updates for acfivity dashboard

moving to an all DB approach since radarr overwrites .nfo files

.env.example

@@ -70,6 +70,21 @@ RADARR_DB_PORT=5432
 RADARR_DB_NAME=radarr-main
 RADARR_DB_USER=postgres
 
+# ===========================================
+# SONARR DATABASE CONNECTION (RECOMMENDED)
+# ===========================================
+# Direct database access for better performance
+# Phase 7: High-performance TV episode import date detection
+SONARR_DB_TYPE=postgresql
+SONARR_DB_HOST=192.168.255.50
+SONARR_DB_PORT=5432
+SONARR_DB_NAME=sonarr-main
+SONARR_DB_USER=postgres
+
+# Alternative: SQLite (if Sonarr uses SQLite)
+# SONARR_DB_TYPE=sqlite
+# SONARR_DB_PATH=/path/to/sonarr.db
+
 # ===========================================
 # API CONNECTIONS (OPTIONAL)
 # ===========================================
@@ -97,18 +112,22 @@ ALLOW_FILE_DATE_FALLBACK=false
 TMDB_COUNTRY=US
 
 # ===========================================
-# NFO FILE MANAGEMENT
+# NFO FILE MANAGEMENT (DEPRECATED - Phase 1 Migration)
 # ===========================================
-# Create/update .nfo files
-MANAGE_NFO=true
+# NFO file operations have been removed in favor of database-only architecture
+# These settings are preserved for backward compatibility but no longer have effect
+# The PostgreSQL database is now the single source of truth for all metadata
 
-# Update file modification times to match import dates
-FIX_DIR_MTIMES=true
+# Create/update .nfo files (DEPRECATED - no longer used)
+MANAGE_NFO=false
 
-# Add lockdata tags to prevent metadata overwrites
-LOCK_METADATA=true
+# Update file modification times to match import dates (DEPRECATED - no longer used)
+FIX_DIR_MTIMES=false
 
-# Brand name in NFO comments
+# Add lockdata tags to prevent metadata overwrites (DEPRECATED - no longer used)
+LOCK_METADATA=false
+
+# Brand name in NFO comments (DEPRECATED - no longer used)
 MANAGER_BRAND=NFOGuard
 
 # ===========================================

VERSION

@@ -1 +1 @@
-2.8.0
+2.10.0-skipped-imdb-edit-v6

api/routes.py

@@ -2538,6 +2538,115 @@ async def lookup_movie(imdb_id: str, dependencies: dict):
         raise HTTPException(status_code=500, detail=f"Movie lookup failed: {str(e)}")
 
 
+async def populate_database(background_tasks: BackgroundTasks, media_type: str = "both", dependencies: dict = None):
+    """
+    Populate NFOGuard database from Radarr/Sonarr sources
+
+    Args:
+        background_tasks: FastAPI background tasks
+        media_type: Type of media to populate ("movies", "tv", or "both")
+        dependencies: Dictionary with db, radarr_client, sonarr_client
+
+    Returns:
+        Status message indicating population has started
+    """
+    from core.database_populator import DatabasePopulator
+
+    db = dependencies["db"]
+    config = dependencies["config"]
+
+    # Get Radarr and Sonarr clients
+    from clients.radarr_client import RadarrClient
+    from clients.sonarr_client import SonarrClient
+
+    radarr_client = RadarrClient(config)
+    sonarr_client = SonarrClient(config)
+
+    if media_type not in ["both", "movies", "tv"]:
+        raise HTTPException(status_code=400, detail="media_type must be 'both', 'movies', or 'tv'")
+
+    # Create global status tracking
+    populate_status = {
+        "running": True,
+        "media_type": media_type,
+        "start_time": datetime.now().isoformat(),
+        "movies": {"status": "pending", "stats": None},
+        "tv": {"status": "pending", "stats": None},
+        "completed": False,
+        "error": None
+    }
+
+    # Store status globally so it can be queried
+    global _populate_status
+    _populate_status = populate_status
+
+    async def run_population():
+        """Background task to populate the database"""
+        try:
+            populator = DatabasePopulator(db, radarr_client, sonarr_client)
+
+            _log("INFO", f"Starting database population: {media_type}")
+
+            if media_type == "movies":
+                populate_status["movies"]["status"] = "running"
+                movie_stats = populator.populate_movies()
+                populate_status["movies"]["status"] = "completed"
+                populate_status["movies"]["stats"] = movie_stats
+                _log("INFO", f"Movie population completed: {movie_stats}")
+
+            elif media_type == "tv":
+                populate_status["tv"]["status"] = "running"
+                tv_stats = populator.populate_tv_episodes()
+                populate_status["tv"]["status"] = "completed"
+                populate_status["tv"]["stats"] = tv_stats
+                _log("INFO", f"TV population completed: {tv_stats}")
+
+            elif media_type == "both":
+                populate_status["movies"]["status"] = "running"
+                movie_stats = populator.populate_movies()
+                populate_status["movies"]["status"] = "completed"
+                populate_status["movies"]["stats"] = movie_stats
+                _log("INFO", f"Movie population completed: {movie_stats}")
+
+                populate_status["tv"]["status"] = "running"
+                tv_stats = populator.populate_tv_episodes()
+                populate_status["tv"]["status"] = "completed"
+                populate_status["tv"]["stats"] = tv_stats
+                _log("INFO", f"TV population completed: {tv_stats}")
+
+            populate_status["completed"] = True
+            populate_status["running"] = False
+            _log("INFO", "Database population completed successfully")
+
+        except Exception as e:
+            _log("ERROR", f"Database population failed: {e}")
+            populate_status["error"] = str(e)
+            populate_status["running"] = False
+            populate_status["completed"] = True
+
+    # Add task to background
+    background_tasks.add_task(run_population)
+
+    _log("INFO", f"Database population started for: {media_type}")
+    return {
+        "status": "started",
+        "media_type": media_type,
+        "message": f"Database population started for {media_type}"
+    }
+
+
+async def get_populate_status():
+    """Get the current status of database population"""
+    global _populate_status
+    if '_populate_status' not in globals():
+        return {"running": False, "completed": False}
+    return _populate_status
+
+
+# Initialize global populate status
+_populate_status = {"running": False, "completed": False}
+
+
 def register_routes(app, dependencies: dict):
     """
     Register all routes with the FastAPI app
@@ -2641,6 +2750,14 @@ def register_routes(app, dependencies: dict):
     async def _scan_status():
         return await get_scan_status()
 
+    @app.post("/admin/populate-database")
+    async def _populate_database(background_tasks: BackgroundTasks, media_type: str = "both"):
+        return await populate_database(background_tasks, media_type, dependencies)
+
+    @app.get("/api/populate/status")
+    async def _populate_status():
+        return await get_populate_status()
+
     @app.post("/tv/scan-season")
     async def _scan_tv_season(background_tasks: BackgroundTasks, request: TVSeasonRequest):
         return await scan_tv_season(background_tasks, request, dependencies)

api/web_routes.py

@@ -3,14 +3,25 @@ Web interface API routes for NFOGuard database management
 Provides endpoints for the web-based database manipulation interface
 """
 import json
+import os
+import tempfile
+import multiprocessing
 from datetime import datetime, timezone
 from typing import List, Optional, Dict, Any
-from fastapi import HTTPException, Query
+from fastapi import HTTPException, Query, BackgroundTasks
 from pathlib import Path
 
 from api.models import *
 
 
+# Status file for cross-process communication
+# Use /tmp which is writable in both core and web containers
+POPULATE_STATUS_FILE = "/tmp/nfoguard_populate_status.json"
+
+# Process tracking
+_populate_process = None
+
+
 def map_source_to_description(source: str) -> str:
     """Map technical source codes to user-friendly descriptions"""
     if not source or source == "no_valid_date_source":
@@ -45,16 +56,24 @@ def map_source_to_description(source: str) -> str:
     elif "omdb:" in source_lower:
         return "OMDb Release"
     
+    # Sonarr sources
+    elif "sonarr:" in source_lower:
+        return "Sonarr API"
+
     # Manual and other sources
     elif "manual" in source_lower:
         return "Manual Entry"
     elif "digital_release" in source_lower:
         return "Digital Release"
+    elif "nfo_file_existing" in source_lower:
+        return "NFO File (Legacy)"
     elif "nfo:" in source_lower:
         return "NFO File"
     elif "webhook:" in source_lower:
         return "Webhook/API"
-    
+    elif "database" in source_lower:
+        return "Database"
+
     # Fallback for unknown patterns
     return source.title()
 
@@ -63,13 +82,14 @@ def map_source_to_description(source: str) -> str:
 # Database Query Endpoints
 # ---------------------------
 
-async def get_movies_list(dependencies: dict, 
+async def get_movies_list(dependencies: dict,
                          skip: int = Query(0, ge=0),
                          limit: int = Query(100, le=1000),
                          has_date: Optional[bool] = Query(None),
                          source_filter: Optional[str] = Query(None),
                          search: Optional[str] = Query(None),
-                         imdb_search: Optional[str] = Query(None)):
+                         imdb_search: Optional[str] = Query(None),
+                         skipped: Optional[bool] = Query(None)):
     """Get paginated list of movies with filtering options"""
     db = dependencies["db"]
     
@@ -79,7 +99,13 @@ async def get_movies_list(dependencies: dict,
         # Build dynamic query
         where_conditions = []
         params = []
-        
+
+        if skipped is not None:
+            if skipped:
+                where_conditions.append("skipped = TRUE")
+            else:
+                where_conditions.append("(skipped = FALSE OR skipped IS NULL)")
+
         if has_date is not None:
             if has_date:
                 # PostgreSQL - NULL handling
@@ -87,15 +113,15 @@ async def get_movies_list(dependencies: dict,
             else:
                 # PostgreSQL - NULL handling
                 where_conditions.append("dateadded IS NULL")
-        
+
         if source_filter:
             where_conditions.append("source = %s")
             params.append(source_filter)
-        
+
         if search:
-            where_conditions.append("(imdb_id ILIKE %s OR path ILIKE %s)")
-            params.extend([f"%{search}%", f"%{search}%"])
-        
+            where_conditions.append("(imdb_id ILIKE %s OR path ILIKE %s OR title ILIKE %s)")
+            params.extend([f"%{search}%", f"%{search}%", f"%{search}%"])
+
         if imdb_search:
             where_conditions.append("imdb_id ILIKE %s")
             params.append(f"%{imdb_search}%")
@@ -109,22 +135,23 @@ async def get_movies_list(dependencies: dict,
         
         # Get paginated results - PostgreSQL
         query = f"""
-            SELECT imdb_id, path, released, dateadded, source, has_video_file, last_updated
-            FROM movies 
+            SELECT imdb_id, title, year, path, released, dateadded, source, has_video_file, last_updated, skipped, skip_reason
+            FROM movies
             WHERE {where_clause}
             ORDER BY last_updated DESC
             LIMIT %s OFFSET %s
         """
         cursor.execute(query, params + [limit, skip])
-        
+
         movies = []
         for row in cursor.fetchall():
             movie = dict(row)
-            # Extract title from path for display
-            try:
-                movie['title'] = Path(movie['path']).name if movie['path'] else movie['imdb_id']
-            except:
-                movie['title'] = movie['imdb_id']
+            # Use database title if available, otherwise extract from path
+            if not movie.get('title'):
+                try:
+                    movie['title'] = Path(movie['path']).name if movie['path'] else movie['imdb_id']
+                except:
+                    movie['title'] = movie['imdb_id']
             # Map source to user-friendly description
             movie['source_description'] = map_source_to_description(movie.get('source'))
             movies.append(movie)
@@ -150,8 +177,8 @@ async def get_tv_series_list(dependencies: dict,
     db = dependencies["db"]
     
