasks: BackgroundTasks, dependencies: dict):
+    """Handle Sonarr webhooks"""
+    tv_processor = dependencies["tv_processor"]
+    batcher = dependencies["batcher"]
+    config = dependencies["config"]
+    
+    try:
+        payload = await _read_payload(request)
+        if not payload:
+            raise HTTPException(status_code=422, detail="Empty Sonarr payload")
+        
+        webhook = SonarrWebhook(**payload)
+        print(f"INFO: Received Sonarr webhook: {webhook.eventType}")
+        
+        if webhook.eventType not in ["Download", "Upgrade", "Rename"]:
+            return {"status": "ignored", "reason": f"Event type {webhook.eventType} not processed"}
+        
+        if not webhook.series:
+            return {"status": "ignored", "reason": "No series data"}
+        
+        series_info = webhook.series
+        series_title = series_info.get("title", "")
+        imdb_id = series_info.get("imdbId", "").replace("tt", "").strip()
+        if imdb_id:
+            imdb_id = f"tt{imdb_id}"
+        sonarr_path = series_info.get("path", "")
+        
+        if not imdb_id:
+            print(f"ERROR: No IMDb ID for series: {series_title}")
+            return {"status": "error", "reason": "No IMDb ID"}
+        
+        # Find series path
+        series_path = tv_processor.find_series_path(series_title, imdb_id, sonarr_path)
+        if not series_path:
+            print(f"ERROR: Could not find series directory: {series_title} ({imdb_id})")
+            return {"status": "error", "reason": "Series directory not found"}
+        
+        # Add to batch queue with TV-prefixed key to avoid movie conflicts
+        tv_batch_key = f"tv:{imdb_id}"
+        webhook_dict = {
+            'path': str(series_path),
+            'series_info': series_info,
+            'event_type': webhook.eventType,
+            'episodes': webhook.episodes or [],  # Include episode data for targeted processing
+            'processing_mode': config.tv_webhook_processing_mode
+        }
+        batcher.add_webhook(tv_batch_key, webhook_dict, 'tv')
+        
+        return {"status": "accepted", "message": f"Sonarr webhook queued for {tv_batch_key}"}
+        
+    except Exception as e:
+        print(f"ERROR: Sonarr webhook error: {e}")
+        raise HTTPException(status_code=422, detail=f"Invalid webhook: {e}")
+
+
+async def radarr_webhook(request: Request, background_tasks: BackgroundTasks, dependencies: dict):
+    """Handle Radarr webhooks"""
+    path_mapper = dependencies["path_mapper"]
+    batcher = dependencies["batcher"]
+    
+    try:
+        payload = await _read_payload(request)
+        print(f"INFO: Received Radarr webhook: {payload.get('eventType', 'Unknown')}")
+        print(f"DEBUG: Full Radarr webhook payload: {payload}")
+        
+        # Filter supported event types (same as Sonarr: Download, Upgrade, Rename)
+        event_type = payload.get('eventType', '')
+        if event_type not in ["Download", "Upgrade", "Rename"]:
+            return {"status": "ignored", "reason": f"Event type {event_type} not processed"}
+        
+        # Extract movie info
+        movie_data = payload.get("movie", {})
+        if not movie_data:
+            print("WARNING: No movie data in Radarr webhook")
+            return {"status": "error", "message": "No movie data"}
+        
+        # Get IMDb ID for batching key
+        imdb_id = movie_data.get("imdbId", "").lower()
+        if not imdb_id:
+            print("WARNING: No IMDb ID in Radarr webhook movie data")
+            return {"status": "error", "message": "No IMDb ID"}
+        
+        # Get movie path and map it
+        movie_path = movie_data.get("folderPath") or movie_data.get("path", "")
+        if not movie_path:
+            print("ERROR: No movie path in Radarr webhook")
+            return {"status": "error", "message": "No movie path provided"}
+        
+        # Map the path to container path
+        container_path = path_mapper.radarr_path_to_container_path(movie_path)
+        print(f"DEBUG: Mapped Radarr path {movie_path} -> {container_path}")
+        
+        # CRITICAL: Verify the mapped path actually exists
+        if not Path(container_path).exists():
+            print(f"ERROR: RADARR WEBHOOK REJECTED: Mapped path does not exist: {container_path}")
+            print(f"ERROR: This prevents processing wrong movies due to path mapping issues")
+            return {"status": "error", "message": f"Mapped movie path does not exist: {container_path}"}
+        
+        # Verify the path contains the expected IMDb ID
+        if imdb_id not in container_path.lower():
+            print(f"WARNING: IMDb ID {imdb_id} not found in container path {container_path}")
+        
+        # Create movie-specific webhook data with proper path validation
+        movie_webhook_data = {
+            'path': container_path,  # Use verified container path
+            'movie_info': movie_data,
+            'event_type': payload.get('eventType'),
+            'original_payload': payload
+        }
+        
+        # Add to batch queue with movie-prefixed key to avoid TV conflicts
+        movie_batch_key = f"movie:{imdb_id}"
+        print(f"DEBUG: Adding Radarr webhook to batch: key={movie_batch_key}, movie_title={movie_data.get('title', 'Unknown')}")
+        batcher.add_webhook(movie_batch_key, movie_webhook_data, "movie")
+        
+        return {"status": "success", "message": f"Radarr webhook queued for {movie_batch_key}"}
+        
+    except Exception as e:
+        print(f"ERROR: Radarr webhook error: {e}")
+        return {"status": "error", "message": str(e)}
+
+
+async def health(dependencies: dict) -> HealthResponse:
+    """Health check endpoint with Radarr database status"""
+    db = dependencies["db"]
+    movie_processor = dependencies["movie_processor"]
+    start_time = dependencies["start_time"]
+    version = dependencies["version"]
+    
+    uptime = datetime.now(timezone.utc) - start_time
+    
+    # Check NFOGuard database
+    try:
+        with db.get_connection() as conn:
+            conn.execute("SELECT 1").fetchone()
+        db_status = "healthy"
+    except Exception as e:
+        db_status = f"error: {e}"
+    
+    # Check Radarr database if available
+    radarr_db_health = None
+    overall_status = "healthy" if db_status == "healthy" else "degraded"
+    
+    # Get Radarr client with database access from movie processor
+    try:
+        if hasattr(movie_processor, 'radarr') and movie_processor.radarr:
+            radarr_client = movie_processor.radarr
+            if hasattr(radarr_client, 'db_client') and radarr_client.db_client:
+                try:
+                    radarr_db_health = radarr_client.db_client.health_check()
+                    if radarr_db_health["status"] != "healthy":
+                        overall_status = "degraded"
+                except Exception as e:
+                    radarr_db_health = {
+                        "status": "error",
+                        "error": str(e),
+                        "tested_at": datetime.now(timezone.utc).isoformat(timespec="seconds")
+                    }
+                    overall_status = "degraded"
+    except Exception as e:
+        # If movie processor isn't available, skip database health check
+        print(f"DEBUG: Skipping Radarr database health check: {e}")
+    
+    return HealthResponse(
+        status=overall_status,
+        version=version,
+        uptime=str(uptime),
+        database_status=db_status,
+        radarr_database=radarr_db_health
+    )
+
+
+async def get_stats(dependencies: dict):
+    """Get database statistics"""
+    db = dependencies["db"]
+    try:
+        return db.get_stats()
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+async def batch_status(dependencies: dict):
+    """Get batch queue status"""
+    batcher = dependencies["batcher"]
+    return batcher.get_status()
+
+
+async def debug_movie_import_date(imdb_id: str, dependencies: dict):
+    """Debug endpoint to analyze movie import date detection"""
+    movie_processor = dependencies["movie_processor"]
+    
+    try:
+        if not imdb_id.startswith("tt"):
+            imdb_id = f"tt{imdb_id}"
+            
+        print(f"INFO: === DEBUG MOVIE IMPORT DATE: {imdb_id} ===")
+        
+        if not (os.environ.get("RADARR_URL") and os.environ.get("RADARR_API_KEY")):
+            return {
+                "error": "Radarr not configured", 
+                "imdb_id": imdb_id,
+                "radarr_configured": False
+            }
+        
+        # Create Radarr client
+        from clients.radarr_client import RadarrClient
+        radarr_client = RadarrClient(
+            os.environ.get("RADARR_URL"),
+            os.environ.get("RADARR_API_KEY")
+        )
+        
+        # Look up movie
+        movie_obj = radarr_client.movie_by_imdb(imdb_id)
+        if not movie_obj:
+            return {
+                "error": f"Movie not found in Radarr for IMDb ID {imdb_id}",
+                "imdb_id": imdb_id,
+                "radarr_configured": True,
+                "movie_found": False
+            }
+            
+        movie_id = movie_obj.get("id")
+        movie_title = movie_obj.get("title")
+        
+        print(f"INFO: Found movie: {movie_title} (Radarr ID: {movie_id})")
+        
+        # Test the FULL movie processing pipeline (not just database lookup)
+        print(f"INFO: === TESTING FULL MOVIE PROCESSING PIPELINE ===")
+        
+        # Create a dummy path for testing the decision logic
+        dummy_path = Path("/tmp/test")
+        
+        try:
+            # Use the global movie processor instance to test full decision logic
+            if movie_processor:
+                # First check external clients configuration
+                print(f"INFO: === CHECKING EXTERNAL CLIENTS CONFIG ===")
+                try:
+                    tmdb_key = os.environ.get("TMDB_API_KEY", "")
+                    print(f"INFO: TMDB API Key configured: {'✅ YES' if tmdb_key else '❌ NO'}")
+                    if tmdb_key:
+                        print(f"INFO: TMDB API Key length: {len(tmdb_key)} chars")
+                    
+                    # Check if external clients exist
+                    external_clients_available = hasattr(movie_processor, 'external_clients') and movie_processor.external_clients
+                    print(f"INFO: External clients initialized: {'✅ YES' if external_clients_available else '❌ NO'}")
+                    
+                except Exception as e:
+                    print(f"ERROR: Error checking external clients config: {e}")
+                
+                # Test the full decision logic (including TMDB fallback)
+                final_date, final_source, released = movie_processor._decide_movie_dates(
+                    imdb_id, dummy_path, should_query=True, existing=None
+                )
+                
+                print(f"INFO: === FULL PIPELINE RESULT ===")
+                print(f"INFO: Final date: {final_date}")
+                print(f"INFO: Final source: {final_source}")
+                print(f"INFO: Released (theater): {released}")
+                
+                return {
+                    "imdb_id": imdb_id,
+                    "radarr_configured": True,
+                    "movie_found": True,
+                    "movie_title": movie_title,
+                    "movie_id": movie_id,
+                    "full_pipeline_test": {
+                        "final_date": final_date,
+                        "final_source": final_source,
+                        "theater_release": released,
+                        "decision_logic": "✅ TESTED FULL PIPELINE INCLUDING TMDB FALLBACK"
+                    },
+                    "database_only_test": {
+                        "radarr_db_result": radarr_client.get_movie_import_date(movie_id, fallback_to_file_date=True),
+                        "note": "This is just the database part - fallback happens in full pipeline"
+                    },
+                    "debug_info": {
+                        "radarr_url": os.environ.get("RADARR_URL"),
+                        "movie_digital_release": movie_obj.get("digitalRelease"),
+                        "movie_in_cinemas": movie_obj.get("inCinemas"),
+                        "movie_physical_release": movie_obj.get("physicalRelease"),
+                        "movie_folder_path": movie_obj.get("folderPath")
+                    }
+                }
+            else:
+                print("ERROR: Movie processor not available - testing database only")
+                # Fallback to database-only testing
+                import_date, source = radarr_client.get_movie_import_date(movie_id, fallback_to_file_date=True)
+                return {
+                    "error": "Movie processor not available - only database test performed",
+                    "imdb_id": imdb_id,
+                    "radarr_configured": True,
+                    "movie_found": True,
+                    "movie_title": movie_title,
+                    "movie_id": movie_id,
+                    "detected_import_date": import_date,
+                    "import_source": source,
+                    "debug_info": {
+                        "note": "FULL PIPELINE TEST FAILED - movie processor not initialized"
+                    }
+                }
+                
+        except Exception as pipeline_error:
+            print(f"ERROR: Full pipeline test failed: {pipeline_error}")
+            # Fallback to database-only testing
+            import_date, source = radarr_client.get_movie_import_date(movie_id, fallback_to_file_date=True)
+            return {
+                "pipeline_error": str(pipeline_error),
+                "imdb_id": imdb_id,
+                "radarr_configured": True,