     # Validate date_filter values
-    if date_filter and date_filter not in ['complete', 'incomplete', 'none']:
-        raise HTTPException(status_code=422, detail=f"Invalid date_filter: must be 'complete', 'incomplete', or 'none', got '{date_filter}'")
+    if date_filter and date_filter not in ['complete', 'incomplete', 'none', 'skipped']:
+        raise HTTPException(status_code=422, detail=f"Invalid date_filter: must be 'complete', 'incomplete', 'none', or 'skipped', got '{date_filter}'")
     
     with db.get_connection() as conn:
         cursor = conn.cursor()
@@ -184,13 +211,19 @@ async def get_tv_series_list(dependencies: dict,
             elif date_filter == "none":
                 # No episodes have dates
                 having_conditions.append("COUNT(e.episode) > 0 AND COUNT(CASE WHEN e.dateadded IS NOT NULL THEN 1 END) = 0")
+            elif date_filter == "skipped":
+                # Has skipped episodes
+                having_conditions.append("COUNT(CASE WHEN e.skipped = TRUE THEN 1 END) > 0")
         
         where_clause = " AND ".join(where_conditions) if where_conditions else "1=1"
         having_clause = " AND ".join(having_conditions) if having_conditions else ""
-        
+
+        # Check if where_clause references episodes table (e.source, e.dateadded, etc.)
+        needs_episode_join = any(cond.startswith("e.") for cond in where_conditions)
+
         # Get total count with same filtering logic as main query
-        if having_clause:
-            # When using HAVING clause, need to count filtered results
+        if having_clause or needs_episode_join:
+            # When using HAVING clause or filtering by episode fields, need to count filtered results with JOIN
             count_query = f"""
                 SELECT COUNT(*) FROM (
                     SELECT s.imdb_id
@@ -198,12 +231,12 @@ async def get_tv_series_list(dependencies: dict,
                     LEFT JOIN episodes e ON s.imdb_id = e.imdb_id
                     WHERE {where_clause}
                     GROUP BY s.imdb_id
-                    HAVING {having_clause}
+                    {('HAVING ' + having_clause) if having_clause else ''}
                 ) filtered_series
             """
             cursor.execute(count_query, params)
         else:
-            # Simple count when no HAVING clause
+            # Simple count when no HAVING clause and no episode filtering
             count_query = f"SELECT COUNT(*) FROM series s WHERE {where_clause}"
             cursor.execute(count_query, params)
         total_count = db._get_first_value(cursor.fetchone())
@@ -212,13 +245,14 @@ async def get_tv_series_list(dependencies: dict,
         having_part = f" HAVING {having_clause}" if having_clause else ""
         # PostgreSQL query
         query = f"""
-            SELECT 
-                s.imdb_id, 
-                s.path, 
+            SELECT
+                s.imdb_id,
+                s.path,
                 s.last_updated,
                 COUNT(e.episode) as total_episodes,
                 COUNT(CASE WHEN e.dateadded IS NOT NULL THEN 1 END) as episodes_with_dates,
-                COUNT(CASE WHEN e.has_video_file = TRUE THEN 1 END) as episodes_with_video
+                COUNT(CASE WHEN e.has_video_file = TRUE THEN 1 END) as episodes_with_video,
+                COUNT(CASE WHEN e.skipped = TRUE THEN 1 END) as episodes_skipped
             FROM series s
             LEFT JOIN episodes e ON s.imdb_id = e.imdb_id
             WHERE {where_clause}
@@ -465,7 +499,14 @@ async def get_dashboard_stats(dependencies: dict):
         
         cursor.execute("SELECT COUNT(*) FROM episodes WHERE source = 'no_valid_date_source'")
         episodes_no_valid_source = db._get_first_value(cursor.fetchone())
-        
+
+        # Skipped items
+        cursor.execute("SELECT COUNT(*) FROM movies WHERE skipped = TRUE")
+        movies_skipped = db._get_first_value(cursor.fetchone())
+
+        cursor.execute("SELECT COUNT(*) FROM episodes WHERE skipped = TRUE")
+        episodes_skipped = db._get_first_value(cursor.fetchone())
+
         # Recent activity (last 7 days)
         cursor.execute("""
             SELECT COUNT(*) FROM processing_history 
@@ -495,7 +536,8 @@ async def get_dashboard_stats(dependencies: dict):
         
     # Calculate total missing dates (movies + episodes)
     total_missing_dates = movies_without_dates + episodes_without_dates
-    
+    total_skipped = movies_skipped + episodes_skipped
+
     # Combine with enhanced stats
     stats.update({
         "movies_with_dates": movies_with_dates,
@@ -507,6 +549,9 @@ async def get_dashboard_stats(dependencies: dict):
         "total_missing_dates": total_missing_dates,
         "movies_no_valid_source": movies_no_valid_source,
         "episodes_no_valid_source": episodes_no_valid_source,
+        "movies_skipped": movies_skipped,
+        "episodes_skipped": episodes_skipped,
+        "total_skipped": total_skipped,
         "recent_activity_count": recent_activity,
         "movie_sources": movie_sources,
         "episode_sources": episode_sources
@@ -722,8 +767,7 @@ async def bulk_update_source(dependencies: dict, media_type: str, old_source: st
 async def get_movie_date_options(dependencies: dict, imdb_id: str):
     """Get available date options for a movie (Radarr import, digital release, etc.)"""
     db = dependencies["db"]
-    nfo_manager = dependencies["nfo_manager"]
-    
+
     # Get current movie data
     movie = db.get_movie_dates(imdb_id)
     if not movie:
@@ -1234,6 +1278,195 @@ async def get_episode_date_options(dependencies: dict, imdb_id: str, season: int
     }
 
 
+def _populate_worker_process(media_type: str, status_file: str):
+    """
+    Worker process that runs database population in complete isolation.
+    Runs in separate process - keeps web interface responsive.
+    """
+    import os
+    import sys
+    import json
+    from datetime import datetime
+
+    # Add parent directory to path for imports
+    sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+    def update_status(status_data):
+        """Write status to file for main process to read"""
+        try:
+            with open(status_file, 'w') as f:
+                json.dump(status_data, f)
+        except Exception as e:
+            print(f"ERROR: Failed to update status file: {e}")
+
+    # Initialize status
+    status = {
+        "running": True,
+        "media_type": media_type,
+        "start_time": datetime.now().isoformat(),
+        "movies": {"status": "pending", "stats": None},
+        "tv": {"status": "pending", "stats": None},
+        "completed": False,
+        "error": None
+    }
+    update_status(status)
+
+    try:
+        # Import here (inside process) to avoid pickling issues
+        from core.database import NFOGuardDatabase
+        from core.database_populator import DatabasePopulator
+        from clients.radarr_client import RadarrClient
+        from clients.sonarr_client import SonarrClient
+        from config.settings import config
+
+        # Initialize components
+        db = NFOGuardDatabase(config)
+        radarr_client = RadarrClient(
+            os.environ.get("RADARR_URL", ""),
+            os.environ.get("RADARR_API_KEY", "")
+        )
+        sonarr_client = SonarrClient(
+            os.environ.get("SONARR_URL", ""),
+            os.environ.get("SONARR_API_KEY", "")
+        )
+
+        populator = DatabasePopulator(db, radarr_client, sonarr_client)
+
+        print(f"INFO: [Worker Process] Starting database population: {media_type}")
+
+        # Run population based on media type
+        if media_type in ["movies", "both"]:
+            status["movies"]["status"] = "running"
+            update_status(status)
+
+            movie_stats = populator.populate_movies()
+
+            status["movies"]["status"] = "completed"
+            status["movies"]["stats"] = movie_stats
+            update_status(status)
+            print(f"INFO: [Worker Process] Movie population completed: {movie_stats}")
+
+        if media_type in ["tv", "both"]:
+            status["tv"]["status"] = "running"
+            update_status(status)
+
+            tv_stats = populator.populate_tv_episodes()
+
+            status["tv"]["status"] = "completed"
+            status["tv"]["stats"] = tv_stats
+            update_status(status)
+            print(f"INFO: [Worker Process] TV population completed: {tv_stats}")
+
+        # Mark as completed
+        status["completed"] = True
+        status["running"] = False
+        update_status(status)
+        print("INFO: [Worker Process] Database population completed successfully")
+
+    except Exception as e:
+        print(f"ERROR: [Worker Process] Database population failed: {e}")
+        import traceback
+        traceback.print_exc()
+
+        status["error"] = str(e)
+        status["running"] = False
+        status["completed"] = True
+        update_status(status)
+
+
+async def populate_database(background_tasks: BackgroundTasks, media_type: str = "both", dependencies: dict = None):
+    """
+    Populate NFOGuard database from Radarr/Sonarr sources in separate process.
+    This keeps the web interface responsive during population.
+
+    Args:
+        background_tasks: FastAPI background tasks (not used - kept for compatibility)
+        media_type: Type of media to populate ("movies", "tv", or "both")
+        dependencies: Dictionary with dependencies (not used in multiprocessing mode)
+
+    Returns:
+        Status message indicating population has started
+    """
+    global _populate_process
+
+    if media_type not in ["both", "movies", "tv"]:
+        raise HTTPException(status_code=400, detail="media_type must be 'both', 'movies', or 'tv'")
+
+    # Check if process is already running
+    if _populate_process and _populate_process.is_alive():
+        return {
+            "status": "already_running",
+            "message": "Database population is already in progress"
+        }
+
+    # Initialize status file
+    initial_status = {
+        "running": True,
+        "media_type": media_type,
+        "start_time": datetime.now().isoformat(),
+        "movies": {"status": "pending", "stats": None},
+        "tv": {"status": "pending", "stats": None},
+        "completed": False,
+        "error": None
+    }
+
+    try:
+        with open(POPULATE_STATUS_FILE, 'w') as f:
+            json.dump(initial_status, f)
+    except Exception as e:
+        print(f"ERROR: Failed to initialize status file: {e}")
+        raise HTTPException(status_code=500, detail=f"Failed to initialize status tracking: {e}")
+
+    # Start population in separate process
+    _populate_process = multiprocessing.Process(
+        target=_populate_worker_process,
+        args=(media_type, POPULATE_STATUS_FILE),
+        daemon=False  # Keep process alive even if parent exits
+    )
+    _populate_process.start()
+
+    print(f"INFO: Database population process started (PID: {_populate_process.pid}) for: {media_type}")
+    return {
+        "status": "started",
+        "media_type": media_type,
+        "message": f"Database population started for {media_type} in separate process (PID: {_populate_process.pid})"
+    }
+
+
+async def get_populate_status():
+    """Get the current status of database population from status file"""
+    global _populate_process
+
+    # Check if status file exists
+    if not os.path.exists(POPULATE_STATUS_FILE):
+        return {"running": False, "completed": False}
+
+    # Read status from file
+    try:
+        with open(POPULATE_STATUS_FILE, 'r') as f:
+            status = json.load(f)
+
+        # Check if process is still alive
+        if _populate_process:
+            status["process_alive"] = _populate_process.is_alive()
+            if not _populate_process.is_alive() and status.get("running"):
+                # Process died unexpectedly
+                status["running"] = False
+                status["completed"] = True
+                if not status.get("error"):
+                    status["error"] = "Process terminated unexpectedly"
+
+        return status
+
+    except Exception as e:
+        print(f"ERROR: Failed to read status file: {e}")
+        return {
+            "running": False,
+            "completed": True,
+            "error": f"Failed to read status: {e}"
+        }
+
+
 def register_web_routes(app, dependencies):
     """Register all web API routes with FastAPI app"""
     from fastapi import Request, Response
@@ -1249,22 +1482,59 @@ def register_web_routes(app, dependencies):
     
     # Movies endpoints
     @app.get("/api/movies")
-    async def api_movies_list(skip: int = 0, limit: int = 100, has_date: bool = None, 
-                             source_filter: str = None, search: str = None, imdb_search: str = None):
-        return await get_movies_list(dependencies, skip, limit, has_date, source_filter, search, imdb_search)
+    async def api_movies_list(skip: int = 0, limit: int = 100, has_date: bool = None,
+                             source_filter: str = None, search: str = None, imdb_search: str = None,
+                             skipped: bool = None):
+        return await get_movies_list(dependencies, skip, limit, has_date, source_filter, search, imdb_search, skipped)
     
     @app.post("/api/movies/{imdb_id}/update-date")
     async def api_update_movie_date(imdb_id: str, dateadded: str = None, source: str = "manual"):
         return await update_movie_date(dependencies, imdb_id, dateadded, source)
     
     @app.put("/api/movies/{imdb_id}")
-    async def api_update_movie(imdb_id: str, dateadded: str = None, source: str = "manual"):
-        return await update_movie_date(dependencies, imdb_id, dateadded, source)
+    async def api_update_movie(imdb_id: str, request: Request):
+        """Update movie date from JSON body"""
+        try:
+            data = await request.json()
+            dateadded = data.get('dateadded')
+            source = data.get('source', 'manual')
+
+            print(f"🔍 API PUT /api/movies/{imdb_id} - Received JSON:")
+            print(f"   - Raw data: {data}")
+            print(f"   - dateadded: {dateadded}")
+            print(f"   - source: {source}")
+
+            return await update_movie_date(dependencies, imdb_id, dateadded, source)
+        except Exception as e:
+            print(f"❌ Error parsing request body: {e}")
+            raise HTTPException(status_code=400, detail=f"Invalid request body: {str(e)}")
     
     @app.get("/api/movies/{imdb_id}/date-options")
     async def api_movie_date_options(imdb_id: str):
         return await get_movie_date_options(dependencies, imdb_id)
-    
+
+    @app.get("/api/debug/movie/{imdb_id}/raw")
+    async def api_debug_movie_raw(imdb_id: str):
+        """Get raw database data for a movie for debugging"""
+        db = dependencies["db"]
+
+        try:
+            movie = db.get_movie_dates(imdb_id)
+
+            if not movie:
+                raise HTTPException(status_code=404, detail="Movie not found")
+
+            return {
+                "success": True,
+                "raw_data": movie
+            }
+
+        except HTTPException:
+            raise
+        except Exception as e:
+            print(f"❌ Error getting movie debug data: {e}")
+            raise HTTPException(status_code=500, detail=f"Failed to get debug data: {str(e)}")
+
     @app.delete("/api/movies/{imdb_id}")
     async def api_delete_movie(imdb_id: str):
         """Delete a movie from the database"""
@@ -1289,7 +1559,42 @@ def register_web_routes(app, dependencies):
         except Exception as e:
             print(f"❌ Error deleting movie: {e}")
             raise HTTPException(status_code=500, detail=f"Failed to delete movie: {str(e)}")
-    
+
+    @app.post("/api/movies/{old_imdb_id}/migrate-imdb")
+    async def api_migrate_movie_imdb(old_imdb_id: str, request: Request):
+        """Migrate a movie from placeholder IMDb ID to real IMDb ID"""
+        db = dependencies["db"]
+
+        try:
+            data = await request.json()
+            new_imdb_id = data.get('new_imdb_id')
+
+            if not new_imdb_id:
+                raise HTTPException(status_code=422, detail="new_imdb_id is required")
+
+            # Normalize IMDb ID
+            if not new_imdb_id.startswith('tt'):
+                new_imdb_id = f"tt{new_imdb_id}"
+
+            success = db.migrate_movie_imdb_id(old_imdb_id, new_imdb_id)
+
+            if success:
+                return {
+                    "success": True,
+                    "status": "success",
+                    "message": f"Migrated movie from {old_imdb_id} to {new_imdb_id}",
+                    "old_imdb_id": old_imdb_id,
+                    "new_imdb_id": new_imdb_id
+                }
+            else:
+                raise HTTPException(status_code=404, detail="Movie not found")
+
+        except HTTPException:
+            raise
+        except Exception as e:
+            print(f"❌ Error migrating movie IMDb ID: {e}")
+            raise HTTPException(status_code=500, detail=f"Failed to migrate IMDb ID: {str(e)}")
+
     # TV series endpoints
     @app.get("/api/series")
     async def api_series_list(skip: int = 0, limit: int = 50, search: str = None, 
@@ -1307,7 +1612,42 @@ def register_web_routes(app, dependencies):
     @app.get("/api/series/debug/date-distribution")
     async def api_debug_series_date_distribution():
         return await debug_series_date_distribution(dependencies)
-    
+
+    @app.post("/api/series/{old_imdb_id}/migrate-imdb")
+    async def api_migrate_series_imdb(old_imdb_id: str, request: Request):
+        """Migrate a series and all its episodes from placeholder IMDb ID to real IMDb ID"""
+        db = dependencies["db"]
+
+        try:
+            data = await request.json()
+            new_imdb_id = data.get('new_imdb_id')
+
+            if not new_imdb_id:
+                raise HTTPException(status_code=422, detail="new_imdb_id is required")
+
+            # Normalize IMDb ID
+            if not new_imdb_id.startswith('tt'):
+                new_imdb_id = f"tt{new_imdb_id}"
+
+            success = db.migrate_series_imdb_id(old_imdb_id, new_imdb_id)
+
+            if success:
+                return {
+                    "success": True,
+                    "status": "success",
+                    "message": f"Migrated series and episodes from {old_imdb_id} to {new_imdb_id}",
+                    "old_imdb_id": old_imdb_id,
+                    "new_imdb_id": new_imdb_id
+                }
+            else:
+                raise HTTPException(status_code=404, detail="Series not found")
+
+        except HTTPException:
+            raise
+        except Exception as e:
+            print(f"❌ Error migrating series IMDb ID: {e}")
+            raise HTTPException(status_code=500, detail=f"Failed to migrate IMDb ID: {str(e)}")
+
     # Episode endpoints
     @app.post("/api/episodes/{imdb_id}/{season}/{episode}/update-date")
     async def api_update_episode_date(imdb_id: str, season: int, episode: int, 
@@ -1361,7 +1701,79 @@ def register_web_routes(app, dependencies):
     @app.post("/api/bulk/update-source")
     async def api_bulk_update_source(media_type: str, old_source: str, new_source: str):
         return {"error": "Bulk operations not available in web container. Use core container on port 8085."}
-    
+
+    @app.post("/api/episodes/bulk-update-dates")
+    async def api_bulk_update_episode_dates(request: Request):
+        """Bulk update episode dates"""
+        try:
+            data = await request.json()
+            episodes = data.get('episodes', [])
+            date_source = data.get('date_source', 'airdate')
+            custom_date = data.get('custom_date')
+
+            if not episodes:
+                return {"success": False, "message": "No episodes provided"}
+
+            db = dependencies["db"]
+            sonarr = dependencies.get("sonarr_client")
+
+            updated_count = 0
+            failed_count = 0
+
+            for ep in episodes:
+                imdb_id = ep.get('imdb_id')
+                season = ep.get('season')
+                episode = ep.get('episode')
+
+                if not all([imdb_id, season is not None, episode is not None]):
+                    failed_count += 1
+                    continue
+
+                try:
+                    dateadded = None
+                    source = "manual"
+
+                    if date_source == 'airdate':
+                        # Get airdate from Sonarr
+                        if sonarr:
+                            episode_data = sonarr.get_episode(imdb_id, season, episode)
+                            if episode_data and episode_data.get('airDateUtc'):
+                                dateadded = episode_data['airDateUtc']
+                                source = "sonarr:airdate"
+                    elif date_source == 'import':
+                        # Get import date from Sonarr history
+                        if sonarr:
+                            import_date = sonarr.get_episode_import_date(imdb_id, season, episode)
+                            if import_date:
+                                dateadded = import_date
+                                source = "sonarr:import"
+                    elif date_source == 'custom':
+                        # Use custom date
+                        if custom_date:
+                            dateadded = custom_date
+                            source = "manual:custom"
+
+                    if dateadded:
+                        db.upsert_episode_dates(imdb_id, season, episode, dateadded, source)
+                        updated_count += 1
+                    else:
+                        failed_count += 1
+
+                except Exception as e:
+                    print(f"❌ Error updating episode {imdb_id} S{season:02d}E{episode:02d}: {e}")
+                    failed_count += 1
+
+            return {
+                "success": True,
+                "updated": updated_count,
+                "failed": failed_count,
+                "message": f"Updated {updated_count} episode(s), {failed_count} failed"
+            }
+
+        except Exception as e:
+            print(f"❌ Bulk update error: {e}")
+            return {"success": False, "message": str(e)}
+
     # Reports
     @app.get("/api/reports/missing-dates")
     async def api_missing_dates_report():
@@ -1839,7 +2251,8 @@ async def bulk_update_nfo_files(dependencies: dict, imdb_ids: list = None, fix_a
 # Add database admin routes to the web interface
 def register_database_admin_routes(app, dependencies):
     """Register database admin routes"""
-    
+    from fastapi import Request, Response
+
     @app.post("/api/admin/database/query")
     async def api_database_query(query: str, limit: int = 100):
         """Execute a database query"""
@@ -1936,6 +2349,28 @@ def register_database_admin_routes(app, dependencies):
         """Get schedule execution history"""
         return await get_schedule_executions(dependencies, schedule_id)
 
+    # Database population endpoints
+    print("🔧 DEBUG: Registering /admin/populate-database endpoint...")
+
+    @app.post("/admin/populate-database")
+    async def api_populate_database(request: Request, background_tasks: BackgroundTasks):
+        """Populate database from Radarr/Sonarr"""
+        print(f"🔥 DEBUG: populate-database endpoint called!")
+        try:
+            data = await request.json()
+            media_type = data.get("media_type", "both")
+        except Exception:
+            # Fallback to query parameter if JSON parsing fails
+            media_type = request.query_params.get("media_type", "both")
+        return await populate_database(background_tasks, media_type, dependencies)
+
+    print("✅ DEBUG: /admin/populate-database registered")
+
+    @app.get("/api/populate/status")
+    async def api_populate_status():
+        """Get database population status"""
+        return await get_populate_status()
+
 
 # Scheduled Scans Functions
 

clients/radarr_db_client.py

@@ -164,7 +164,54 @@ class RadarrDbClient:
             _log("ERROR", f"Database query error for IMDb {imdb_id}: {e}")
             
         return None
-    
+
+    def get_all_movies(self) -> List[Dict[str, Any]]:
+        """
+        Get all movies from Radarr database (only movies with files)
+
+        Returns:
+            List of dictionaries with movie info
+        """
+        query = """
+        SELECT
+            m."Id" as id,
+            m."Path" as path,
+            m."Added" as added,
+            mm."ImdbId" as imdb_id,
+            mm."Title" as title,
+            mm."Year" as year,
+            mm."DigitalRelease" as digital_release,
+            mm."PhysicalRelease" as physical_release,
+            mm."InCinemas" as in_cinemas,
+            (SELECT COUNT(*) FROM "MovieFiles" mf WHERE mf."MovieId" = m."Id") as file_count
+        FROM "Movies" m
+        JOIN "MovieMetadata" mm ON m."MovieMetadataId" = mm."Id"
+        WHERE (SELECT COUNT(*) FROM "MovieFiles" mf WHERE mf."MovieId" = m."Id") > 0
+        ORDER BY mm."Title"
+        """
+
+        if self.db_type == "sqlite":
+            # SQLite uses ? placeholders but this query has none
+            pass
+
+        try:
+            with self._get_connection() as conn:
+                if self.db_type == "postgresql":
+                    cursor = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+                else:
+                    cursor = conn.cursor()
+
+                cursor.execute(query)
+                rows = cursor.fetchall()
+
+                if rows:
+                    return [dict(row) if self.db_type == "sqlite" else row for row in rows]
+                return []
+
+        except Exception as e:
+            _log("ERROR", f"Database query error getting all movies: {e}")
+            return []
+
     def get_earliest_import_date(self, movie_id: int) -> Tuple[Optional[str], str]:
         """
         Get earliest import date from History table, accounting for upgrade scenarios