+                "movie_found": True,
+                "movie_title": movie_title,
+                "movie_id": movie_id,
+                "detected_import_date": import_date,
+                "import_source": source,
+                "debug_info": {
+                    "note": "FULL PIPELINE TEST FAILED - showing database-only result"
+                }
+            }
+        
+    except Exception as e:
+        print(f"ERROR: Debug endpoint error for {imdb_id}: {e}")
+        return {
+            "error": str(e),
+            "imdb_id": imdb_id,
+            "success": False
+        }
+
+
+async def debug_movie_history(imdb_id: str, dependencies: dict):
+    """Detailed history analysis for a movie"""
+    movie_processor = dependencies["movie_processor"]
+    
+    try:
+        if not imdb_id.startswith("tt"):
+            imdb_id = f"tt{imdb_id}"
+            
+        print(f"INFO: === DETAILED HISTORY ANALYSIS: {imdb_id} ===")
+        
+        # This would need the rest of the implementation from the original function
+        # For now, returning a placeholder
+        return {
+            "imdb_id": imdb_id,
+            "message": "History analysis endpoint - implementation needed"
+        }
+        
+    except Exception as e:
+        print(f"ERROR: Debug history endpoint error for {imdb_id}: {e}")
+        return {
+            "error": str(e),
+            "imdb_id": imdb_id,
+            "success": False
+        }
+
+
+async def manual_scan(background_tasks: BackgroundTasks, path: Optional[str] = None, scan_type: str = "both", dependencies: dict = None):
+    """Manual scan endpoint"""
+    config = dependencies["config"]
+    nfo_manager = dependencies["nfo_manager"]
+    tv_processor = dependencies["tv_processor"]
+    movie_processor = dependencies["movie_processor"]
+    
+    if scan_type not in ["both", "tv", "movies"]:
+        raise HTTPException(status_code=400, detail="scan_type must be 'both', 'tv', or 'movies'")
+    
+    async def run_scan():
+        paths_to_scan = []
+        if path:
+            paths_to_scan = [Path(path)]
+        else:
+            if scan_type in ["both", "tv"]:
+                paths_to_scan.extend(config.tv_paths)
+            if scan_type in ["both", "movies"]:  
+                paths_to_scan.extend(config.movie_paths)
+        
+        for scan_path in paths_to_scan:
+            if not scan_path.exists():
+                continue
+                
+            if scan_type in ["both", "tv"] and (scan_path in config.tv_paths or path):
+                # Handle specific season/episode path
+                if path and scan_path.name.lower().startswith('season'):
+                    # Single season processing
+                    series_path = scan_path.parent
+                    if nfo_manager.parse_imdb_from_path(series_path):
+                        print(f"INFO: Processing single season: {scan_path}")
+                        try:
+                            tv_processor.process_season(series_path, scan_path)
+                        except Exception as e:
+                            print(f"ERROR: Failed processing season {scan_path}: {e}")
+                elif path and scan_path.is_file() and scan_path.suffix.lower() in ('.mkv', '.mp4', '.avi'):
+                    # Single episode processing
+                    season_path = scan_path.parent
+                    series_path = season_path.parent
+                    if nfo_manager.parse_imdb_from_path(series_path):
+                        print(f"INFO: Processing single episode: {scan_path}")
+                        try:
+                            tv_processor.process_episode_file(series_path, season_path, scan_path)
+                        except Exception as e:
+                            print(f"ERROR: Failed processing episode {scan_path}: {e}")
+                else:
+                    # Check if this path itself is a series (has IMDb ID in the directory name)
+                    if nfo_manager.parse_imdb_from_path(scan_path):
+                        try:
+                            tv_processor.process_series(scan_path)
+                        except Exception as e:
+                            print(f"ERROR: Failed processing TV series {scan_path}: {e}")
+                    else:
+                        # Full series processing - scan subdirectories
+                        import re
+                        for item in scan_path.iterdir():
+                            if (item.is_dir() and 
+                                not item.name.lower().startswith('season') and
+                                not re.match(r'^season\s+\d+$', item.name, re.IGNORECASE) and
+                                nfo_manager.parse_imdb_from_path(item)):
+                                try:
+                                    tv_processor.process_series(item)
+                                except Exception as e:
+                                    print(f"ERROR: Failed processing TV series {item}: {e}")
+            
+            if scan_type in ["both", "movies"] and scan_path in config.movie_paths:
+                print(f"INFO: Scanning movies in: {scan_path}")
+                movie_count = 0
+                for item in scan_path.iterdir():
+                    if item.is_dir() and nfo_manager.find_movie_imdb_id(item):
+                        movie_count += 1
+                        print(f"INFO: Processing movie: {item.name}")
+                        try:
+                            movie_processor.process_movie(item)  
+                        except Exception as e:
+                            print(f"ERROR: Failed processing movie {item}: {e}")
+                print(f"INFO: Completed movie scan: {movie_count} movies processed in {scan_path}")
+    
+    background_tasks.add_task(run_scan)
+    return {"status": "started", "message": f"Manual {scan_type} scan started"}
+
+
+async def scan_tv_season(background_tasks: BackgroundTasks, request: TVSeasonRequest, dependencies: dict):
+    """Scan a specific TV season - URL-safe endpoint"""
+    nfo_manager = dependencies["nfo_manager"]
+    tv_processor = dependencies["tv_processor"]
+    
+    try:
+        series_dir = Path(request.series_path)
+        season_dir = series_dir / request.season_name
+        
+        if not series_dir.exists():
+            raise HTTPException(status_code=404, detail=f"Series path not found: {request.series_path}")
+        if not season_dir.exists():
+            raise HTTPException(status_code=404, detail=f"Season path not found: {season_dir}")
+        
+        imdb_id = nfo_manager.parse_imdb_from_path(series_dir)
+        if not imdb_id:
+            raise HTTPException(status_code=400, detail="No IMDb ID found in series path")
+        
+        async def process_season():
+            print(f"INFO: Processing TV season: {season_dir}")
+            try:
+                tv_processor.process_season(series_dir, season_dir)
+            except Exception as e:
+                print(f"ERROR: Failed processing season {season_dir}: {e}")
+        
+        background_tasks.add_task(process_season)
+        return {"status": "started", "message": f"Season scan started for {request.season_name}"}
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+async def scan_tv_episode(background_tasks: BackgroundTasks, request: TVEpisodeRequest, dependencies: dict):
+    """Scan a specific TV episode - URL-safe endpoint"""
+    nfo_manager = dependencies["nfo_manager"]
+    tv_processor = dependencies["tv_processor"]
+    
+    try:
+        series_dir = Path(request.series_path)
+        season_dir = series_dir / request.season_name
+        episode_file = season_dir / request.episode_name
+        
+        if not series_dir.exists():
+            raise HTTPException(status_code=404, detail=f"Series path not found: {request.series_path}")
+        if not episode_file.exists():
+            raise HTTPException(status_code=404, detail=f"Episode file not found: {episode_file}")
+        
+        imdb_id = nfo_manager.parse_imdb_from_path(series_dir)
+        if not imdb_id:
+            raise HTTPException(status_code=400, detail="No IMDb ID found in series path")
+        
+        async def process_episode():
+            print(f"INFO: Processing TV episode: {episode_file}")
+            try:
+                tv_processor.process_episode_file(series_dir, season_dir, episode_file)
+            except Exception as e:
+                print(f"ERROR: Failed processing episode {episode_file}: {e}")
+        
+        background_tasks.add_task(process_episode)
+        return {"status": "started", "message": f"Episode scan started for {request.episode_name}"}
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+async def test_bulk_update(dependencies: dict):
+    """Test bulk update functionality without modifying data"""
+    try:
+        from clients.radarr_db_client import RadarrDbClient
+        
+        # Test Radarr database
+        radarr_db = RadarrDbClient.from_env()
+        if not radarr_db:
+            return {"status": "error", "message": "Radarr database connection failed"}
+        
+        # Test query execution
+        query = 'SELECT COUNT(*) FROM "Movies" m JOIN "MovieMetadata" mm ON m."MovieMetadataId" = mm."Id" WHERE mm."ImdbId" IS NOT NULL'
+        with radarr_db._get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute(query)
+            movie_count = cursor.fetchone()[0]
+        
+        return {
+            "status": "success", 
+            "message": "Bulk update test passed",
+            "movies_with_imdb": movie_count,
+            "database_type": radarr_db.db_type
+        }
+    except Exception as e:
+        return {"status": "error", "message": f"Bulk update test failed: {e}"}
+
+
+async def test_movie_scan(dependencies: dict):
+    """Test movie directory scanning logic"""
+    config = dependencies["config"]
+    nfo_manager = dependencies["nfo_manager"]
+    
+    try:
+        results = []
+        for path in config.movie_paths:
+            path_result = {
+                "path": str(path),
+                "exists": path.exists(),
+                "movies_found": 0
+            }
+            
+            if path.exists():
+                for item in path.iterdir():
+                    if item.is_dir() and nfo_manager.find_movie_imdb_id(item):
+                        path_result["movies_found"] += 1
+            
+            results.append(path_result)
+        
+        total_movies = sum(r["movies_found"] for r in results)
+        return {
+            "status": "success",
+            "message": f"Movie scan test found {total_movies} movies",
+            "path_results": results
+        }
+    except Exception as e:
+        return {"status": "error", "message": f"Movie scan test failed: {e}"}
+
+
+async def trigger_bulk_update(background_tasks: BackgroundTasks, dependencies: dict):
+    """Trigger bulk update of all movies"""
+    async def run_bulk_update():
+        try:
+            from bulk_update_movies import bulk_update_all_movies
+            success = bulk_update_all_movies()
+            print(f"INFO: Bulk update completed: {'success' if success else 'failed'}")
+        except Exception as e:
+            print(f"ERROR: Bulk update error: {e}")
+    
+    background_tasks.add_task(run_bulk_update)
+    return {"status": "started", "message": "Bulk update started"}
+
+
+async def debug_movie_priority_logic(imdb_id: str, dependencies: dict):
+    """Debug endpoint showing how MOVIE_PRIORITY affects date selection"""
+    config = dependencies["config"]
+    movie_processor = dependencies["movie_processor"]
+    
+    try:
+        if not imdb_id.startswith("tt"):
+            imdb_id = f"tt{imdb_id}"
+        
+        result = {
+            "imdb_id": imdb_id,
+            "movie_priority": config.movie_priority,
+            "release_date_priority": config.release_date_priority,
+            "priority_explanation": "",
+            "date_sources": {},
+            "selected_date": None,
+            "selected_source": None
+        }
+        
+        # Get Radarr import date
+        if movie_processor.radarr.api_key:
+            radarr_movie = movie_processor.radarr.movie_by_imdb(imdb_id)
+            if radarr_movie:
+                movie_id = radarr_movie.get("id")
+                if movie_id:
+                    import_date, import_source = movie_processor.radarr.get_movie_import_date(movie_id)
+                    if import_date:
+                        result["date_sources"]["radarr_import"] = {
+                            "date": import_date,
+                            "source": import_source
+                        }
+        
+        # Get digital release dates with detailed logging
+        digital_date, digital_source = movie_processor._get_digital_release_date(imdb_id)
+        if digital_date:
+            result["date_sources"]["digital_release"] = {
+                "date": digital_date,
+                "source": digital_source
+            }
+        else:
+            # Add debug info about why digital date wasn't found
+            candidates = movie_processor.external_clients.get_digital_release_candidates(imdb_id)
+            result["date_sources"]["digital_release_debug"] = {
+                "candidates_found": len(candidates),
+                "candidates": candidates[:3] if candidates else [],  # Show first 3
+                "reason": digital_source if digital_source else "no_digital_dates_found"
+            }
+        
+        # Show priority logic
+        if config.movie_priority == "import_then_digital":
+            priority_list = " → ".join(config.release_date_priority)
+            result["priority_explanation"] = f"1st: Radarr import history, 2nd: Release dates ({priority_list}), 3rd: file mtime. Note: If import is only file date, prefer reasonable release dates."