clients/sonarr_db_client.py

@@ -0,0 +1,582 @@
+#!/usr/bin/env python3
+"""
+Direct Sonarr Database Client for NFOGuard
+Provides high-performance access to Sonarr's SQLite/PostgreSQL database
+"""
+
+import os
+import sqlite3
+import psycopg2
+import psycopg2.extras
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Dict, Any, List, Optional, Tuple, Union
+from urllib.parse import urlparse
+
+from core.logging import _log
+
+
+class SonarrDbClient:
+    """Direct database client for Sonarr's SQLite or PostgreSQL database"""
+
+    def __init__(self,
+                 db_type: str = "sqlite",
+                 db_path: Optional[str] = None,
+                 db_host: Optional[str] = None,
+                 db_port: Optional[int] = None,
+                 db_name: Optional[str] = None,
+                 db_user: Optional[str] = None,
+                 db_password: Optional[str] = None):
+        """
+        Initialize Sonarr database client
+
+        Args:
+            db_type: "sqlite" or "postgresql"
+            db_path: Path to SQLite database file
+            db_host: PostgreSQL host
+            db_port: PostgreSQL port
+            db_name: PostgreSQL database name
+            db_user: PostgreSQL username
+            db_password: PostgreSQL password
+        """
+        self.db_type = db_type.lower()
+        self.db_path = db_path
+        self.db_host = db_host
+        self.db_port = db_port or 5432
+        self.db_name = db_name
+        self.db_user = db_user
+        self.db_password = db_password
+
+        self._test_connection()
+
+    @classmethod
+    def from_env(cls) -> Optional['SonarrDbClient']:
+        """Create client from environment variables"""
+        db_type = os.environ.get("SONARR_DB_TYPE", "").lower()
+
+        if not db_type:
+            return None
+
+        if db_type == "sqlite":
+            db_path = os.environ.get("SONARR_DB_PATH")
+            if not db_path or not Path(db_path).exists():
+                _log("WARNING", f"SONARR_DB_PATH not found or invalid: {db_path}")
+                return None
+            return cls(db_type="sqlite", db_path=db_path)
+
+        elif db_type == "postgresql":
+            # Support both individual vars and connection string
+            db_url = os.environ.get("SONARR_DB_URL")
+            if db_url:
+                parsed = urlparse(db_url)
+                return cls(
+                    db_type="postgresql",
+                    db_host=parsed.hostname,
+                    db_port=parsed.port or 5432,
+                    db_name=parsed.path.lstrip('/'),
+                    db_user=parsed.username,
+                    db_password=parsed.password
+                )
+            else:
+                return cls(
+                    db_type="postgresql",
+                    db_host=os.environ.get("SONARR_DB_HOST"),
+                    db_port=int(os.environ.get("SONARR_DB_PORT", "5432")),
+                    db_name=os.environ.get("SONARR_DB_NAME"),
+                    db_user=os.environ.get("SONARR_DB_USER"),
+                    db_password=os.environ.get("SONARR_DB_PASSWORD")
+                )
+        else:
+            _log("ERROR", f"Unsupported database type: {db_type}")
+            return None
+
+    def _test_connection(self) -> None:
+        """Test database connection on initialization"""
+        try:
+            conn = self._get_connection()
+            if conn:
+                conn.close()
+                _log("INFO", f"Connected to Sonarr {self.db_type} database successfully")
+            else:
+                raise Exception("Failed to create connection")
+        except Exception as e:
+            _log("ERROR", f"Failed to connect to Sonarr database: {e}")
+            raise
+
+    def _get_connection(self) -> Union[sqlite3.Connection, psycopg2.extensions.connection]:
+        """Get database connection"""
+        if self.db_type == "sqlite":
+            conn = sqlite3.connect(self.db_path)
+            conn.row_factory = sqlite3.Row
+            return conn
+        elif self.db_type == "postgresql":
+            conn = psycopg2.connect(
+                host=self.db_host,
+                port=self.db_port,
+                database=self.db_name,
+                user=self.db_user,
+                password=self.db_password
+            )
+            return conn
+        else:
+            raise ValueError(f"Unsupported database type: {self.db_type}")
+
+    def get_series_by_imdb(self, imdb_id: str) -> Optional[Dict[str, Any]]:
+        """
+        Find series by IMDb ID using database query
+
+        Returns:
+            Dictionary with series info including id, imdb_id, title, path
+        """
+        imdb_id = imdb_id if imdb_id.startswith("tt") else f"tt{imdb_id}"
+
+        query = """
+        SELECT
+            "Id" as id,
+            "ImdbId" as imdb_id,
+            "TvdbId" as tvdb_id,
+            "Title" as title,
+            "Path" as path,
+            "Added" as added
+        FROM "Series"
+        WHERE "ImdbId" = %s
+        """
+
+        if self.db_type == "sqlite":
+            query = query.replace("%s", "?")
+
+        try:
+            with self._get_connection() as conn:
+                if self.db_type == "postgresql":
+                    cursor = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+                else:
+                    cursor = conn.cursor()
+
+                cursor.execute(query, (imdb_id,))
+                row = cursor.fetchone()
+
+                if row:
+                    return dict(row) if self.db_type == "sqlite" else row
+
+        except Exception as e:
+            _log("ERROR", f"Database query error for IMDb {imdb_id}: {e}")
+
+        return None
+
+    def get_all_episodes_for_series(self, series_id: int) -> List[Dict[str, Any]]:
+        """
+        Get all episodes for a series
+
+        Args:
+            series_id: Sonarr series ID
+
+        Returns:
+            List of episode dictionaries with season, episode, air_date
+        """
+        query = """
+        SELECT
+            "Id" as id,
+            "SeasonNumber" as season,
+            "EpisodeNumber" as episode,
+            "Title" as title,
+            "AirDate" as air_date,
+            "EpisodeFileId" as episode_file_id
+        FROM "Episodes"
+        WHERE "SeriesId" = %s
+        ORDER BY "SeasonNumber", "EpisodeNumber"
+        """
+
+        if self.db_type == "sqlite":
+            query = query.replace("%s", "?")
+
+        try:
+            with self._get_connection() as conn:
+                if self.db_type == "postgresql":
+                    cursor = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+                else:
+                    cursor = conn.cursor()
+
+                cursor.execute(query, (series_id,))
+                rows = cursor.fetchall()
+
+                if self.db_type == "sqlite":
+                    return [dict(row) for row in rows]
+                else:
+                    return rows
+
+        except Exception as e:
+            _log("ERROR", f"Database query error for series {series_id}: {e}")
+            return []
+
+    def get_episode_import_date(self, episode_id: int) -> Tuple[Optional[str], str]:
+        """
+        Get earliest import date for an episode from History table
+
+        Args:
+            episode_id: Sonarr episode ID
+
+        Returns:
+            (date_iso, source_description)
+        """
+        # Query for earliest import event (EventType 3)
+        import_query = """
+        SELECT
+            "Date" as event_date,
+            "EventType" as event_type
+        FROM "History"
+        WHERE "EpisodeId" = %s
+            AND "EventType" = 3
+        ORDER BY "Date" ASC
+        LIMIT 1
+        """
+
+        if self.db_type == "sqlite":
+            import_query = import_query.replace("%s", "?")
+
+        try:
+            with self._get_connection() as conn:
+                if self.db_type == "postgresql":
+                    cursor = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+                else:
+                    cursor = conn.cursor()
+
+                # Try import events first
+                cursor.execute(import_query, (episode_id,))
+                row = cursor.fetchone()
+
+                if row:
+                    event_date = row['event_date'] if self.db_type == "postgresql" else row[0]
+                    if isinstance(event_date, str):
+                        dt = datetime.fromisoformat(event_date.replace("Z", "+00:00"))
+                    else:
+                        dt = event_date.replace(tzinfo=timezone.utc)
+
+                    date_iso = dt.astimezone(timezone.utc).isoformat(timespec="seconds")
+                    return date_iso, "sonarr:db.history.import"
+
+        except Exception as e:
+            _log("ERROR", f"Database query error for episode {episode_id}: {e}")
+
+        return None, "sonarr:db.no_import_found"
+
+    def get_episode_file_date(self, series_id: int, season: int, episode: int) -> Optional[str]:
+        """
+        Get episode file DateAdded as fallback
+
+        Args:
+            series_id: Sonarr series ID
+            season: Season number
+            episode: Episode number
+
+        Returns:
+            ISO date string or None
+        """
+        # First get the episode ID to find the file
+        episode_query = """
+        SELECT "EpisodeFileId"
+        FROM "Episodes"
+        WHERE "SeriesId" = %s
+            AND "SeasonNumber" = %s
+            AND "EpisodeNumber" = %s
+        """
+
+        file_query = """
+        SELECT "DateAdded"
+        FROM "EpisodeFiles"
+        WHERE "Id" = %s
+        """
+
+        if self.db_type == "sqlite":
+            episode_query = episode_query.replace("%s", "?")
+            file_query = file_query.replace("%s", "?")
+
+        try:
+            with self._get_connection() as conn:
+                if self.db_type == "postgresql":
+                    cursor = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+                else:
+                    cursor = conn.cursor()
+
+                # Get episode file ID
+                cursor.execute(episode_query, (series_id, season, episode))
+                row = cursor.fetchone()
+
+                if row:
+                    file_id = row['EpisodeFileId'] if self.db_type == "postgresql" else row[0]
+
+                    if file_id:
+                        # Get file date
+                        cursor.execute(file_query, (file_id,))
+                        file_row = cursor.fetchone()
+
+                        if file_row:
+                            date_value = file_row['DateAdded'] if self.db_type == "postgresql" else file_row[0]
+
+                            if isinstance(date_value, str):
+                                dt = datetime.fromisoformat(date_value.replace("Z", "+00:00"))
+                            else:
+                                dt = date_value.replace(tzinfo=timezone.utc)
+
+                            return dt.astimezone(timezone.utc).isoformat(timespec="seconds")
+
+        except Exception as e:
+            _log("ERROR", f"Database query error for episode file: {e}")
+
+        return None
+
+    def bulk_import_dates_for_series(self, series_id: int) -> Dict[Tuple[int, int], Tuple[Optional[str], str]]:
+        """
+        Get import dates for all episodes in a series in a single query
+
+        Args:
+            series_id: Sonarr series ID
+
+        Returns:
+            Dictionary mapping (season, episode) -> (date_iso, source)
+        """
+        query = """
+        SELECT
+            e."SeasonNumber" as season,
+            e."EpisodeNumber" as episode,
+            e."Id" as episode_id,
+            MIN(h."Date") as earliest_import
+        FROM "Episodes" e
+        LEFT JOIN "History" h ON e."Id" = h."EpisodeId" AND h."EventType" = 3
+        WHERE e."SeriesId" = %s
+        GROUP BY e."SeasonNumber", e."EpisodeNumber", e."Id"
+        ORDER BY e."SeasonNumber", e."EpisodeNumber"
+        """
+
+        if self.db_type == "sqlite":
+            query = query.replace("%s", "?")
+
+        results = {}
+
+        try:
+            with self._get_connection() as conn:
+                if self.db_type == "postgresql":
+                    cursor = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+                else:
+                    cursor = conn.cursor()
+
+                cursor.execute(query, (series_id,))
+                rows = cursor.fetchall()
+
+                for row in rows:
+                    if self.db_type == "postgresql":
+                        season, episode, episode_id, earliest_import = row['season'], row['episode'], row['episode_id'], row['earliest_import']
+                    else:
+                        season, episode, episode_id, earliest_import = row[0], row[1], row[2], row[3]
+
+                    if earliest_import:
+                        if isinstance(earliest_import, str):
+                            dt = datetime.fromisoformat(earliest_import.replace("Z", "+00:00"))
+                        else:
+                            dt = earliest_import.replace(tzinfo=timezone.utc)
+
+                        date_iso = dt.astimezone(timezone.utc).isoformat(timespec="seconds")
+                        results[(season, episode)] = (date_iso, "sonarr:db.bulk.import")
+                    else:
+                        results[(season, episode)] = (None, "sonarr:db.bulk.no_import")
+
+        except Exception as e:
+            _log("ERROR", f"Bulk query error for series {series_id}: {e}")
+
+        return results
+
+    def get_database_stats(self) -> Dict[str, Any]:
+        """Get basic statistics about the Sonarr database"""
+        stats = {}
+
+        queries = {
+            "total_series": 'SELECT COUNT(*) FROM "Series"',
+            "total_episodes": 'SELECT COUNT(*) FROM "Episodes"',
+            "total_episode_files": 'SELECT COUNT(*) FROM "EpisodeFiles"',
+            "total_history_events": 'SELECT COUNT(*) FROM "History"',
+            "import_events": 'SELECT COUNT(*) FROM "History" WHERE "EventType" = 3',
+            "grab_events": 'SELECT COUNT(*) FROM "History" WHERE "EventType" = 1'
+        }
+
+        try:
+            with self._get_connection() as conn:
+                cursor = conn.cursor()
+
+                for stat_name, query in queries.items():
+                    cursor.execute(query)
+                    result = cursor.fetchone()
+                    stats[stat_name] = result[0] if result else 0
+
+        except Exception as e:
+            _log("ERROR", f"Stats query error: {e}")
+            stats["error"] = str(e)
+
+        return stats
+
+    def health_check(self) -> Dict[str, Any]:
+        """
+        Comprehensive health check for the Sonarr database connection
+
+        Returns:
+            Dictionary with health status, connection info, and basic functionality tests
+        """
+        health = {
+            "status": "healthy",
+            "database_type": self.db_type,
+            "connection": "ok",
+            "readable": False,
+            "tables_exist": False,
+            "sample_data": False,
+            "issues": [],
+            "tested_at": datetime.now(timezone.utc).isoformat(timespec="seconds")
+        }
+
+        try:
+            with self._get_connection() as conn:
+                cursor = conn.cursor()
+
+                # Test 1: Basic read
+                try:
+                    cursor.execute('SELECT 1')
+                    result = cursor.fetchone()
+                    if result and result[0] == 1:
+                        health["readable"] = True
+                        health["connection"] = "readable"
+                    else:
+                        health["issues"].append("Basic SELECT query failed")
+                except Exception as e:
+                    health["issues"].append(f"Read test failed: {e}")
+                    health["status"] = "degraded"
+
+                # Test 2: Check required tables
+                required_tables = ["Series", "Episodes", "EpisodeFiles", "History"]
+                existing_tables = []
+
+                try:
+                    if self.db_type == "postgresql":
+                        cursor.execute("""
+                            SELECT table_name
+                            FROM information_schema.tables
+                            WHERE table_schema = 'public'
+                            AND table_name IN ('Series', 'Episodes', 'EpisodeFiles', 'History')
+                        """)
+                    else:  # SQLite
+                        cursor.execute("""
+                            SELECT name
+                            FROM sqlite_master
+                            WHERE type='table'
+                            AND name IN ('Series', 'Episodes', 'EpisodeFiles', 'History')
+                        """)
+
+                    rows = cursor.fetchall()
+                    existing_tables = [row[0] for row in rows]
+
+                    if len(existing_tables) == len(required_tables):
+                        health["tables_exist"] = True
+                    else:
+                        missing = set(required_tables) - set(existing_tables)
+                        health["issues"].append(f"Missing tables: {list(missing)}")
+                        health["status"] = "degraded"
+
+                    health["existing_tables"] = existing_tables
+
+                except Exception as e:
+                    health["issues"].append(f"Table check failed: {e}")
+                    health["status"] = "degraded"
+
+                # Test 3: Check for sample data
+                if health["tables_exist"]:
+                    try:
+                        cursor.execute('SELECT COUNT(*) FROM "Series"')
+                        series_count = cursor.fetchone()[0]
+
+                        cursor.execute('SELECT COUNT(*) FROM "Episodes"')
+                        episode_count = cursor.fetchone()[0]
+
+                        cursor.execute('SELECT COUNT(*) FROM "History"')
+                        history_count = cursor.fetchone()[0]
+
+                        if series_count > 0 and episode_count > 0:
+                            health["sample_data"] = True
+                            health["series_count"] = series_count
+                            health["episode_count"] = episode_count
+                            health["history_count"] = history_count
+                        else:
+                            health["issues"].append(f"Low data counts - Series: {series_count}, Episodes: {episode_count}")
+
+                    except Exception as e:
+                        health["issues"].append(f"Sample data check failed: {e}")
+
+                # Test 4: Test a real query
+                if health["sample_data"]:
+                    try:
+                        cursor.execute("""
+                            SELECT COUNT(*)
+                            FROM "Series"
+                            WHERE "ImdbId" IS NOT NULL
+                        """)
+                        imdb_series = cursor.fetchone()[0]
+                        health["series_with_imdb"] = imdb_series
+
+                        if imdb_series > 0:
+                            health["functional"] = True
+                        else:
+                            health["issues"].append("No series with IMDb IDs found")
+
+                    except Exception as e:
+                        health["issues"].append(f"Functional test failed: {e}")
+                        health["status"] = "degraded"
+
+        except Exception as e:
+            health["status"] = "error"
+            health["connection"] = "failed"
+            health["issues"].append(f"Connection failed: {e}")
+            _log("ERROR", f"Database health check failed: {e}")
+
+        # Overall status
+        if health["issues"]:
+            if health["status"] == "healthy":
+                health["status"] = "degraded"
+
+        # Add connection details (safe info only)
+        health["connection_info"] = {
+            "type": self.db_type,
+            "host": self.db_host if self.db_type == "postgresql" else None,
+            "port": self.db_port if self.db_type == "postgresql" else None,
+            "database": self.db_name if self.db_type == "postgresql" else None,
+            "path": self.db_path if self.db_type == "sqlite" else None
+        }
+
+        return health
+
+
+if __name__ == "__main__":
+    # Test the database client
+    print("Testing SonarrDbClient...")
+
+    # Test with environment variables
+    client = SonarrDbClient.from_env()
+    if client:
+        print("✅ Connected to Sonarr database")
+
+        # Test stats
+        stats = client.get_database_stats()
+        print(f"Database stats: {stats}")
+
+        # Test series lookup
+        test_series = client.get_series_by_imdb("tt1628033")  # Top Gear from your data
+        if test_series:
+            print(f"Found test series: {test_series}")
+
+            # Test episodes
+            series_id = test_series['id']
+            episodes = client.get_all_episodes_for_series(series_id)
+            print(f"Found {len(episodes)} episodes")
+
+            # Test bulk import dates
+            if episodes:
+                import_dates = client.bulk_import_dates_for_series(series_id)
+                print(f"Import dates for {len(import_dates)} episodes")
+        else:
+            print("Test series not found")
+    else:
+        print("❌ Could not connect to database - check environment variables")