+            
+            radarr_import = result["date_sources"].get("radarr_import")
+            digital_release = result["date_sources"].get("digital_release")
+            
+            # Check for file date fallback logic
+            if radarr_import and radarr_import["source"] == "radarr:db.file.dateAdded" and digital_release:
+                # Test the smart logic
+                would_prefer_digital = movie_processor._should_prefer_release_over_file_date(
+                    digital_release["date"],
+                    digital_release["source"], 
+                    None,  # We don't have theatrical date in this debug context
+                    imdb_id
+                )
+                result["file_date_detected"] = True
+                result["would_prefer_digital"] = would_prefer_digital
+                
+                if would_prefer_digital:
+                    result["selected_date"] = digital_release["date"]
+                    result["selected_source"] = digital_release["source"] + " (preferred over file date)"
+                else:
+                    result["selected_date"] = radarr_import["date"]
+                    result["selected_source"] = radarr_import["source"] + " (digital too old)"
+            elif radarr_import and radarr_import["source"] != "radarr:db.file.dateAdded":
+                result["selected_date"] = radarr_import["date"]
+                result["selected_source"] = radarr_import["source"]
+            elif digital_release:
+                result["selected_date"] = digital_release["date"]
+                result["selected_source"] = digital_release["source"]
+        else:  # digital_then_import
+            result["priority_explanation"] = "1st: TMDB/OMDb digital release, 2nd: Radarr import history, 3rd: file mtime"
+            if result["date_sources"].get("digital_release"):
+                result["selected_date"] = result["date_sources"]["digital_release"]["date"]
+                result["selected_source"] = result["date_sources"]["digital_release"]["source"]
+            elif result["date_sources"].get("radarr_import"):
+                result["selected_date"] = result["date_sources"]["radarr_import"]["date"]
+                result["selected_source"] = result["date_sources"]["radarr_import"]["source"]
+        
+        # Show external API status
+        result["external_apis"] = {
+            "tmdb_enabled": movie_processor.external_clients.tmdb.enabled,
+            "omdb_enabled": movie_processor.external_clients.omdb.enabled,
+            "jellyseerr_enabled": movie_processor.external_clients.jellyseerr.enabled
+        }
+        
+        return result
+        
+    except Exception as e:
+        return {"error": str(e), "imdb_id": imdb_id}
+
+
+async def debug_tmdb_lookup(imdb_id: str, dependencies: dict):
+    """Debug TMDB API lookup for a specific movie"""
+    movie_processor = dependencies["movie_processor"]
+    
+    try:
+        if not imdb_id.startswith("tt"):
+            imdb_id = f"tt{imdb_id}"
+        
+        result = {
+            "imdb_id": imdb_id,
+            "tmdb_api_enabled": movie_processor.external_clients.tmdb.enabled,
+            "tmdb_api_key_configured": bool(movie_processor.external_clients.tmdb.api_key),
+            "steps": {}
+        }
+        
+        if not movie_processor.external_clients.tmdb.enabled:
+            result["error"] = "TMDB API not enabled - check TMDB_API_KEY environment variable"
+            return result
+        
+        # Step 1: Find movie by IMDb ID
+        print(f"INFO: TMDB Debug: Looking up {imdb_id}")
+        tmdb_movie = movie_processor.external_clients.tmdb.find_by_imdb(imdb_id)
+        result["steps"]["1_find_by_imdb"] = {
+            "found": bool(tmdb_movie),
+            "tmdb_movie": tmdb_movie if tmdb_movie else None
+        }
+        
+        if not tmdb_movie:
+            result["error"] = f"Movie {imdb_id} not found in TMDB"
+            return result
+        
+        tmdb_id = tmdb_movie.get("id")
+        result["tmdb_id"] = tmdb_id
+        
+        # Step 2: Get release dates
+        if tmdb_id:
+            print(f"INFO: TMDB Debug: Getting release dates for TMDB ID {tmdb_id}")
+            release_dates_result = movie_processor.external_clients.tmdb._get(f"/movie/{tmdb_id}/release_dates")
+            result["steps"]["2_release_dates"] = {
+                "raw_response": release_dates_result,
+                "has_results": bool(release_dates_result and release_dates_result.get("results"))
+            }
+            
+            # Step 3: Look for US digital releases
+            if release_dates_result and release_dates_result.get("results"):
+                us_releases = []
+                for country_data in release_dates_result["results"]:
+                    if country_data.get("iso_3166_1") == "US":
+                        us_releases = country_data.get("release_dates", [])
+                        break
+                
+                result["steps"]["3_us_releases"] = {
+                    "found_us_data": bool(us_releases),
+                    "us_releases": us_releases
+                }
+                
+                # Step 4: Look for digital releases (type 4)
+                digital_releases = [r for r in us_releases if r.get("type") == 4]
+                result["steps"]["4_digital_releases"] = {
+                    "digital_count": len(digital_releases),
+                    "digital_releases": digital_releases
+                }
+        
+        # Step 5: Test the full digital release function
+        digital_date = movie_processor.external_clients.tmdb.get_digital_release_date(imdb_id)
+        result["steps"]["5_final_result"] = {
+            "digital_date": digital_date,
+            "success": bool(digital_date)
+        }
+        
+        return result
+        
+    except Exception as e:
+        return {"error": str(e), "imdb_id": imdb_id, "traceback": str(e)}
+
+
+# ---------------------------
+# Route Registration
+# ---------------------------
+
+def register_routes(app, dependencies: dict):
+    """
+    Register all routes with the FastAPI app
+    
+    Args:
+        app: FastAPI application instance
+        dependencies: Dictionary containing:
+            - db: NFOGuardDatabase instance
+            - nfo_manager: NFOManager instance
+            - path_mapper: PathMapper instance
+            - tv_processor: TVProcessor instance
+            - movie_processor: MovieProcessor instance
+            - batcher: WebhookBatcher instance
+            - start_time: Application start time
+            - config: NFOGuardConfig instance
+            - version: Application version string
+    """
+    
+    @app.post("/webhook/sonarr")
+    async def _sonarr_webhook(request: Request, background_tasks: BackgroundTasks):
+        return await sonarr_webhook(request, background_tasks, dependencies)
+
+    @app.post("/webhook/radarr") 
+    async def _radarr_webhook(request: Request, background_tasks: BackgroundTasks):
+        return await radarr_webhook(request, background_tasks, dependencies)
+
+    @app.get("/health")
+    async def _health() -> HealthResponse:
+        return await health(dependencies)
+
+    @app.get("/stats")
+    async def _get_stats():
+        return await get_stats(dependencies)
+
+    @app.get("/batch/status") 
+    async def _batch_status():
+        return await batch_status(dependencies)
+
+    @app.get("/debug/movie/{imdb_id}")
+    async def _debug_movie_import_date(imdb_id: str):
+        return await debug_movie_import_date(imdb_id, dependencies)
+
+    @app.get("/debug/movie/{imdb_id}/history")
+    async def _debug_movie_history(imdb_id: str):
+        return await debug_movie_history(imdb_id, dependencies)
+
+    @app.post("/manual/scan")
+    async def _manual_scan(background_tasks: BackgroundTasks, path: Optional[str] = None, scan_type: str = "both"):
+        return await manual_scan(background_tasks, path, scan_type, dependencies)
+
+    @app.post("/tv/scan-season")
+    async def _scan_tv_season(background_tasks: BackgroundTasks, request: TVSeasonRequest):
+        return await scan_tv_season(background_tasks, request, dependencies)
+
+    @app.post("/tv/scan-episode")
+    async def _scan_tv_episode(background_tasks: BackgroundTasks, request: TVEpisodeRequest):
+        return await scan_tv_episode(background_tasks, request, dependencies)
+
+    @app.post("/test/bulk-update")
+    async def _test_bulk_update():
+        return await test_bulk_update(dependencies)
+
+    @app.post("/test/movie-scan")
+    async def _test_movie_scan():
+        return await test_movie_scan(dependencies)
+
+    @app.post("/bulk/update")
+    async def _trigger_bulk_update(background_tasks: BackgroundTasks):
+        return await trigger_bulk_update(background_tasks, dependencies)
+
+    @app.get("/debug/movie/{imdb_id}/priority")
+    async def _debug_movie_priority_logic(imdb_id: str):
+        return await debug_movie_priority_logic(imdb_id, dependencies)
+
+    @app.get("/debug/tmdb/{imdb_id}")
+    async def _debug_tmdb_lookup(imdb_id: str):
+        return await debug_tmdb_lookup(imdb_id, dependencies)

config/settings.py

@@ -0,0 +1,65 @@
+"""
+NFOGuard Configuration Module
+Handles all configuration loading and validation
+"""
+import os
+from pathlib import Path
+from typing import List
+
+
+def _bool_env(name: str, default: bool) -> bool:
+    """Convert environment variable to boolean"""
+    v = os.environ.get(name)
+    if v is None:
+        return default
+    return v.lower() in ("1", "true", "yes", "y", "on")
+
+
+class NFOGuardConfig:
+    """Configuration class for NFOGuard"""
+    
+    def __init__(self):
+        # Paths - No hardcoded defaults, must be configured via environment
+        tv_paths_env = os.environ.get("TV_PATHS", "")
+        movie_paths_env = os.environ.get("MOVIE_PATHS", "")
+        
+        if not tv_paths_env:
+            raise ValueError("TV_PATHS environment variable is required but not set")
+        if not movie_paths_env:
+            raise ValueError("MOVIE_PATHS environment variable is required but not set")
+            
+        self.tv_paths = [Path(p.strip()) for p in tv_paths_env.split(",") if p.strip()]
+        self.movie_paths = [Path(p.strip()) for p in movie_paths_env.split(",") if p.strip()]
+        
+        # Core settings
+        self.manage_nfo = _bool_env("MANAGE_NFO", True)
+        self.fix_dir_mtimes = _bool_env("FIX_DIR_MTIMES", True)
+        self.lock_metadata = _bool_env("LOCK_METADATA", True)
+        self.debug = _bool_env("DEBUG", False)
+        self.manager_brand = os.environ.get("MANAGER_BRAND", "NFOGuard")
+        
+        # Batching
+        self.batch_delay = float(os.environ.get("BATCH_DELAY", "5.0"))
+        self.max_concurrent = int(os.environ.get("MAX_CONCURRENT_SERIES", "3"))
+        
+        # Database
+        self.db_path = Path(os.environ.get("DB_PATH", "/app/data/media_dates.db"))
+        
+        # Movie processing
+        self.movie_priority = os.environ.get("MOVIE_PRIORITY", "import_then_digital").lower()
+        self.prefer_release_dates_over_file_dates = _bool_env("PREFER_RELEASE_DATES_OVER_FILE_DATES", True)
+        self.allow_file_date_fallback = _bool_env("ALLOW_FILE_DATE_FALLBACK", False)