core/async_nfo_manager.py

@@ -1,473 +0,0 @@
-"""
-Async NFO Manager for NFOGuard
-High-performance async NFO file operations with concurrent processing
-"""
-import asyncio
-from pathlib import Path
-from typing import Optional, List, Dict, Any, Tuple
-from datetime import datetime
-import xml.etree.ElementTree as ET
-
-from utils.logging import _log
-from utils.async_file_utils import (
-    async_read_nfo_file,
-    async_write_nfo_file,
-    async_file_exists,
-    async_set_file_mtime,
-    async_batch_nfo_operations,
-    async_concurrent_episode_processing,
-    aiofiles
-)
-from utils.nfo_patterns import (
-    create_basic_nfo_structure,
-    extract_imdb_from_nfo_content,
-    extract_dates_from_nfo,
-    extract_imdb_id_from_text
-)
-from utils.validation import validate_date_string
-from utils.file_utils import VIDEO_EXTENSIONS
-
-
-class AsyncNFOManager:
-    """Async NFO file manager with concurrent processing capabilities"""
-    
-    def __init__(self, manager_brand: str = "NFOGuard", debug: bool = False):
-        self.manager_brand = manager_brand
-        self.debug = debug
-    
-    async def _async_get_target_nfo_path(self, season_dir: Path, season: int, episode: int) -> Path:
-        """
-        Get the target NFO path using video filename matching to prevent concatenation
-        
-        Args:
-            season_dir: Path to season directory
-            season: Season number
-            episode: Episode number
-            
-        Returns:
-            Path to target NFO file (video-matching preferred, generic fallback)
-        """
-        try:
-            # Find video files in the season directory
-            video_files = []
-            if await async_file_exists(season_dir):
-                import re
-                try:
-                    entries = await aiofiles.os.listdir(season_dir)
-                    for entry in entries:
-                        entry_path = season_dir / entry
-                        if await aiofiles.os.path.isfile(entry_path):
-                            if entry_path.suffix.lower() in VIDEO_EXTENSIONS:
-                                # Parse episode info from filename
-                                match = re.search(r'[Ss](\d{1,2})[Ee](\d{1,2})', entry)
-                                if match:
-                                    s, e = int(match.group(1)), int(match.group(2))
-                                    if s == season and e == episode:
-                                        # Found matching video file - use its name for NFO
-                                        target_nfo = season_dir / f"{entry_path.stem}.nfo"
-                                        if self.debug:
-                                            _log("DEBUG", f"Video-matching NFO path: {target_nfo.name}")
-                                        return target_nfo
-                except Exception as e:
-                    if self.debug:
-                        _log("WARNING", f"Failed to scan season directory {season_dir}: {e}")
-            
-            # Fallback to generic filename if no matching video found
-            target_nfo = season_dir / f"S{season:02d}E{episode:02d}.nfo"
-            if self.debug:
-                _log("WARNING", f"No video file found for S{season:02d}E{episode:02d}, using generic: {target_nfo.name}")
-            return target_nfo
-            
-        except Exception as e:
-            _log("ERROR", f"Failed to determine NFO path for S{season:02d}E{episode:02d}: {e}")
-            # Emergency fallback
-            return season_dir / f"S{season:02d}E{episode:02d}.nfo"
-    
-    async def async_parse_imdb_from_path(self, path: Path) -> Optional[str]:
-        """
-        Async extract IMDb ID from directory path or filename
-        
-        Args:
-            path: Path to examine
-            
-        Returns:
-            IMDb ID if found, None otherwise
-        """
-        # Use the sync version since it's just string processing
-        return extract_imdb_id_from_text(str(path))
-    
-    async def async_parse_imdb_from_nfo(self, nfo_path: Path) -> Optional[str]:
-        """
-        Async extract IMDb ID from NFO file content
-        
-        Args:
-            nfo_path: Path to NFO file
-            
-        Returns:
-            IMDb ID if found, None otherwise
-        """
-        root = await async_read_nfo_file(nfo_path)
-        if root is None:
-            return None
-        
-        return extract_imdb_from_nfo_content(root)
-    
-    async def async_find_movie_imdb_id(self, movie_dir: Path) -> Optional[str]:
-        """
-        Async find IMDb ID from directory name, filenames, or NFO file
-        
-        Args:
-            movie_dir: Path to movie directory
-            
-        Returns:
-            IMDb ID if found, None otherwise
-        """
-        if self.debug:
-            _log("DEBUG", f"Async searching for IMDb ID in: {movie_dir.name}")
-        
-        # First try directory name
-        imdb_id = await self.async_parse_imdb_from_path(movie_dir)
-        if imdb_id:
-            if self.debug:
-                _log("DEBUG", f"Found IMDb ID in directory name: {imdb_id}")
-            return imdb_id
-        
-        # Try all files in the directory concurrently
-        if await async_file_exists(movie_dir):
-            try:
-                from utils.async_file_utils import aiofiles
-                entries = await aiofiles.os.listdir(movie_dir)
-                
-                # Create tasks to check all files
-                async def check_file(filename: str) -> Optional[str]:
-                    file_path = movie_dir / filename
-                    if await aiofiles.os.path.isfile(file_path):
-                        return await self.async_parse_imdb_from_path(file_path)
-                    return None
-                
-                # Check all files concurrently
-                results = await asyncio.gather(
-                    *[check_file(filename) for filename in entries],
-                    return_exceptions=True
-                )
-                
-                # Find first valid IMDb ID
-                for result in results:
-                    if isinstance(result, str) and result:
-                        if self.debug:
-                            _log("DEBUG", f"Found IMDb ID in filename: {result}")
-                        return result
-                        
-            except Exception as e:
-                _log("WARNING", f"Failed to scan directory {movie_dir}: {e}")
-        
-        # Finally, try NFO file content
-        nfo_path = movie_dir / "movie.nfo"
-        imdb_id = await self.async_parse_imdb_from_nfo(nfo_path)
-        if imdb_id:
-            if self.debug:
-                _log("DEBUG", f"Found IMDb ID in NFO file: {imdb_id}")
-            return imdb_id
-        
-        if self.debug:
-            _log("DEBUG", f"No IMDb ID found for: {movie_dir.name}")
-        return None
-    
-    async def async_create_movie_nfo(
-        self,
-        movie_dir: Path,
-        imdb_id: str,
-        dateadded: str,
-        premiered: Optional[str] = None,
-        lock_metadata: bool = True
-    ) -> bool:
-        """
-        Async create movie NFO file
-        
-        Args:
-            movie_dir: Path to movie directory
-            imdb_id: IMDb ID
-            dateadded: Date added
-            premiered: Optional premiere date
-            lock_metadata: Whether to lock metadata
-            
-        Returns:
-            True if successful, False otherwise
-        """
-        try:
-            nfo_path = movie_dir / "movie.nfo"
-            
-            # Prepare dates
-            dates = {"dateadded": dateadded}
-            if premiered and validate_date_string(premiered):
-                dates["premiered"] = premiered
-            
-            # Create NFO structure
-            root = create_basic_nfo_structure(
-                media_type="movie",
-                title=movie_dir.name,
-                imdb_id=imdb_id,
-                dates=dates,
-                additional_fields={"source": self.manager_brand}
-            )
-            
-            # Write NFO file asynchronously
-            success = await async_write_nfo_file(nfo_path, root, lock_metadata)
-            
-            if success and self.debug:
-                _log("DEBUG", f"Created movie NFO: {nfo_path}")
-            
-            return success
-            
-        except Exception as e:
-            _log("ERROR", f"Failed to create movie NFO for {movie_dir}: {e}")
-            return False
-    
-    async def async_create_episode_nfo(
-        self,
-        season_dir: Path,
-        season: int,
-        episode: int,
-        aired: Optional[str] = None,
-        dateadded: Optional[str] = None,
-        source: str = "unknown",
-        lock_metadata: bool = True
-    ) -> bool:
-        """
-        Async create episode NFO file with proper video filename matching
-        
-        Args:
-            season_dir: Path to season directory
-            season: Season number
-            episode: Episode number
-            aired: Optional air date
-            dateadded: Optional date added
-            source: Source of the data
-            lock_metadata: Whether to lock metadata
-            
-        Returns:
-            True if successful, False otherwise
-        """
-        try:
-            # Use proper video filename matching to prevent NFO concatenation
-            nfo_path = await self._async_get_target_nfo_path(season_dir, season, episode)
-            
-            # Prepare dates
-            dates = {}
-            if aired and validate_date_string(aired):
-                dates["aired"] = aired
-            if dateadded and validate_date_string(dateadded):
-                dates["dateadded"] = dateadded
-            
-            # Create NFO structure
-            root = create_basic_nfo_structure(
-                media_type="episodedetails",
-                title=f"S{season:02d}E{episode:02d}",
-                dates=dates,
-                additional_fields={
-                    "season": str(season),
-                    "episode": str(episode),
-                    "source": source
-                }
-            )
-            
-            # Write NFO file asynchronously
-            success = await async_write_nfo_file(nfo_path, root, lock_metadata)
-            
-            if success and self.debug:
-                _log("DEBUG", f"Created episode NFO: {nfo_path}")
-            
-            return success
-            
-        except Exception as e:
-            _log("ERROR", f"Failed to create episode NFO S{season:02d}E{episode:02d}: {e}")
-            return False
-    
-    async def async_batch_create_episode_nfos(
-        self,
-        episode_data_list: List[Dict[str, Any]],
-        max_concurrent: int = 5
-    ) -> List[bool]:
-        """
-        Batch create multiple episode NFOs concurrently
-        
-        Args:
-            episode_data_list: List of episode data dictionaries
-            max_concurrent: Maximum concurrent NFO operations
-            
-        Returns:
-            List of success/failure results
-        """
-        async def _create_episode_nfo(episode_data: Dict[str, Any]) -> bool:
-            return await self.async_create_episode_nfo(
-                season_dir=episode_data.get('season_dir'),
-                season=episode_data.get('season'),
-                episode=episode_data.get('episode'),
-                aired=episode_data.get('aired'),
-                dateadded=episode_data.get('dateadded'),
-                source=episode_data.get('source', 'unknown'),
-                lock_metadata=episode_data.get('lock_metadata', True)
-            )
-        
-        return await async_concurrent_episode_processing(
-            episode_data_list,
-            _create_episode_nfo,
-            max_concurrent
-        )
-    
-    async def async_set_file_mtime(self, file_path: Path, date_str: str) -> bool:
-        """
-        Async set file modification time from date string
-        
-        Args:
-            file_path: Path to file
-            date_str: Date string in ISO format
-            
-        Returns:
-            True if successful, False otherwise
-        """
-        try:
-            if not validate_date_string(date_str):
-                _log("WARNING", f"Invalid date format for mtime: {date_str}")
-                return False
-            
-            # Parse date string to timestamp
-            dt = datetime.fromisoformat(date_str.replace('Z', '+00:00'))
-            timestamp = dt.timestamp()
-            
-            # Set file mtime asynchronously
-            success = await async_set_file_mtime(file_path, timestamp)
-            
-            if success and self.debug:
-                _log("DEBUG", f"Set mtime for {file_path}: {date_str}")
-            
-            return success
-            
-        except Exception as e:
-            _log("ERROR", f"Failed to set mtime for {file_path}: {e}")
-            return False
-    
-    async def async_batch_set_file_mtimes(
-        self,
-        file_mtime_pairs: List[Tuple[Path, str]],
-        max_concurrent: int = 10
-    ) -> List[bool]:
-        """
-        Batch set file modification times concurrently
-        
-        Args:
-            file_mtime_pairs: List of (file_path, date_str) tuples
-            max_concurrent: Maximum concurrent operations
-            
-        Returns:
-            List of success/failure results
-        """
-        async def _set_single_mtime(file_path: Path, date_str: str) -> bool:
-            return await self.async_set_file_mtime(file_path, date_str)
-        
-        # Create tasks for all mtime operations
-        semaphore = asyncio.Semaphore(max_concurrent)
-        
-        async def _set_mtime_with_semaphore(file_path: Path, date_str: str) -> bool:
-            async with semaphore:
-                return await _set_single_mtime(file_path, date_str)
-        
-        tasks = [
-            _set_mtime_with_semaphore(file_path, date_str)
-            for file_path, date_str in file_mtime_pairs
-        ]
-        
-        results = await asyncio.gather(*tasks, return_exceptions=True)
-        
-        return [result if isinstance(result, bool) else False for result in results]
-    
-    async def async_validate_nfo_integrity(
-        self,
-        nfo_paths: List[Path],
-        max_concurrent: int = 10
-    ) -> Dict[str, Any]:
-        """
-        Async validate integrity of multiple NFO files
-        
-        Args:
-            nfo_paths: List of NFO file paths to validate
-            max_concurrent: Maximum concurrent validations
-            
-        Returns:
-            Dictionary with validation results and statistics
-        """
-        results = {
-            'total_files': len(nfo_paths),
-            'valid_files': 0,
-            'invalid_files': 0,
-            'missing_files': 0,
-            'validation_errors': [],
-            'file_results': {}
-        }
-        
-        async def _validate_single_nfo(nfo_path: Path) -> Dict[str, Any]:
-            file_result = {
-                'path': str(nfo_path),
-                'exists': False,
-                'valid_xml': False,
-                'has_imdb_id': False,
-                'has_dates': False,
-                'error': None
-            }
-            
-            try:
-                # Check if file exists
-                if not await async_file_exists(nfo_path):
-                    file_result['error'] = 'File does not exist'
-                    return file_result
-                
-                file_result['exists'] = True
-                
-                # Try to parse NFO
-                root = await async_read_nfo_file(nfo_path)
-                if root is None:
-                    file_result['error'] = 'Failed to parse XML'
-                    return file_result
-                
-                file_result['valid_xml'] = True
-                
-                # Check for IMDb ID
-                imdb_id = extract_imdb_from_nfo_content(root)
-                file_result['has_imdb_id'] = bool(imdb_id)
-                
-                # Check for dates
-                dates = extract_dates_from_nfo(root)
-                file_result['has_dates'] = any(dates.values())
-                
-            except Exception as e:
-                file_result['error'] = str(e)
-            
-            return file_result
-        
-        # Validate all files concurrently
-        semaphore = asyncio.Semaphore(max_concurrent)
-        
-        async def _validate_with_semaphore(nfo_path: Path) -> Dict[str, Any]:
-            async with semaphore:
-                return await _validate_single_nfo(nfo_path)
-        
-        tasks = [_validate_with_semaphore(nfo_path) for nfo_path in nfo_paths]
-        file_results = await asyncio.gather(*tasks, return_exceptions=True)
-        
-        # Process results
-        for i, result in enumerate(file_results):
-            if isinstance(result, dict):
-                path_str = str(nfo_paths[i])
-                results['file_results'][path_str] = result
-                
-                if not result['exists']:
-                    results['missing_files'] += 1
-                elif result['valid_xml']:
-                    results['valid_files'] += 1
-                else:
-                    results['invalid_files'] += 1
-                
-                if result.get('error'):
-                    results['validation_errors'].append(f"{path_str}: {result['error']}")
-        
-        return results