+        self.release_date_priority = [p.strip() for p in os.environ.get("RELEASE_DATE_PRIORITY", "digital,physical,theatrical").split(",")]
+        self.enable_smart_date_validation = _bool_env("ENABLE_SMART_DATE_VALIDATION", True)
+        self.max_release_date_gap_years = int(os.environ.get("MAX_RELEASE_DATE_GAP_YEARS", "10"))
+        self.movie_poll_mode = os.environ.get("MOVIE_POLL_MODE", "always").lower()
+        self.movie_update_mode = os.environ.get("MOVIE_DATE_UPDATE_MODE", "backfill_only").lower()
+        
+        # TV processing
+        self.tv_season_dir_format = os.environ.get("TV_SEASON_DIR_FORMAT", "Season {season:02d}")
+        self.tv_season_dir_pattern = os.environ.get("TV_SEASON_DIR_PATTERN", "season ").lower()
+        self.tv_webhook_processing_mode = os.environ.get("TV_WEBHOOK_PROCESSING_MODE", "targeted").lower()
+
+
+# Global config instance
+config = NFOGuardConfig()

main.py

@@ -0,0 +1,160 @@
+#!/usr/bin/env python3
+"""
+NFOGuard - Automated NFO file management for Radarr and Sonarr
+Modular architecture with webhook processing and intelligent date handling
+"""
+import os
+import sys
+import signal
+from pathlib import Path
+from datetime import datetime, timezone
+
+import uvicorn
+from fastapi import FastAPI
+
+# Import configuration first
+from config.settings import config
+from utils.logging import _log
+
+# Import core components
+from core.database import NFOGuardDatabase
+from core.nfo_manager import NFOManager
+from core.path_mapper import PathMapper
+
+# Import clients
+from clients.external_clients import ExternalClientManager
+
+# Import processors
+from processors.tv_processor import TVProcessor
+from processors.movie_processor import MovieProcessor
+
+# Import webhook handling
+from webhooks.webhook_batcher import WebhookBatcher
+
+# Import API routes
+from api.routes import register_routes
+
+
+def get_version() -> str:
+    """Get application version"""
+    try:
+        version = (Path(__file__).parent / "VERSION").read_text().strip()
+    except:
+        version = "0.1.0"
+
+    # Check if running from dev branch (detect at runtime)
+    try:
+        # Try to read git branch from .git/HEAD
+        git_head_path = Path(__file__).parent / ".git" / "HEAD"
+        if git_head_path.exists():
+            head_content = git_head_path.read_text().strip()
+            if "ref: refs/heads/dev" in head_content:
+                version = f"{version}-dev"
+            elif head_content.startswith("ref: refs/heads/"):
+                # Extract branch name for other branches
+                branch = head_content.split("refs/heads/")[-1]
+                if branch != "main":
+                    version = f"{version}-{branch}"
+    except Exception:
+        # If git detection fails, that's fine - use base version
+        pass
+
+    # Check for build source (only add -gitea for local Gitea builds)
+    build_source = os.environ.get("BUILD_SOURCE", "")
+    if build_source == "gitea":
+        if "gitea" not in version:  # Don't double-add gitea suffix
+            version = f"{version}-gitea"
+
+    return version
+
+
+def create_app() -> FastAPI:
+    """Create and configure the FastAPI application"""
+    version = get_version()
+    
+    app = FastAPI(
+        title="NFOGuard",
+        description="Webhook server for preserving media import dates",
+        version=version
+    )
+    
+    return app
+
+
+def initialize_components():
+    """Initialize all application components"""
+    start_time = datetime.now(timezone.utc)
+    
+    # Initialize core components
+    db = NFOGuardDatabase(config.db_path)
+    nfo_manager = NFOManager(config.manager_brand, config.debug)
+    path_mapper = PathMapper(config)
+    
+    # Initialize processors
+    tv_processor = TVProcessor(db, nfo_manager, path_mapper)
+    movie_processor = MovieProcessor(db, nfo_manager, path_mapper)
+    
+    # Initialize webhook batcher
+    batcher = WebhookBatcher()
+    batcher.set_processors(tv_processor, movie_processor)
+    
+    return {
+        "db": db,
+        "nfo_manager": nfo_manager,
+        "path_mapper": path_mapper,
+        "tv_processor": tv_processor,
+        "movie_processor": movie_processor,
+        "batcher": batcher,
+        "start_time": start_time,
+        "config": config,
+        "version": get_version()
+    }
+
+
+def signal_handler(signum, frame):
+    """Handle shutdown signals gracefully"""
+    _log("INFO", f"Received signal {signum}, shutting down gracefully...")
+    sys.exit(0)
+
+
+def main():
+    """Main application entry point"""
+    # Register signal handlers for graceful shutdown
+    signal.signal(signal.SIGTERM, signal_handler)
+    signal.signal(signal.SIGINT, signal_handler)
+    
+    version = get_version()
+    
+    _log("INFO", "Starting NFOGuard")
+    _log("INFO", f"Version: {version}")
+    _log("INFO", f"TV paths: {[str(p) for p in config.tv_paths]}")
+    _log("INFO", f"Movie paths: {[str(p) for p in config.movie_paths]}")
+    _log("INFO", f"Database: {config.db_path}")
+    _log("INFO", f"Config: manage_nfo={config.manage_nfo}, fix_mtimes={config.fix_dir_mtimes}")
+    _log("INFO", f"Movie priority: {config.movie_priority}")
+    
+    # Create FastAPI app
+    app = create_app()
+    
+    # Initialize components
+    dependencies = initialize_components()
+    
+    # Register routes
+    register_routes(app, dependencies)
+    
+    try:
+        uvicorn.run(
+            app,
+            host="0.0.0.0", 
+            port=int(os.environ.get("PORT", "8080")),
+            reload=False
+        )
+    except KeyboardInterrupt:
+        _log("INFO", "NFOGuard stopped by user")
+    except Exception as e:
+        _log("ERROR", f"NFOGuard crashed: {e}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

processors/movie_processor.py

@@ -0,0 +1,560 @@
+"""
+Movie Processor for NFOGuard
+Handles movie processing and metadata management
+"""
+import os
+import glob
+import re
+import xml.etree.ElementTree as ET
+from pathlib import Path
+from typing import Optional, Dict, List, Tuple
+from datetime import datetime, timezone
+from zoneinfo import ZoneInfo
+
+from core.database import NFOGuardDatabase
+from core.nfo_manager import NFOManager
+from core.path_mapper import PathMapper
+from clients.radarr_client import RadarrClient
+from clients.external_clients import ExternalClientManager
+from config.settings import config
+from utils.logging import _log
+
+
+def _get_local_timezone():
+    """Get the local timezone, respecting TZ environment variable"""
+    tz_name = os.environ.get('TZ', 'UTC')
+    
+    try:
+        # Try zoneinfo first (Python 3.9+)
+        return ZoneInfo(tz_name)
+    except ImportError:
+        # Fallback for older Python versions
+        try:
+            import pytz
+            return pytz.timezone(tz_name)
+        except:
+            # Final fallback to UTC
+            return timezone.utc
+    except:
+        # Final fallback to UTC
+        return timezone.utc
+
+
+def convert_utc_to_local(utc_iso_string: str) -> str:
+    """Convert UTC ISO timestamp to local timezone timestamp"""
+    if not utc_iso_string:
+        return utc_iso_string
+    
+    try:
+        # Parse UTC timestamp
+        if utc_iso_string.endswith('Z'):
+            dt_utc = datetime.fromisoformat(utc_iso_string.replace('Z', '+00:00'))
+        elif '+00:00' in utc_iso_string:
+            dt_utc = datetime.fromisoformat(utc_iso_string)
+        else:
+            # Assume UTC if no timezone info
+            dt_utc = datetime.fromisoformat(utc_iso_string).replace(tzinfo=timezone.utc)
+        
+        # Convert to local timezone
+        local_tz = _get_local_timezone()
+        dt_local = dt_utc.astimezone(local_tz)
+        
+        return dt_local.isoformat(timespec='seconds')
+    except Exception:
+        # If conversion fails, return original
+        return utc_iso_string
+
+
+class MovieProcessor:
+    """Handles movie processing"""
+    
+    def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager, path_mapper: PathMapper):
+        self.db = db
+        self.nfo_manager = nfo_manager
+        self.path_mapper = path_mapper
+        self.radarr = RadarrClient(
+            os.environ.get("RADARR_URL", ""),
+            os.environ.get("RADARR_API_KEY", "")
+        )
+        self.external_clients = ExternalClientManager()
+    
+    def find_movie_path(self, movie_title: str, imdb_id: str, radarr_path: str = None) -> Optional[Path]:
+        """Find movie directory path"""
+        # Try webhook path first
+        if radarr_path:
+            container_path = self.path_mapper.radarr_path_to_container_path(radarr_path)
+            path_obj = Path(container_path)
+            if path_obj.exists():
+                return path_obj
+        
+        # Search by IMDb ID or title
+        for media_path in config.movie_paths:
+            if not media_path.exists():
+                continue
+            
+            # Search by IMDb ID
+            if imdb_id:
+                pattern = str(media_path / f"*[imdb-{imdb_id}]*")
+                matches = glob.glob(pattern)
+                if matches:
+                    return Path(matches[0])
+            
+            # Search by title
+            if movie_title:
+                title_clean = movie_title.lower().replace(" ", "").replace("-", "")
+                for item in media_path.iterdir():
+                    if item.is_dir() and "[imdb-" in item.name.lower():
+                        item_clean = item.name.lower().replace(" ", "").replace("-", "")
+                        if title_clean in item_clean:
+                            return item
+        
+        return None
+    
+    def process_movie(self, movie_path: Path, webhook_mode: bool = False) -> None:
+        """Process a movie directory"""
+        imdb_id = self.nfo_manager.find_movie_imdb_id(movie_path)
+        if not imdb_id:
+            _log("ERROR", f"No IMDb ID found in movie directory, filenames, or NFO file: {movie_path}")
+            return
+        
+        # Handle TMDB ID fallback case
+        is_tmdb_fallback = imdb_id.startswith("tmdb-")
+        if is_tmdb_fallback:
+            _log("INFO", f"Processing movie: {movie_path.name} (TMDB: {imdb_id})")
+        else:
+            _log("INFO", f"Processing movie: {movie_path.name} (IMDb: {imdb_id})")
+        
+        # Update database
+        self.db.upsert_movie(imdb_id, str(movie_path))
+        
+        # Check for video files
+        video_exts = (".mkv", ".mp4", ".avi", ".mov", ".m4v")
+        has_video = any(f.is_file() and f.suffix.lower() in video_exts for f in movie_path.iterdir())
+        
+        if not has_video:
+            _log("WARNING", f"No video files found in: {movie_path}")
+            self.db.upsert_movie_dates(imdb_id, None, None, None, False)
+            return
+        
+        # TIER 1: Check if NFO file already has NFOGuard data (fastest - no DB or API calls)
+        nfo_path = movie_path / "movie.nfo"
+        nfo_data = self.nfo_manager.extract_nfoguard_dates_from_nfo(nfo_path)
+        if nfo_data:
+            _log("INFO", f"🚀 Using existing NFOGuard data from NFO file: {nfo_data['dateadded']} (source: {nfo_data['source']})")
+            dateadded = nfo_data["dateadded"]
+            source = nfo_data["source"] 
+            released = nfo_data.get("released")
+            