core/database.py

@@ -108,6 +108,8 @@ class NFOGuardDatabase:
         cursor.execute("""
             CREATE TABLE IF NOT EXISTS movies (
                 imdb_id VARCHAR(20) PRIMARY KEY,
+                title TEXT,
+                year INTEGER,
                 path TEXT NOT NULL,
                 released DATE,
                 dateadded TIMESTAMP,
@@ -116,6 +118,44 @@ class NFOGuardDatabase:
                 has_video_file BOOLEAN DEFAULT FALSE
             )
         """)
+
+        # Add title and year columns if they don't exist (migration for existing databases)
+        cursor.execute("""
+            DO $$
+            BEGIN
+                IF NOT EXISTS (SELECT 1 FROM information_schema.columns
+                              WHERE table_name='movies' AND column_name='title') THEN
+                    ALTER TABLE movies ADD COLUMN title TEXT;
+                END IF;
+                IF NOT EXISTS (SELECT 1 FROM information_schema.columns
+                              WHERE table_name='movies' AND column_name='year') THEN
+                    ALTER TABLE movies ADD COLUMN year INTEGER;
+                END IF;
+            END $$;
+        """)
+
+        # Add skipped and skip_reason columns if they don't exist (migration for skip tracking)
+        cursor.execute("""
+            DO $$
+            BEGIN
+                IF NOT EXISTS (SELECT 1 FROM information_schema.columns
+                              WHERE table_name='movies' AND column_name='skipped') THEN
+                    ALTER TABLE movies ADD COLUMN skipped BOOLEAN DEFAULT FALSE;
+                END IF;
+                IF NOT EXISTS (SELECT 1 FROM information_schema.columns
+                              WHERE table_name='movies' AND column_name='skip_reason') THEN
+                    ALTER TABLE movies ADD COLUMN skip_reason TEXT;
+                END IF;
+                IF NOT EXISTS (SELECT 1 FROM information_schema.columns
+                              WHERE table_name='episodes' AND column_name='skipped') THEN
+                    ALTER TABLE episodes ADD COLUMN skipped BOOLEAN DEFAULT FALSE;
+                END IF;
+                IF NOT EXISTS (SELECT 1 FROM information_schema.columns
+                              WHERE table_name='episodes' AND column_name='skip_reason') THEN
+                    ALTER TABLE episodes ADD COLUMN skip_reason TEXT;
+                END IF;
+            END $$;
+        """)
         
         # Processing history table
         cursor.execute("""
@@ -254,26 +294,29 @@ class NFOGuardDatabase:
                     last_updated = EXCLUDED.last_updated
             """, (imdb_id, path, timestamp))
     
-    def upsert_movie_dates(self, imdb_id: str, released: Optional[str], 
-                          dateadded: Optional[str], source: str, has_video_file: bool = False):
+    def upsert_movie_dates(self, imdb_id: str, released: Optional[str],
+                          dateadded: Optional[str], source: str, has_video_file: bool = False,
+                          title: Optional[str] = None, year: Optional[int] = None):
         """Insert or update movie date record"""
         import os
         if os.environ.get("DEBUG", "false").lower() == "true":
-            print(f"🔍 DATABASE UPSERT: imdb_id={imdb_id}, dateadded={dateadded}, source={source}")
+            print(f"🔍 DATABASE UPSERT: imdb_id={imdb_id}, title={title}, dateadded={dateadded}, source={source}")
         with self.get_connection() as conn:
             cursor = conn.cursor()
             timestamp = datetime.utcnow()
-            
+
             cursor.execute("""
-                INSERT INTO movies (imdb_id, path, released, dateadded, source, has_video_file, last_updated)
-                VALUES (%s, COALESCE((SELECT path FROM movies WHERE imdb_id = %s), 'unknown'), %s, %s, %s, %s, %s)
+                INSERT INTO movies (imdb_id, title, year, path, released, dateadded, source, has_video_file, last_updated)
+                VALUES (%s, %s, %s, COALESCE((SELECT path FROM movies WHERE imdb_id = %s), 'unknown'), %s, %s, %s, %s, %s)
                 ON CONFLICT (imdb_id) DO UPDATE SET
+                    title = EXCLUDED.title,
+                    year = EXCLUDED.year,
                     released = EXCLUDED.released,
                     dateadded = EXCLUDED.dateadded,
                     source = EXCLUDED.source,
                     has_video_file = EXCLUDED.has_video_file,
                     last_updated = EXCLUDED.last_updated
-            """, (imdb_id, imdb_id, released, dateadded, source, has_video_file, timestamp))
+            """, (imdb_id, title, year, imdb_id, released, dateadded, source, has_video_file, timestamp))
             
             # Debug: Check what was actually saved
             cursor.execute("SELECT dateadded, source FROM movies WHERE imdb_id = %s", (imdb_id,))
@@ -281,7 +324,75 @@ class NFOGuardDatabase:
             import os
             if os.environ.get("DEBUG", "false").lower() == "true":
                 print(f"🔍 DATABASE VERIFY: After upsert, found dateadded={result['dateadded'] if result else 'NOT_FOUND'}, source={result['source'] if result else 'NOT_FOUND'}")
-    
+
+    def mark_movie_skipped(self, imdb_id: str, title: str, year: int, path: str, reason: str):
+        """Mark a movie as skipped with reason"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            timestamp = datetime.utcnow()
+            cursor.execute("""
+                INSERT INTO movies (imdb_id, title, year, path, skipped, skip_reason, has_video_file, last_updated)
+                VALUES (%s, %s, %s, %s, TRUE, %s, FALSE, %s)
+                ON CONFLICT (imdb_id) DO UPDATE SET
+                    title = EXCLUDED.title,
+                    year = EXCLUDED.year,
+                    path = EXCLUDED.path,
+                    skipped = TRUE,
+                    skip_reason = EXCLUDED.skip_reason,
+                    last_updated = EXCLUDED.last_updated
+            """, (imdb_id, title, year, path, reason, timestamp))
+
+    def mark_episode_skipped(self, imdb_id: str, season: int, episode: int, reason: str):
+        """Mark an episode as skipped with reason"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            timestamp = datetime.utcnow()
+            cursor.execute("""
+                INSERT INTO episodes (imdb_id, season, episode, skipped, skip_reason, has_video_file, last_updated)
+                VALUES (%s, %s, %s, TRUE, %s, FALSE, %s)
+                ON CONFLICT (imdb_id, season, episode) DO UPDATE SET
+                    skipped = TRUE,
+                    skip_reason = EXCLUDED.skip_reason,
+                    last_updated = EXCLUDED.last_updated
+            """, (imdb_id, season, episode, reason, timestamp))
+
+    def clear_movie_skipped(self, imdb_id: str):
+        """Clear skipped flag for a movie"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute("""
+                UPDATE movies SET skipped = FALSE, skip_reason = NULL
+                WHERE imdb_id = %s
+            """, (imdb_id,))
+
+    def clear_episode_skipped(self, imdb_id: str, season: int, episode: int):
+        """Clear skipped flag for an episode"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute("""
+                UPDATE episodes SET skipped = FALSE, skip_reason = NULL
+                WHERE imdb_id = %s AND season = %s AND episode = %s
+            """, (imdb_id, season, episode))
+
+    def get_skipped_counts(self) -> Dict:
+        """Get counts of skipped movies and episodes"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+
+            # Count skipped movies
+            cursor.execute("SELECT COUNT(*) as count FROM movies WHERE skipped = TRUE")
+            skipped_movies = cursor.fetchone()['count']
+
+            # Count skipped episodes
+            cursor.execute("SELECT COUNT(*) as count FROM episodes WHERE skipped = TRUE")
+            skipped_episodes = cursor.fetchone()['count']
+
+            return {
+                'movies': skipped_movies,
+                'episodes': skipped_episodes,
+                'total': skipped_movies + skipped_episodes
+            }
+
     def get_series_episodes(self, imdb_id: str, has_video_file_only: bool = False) -> List[Dict]:
         """Get all episodes for a series"""
         with self.get_connection() as conn:
@@ -326,6 +437,81 @@ class NFOGuardDatabase:
             """, (imdb_id, media_type, event_type, datetime.utcnow().isoformat(), 
                   json.dumps(details) if details else None))
     
+    def migrate_movie_imdb_id(self, old_imdb_id: str, new_imdb_id: str) -> bool:
+        """Migrate a movie from placeholder IMDb ID to real IMDb ID"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+
+            # Check if old record exists
+            cursor.execute("SELECT * FROM movies WHERE imdb_id = %s", (old_imdb_id,))
+            old_record = cursor.fetchone()
+            if not old_record:
+                return False
+
+            old_data = dict(old_record)
+
+            # Check if new IMDb ID already exists
+            cursor.execute("SELECT * FROM movies WHERE imdb_id = %s", (new_imdb_id,))
+            if cursor.fetchone():
+                # New IMDb ID already exists, just delete the old one
+                cursor.execute("DELETE FROM movies WHERE imdb_id = %s", (old_imdb_id,))
+                return True
+
+            # Create new record with correct IMDb ID
+            cursor.execute("""
+                INSERT INTO movies (imdb_id, title, year, path, released, dateadded, source,
+                                   has_video_file, last_updated, skipped, skip_reason)
+                VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
+            """, (new_imdb_id, old_data.get('title'), old_data.get('year'),
+                  old_data.get('path'), old_data.get('released'), old_data.get('dateadded'),
+                  old_data.get('source'), old_data.get('has_video_file'),
+                  datetime.utcnow(), False, None))  # Clear skipped status
+
+            # Delete old placeholder record
+            cursor.execute("DELETE FROM movies WHERE imdb_id = %s", (old_imdb_id,))
+            return True
+
+    def migrate_series_imdb_id(self, old_imdb_id: str, new_imdb_id: str) -> bool:
+        """Migrate a series and all its episodes from placeholder IMDb ID to real IMDb ID"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+
+            # Check if old series exists
+            cursor.execute("SELECT * FROM series WHERE imdb_id = %s", (old_imdb_id,))
+            old_series = cursor.fetchone()
+            if not old_series:
+                return False
+
+            old_series_data = dict(old_series)
+
+            # Check if new series IMDb ID already exists
+            cursor.execute("SELECT * FROM series WHERE imdb_id = %s", (new_imdb_id,))
+            if cursor.fetchone():
+                # New series already exists, migrate episodes and delete old series
+                cursor.execute("""
+                    UPDATE episodes SET imdb_id = %s WHERE imdb_id = %s
+                """, (new_imdb_id, old_imdb_id))
+                cursor.execute("DELETE FROM series WHERE imdb_id = %s", (old_imdb_id,))
+                return True
+
+            # Create new series record
+            cursor.execute("""
+                INSERT INTO series (imdb_id, path, last_updated, metadata)
+                VALUES (%s, %s, %s, %s)
+            """, (new_imdb_id, old_series_data.get('path'),
+                  datetime.utcnow(), old_series_data.get('metadata')))
+
+            # Migrate all episodes to new series IMDb ID and clear skipped status
+            cursor.execute("""
+                UPDATE episodes
+                SET imdb_id = %s, skipped = FALSE, skip_reason = NULL
+                WHERE imdb_id = %s
+            """, (new_imdb_id, old_imdb_id))
+
+            # Delete old placeholder series
+            cursor.execute("DELETE FROM series WHERE imdb_id = %s", (old_imdb_id,))
+            return True
+
     def get_stats(self) -> Dict[str, Any]:
         """Get database statistics"""
         with self.get_connection() as conn:
@@ -531,7 +717,68 @@ class NFOGuardDatabase:
             conn.commit()
             