+            # Update file mtimes if enabled (NFO is already correct)
+            if config.fix_dir_mtimes and dateadded:
+                self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
+            
+            _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source}) [nfo-only]")
+            return
+            
+        # TIER 1.5: Special handling for TMDB-only movies - extract dates from existing NFO
+        if is_tmdb_fallback:
+            tmdb_nfo_data = self._extract_dates_from_tmdb_nfo(nfo_path)
+            if tmdb_nfo_data:
+                _log("INFO", f"🎬 Using TMDB data from existing NFO file: {tmdb_nfo_data['dateadded']} (source: {tmdb_nfo_data['source']})")
+                dateadded = tmdb_nfo_data["dateadded"]
+                source = tmdb_nfo_data["source"]
+                released = tmdb_nfo_data.get("released")
+                
+                # Create NFO with NFOGuard fields added
+                if config.manage_nfo:
+                    self.nfo_manager.create_movie_nfo(
+                        movie_path, imdb_id, dateadded, released, source, config.lock_metadata
+                    )
+                
+                # Update file mtimes if enabled
+                if config.fix_dir_mtimes and dateadded:
+                    self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
+                
+                # Save to database
+                self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
+                
+                _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source}) [tmdb-nfo]")
+                return
+            
+        # TIER 2: Check database for existing data
+        existing = self.db.get_movie_dates(imdb_id)
+        _log("DEBUG", f"Database lookup for {imdb_id}: {existing}")
+        
+        # If we have complete data in database, use it and skip expensive API calls
+        if existing and existing.get("dateadded") and existing.get("source") != "no_valid_date_source":
+            _log("INFO", f"✅ Using complete database data for {imdb_id}: {existing['dateadded']} (source: {existing['source']})")
+            # Still create NFO and update files but skip API queries
+            dateadded, source, released = existing["dateadded"], existing["source"], existing.get("released")
+            
+            # Create NFO with existing data
+            if config.manage_nfo:
+                self.nfo_manager.create_movie_nfo(
+                    movie_path, imdb_id, dateadded, released, source, config.lock_metadata
+                )
+            
+            # Update file mtimes if enabled
+            if config.fix_dir_mtimes and dateadded:
+                self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
+            
+            _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source}) [database-only]")
+            return
+        
+        # Handle webhook mode - prioritize database, then use proper date logic
+        if webhook_mode:
+            _log("DEBUG", f"Webhook mode: existing={bool(existing)}, has_dateadded={bool(existing and existing.get('dateadded')) if existing else 'N/A'}")
+            if existing and existing.get("dateadded"):
+                _log("INFO", f"Webhook processing - using existing database entry: {existing['dateadded']} (source: {existing.get('source', 'unknown')})")
+                dateadded, source, released = existing["dateadded"], existing["source"], existing.get("released")
+            else:
+                if existing:
+                    _log("INFO", f"Webhook processing - database entry exists but no dateadded field: {existing}")
+                else:
+                    _log("INFO", f"Webhook processing - no database entry found for {imdb_id}")
+                _log("INFO", f"Using full date decision logic")
+                # Use same logic as manual scan to check Radarr import dates, release dates, etc.
+                should_query = True  # Always query for webhooks when no database entry exists
+                dateadded, source, released = self._decide_movie_dates(imdb_id, movie_path, should_query, existing)
+                
+                # Only if ALL date sources fail, fall back to current timestamp
+                if dateadded is None:
+                    local_tz = _get_local_timezone()
+                    current_time = datetime.now(local_tz).isoformat(timespec="seconds")
+                    _log("INFO", f"Webhook processing - all date sources failed, using current timestamp as last resort: {current_time}")
+                    dateadded, source = current_time, "webhook:fallback_timestamp"
+        else:
+            # Manual scan mode - determine if we should query APIs
+            should_query = (
+                config.movie_poll_mode == "always" or
+                (config.movie_poll_mode == "if_missing" and not existing) or
+                (config.movie_poll_mode == "if_missing" and existing and existing.get("source") == "file:mtime") or
+                (config.movie_poll_mode == "if_missing" and existing and not existing.get("dateadded"))
+            )
+            
+            _log("DEBUG", f"Movie {imdb_id}: should_query={should_query}, poll_mode={config.movie_poll_mode}, existing={bool(existing)}, has_dateadded={bool(existing and existing.get('dateadded')) if existing else False}")
+            
+            # Use existing movie date decision logic
+            dateadded, source, released = self._decide_movie_dates(imdb_id, movie_path, should_query, existing)
+        
+        # If we don't have an import/download date but we have a release date, use it as dateadded
+        # This ensures we save digital release dates, theatrical dates, etc. to the database
+        final_dateadded = dateadded
+        final_source = source
+        
+        if dateadded is None and released is not None:
+            final_dateadded = released
+            final_source = f"{source}_as_dateadded" if source else "release_date_fallback"
+            _log("INFO", f"Using release date as dateadded: {final_dateadded} (source: {final_source})")
+        
+        # Create NFO regardless of date availability (preserves existing metadata)
+        if config.manage_nfo:
+            self.nfo_manager.create_movie_nfo(
+                movie_path, imdb_id, final_dateadded, released, final_source, config.lock_metadata
+            )
+        
+        # Skip remaining processing if no valid date found and file dates disabled
+        if final_dateadded is None:
+            _log("WARNING", f"Movie {movie_path.name} - no valid date source available, but NFO was still processed")
+            self.db.upsert_movie_dates(imdb_id, released, None, source, True)
+            return
+            
+        # Update dateadded and source for the rest of processing
+        dateadded = final_dateadded
+        source = final_source
+        
+        _log("DEBUG", f"Movie {movie_path.name} proceeding to save: dateadded={dateadded}, source={source}")
+        
+        # Update file mtimes (only if we have a valid date)
+        if config.fix_dir_mtimes and dateadded and dateadded != "MANUAL_REVIEW_NEEDED":
+            self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
+        
+        _log("DEBUG", f"Movie processing reached file mtime section: fix_dir_mtimes={config.fix_dir_mtimes}, dateadded={dateadded}")
+        
+        # Save to database
+        _log("DEBUG", f"About to save to database: imdb_id={imdb_id}, dateadded={dateadded}")
+        try:
+            self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
+            _log("DEBUG", f"Database save completed for {imdb_id}")
+        except Exception as e:
+            _log("ERROR", f"Database save failed for {imdb_id}: {e}")
+            raise
+        
+        _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source})")
+    
+    def _extract_dates_from_tmdb_nfo(self, nfo_path: Path) -> Optional[Dict[str, str]]:
+        """Extract date information from TMDB-based NFO file"""
+        if not nfo_path.exists():
+            return None
+            
+        try:
+            root = self.nfo_manager._parse_nfo_with_tolerance(nfo_path)
+            
+            # Look for premiered date (from TMDB)
+            premiered_elem = root.find('.//premiered')
+            if premiered_elem is not None and premiered_elem.text:
+                premiered_date = premiered_elem.text.strip()
+                print(f"✅ Found TMDB premiered date: {premiered_date}")
+                
+                return {
+                    "dateadded": premiered_date,
+                    "source": "tmdb:premiered_from_nfo",
+                    "released": premiered_date
+                }
+                
+        except (ET.ParseError, Exception) as e:
+            print(f"⚠️ Error parsing TMDB NFO for dates: {e}")
+            
+        return None
+    
+    def _decide_movie_dates(self, imdb_id: str, movie_path: Path, should_query: bool, existing: Optional[Dict]) -> Tuple[str, str, Optional[str]]:
+        """Decide movie dates based on configuration and available data"""
+        _log("DEBUG", f"_decide_movie_dates for {imdb_id}: should_query={should_query}, existing={existing}")
+        
+        if not should_query and existing:
+            _log("DEBUG", f"Using existing data without querying: dateadded={existing.get('dateadded')}, source={existing.get('source')}")
+            return existing["dateadded"], existing["source"], existing.get("released")
+        
+        # Query Radarr for movie info
+        radarr_movie = None
+        if should_query and self.radarr.api_key:
+            radarr_movie = self.radarr.movie_by_imdb(imdb_id)
+        
+        released = None
+        if radarr_movie:
+            released = self._parse_date_to_iso(radarr_movie.get("inCinemas"))
+        
+        # Try import history first if configured
+        if config.movie_priority == "import_then_digital":
+            import_date, import_source = None, None
+            if radarr_movie:
+                movie_id = radarr_movie.get("id")
+                if movie_id:
+                    import_date, import_source = self.radarr.get_movie_import_date(movie_id, fallback_to_file_date=config.allow_file_date_fallback)
+                    _log("INFO", f"Movie {imdb_id}: Radarr import result: date={import_date}, source={import_source}")
+            
+            # Check for special case: rename-first scenario (should prefer release dates)
+            if import_source == "radarr:db.prefer_release_dates":
+                _log("INFO", f"🎯 Movie {imdb_id} has rename-first history - skipping import, preferring release dates")
+                # Fall through to release date logic below
+            # Check if we got a real import date or just file date fallback
+            elif import_date and import_source != "radarr:db.file.dateAdded":
+                # Convert import date to local timezone for NFO files
+                local_import_date = convert_utc_to_local(import_date)
+                _log("INFO", f"✅ Movie {imdb_id}: Using import date {local_import_date} from {import_source}")
+                return local_import_date, import_source, released
+            
+            # Get digital release date for comparison/fallback
+            _log("INFO", f"🔍 Movie {imdb_id}: Trying digital release date fallback...")