             return deleted_count > 0
-    
+
+    def update_movie_file_info(self, imdb_id: str, path: str, has_video_file: bool = True) -> bool:
+        """
+        Update path and video file status for an existing movie
+        Used when population finds a video file for a manually-added movie
+
+        Args:
+            imdb_id: Movie IMDb ID
+            path: File path to the video file
+            has_video_file: Whether a video file exists (default True)
+
+        Returns:
+            True if movie was updated, False if not found
+        """
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+
+            cursor.execute("""
+                UPDATE movies
+                SET path = %s,
+                    has_video_file = %s,
+                    last_updated = %s
+                WHERE imdb_id = %s
+            """, (path, has_video_file, datetime.utcnow(), imdb_id))
+
+            updated_count = cursor.rowcount
+            conn.commit()
+
+            return updated_count > 0
+
+    def update_episode_file_info(self, imdb_id: str, season: int, episode: int,
+                                  path: str, has_video_file: bool = True) -> bool:
+        """
+        Update path and video file status for an existing episode
+        Used when population finds a video file for a manually-added episode
+
+        Args:
+            imdb_id: Series IMDb ID
+            season: Season number
+            episode: Episode number
+            path: File path to the video file
+            has_video_file: Whether a video file exists (default True)
+
+        Returns:
+            True if episode was updated, False if not found
+        """
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+
+            cursor.execute("""
+                UPDATE episodes
+                SET path = %s,
+                    has_video_file = %s,
+                    last_updated = %s
+                WHERE imdb_id = %s AND season = %s AND episode = %s
+            """, (path, has_video_file, datetime.utcnow(), imdb_id, season, episode))
+
+            updated_count = cursor.rowcount
+            conn.commit()
+
+            return updated_count > 0
+
     def delete_orphaned_movies(self) -> List[Dict]:
         """
         Find and delete movies that don't have corresponding video files on disk

core/database_populator.py

@@ -0,0 +1,476 @@
+#!/usr/bin/env python3
+"""
+Database Populator for NFOGuard
+Bulk populates the NFOGuard database from Radarr/Sonarr
+Phase 4: Replace NFO-based initial population with direct DB/API queries
+"""
+import time
+import hashlib
+from typing import Dict, List, Optional, Tuple
+from datetime import datetime
+from pathlib import Path
+
+from core.database import NFOGuardDatabase
+from clients.radarr_client import RadarrClient
+from clients.sonarr_client import SonarrClient
+from utils.logging import _log
+from utils.imdb_utils import parse_imdb_from_path
+
+
+class DatabasePopulator:
+    """Populates NFOGuard database from Radarr/Sonarr sources"""
+
+    def __init__(self, db: NFOGuardDatabase, radarr_client: RadarrClient, sonarr_client: SonarrClient):
+        self.db = db
+        self.radarr = radarr_client
+        self.sonarr = sonarr_client
+
+    def populate_movies(self) -> Dict[str, any]:
+        """
+        Populate movies from Radarr database/API
+
+        Returns:
+            Dictionary with statistics: {
+                'total': int,
+                'added': int,
+                'updated': int,
+                'skipped': int,
+                'errors': int,
+                'duration': float
+            }
+        """
+        _log("INFO", "Starting movie population from Radarr")
+        start_time = time.time()
+
+        stats = {
+            'total': 0,
+            'added': 0,
+            'updated': 0,
+            'skipped': 0,
+            'errors': 0,
+            'duration': 0.0,
+            'skipped_items': []  # Track what was skipped and why
+        }
+
+        try:
+            # Get all movies from Radarr database
+            if not hasattr(self.radarr, 'db_client') or not self.radarr.db_client:
+                _log("ERROR", "Radarr database client not available - cannot populate movies")
+                stats['errors'] += 1
+                return stats
+
+            movies = self.radarr.db_client.get_all_movies()
+            if not movies:
+                _log("WARNING", "No movies found in Radarr database")
+                return stats
+
+            stats['total'] = len(movies)
+            _log("INFO", f"Found {stats['total']} movies in Radarr")
+
+            # Process each movie
+            for movie in movies:
+                try:
+                    # Get movie path first (we'll need it for IMDb extraction)
+                    path = movie.get('path', '')
+
+                    # Try to get IMDb ID from Radarr database
+                    imdb_id = movie.get('imdb_id')
+
+                    # If not in database, try extracting from directory/filename
+                    if not imdb_id and path:
+                        imdb_id = parse_imdb_from_path(Path(path))
+                        if imdb_id:
+                            _log("DEBUG", f"Extracted IMDb ID {imdb_id} from path for: {movie.get('title')}")
+
+                    if not imdb_id:
+                        # Generate placeholder IMDb ID using hash of path
+                        path_hash = hashlib.md5(path.encode()).hexdigest()[:12]
+                        imdb_id = f"missing-{path_hash}"
+                        skip_reason = 'No IMDb ID found'
+                        skip_info = {
+                            'title': movie.get('title', 'Unknown'),
+                            'year': movie.get('year'),
+                            'imdb_id': imdb_id,
+                            'path': path,
+                            'reason': skip_reason
+                        }
+                        stats['skipped_items'].append(skip_info)
+                        _log("DEBUG", f"Movie without IMDb ID: {movie.get('title')} (path: {path}), using placeholder {imdb_id}")
+
+                        # Mark as skipped in database with placeholder IMDb ID
+                        self.db.mark_movie_skipped(
+                            imdb_id=imdb_id,
+                            title=movie.get('title', 'Unknown'),
+                            year=movie.get('year', 0),
+                            path=path,
+                            reason=skip_reason
+                        )
+                        stats['skipped'] += 1
+                        continue
+
+                    # Check if movie already exists in database
+                    existing = self.db.get_movie_dates(imdb_id)
+                    if existing and existing.get('dateadded'):
+                        # Already in database - update file path and video status if needed
+                        existing_path = existing.get('path')
+                        if not existing_path or existing_path == 'unknown' or existing_path != path:
+                            _log("INFO", f"Movie {imdb_id} exists but updating file info: {path}")
+                            self.db.update_movie_file_info(imdb_id, path, has_video_file=True)
+
+                            # Add to processing history
+                            try:
+                                self.db.add_processing_history(
+                                    imdb_id=imdb_id,
+                                    media_type='movie',
+                                    event_type='file_info_update',
+                                    details={'path': path}
+                                )
+                            except Exception as e:
+                                _log("WARNING", f"Failed to add processing history for {imdb_id}: {e}")
+
+                            stats['updated'] += 1
+                        else:
+                            _log("DEBUG", f"Movie {imdb_id} already in database with correct path, skipping")
+                        continue
+
+                    # Get release date
+                    released = None
+                    if movie.get('digital_release'):
+                        released = movie.get('digital_release')
+                        source_type = 'radarr:digital'
+                    elif movie.get('physical_release'):
+                        released = movie.get('physical_release')
+                        source_type = 'radarr:physical'
+                    elif movie.get('in_cinemas'):
+                        released = movie.get('in_cinemas')
+                        source_type = 'radarr:theatrical'
+                    else:
+                        source_type = 'radarr:unknown'
+
+                    # Get import date from Radarr history using Radarr's internal movie ID
+                    radarr_movie_id = movie.get('id')
+                    if radarr_movie_id:
+                        # get_movie_import_date returns tuple (date, source)
+                        import_date, import_source = self.radarr.get_movie_import_date(radarr_movie_id)
+                        if import_date:
+                            dateadded = import_date
+                            source = import_source
+                        elif released:
+                            # Use release date as fallback
+                            dateadded = released
+                            source = f'{source_type}_fallback'
+                        else:
+                            skip_reason = 'No import date in Radarr history and no release dates available'
+                            skip_info = {
+                                'title': movie.get('title', 'Unknown'),
+                                'year': movie.get('year'),
+                                'imdb_id': imdb_id,
+                                'reason': skip_reason
+                            }
+                            stats['skipped_items'].append(skip_info)
+                            _log("DEBUG", f"No date available for movie {imdb_id}, skipping")
+
+                            # Mark as skipped in database for troubleshooting
+                            self.db.mark_movie_skipped(
+                                imdb_id=imdb_id,
+                                title=movie.get('title', 'Unknown'),
+                                year=movie.get('year', 0),
+                                path=path or 'unknown',
+                                reason=skip_reason
+                            )
+                            stats['skipped'] += 1
+                            continue
+                    elif released:
+                        # No Radarr ID, use release date
+                        dateadded = released
+                        source = f'{source_type}_fallback'
+                    else:
+                        skip_reason = 'No Radarr movie ID and no release dates available'
+                        skip_info = {
+                            'title': movie.get('title', 'Unknown'),
+                            'year': movie.get('year'),
+                            'imdb_id': imdb_id,
+                            'reason': skip_reason
+                        }
+                        stats['skipped_items'].append(skip_info)
+                        _log("DEBUG", f"No date available for movie {imdb_id}, skipping")
+
+                        # Mark as skipped in database for troubleshooting
+                        self.db.mark_movie_skipped(
+                            imdb_id=imdb_id,
+                            title=movie.get('title', 'Unknown'),
+                            year=movie.get('year', 0),
+                            path=path or 'unknown',
+                            reason=skip_reason
+                        )
+                        stats['skipped'] += 1
+                        continue
+
+                    # Insert into database with title and year
+                    title = movie.get('title')
+                    year = movie.get('year')
+                    self.db.upsert_movie_dates(
+                        imdb_id, released, dateadded, source,
+                        has_video_file=True, title=title, year=year
+                    )
+
+                    # Add to processing history
+                    try:
+                        self.db.add_processing_history(
+                            imdb_id=imdb_id,
+                            media_type='movie',
+                            event_type='database_population',
+                            details={'source': source, 'title': title}
+                        )
+                    except Exception as e:
+                        _log("WARNING", f"Failed to add processing history for {imdb_id}: {e}")
+
+                    stats['added'] += 1
+                    _log("DEBUG", f"Added movie {imdb_id}: {title} ({year}) (source: {source})")
+
+                except Exception as e:
+                    _log("ERROR", f"Error processing movie {movie.get('title', 'unknown')}: {e}")
+                    stats['errors'] += 1
+                    continue
+
+        except Exception as e:
+            _log("ERROR", f"Error during movie population: {e}")
+            stats['errors'] += 1
+
+        stats['duration'] = time.time() - start_time
+        _log("INFO", f"Movie population complete: {stats['added']} added, {stats['skipped']} skipped, {stats['errors']} errors in {stats['duration']:.2f}s")
+
+        # Log details of skipped items
+        if stats['skipped_items']:
+            _log("INFO", f"Skipped items details ({len(stats['skipped_items'])} total):")
+            for item in stats['skipped_items']:
+                _log("INFO", f"  - {item['title']} ({item.get('year', 'N/A')}) [{item.get('imdb_id', 'No IMDb')}]: {item['reason']}")
+
+        return stats
+
+    def populate_tv_episodes(self) -> Dict[str, any]:
+        """
+        Populate TV episodes from Sonarr API
+
+        Returns:
+            Dictionary with statistics: {
+                'total_series': int,
+                'total_episodes': int,
+                'added': int,
+                'updated': int,
+                'skipped': int,
+                'errors': int,
+                'duration': float
+            }
+        """
+        _log("INFO", "Starting TV episode population from Sonarr")
+        start_time = time.time()
+
+        stats = {
+            'total_series': 0,
+            'total_episodes': 0,
+            'added': 0,
+            'updated': 0,
+            'skipped': 0,
+            'errors': 0,
+            'duration': 0.0,
+            'skipped_items': []  # Track what was skipped and why
+        }
+
+        try:
+            # Get all series from Sonarr
+            all_series = self.sonarr.get_all_series()
+            if not all_series:
+                _log("WARNING", "No series found in Sonarr")
+                return stats
+
+            stats['total_series'] = len(all_series)
+            _log("INFO", f"Found {stats['total_series']} series in Sonarr")
+
+            # Process each series
+            for series in all_series:
+                try:
+                    imdb_id = series.get('imdbId')
+                    series_id = series.get('id')
+                    series_path = series.get('path', '')
+                    series_title = series.get('title', 'Unknown')
+
+                    if not imdb_id:
+                        # Generate placeholder IMDb ID using hash of path
+                        path_hash = hashlib.md5(series_path.encode()).hexdigest()[:12]
+                        imdb_id = f"missing-{path_hash}"
+                        _log("DEBUG", f"Series without IMDb ID: {series_title} (path: {series_path}), using placeholder {imdb_id}")
+
+                    # Update series record
+                    self.db.upsert_series(imdb_id, series_path)
+
+                    # Try high-performance database bulk query first
+                    sonarr_db = getattr(self.sonarr, 'db_client', None)
+                    bulk_import_dates = {}
+
+                    if sonarr_db:
+                        try:
+                            _log("DEBUG", f"Using DB bulk query for {series_title}")
+                            bulk_import_dates = sonarr_db.bulk_import_dates_for_series(series_id)
+                            _log("DEBUG", f"✅ Got {len(bulk_import_dates)} import dates from DB for {series_title}")
+                        except Exception as e:
+                            _log("WARNING", f"DB bulk query failed for {series_title}, falling back to API: {e}")
+
+                    # Get all episodes for this series
+                    episodes = self.sonarr.episodes_for_series(series_id)
+                    if not episodes:
+                        continue
+
+                    _log("DEBUG", f"Processing {len(episodes)} episodes for {series_title}")
+
+                    # Process each episode
+                    for episode in episodes:
+                        try:
+                            season_num = episode.get('seasonNumber', 0)
+                            episode_num = episode.get('episodeNumber', 0)
+                            episode_title = episode.get('title', 'Unknown')
+
+                            if season_num < 0 or episode_num <= 0:
+                                continue
+
+                            stats['total_episodes'] += 1
+
+                            # Check if episode already exists
+                            existing = self.db.get_episode_date(imdb_id, season_num, episode_num)
+                            if existing and existing.get('dateadded'):
+                                # Already in database - update file path and video status if needed
+                                existing_path = existing.get('path')
+                                episode_path = episode.get('path', 'unknown')
+                                if not existing_path or existing_path == 'unknown' or existing_path != episode_path:
+                                    _log("INFO", f"Episode {imdb_id} S{season_num:02d}E{episode_num:02d} exists but updating file info: {episode_path}")
+                                    self.db.update_episode_file_info(imdb_id, season_num, episode_num, episode_path, has_video_file=True)
+
+                                    # Add to processing history
+                                    try:
+                                        self.db.add_processing_history(
+                                            imdb_id=imdb_id,
+                                            media_type='episode',
+                                            event_type='file_info_update',
+                                            details={'season': season_num, 'episode': episode_num, 'path': episode_path}
+                                        )
+                                    except Exception as e:
+                                        _log("WARNING", f"Failed to add processing history for {imdb_id} S{season_num:02d}E{episode_num:02d}: {e}")
+
+                                    stats['updated'] += 1
+                                continue
+
+                            # Only process episodes that have video files
+                            has_file = episode.get('hasFile', False)
+                            if not has_file:
+                                # No video file - skip silently (intentionally filtered)
+                                continue
+
+                            # Get air date
+                            aired = episode.get('airDate')
+
+                            # Get import date
+                            dateadded = None
+                            source = None
+
+                            # Try bulk DB result first
+                            if (season_num, episode_num) in bulk_import_dates:
+                                dateadded, source = bulk_import_dates[(season_num, episode_num)]
+                            # Fall back to API query
+                            else:
+                                episode_id = episode.get('id')
+                                if episode_id:
+                                    import_date = self.sonarr.get_episode_import_history(episode_id)
+                                    if import_date:
+                                        dateadded = import_date
+                                        source = 'sonarr:api.import_history'
+
+                            # Fallback to air date if no import date
+                            if not dateadded and aired:
+                                dateadded = aired
+                                source = 'sonarr:aired_fallback'
+                            elif not dateadded:
+                                # No date available
+                                skip_reason = 'No import date from Sonarr history and no air date available'
+                                skip_info = {
+                                    'title': series_title,
+                                    'episode_title': episode_title,
+                                    'season': season_num,
+                                    'episode': episode_num,
+                                    'reason': skip_reason
+                                }
+                                stats['skipped_items'].append(skip_info)
+
+                                # Mark as skipped in database for troubleshooting
+                                self.db.mark_episode_skipped(
+                                    imdb_id=imdb_id,
+                                    season=season_num,
+                                    episode=episode_num,
+                                    reason=skip_reason
+                                )
+                                stats['skipped'] += 1
+                                continue
+
+                            # Insert into database
+                            self.db.upsert_episode_date(imdb_id, season_num, episode_num, aired, dateadded, source, has_file)
+
+                            # Add to processing history
+                            try:
+                                self.db.add_processing_history(
+                                    imdb_id=imdb_id,
+                                    media_type='episode',
+                                    event_type='database_population',
+                                    details={'season': season_num, 'episode': episode_num, 'source': source, 'title': episode_title}
+                                )
+                            except Exception as e:
+                                _log("WARNING", f"Failed to add processing history for {imdb_id} S{season_num:02d}E{episode_num:02d}: {e}")
+
+                            stats['added'] += 1
+
+                        except Exception as e:
+                            _log("ERROR", f"Error processing episode S{season_num:02d}E{episode_num:02d} of {series_title}: {e}")
+                            stats['errors'] += 1
+                            continue
+
+                except Exception as e:
+                    _log("ERROR", f"Error processing series {series.get('title', 'unknown')}: {e}")
+                    stats['errors'] += 1
+                    continue
+
+        except Exception as e:
+            _log("ERROR", f"Error during TV episode population: {e}")
+            stats['errors'] += 1
+
+        stats['duration'] = time.time() - start_time
+        _log("INFO", f"TV episode population complete: {stats['added']} added, {stats['skipped']} skipped, {stats['errors']} errors in {stats['duration']:.2f}s")
+
+        # Log details of skipped items
+        if stats['skipped_items']:
+            _log("INFO", f"Skipped episodes details ({len(stats['skipped_items'])} total):")
+            for item in stats['skipped_items'][:20]:  # Only log first 20 to avoid spam
+                _log("INFO", f"  - {item['title']} S{str(item['season']).zfill(2)}E{str(item['episode']).zfill(2)} ({item.get('episode_title', 'Unknown')}): {item['reason']}")
+            if len(stats['skipped_items']) > 20:
+                _log("INFO", f"  ... and {len(stats['skipped_items']) - 20} more (see web interface for full list)")
+
+        return stats
+
+    def populate_all(self) -> Dict[str, any]:
+        """
+        Populate both movies and TV episodes
+
+        Returns:
+            Combined statistics dictionary
+        """
+        _log("INFO", "Starting full database population")
+        start_time = time.time()
+
+        movie_stats = self.populate_movies()
+        tv_stats = self.populate_tv_episodes()
+
+        combined_stats = {
+            'movies': movie_stats,
+            'tv': tv_stats,
+            'total_duration': time.time() - start_time
+        }
+
+        _log("INFO", f"Full database population complete in {combined_stats['total_duration']:.2f}s")
+        return combined_stats