+            digital_date, digital_source = self._get_digital_release_date(imdb_id)
+            _log("INFO", f"Movie {imdb_id}: Digital release result: date={digital_date}, source={digital_source}")
+            
+            # If we only have file date and release date exists, prefer it if reasonable and enabled
+            if import_date and import_source == "radarr:db.file.dateAdded" and digital_date and config.prefer_release_dates_over_file_dates:
+                # Compare dates - prefer release date if it's reasonable
+                if self._should_prefer_release_over_file_date(digital_date, digital_source, released, imdb_id):
+                    _log("INFO", f"✅ Movie {imdb_id}: Preferring digital release date {digital_date} over file date")
+                    return digital_date, digital_source, released
+                else:
+                    # Convert file date to local timezone for NFO files
+                    local_file_date = convert_utc_to_local(import_date)
+                    _log("INFO", f"✅ Movie {imdb_id}: Keeping file date {local_file_date} - digital date not reasonable")
+                    return local_file_date, import_source, released
+            
+            # Use whichever we have
+            if import_date:
+                # Convert import date to local timezone for NFO files
+                local_import_date = convert_utc_to_local(import_date)
+                _log("INFO", f"✅ Movie {imdb_id}: Using import date {local_import_date} from {import_source}")
+                return local_import_date, import_source, released
+            elif digital_date:
+                _log("INFO", f"✅ Movie {imdb_id}: Using digital release date {digital_date} from {digital_source}")
+                return digital_date, digital_source, released
+            else:
+                _log("WARNING", f"⚠️ Movie {imdb_id}: No import date OR digital release date found - trying additional fallbacks")
+                
+                # Try Radarr's own NFO premiered date as fallback
+                radarr_premiered = self._get_radarr_nfo_premiered_date(movie_path)
+                if radarr_premiered:
+                    _log("INFO", f"✅ Movie {imdb_id}: Using Radarr NFO premiered date {radarr_premiered}")
+                    return radarr_premiered, "radarr:nfo.premiered", released
+        
+        else:  # digital_then_import
+            # Try digital release first
+            digital_date, digital_source = self._get_digital_release_date(imdb_id)
+            if digital_date:
+                return digital_date, digital_source, released
+            
+            # Fall back to import history
+            if radarr_movie:
+                movie_id = radarr_movie.get("id")
+                if movie_id:
+                    import_date, import_source = self.radarr.get_movie_import_date(movie_id, fallback_to_file_date=config.allow_file_date_fallback)
+                    if import_date:
+                        # Convert import date to local timezone for NFO files
+                        local_import_date = convert_utc_to_local(import_date)
+                        return local_import_date, import_source, released
+        
+        # Last resort: file mtime (if allowed)
+        if config.allow_file_date_fallback:
+            return self._get_file_mtime_date(movie_path)
+        else:
+            _log("INFO", f"No valid dates found for {imdb_id} and file date fallback disabled - skipping NFO creation")
+            
+            # Log to failed movies debug file for troubleshooting
+            self._log_failed_movie(movie_path, imdb_id, "No import date, no release date, file date fallback disabled")
+            
+            return None, "no_valid_date_source", None
+    
+    def _get_digital_release_date(self, imdb_id: str) -> Tuple[Optional[str], str]:
+        """Get release date from external sources using configured priority"""
+        _log("INFO", f"🔍 Calling external clients for {imdb_id}")
+        _log("INFO", f"Release date priority: {config.release_date_priority}")
+        _log("INFO", f"Smart validation enabled: {config.enable_smart_date_validation}")
+        
+        try:
+            release_result = self.external_clients.get_release_date_by_priority(
+                imdb_id, 
+                config.release_date_priority,
+                enable_smart_validation=config.enable_smart_date_validation
+            )
+            _log("INFO", f"External clients result for {imdb_id}: {release_result}")
+            
+            if release_result:
+                _log("INFO", f"✅ Got release date: {release_result[0]} from {release_result[1]}")
+                return release_result[0], release_result[1]
+            else:
+                _log("WARNING", f"❌ No release date found from external clients for {imdb_id}")
+                return None, "release:none"
+        except Exception as e:
+            _log("ERROR", f"External clients error for {imdb_id}: {e}")
+            return None, f"release:error:{str(e)}"
+    
+    def _get_radarr_nfo_premiered_date(self, movie_path: Path) -> Optional[str]:
+        """Extract premiered date from Radarr's existing movie.nfo file"""
+        try:
+            nfo_path = movie_path / "movie.nfo"
+            if not nfo_path.exists():
+                _log("DEBUG", f"No existing NFO file found at {nfo_path}")
+                return None
+                
+            nfo_content = nfo_path.read_text(encoding='utf-8')
+            
+            # Look for <premiered>YYYY-MM-DD</premiered>
+            match = re.search(r'<premiered>(\d{4}-\d{2}-\d{2})</premiered>', nfo_content)
+            if match:
+                premiered_date = match.group(1)
+                # Convert to ISO format with timezone
+                iso_date = f"{premiered_date}T00:00:00+00:00"
+                _log("INFO", f"✅ Found Radarr NFO premiered date: {premiered_date}")
+                return iso_date
+            else:
+                _log("DEBUG", f"No <premiered> tag found in existing NFO")
+                return None
+                
+        except Exception as e:
+            _log("ERROR", f"Error reading Radarr NFO file: {e}")
+            return None
+    
+    def _log_failed_movie(self, movie_path: Path, imdb_id: str, reason: str, available_countries: List[str] = None):
+        """Log movies that failed to get valid dates to a debug file"""
+        try:
+            log_dir = Path("logs")
+            log_dir.mkdir(exist_ok=True)
+            
+            failed_log_path = log_dir / "failed_movies.log"
+            timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+            
+            log_entry = f"[{timestamp}] {movie_path.name} | IMDb: {imdb_id} | Reason: {reason}"
+            if available_countries:
+                log_entry += f" | Available Countries: {', '.join(available_countries)}"
+            log_entry += "\n"
+            
+            with open(failed_log_path, "a", encoding="utf-8") as f:
+                f.write(log_entry)
+            
+            _log("INFO", f"📝 Logged failed movie to {failed_log_path}: {movie_path.name}")
+            
+        except Exception as e:
+            _log("ERROR", f"Failed to write to failed movies log: {e}")
+    
+    def _get_file_mtime_date(self, movie_path: Path) -> Tuple[str, str, Optional[str]]:
+        """Get date from file modification time as last resort"""
+        video_exts = (".mkv", ".mp4", ".avi", ".mov", ".m4v")
+        newest_mtime = None
+        
+        for file_path in movie_path.iterdir():
+            if file_path.is_file() and file_path.suffix.lower() in video_exts:
+                try:
+                    mtime = file_path.stat().st_mtime
+                    if newest_mtime is None or mtime > newest_mtime:
+                        newest_mtime = mtime
+                except Exception:
+                    continue
+        
+        if newest_mtime:
+            try:
+                # Use local timezone for file modification times
+                local_tz = _get_local_timezone()
+                iso_date = datetime.fromtimestamp(newest_mtime, tz=local_tz).isoformat(timespec="seconds")
+                return iso_date, "file:mtime", None
+            except Exception:
+                pass
+        
+        return "MANUAL_REVIEW_NEEDED", "manual_review_required", None
+    
+    def _should_prefer_release_over_file_date(self, release_date: str, release_source: str, theatrical_release: Optional[str], imdb_id: str) -> bool:
+        """
+        Decide if release date should be preferred over file date
+        
+        Logic:
+        - For theatrical dates: Always prefer over file dates (they're authoritative)
+        - For physical dates: Usually prefer over file dates  
+        - For digital dates: Prefer if reasonable (not decades before theatrical)
+        """
+        try:
+            release_dt = datetime.fromisoformat(release_date.replace("Z", "+00:00"))
+            
+            # Always prefer theatrical and physical releases over file dates
+            if any(release_type in release_source for release_type in ["theatrical", "physical"]):
+                _log("INFO", f"Release date {release_date} ({release_source}) for {imdb_id}, preferring over file date")
+                return True
+            
+            # If we have theatrical release date, compare digital against it
+            if theatrical_release:
+                theatrical_dt = datetime.fromisoformat(theatrical_release.replace("Z", "+00:00"))
+                year_diff = release_dt.year - theatrical_dt.year
+                
+                # If digital is more than 10 years before theatrical, it's probably wrong
+                if year_diff < -10:
+                    _log("INFO", f"Release date {release_date} is {abs(year_diff)} years before theatrical {theatrical_release} for {imdb_id}, using file date instead")
+                    return False
+                    
+                # If digital is within reasonable range (theatrical to +20 years), use it
+                if -2 <= year_diff <= 20:
+                    _log("INFO", f"Release date {release_date} is reasonable for {imdb_id} (theatrical: {theatrical_release}), preferring over file date")
+                    return True
+            
+            # If no theatrical date, use digital if it's not absurdly old
+            if release_dt.year >= 1990:  # Reasonable minimum for digital releases
+                _log("INFO", f"Release date {release_date} seems reasonable for {imdb_id}, preferring over file date")
+                return True
+                
+            _log("INFO", f"Release date {release_date} seems too old for {imdb_id}, using file date instead")
+            return False
+            
+        except Exception as e:
+            _log("WARNING", f"Error comparing dates for {imdb_id}: {e}")
+            return False
+    
+    def _parse_date_to_iso(self, date_str: str) -> Optional[str]:
+        """Parse date string to ISO format"""
+        if not date_str:
+            return None
+        try:
+            if len(date_str) == 10 and date_str[4] == "-":
+                dt = datetime.fromisoformat(date_str).replace(tzinfo=timezone.utc)
+            else:
+                dt = datetime.fromisoformat(date_str.replace("Z", "+00:00")).astimezone(timezone.utc)
+            return dt.isoformat(timespec="seconds")
+        except Exception:
+            return None

processors/tv_processor.py

@@ -0,0 +1,365 @@
+"""
+TV Series Processor for NFOGuard
+Handles TV series processing and episode management
+"""
+import os
+import glob
+import re
+from pathlib import Path
+from typing import Optional, Dict, List, Set, Tuple, Any
+from datetime import datetime
+
+from core.database import NFOGuardDatabase
+from core.nfo_manager import NFOManager
+from core.path_mapper import PathMapper
+from clients.sonarr_client import SonarrClient
+from clients.external_clients import ExternalClientManager
+from config.settings import config
+from utils.logging import _log
+
+
+class TVProcessor:
+    """Handles TV series processing"""
+    
+    def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager, path_mapper: PathMapper):
+        self.db = db
+        self.nfo_manager = nfo_manager
+        self.path_mapper = path_mapper
+        self.sonarr = SonarrClient(
+            os.environ.get("SONARR_URL", ""),
+            os.environ.get("SONARR_API_KEY", "")
+        )
+        self.external_clients = ExternalClientManager()
+    
+    def find_series_path(self, series_title: str, imdb_id: str, sonarr_path: str = None) -> Optional[Path]:
+        """Find series directory path"""
+        # Try webhook path first
+        if sonarr_path:
+            container_path = self.path_mapper.sonarr_path_to_container_path(sonarr_path)
+            path_obj = Path(container_path)
+            if path_obj.exists():
+                return path_obj
+        
+        # Search by IMDb ID or title
+        for media_path in config.tv_paths:
+            if not media_path.exists():
+                continue
+            
+            # Search by IMDb ID
+            if imdb_id:
+                pattern = str(media_path / f"*[imdb-{imdb_id}]*")
+                matches = glob.glob(pattern)
+                if matches:
+                    return Path(matches[0])
+            
+            # Search by title
+            if series_title:
+                title_clean = series_title.lower().replace(" ", "").replace("-", "")
+                for item in media_path.iterdir():
+                    if item.is_dir() and "[imdb-" in item.name.lower():
+                        item_clean = item.name.lower().replace(" ", "").replace("-", "")
+                        if title_clean in item_clean:
+                            return item
+        
+        return None
+    
+    def process_series(self, series_path: Path) -> None:
+        """Process a TV series directory"""
+        imdb_id = self.nfo_manager.parse_imdb_from_path(series_path)
+        if not imdb_id:
+            _log("ERROR", f"No IMDb ID found in series path: {series_path}")
+            return
+        
+        _log("INFO", f"Processing TV series: {series_path.name}")
+        
+        # Update database
+        self.db.upsert_series(imdb_id, str(series_path))
+        
+        # Find video files
+        disk_episodes = self._find_disk_episodes(series_path)
+        _log("INFO", f"Found {len(disk_episodes)} episodes on disk")
+        
+        # Get episode dates
+        episode_dates = self._gather_episode_dates(series_path, imdb_id, disk_episodes)
+        
+        # Process episodes
+        for (season, episode), (aired, dateadded, source) in episode_dates.items():
+            if (season, episode) in disk_episodes:
+                # Create NFO
+                if config.manage_nfo:
+                    season_dir = series_path / config.tv_season_dir_format.format(season=season)
+                    self.nfo_manager.create_episode_nfo(
+                        season_dir,
+                        season, episode, aired, dateadded, source, config.lock_metadata
+                    )
+                
+                # Update file mtimes
+                if config.fix_dir_mtimes and dateadded:
+                    video_files = disk_episodes[(season, episode)]
+                    for video_file in video_files:
+                        self.nfo_manager.set_file_mtime(video_file, dateadded)
+                
+                # Save to database
+                self.db.upsert_episode_date(imdb_id, season, episode, aired, dateadded, source, True)
+        
+        # Skip season.nfo and tvshow.nfo creation - focus only on episode NFOs
+        pass
+        
+        _log("INFO", f"Completed processing TV series: {series_path.name}")
+    
+    def _extract_series_title_from_path(self, series_path: Path) -> Optional[str]:
+        """Extract series title from directory path, removing year and IMDb ID"""
+        name = series_path.name
+        
+        # Remove IMDb ID part: [imdb-ttXXXXXX] or [ttXXXXXX]
+        name = re.sub(r'\s*\[imdb-?tt\d+\]', '', name, flags=re.IGNORECASE)
+        name = re.sub(r'\s*\[tt\d+\]', '', name, flags=re.IGNORECASE)
+        
+        # Remove year in parentheses: (YYYY)
+        name = re.sub(r'\s*\(\d{4}\)', '', name)
+        
+        # Clean up extra spaces
+        name = ' '.join(name.split())
+        
+        return name.strip() if name.strip() else None
+    
+    def _find_disk_episodes(self, series_path: Path) -> Dict[Tuple[int, int], List[Path]]:
+        """Find all episodes on disk and return mapping of (season, episode) -> [video_files]"""
+        episodes = {}
+        
+        if not series_path.exists():
+            return episodes
+        
+        video_extensions = {'.mkv', '.mp4', '.avi', '.m4v', '.mov', '.ts'}
+        
+        # Define regex pattern for episode files
+        episode_pattern = re.compile(
+            r'.*[sS](\d{1,2})[eE](\d{1,3}).*|.*(\d{1,2})x(\d{1,3}).*'
+        )
+        
+        for item in series_path.rglob('*'):
+            if item.is_file() and item.suffix.lower() in video_extensions:
+                # Try to extract season/episode from filename
+                match = episode_pattern.match(item.name)
+                if match:
+                    if match.group(1) and match.group(2):  # SxxExx format
+                        season = int(match.group(1))
+                        episode = int(match.group(2))
+                    elif match.group(3) and match.group(4):  # NxNN format
+                        season = int(match.group(3))
+                        episode = int(match.group(4))
+                    else:
+                        continue
+                    
+                    key = (season, episode)
+                    if key not in episodes:
+                        episodes[key] = []
+                    episodes[key].append(item)
+        
+        return episodes
+    
+    def _gather_episode_dates(self, series_path: Path, imdb_id: str, disk_episodes: Dict[Tuple[int, int], List[Path]]) -> Dict[Tuple[int, int], Tuple[Optional[str], Optional[str], str]]:
+        """Gather episode air dates and date added information"""
+        episode_dates = {}
+        
+        # Get data from Sonarr first if available
+        sonarr_episodes = self._get_sonarr_episodes(imdb_id)
+        
+        # Get data from external sources for missing information
+        for (season, episode) in disk_episodes:
+            aired = None
+            dateadded = None
+            source = "unknown"
+            
+            # Try Sonarr first
+            if (season, episode) in sonarr_episodes:
+                sonarr_data = sonarr_episodes[(season, episode)]
+                aired = sonarr_data.get('airDate')
+                dateadded = sonarr_data.get('dateAdded')
+                if dateadded:
+                    source = "sonarr"
+            
+            # Fallback to external sources if needed
+            if not aired:
+                external_aired = self.external_clients.get_episode_air_date(imdb_id, season, episode)
+                if external_aired:
+                    aired = external_aired
+                    if not dateadded:
+                        source = "external"
+            
+            # Use air date as fallback for dateadded if available
+            if not dateadded and aired:
+                dateadded = aired
+                source = f"{source}_fallback" if source != "unknown" else "aired_fallback"
+            
+            episode_dates[(season, episode)] = (aired, dateadded, source)
+        
+        return episode_dates
+    
+    def _get_sonarr_episodes(self, imdb_id: str) -> Dict[Tuple[int, int], Dict[str, Any]]:
+        """Get episode information from Sonarr"""
+        try:
+            series_data = self.sonarr.get_series_by_imdb(imdb_id)
+            if not series_data:
+                return {}
+            
+            series_id = series_data.get('id')
+            if not series_id:
+                return {}
+            
+            episodes = self.sonarr.get_episodes(series_id)
+            
+            episode_map = {}
+            for episode in episodes:
+                season = episode.get('seasonNumber', 0)
+                episode_num = episode.get('episodeNumber', 0)
+                
+                if season > 0 and episode_num > 0:
+                    episode_map[(season, episode_num)] = {
+                        'airDate': episode.get('airDate'),
+                        'dateAdded': episode.get('episodeFile', {}).get('dateAdded') if episode.get('hasFile') else None
+                    }
+            
+            return episode_map
+            
+        except Exception as e:
+            _log("ERROR", f"Failed to get Sonarr episodes for {imdb_id}: {e}")
+            return {}
+    
+    def process_season(self, series_path: str, season_name: str) -> Dict[str, Any]:
+        """Process a specific season"""
+        series_path_obj = Path(series_path)
+        if not series_path_obj.exists():
+            raise FileNotFoundError(f"Series path not found: {series_path}")
+        
+        season_path = series_path_obj / season_name
+        if not season_path.exists():
+            raise FileNotFoundError(f"Season directory not found: {season_path}")
+        
+        # Extract season number from directory name
+        season_match = re.search(r'(\d+)', season_name)
+        if not season_match:
+            raise ValueError(f"Could not extract season number from: {season_name}")
+        
+        season_num = int(season_match.group(1))
+        
+        # Get series IMDb ID
+        imdb_id = self.nfo_manager.parse_imdb_from_path(series_path_obj)
+        if not imdb_id:
+            raise ValueError(f"No IMDb ID found in series path: {series_path}")
+        
+        _log("INFO", f"Processing season {season_num} of series: {series_path_obj.name}")
+        
+        # Find episodes in this season
+        disk_episodes = self._find_disk_episodes(series_path_obj)
+        season_episodes = {k: v for k, v in disk_episodes.items() if k[0] == season_num}
+        
+        if not season_episodes:
+            return {"status": "no_episodes", "season": season_num, "episodes_found": 0}
+        
+        # Get episode dates
+        episode_dates = self._gather_episode_dates(series_path_obj, imdb_id, season_episodes)
+        
+        # Process episodes
+        processed_count = 0
+        for (season, episode), (aired, dateadded, source) in episode_dates.items():
+            if (season, episode) in season_episodes:
+                # Create NFO
+                if config.manage_nfo:
+                    self.nfo_manager.create_episode_nfo(
+                        season_path,
+                        season, episode, aired, dateadded, source, config.lock_metadata
+                    )
+                
+                # Update file mtimes
+                if config.fix_dir_mtimes and dateadded:
+                    video_files = season_episodes[(season, episode)]
+                    for video_file in video_files:
+                        self.nfo_manager.set_file_mtime(video_file, dateadded)
+                
+                # Save to database
+                self.db.upsert_episode_date(imdb_id, season, episode, aired, dateadded, source, True)
+                processed_count += 1
+        
+        _log("INFO", f"Processed {processed_count} episodes in season {season_num}")
+        
+        return {
+            "status": "success",
+            "season": season_num,
+            "episodes_found": len(season_episodes),
+            "episodes_processed": processed_count
+        }
+    
+    def process_episode(self, series_path: str, season_name: str, episode_name: str) -> Dict[str, Any]:
+        """Process a specific episode"""
+        series_path_obj = Path(series_path)
+        if not series_path_obj.exists():
+            raise FileNotFoundError(f"Series path not found: {series_path}")
+        
+        season_path = series_path_obj / season_name
+        if not season_path.exists():
+            raise FileNotFoundError(f"Season directory not found: {season_path}")
+        
+        episode_path = season_path / episode_name
+        if not episode_path.exists():
+            raise FileNotFoundError(f"Episode file not found: {episode_path}")
+        
+        # Extract season and episode numbers
+        season_match = re.search(r'(\d+)', season_name)
+        episode_match = re.search(r'[sS](\d+)[eE](\d+)|(\d+)x(\d+)', episode_name)
+        
+        if not season_match:
+            raise ValueError(f"Could not extract season number from: {season_name}")
+        
+        if not episode_match:
+            raise ValueError(f"Could not extract episode number from: {episode_name}")
+        
+        season_num = int(season_match.group(1))
+        
+        if episode_match.group(1) and episode_match.group(2):  # SxxExx format
+            episode_num = int(episode_match.group(2))
+        elif episode_match.group(3) and episode_match.group(4):  # NxNN format
+            episode_num = int(episode_match.group(4))
+        else:
+            raise ValueError(f"Could not parse episode number from: {episode_name}")
+        
+        # Get series IMDb ID
+        imdb_id = self.nfo_manager.parse_imdb_from_path(series_path_obj)
+        if not imdb_id:
+            raise ValueError(f"No IMDb ID found in series path: {series_path}")
+        
+        _log("INFO", f"Processing episode S{season_num:02d}E{episode_num:02d} of series: {series_path_obj.name}")
+        
+        # Get episode data
+        disk_episodes = {(season_num, episode_num): [episode_path]}
+        episode_dates = self._gather_episode_dates(series_path_obj, imdb_id, disk_episodes)
+        
+        if (season_num, episode_num) not in episode_dates:
+            return {"status": "no_data", "season": season_num, "episode": episode_num}
+        
+        aired, dateadded, source = episode_dates[(season_num, episode_num)]
+        
+        # Create NFO
+        if config.manage_nfo:
+            self.nfo_manager.create_episode_nfo(
+                season_path,
+                season_num, episode_num, aired, dateadded, source, config.lock_metadata
+            )
+        
+        # Update file mtime
+        if config.fix_dir_mtimes and dateadded:
+            self.nfo_manager.set_file_mtime(episode_path, dateadded)
+        
+        # Save to database
+        self.db.upsert_episode_date(imdb_id, season_num, episode_num, aired, dateadded, source, True)
+        
+        _log("INFO", f"Processed episode S{season_num:02d}E{episode_num:02d}")
+        
+        return {
+            "status": "success",
+            "season": season_num,
+            "episode": episode_num,
+            "aired": aired,
+            "dateadded": dateadded,
+            "source": source
+        }

utils/logging.py

@@ -0,0 +1,170 @@
+"""
+Logging utilities for NFOGuard
+"""
+import os
+import re
+import logging
+import logging.handlers
+from pathlib import Path
+from datetime import datetime, timezone
+from zoneinfo import ZoneInfo
+
+
+class TimezoneAwareFormatter(logging.Formatter):
+    """Formatter that respects the container timezone"""
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.timezone = self._get_local_timezone()
+    
+    def _get_local_timezone(self):
+        """Get the local timezone, respecting TZ environment variable"""
+        tz_name = os.environ.get('TZ', 'UTC')
+        
+        try:
+            # Try zoneinfo first (Python 3.9+)
+            return ZoneInfo(tz_name)
+        except ImportError:
+            # Fallback for older Python versions
+            try:
+                import pytz
+                return pytz.timezone(tz_name)
+            except:
+                # Final fallback to UTC
+                return timezone.utc
+        except:
+            # If zone name is invalid, fallback to UTC
+            return timezone.utc
+    
+    def formatTime(self, record, datefmt=None):
+        dt = datetime.fromtimestamp(record.created, tz=self.timezone)
+        if datefmt:
+            return dt.strftime(datefmt)
+        return dt.isoformat(timespec='seconds')
+
+
+def _setup_file_logging():
+    """Setup file logging for NFOGuard"""
+    log_dir = Path(os.environ.get("LOG_DIR", "/app/data/logs"))
+    log_dir.mkdir(parents=True, exist_ok=True)
+    
+    logger = logging.getLogger("NFOGuard")
+    logger.setLevel(logging.DEBUG)
+    
+    file_handler = logging.handlers.RotatingFileHandler(
+        log_dir / "nfoguard.log", maxBytes=50*1024*1024, backupCount=3
+    )
+    
+    formatter = TimezoneAwareFormatter(
+        '[%(asctime)s] %(levelname)s: %(message)s'
+    )
+    file_handler.setFormatter(formatter)
+    logger.addHandler(file_handler)
+    return logger
+
+
+def _mask_sensitive_data(msg: str) -> str:
+    """Mask API keys and other sensitive data in log messages"""
+    # List of patterns to mask
+    sensitive_patterns = [
+        (r'api_key=([a-zA-Z0-9_\-]+)', r'api_key=***masked***'),
+        (r'password=([^\s&]+)', r'password=***masked***'),
+        (r'token=([a-zA-Z0-9_\-]+)', r'token=***masked***'),
+        (r'key=([a-zA-Z0-9_\-]{8,})', r'key=***masked***'),  # Keys longer than 8 chars
+        (r'([a-zA-Z0-9]{32,})', lambda m: m.group(1)[:8] + '***masked***' if len(m.group(1)) > 16 else m.group(1))  # Long strings likely to be keys
+    ]
+    
+    masked_msg = msg
+    for pattern, replacement in sensitive_patterns:
+        if isinstance(replacement, str):
+            masked_msg = re.sub(pattern, replacement, masked_msg, flags=re.IGNORECASE)
+        else:
+            masked_msg = re.sub(pattern, replacement, masked_msg, flags=re.IGNORECASE)
+    
+    return masked_msg
+
+
+def _get_local_timezone():
+    """Get the local timezone, respecting TZ environment variable"""
+    tz_name = os.environ.get('TZ', 'UTC')
+    
+    try:
+        # Try zoneinfo first (Python 3.9+)
+        return ZoneInfo(tz_name)
+    except ImportError:
+        # Fallback for older Python versions
+        try:
+            import pytz
+            return pytz.timezone(tz_name)
+        except:
+            # Final fallback to UTC
+            return timezone.utc
+    except:
+        # If zone name is invalid, fallback to UTC
+        return timezone.utc
+
+
+def _log(level: str, msg: str):
+    """Enhanced logging that writes to both console and file with sensitive data masking"""
+    masked_msg = _mask_sensitive_data(msg)
+    tz = _get_local_timezone()
+    print(f"[{datetime.now(tz).isoformat(timespec='seconds')}] {level}: {masked_msg}")
+    
+    try:
+        file_logger = _setup_file_logging()
+        getattr(file_logger, level.lower(), file_logger.info)(masked_msg)
+    except Exception as e:
+        print(f"File logging error: {e}")
+
+
+def convert_utc_to_local(utc_iso_string: str) -> str:
+    """Convert UTC ISO timestamp to local timezone timestamp"""
+    if not utc_iso_string:
+        return utc_iso_string
+    
+    try:
+        # Parse UTC timestamp
+        if utc_iso_string.endswith('Z'):
+            dt_utc = datetime.fromisoformat(utc_iso_string.replace('Z', '+00:00'))
+        elif '+00:00' in utc_iso_string:
+            dt_utc = datetime.fromisoformat(utc_iso_string)
+        else:
+            # Assume UTC if no timezone info
+            dt_utc = datetime.fromisoformat(utc_iso_string).replace(tzinfo=timezone.utc)
+        
+        # Convert to local timezone
+        local_tz = _get_local_timezone()
+        dt_local = dt_utc.astimezone(local_tz)
+        
+        return dt_local.isoformat(timespec='seconds')
+    except Exception:
+        # If conversion fails, return original
+        return utc_iso_string
+
+
+def _load_environment_files():
+    """Load environment variables from .env and optionally .env.secrets"""
+    from pathlib import Path
+    
+    # Try to load from python-dotenv if available
+    try:
+        from dotenv import load_dotenv
+        
+        # Load main .env file
+        env_file = Path(".env")
+        if env_file.exists():
+            load_dotenv(env_file)
+            _log("INFO", f"Loaded environment from {env_file}")
+        
+        # Load secrets file if it exists
+        secrets_file = Path(".env.secrets")
+        if secrets_file.exists():
+            load_dotenv(secrets_file)
+            _log("INFO", f"Loaded secrets from {secrets_file}")
+            
+    except ImportError:
+        _log("WARNING", "python-dotenv not available - environment files not loaded")
+
+
+# Initialize logging and load environment files
+_setup_file_logging()
+_load_environment_files()

webhooks/webhook_batcher.py

@@ -0,0 +1,130 @@
+"""
+Webhook Batching System for NFOGuard
+Handles batching and processing of webhook events to avoid processing storms
+"""
+import threading
+from pathlib import Path
+from typing import Dict, Set
+from concurrent.futures import ThreadPoolExecutor
+
+from config.settings import config
+from utils.logging import _log
+
+
+class WebhookBatcher:
+    """Batches webhook events to avoid processing storms"""
+    
+    def __init__(self):
+        self.pending: Dict[str, Dict] = {}
+        self.timers: Dict[str, threading.Timer] = {}
+        self.processing: Set[str] = set()
+        self.lock = threading.Lock()
+        self.executor = ThreadPoolExecutor(max_workers=config.max_concurrent)
+        # Will be set by the application when processors are available
+        self.tv_processor = None
+        self.movie_processor = None
+    
+    def set_processors(self, tv_processor, movie_processor):
+        """Set the processor instances"""
+        self.tv_processor = tv_processor
+        self.movie_processor = movie_processor
+    
+    def add_webhook(self, key: str, webhook_data: Dict, media_type: str):
+        """Add webhook to batch queue"""
+        with self.lock:
+            if key in self.timers:
+                self.timers[key].cancel()
+            
+            webhook_data['media_type'] = media_type
+            self.pending[key] = webhook_data
+            _log("INFO", f"Batched {media_type} webhook for {key}")
+            _log("DEBUG", f"Batch added - key: {key}, media_type: {media_type}, timer scheduled for {config.batch_delay}s")
+            
+            timer = threading.Timer(config.batch_delay, self._process_item, args=[key])
+            self.timers[key] = timer
+            timer.start()
+    
+    def _process_item(self, key: str):
+        """Process a batched item"""
+        with self.lock:
+            if key in self.processing or key not in self.pending:
+                return
+            self.processing.add(key)
+            webhook_data = self.pending.pop(key)
+            self.timers.pop(key, None)
+        
+        try:
+            self.executor.submit(self._process_sync, key, webhook_data)
+        except Exception as e:
+            _log("ERROR", f"Error submitting processing for {key}: {e}")
+            with self.lock:
+                self.processing.discard(key)
+    
+    def _process_sync(self, key: str, webhook_data: Dict):
+        """Synchronous processing of webhook data with validation"""
+        try:
+            media_type = webhook_data.get('media_type')
+            path_str = webhook_data.get('path')
+            
+            _log("DEBUG", f"Processing batch item: key={key}, media_type={media_type}, path={path_str}")
+            
+            if not path_str:
+                _log("ERROR", f"No path found for {media_type} {key}")
+                return
+            
+            path_obj = Path(path_str)
+            if not path_obj.exists():
+                _log("ERROR", f"BATCH PROCESSING FAILED: Path does not exist: {path_obj}")
+                _log("ERROR", f"This indicates a path mapping issue - webhook rejected to prevent wrong processing")
+                return
+            
+            # CRITICAL: Validate that the path contains the expected IMDb ID for movies
+            if media_type == 'movie':
+                expected_imdb = key.replace('movie:', '') if key.startswith('movie:') else key
+                if expected_imdb not in path_str.lower():
+                    _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} not found in path {path_str}")
+                    _log("ERROR", f"This prevents processing wrong movies due to batch corruption")
+                    return
+                _log("DEBUG", f"Batch validation passed: IMDb {expected_imdb} found in path")
+            
+            # Process based on media type
+            if media_type == 'tv':
+                if not self.tv_processor:
+                    _log("ERROR", "TV processor not available")
+                    return
+                    
+                # Check processing mode for TV webhooks
+                processing_mode = webhook_data.get('processing_mode', config.tv_webhook_processing_mode)
+                episodes_data = webhook_data.get('episodes', [])
+                
+                if processing_mode == 'targeted' and episodes_data:
+                    _log("INFO", f"Using targeted episode processing for {len(episodes_data)} episodes")
+                    self.tv_processor.process_webhook_episodes(path_obj, episodes_data)
+                else:
+                    _log("INFO", f"Using series processing mode (fallback or configured)")
+                    self.tv_processor.process_series(path_obj)
+                    
+            elif media_type == 'movie':
+                if not self.movie_processor:
+                    _log("ERROR", "Movie processor not available")
+                    return
+                    
+                self.movie_processor.process_movie(path_obj, webhook_mode=True)
+            else:
+                _log("ERROR", f"Unknown media type: {media_type}")
+        
+        except Exception as e:
+            _log("ERROR", f"Error processing {media_type} {key}: {e}")
+        finally:
+            with self.lock:
+                self.processing.discard(key)
+    
+    def get_status(self) -> Dict:
+        """Get batch queue status"""
+        with self.lock:
+            return {
+                "pending_items": list(self.pending.keys()),
+                "processing_items": list(self.processing),
+                "pending_count": len(self.pending),
+                "processing_count": len(self.processing)
+            }