core/episode_nfo_manager.py

@@ -1,276 +0,0 @@
-#!/usr/bin/env python3
-"""
-Episode NFO Manager - Handles TV episode NFO creation with video filename matching
-Core principle: NFO filenames should match video filenames
-"""
-import xml.etree.ElementTree as ET
-from pathlib import Path
-from typing import Optional, Dict, Any, List, Tuple
-import re
-from .logging import _log
-
-
-class EpisodeNFOManager:
-    """Manages episode NFO files with video filename matching"""
-    
-    def __init__(self, manager_brand: str = "NFOGuard"):
-        self.manager_brand = manager_brand
-    
-    def find_video_files_for_season(self, season_dir: Path) -> Dict[Tuple[int, int], List[Path]]:
-        """Find all video files in season directory, grouped by (season, episode)"""
-        if not season_dir.exists():
-            _log("DEBUG", f"Season directory does not exist: {season_dir}")
-            return {}
-        
-        video_extensions = [".mkv", ".mp4", ".avi", ".mov", ".m4v"]
-        episodes = {}
-        
-        _log("DEBUG", f"Scanning video files in: {season_dir}")
-        for video_file in season_dir.iterdir():
-            _log("DEBUG", f"Checking file: {video_file.name} (is_file: {video_file.is_file()}, suffix: {video_file.suffix.lower()})")
-            if (video_file.is_file() and 
-                video_file.suffix.lower() in video_extensions):
-                
-                episode_info = self._parse_episode_from_filename(video_file.name)
-                _log("DEBUG", f"Episode parsing for '{video_file.name}': {episode_info}")
-                if episode_info:
-                    season_num, episode_num = episode_info
-                    key = (season_num, episode_num)
-                    if key not in episodes:
-                        episodes[key] = []
-                    episodes[key].append(video_file)
-                    _log("DEBUG", f"Added video file: S{season_num:02d}E{episode_num:02d} → {video_file.name}")
-        
-        _log("DEBUG", f"Total video files found: {len(episodes)} episodes")
-        return episodes
-    
-    def _parse_episode_from_filename(self, filename: str) -> Optional[Tuple[int, int]]:
-        """Extract season and episode numbers from filename"""
-        # Try S##E## format first (most common)
-        match = re.search(r'[Ss](\d{1,2})[Ee](\d{1,2})', filename)
-        if match:
-            return int(match.group(1)), int(match.group(2))
-        
-        # Try ##x## format  
-        match = re.search(r'(\d{1,2})x(\d{1,2})', filename)
-        if match:
-            return int(match.group(1)), int(match.group(2))
-        
-        return None
-    
-    def find_nfo_for_episode(self, season_dir: Path, season_num: int, episode_num: int) -> Optional[Path]:
-        """Find existing NFO file for episode (prefer video-matching filename)"""
-        if not season_dir.exists():
-            return None
-        
-        # First, look for NFO files that match video filenames
-        video_files = self.find_video_files_for_season(season_dir)
-        key = (season_num, episode_num)
-        
-        if key in video_files:
-            for video_file in video_files[key]:
-                potential_nfo = season_dir / f"{video_file.stem}.nfo"
-                if potential_nfo.exists():
-                    _log("DEBUG", f"Found video-matching NFO: {potential_nfo.name}")
-                    return potential_nfo
-        
-        # Fallback: look for short name NFO
-        short_nfo = season_dir / f"S{season_num:02d}E{episode_num:02d}.nfo"
-        if short_nfo.exists():
-            _log("DEBUG", f"Found short-name NFO: {short_nfo.name}")
-            return short_nfo
-        
-        # Last resort: search all NFO files for matching season/episode data
-        for nfo_file in season_dir.glob("*.nfo"):
-            if self._nfo_matches_episode(nfo_file, season_num, episode_num):
-                _log("DEBUG", f"Found matching NFO by content: {nfo_file.name}")
-                return nfo_file
-        
-        return None
-    
-    def _nfo_matches_episode(self, nfo_path: Path, season_num: int, episode_num: int) -> bool:
-        """Check if NFO file contains the specified season/episode"""
-        try:
-            tree = ET.parse(nfo_path)
-            root = tree.getroot()
-            
-            if root.tag == "episodedetails":
-                season_elem = root.find("season")
-                episode_elem = root.find("episode")
-                
-                if (season_elem is not None and episode_elem is not None and
-                    season_elem.text and episode_elem.text):
-                    try:
-                        file_season = int(season_elem.text)
-                        file_episode = int(episode_elem.text)
-                        return file_season == season_num and file_episode == episode_num
-                    except ValueError:
-                        pass
-        except (ET.ParseError, Exception):
-            pass
-        
-        return False
-    
-    def get_target_nfo_path(self, season_dir: Path, season_num: int, episode_num: int) -> Path:
-        """Get the target NFO path (prefer video filename, fallback to short name)"""
-        video_files = self.find_video_files_for_season(season_dir)
-        key = (season_num, episode_num)
-        
-        if key in video_files and video_files[key]:
-            # Use the first video file found (handle multiple files gracefully)
-            video_file = video_files[key][0]
-            target_nfo = season_dir / f"{video_file.stem}.nfo"
-            _log("DEBUG", f"Target NFO will match video: {target_nfo.name}")
-            return target_nfo
-        else:
-            # Fallback to short name if no video file found
-            target_nfo = season_dir / f"S{season_num:02d}E{episode_num:02d}.nfo"
-            _log("WARNING", f"No video file found for S{season_num:02d}E{episode_num:02d}, using short name: {target_nfo.name}")
-            return target_nfo
-    
-    def migrate_nfo_to_video_filename(self, season_dir: Path, season_num: int, episode_num: int) -> bool:
-        """If short-name NFO exists, rename it to match video filename"""
-        existing_nfo = self.find_nfo_for_episode(season_dir, season_num, episode_num)
-        target_nfo = self.get_target_nfo_path(season_dir, season_num, episode_num)
-        
-        # If we already have the right filename, nothing to do
-        if existing_nfo and existing_nfo == target_nfo:
-            return True
-        
-        # If we have an NFO but it doesn't match target, rename it
-        if existing_nfo and existing_nfo != target_nfo:
-            try:
-                _log("INFO", f"Migrating NFO filename: {existing_nfo.name} -> {target_nfo.name}")
-                existing_nfo.rename(target_nfo)
-                return True
-            except Exception as e:
-                _log("ERROR", f"Failed to rename NFO: {e}")
-                return False
-        
-        return False
-    
-    def create_episode_nfo(self, season_dir: Path, season_num: int, episode_num: int,
-                          aired: Optional[str], dateadded: Optional[str], source: str,
-                          title: Optional[str] = None, plot: Optional[str] = None) -> bool:
-        """Create or update episode NFO with video filename matching"""
-        
-        # Get the target NFO path (matching video filename)
-        nfo_path = self.get_target_nfo_path(season_dir, season_num, episode_num)
-        
-        # Migrate existing NFO if needed
-        self.migrate_nfo_to_video_filename(season_dir, season_num, episode_num)
-        
-        try:
-            # Load existing NFO if it exists
-            episode_elem = None
-            if nfo_path.exists():
-                try:
-                    tree = ET.parse(nfo_path)
-                    episode_elem = tree.getroot()
-                    
-                    if episode_elem.tag != "episodedetails":
-                        raise ValueError("Root element is not <episodedetails>")
-                    
-                    # Remove NFOGuard-managed fields (we'll re-add them)
-                    for tag in ["season", "episode", "aired", "premiered", "dateadded", "lockdata"]:
-                        existing = episode_elem.find(tag)
-                        if existing is not None:
-                            episode_elem.remove(existing)
-                    
-                    _log("DEBUG", f"Loaded existing NFO content for {nfo_path.name}")
-                    
-                except (ET.ParseError, ValueError) as e:
-                    _log("WARNING", f"Corrupted NFO file {nfo_path.name}: {e}. Creating new one.")
-                    episode_elem = None
-            
-            # Create new structure if needed
-            if episode_elem is None:
-                episode_elem = ET.Element("episodedetails")
-            
-            # Add title if provided and not already present
-            if title and not episode_elem.find("title"):
-                title_elem = ET.SubElement(episode_elem, "title")
-                title_elem.text = title
-            
-            # Add plot if provided and not already present  
-            if plot and not episode_elem.find("plot"):
-                plot_elem = ET.SubElement(episode_elem, "plot")
-                plot_elem.text = plot
-            
-            # Add NFOGuard fields at the end
-            season_elem = ET.SubElement(episode_elem, "season")
-            season_elem.text = str(season_num)
-            
-            episode_num_elem = ET.SubElement(episode_elem, "episode")
-            episode_num_elem.text = str(episode_num)
-            
-            if aired:
-                aired_elem = ET.SubElement(episode_elem, "aired")
-                aired_elem.text = aired[:10] if len(aired) >= 10 else aired
-                
-                # Also add premiered for compatibility
-                premiered_elem = ET.SubElement(episode_elem, "premiered") 
-                premiered_elem.text = aired[:10] if len(aired) >= 10 else aired
-            
-            if dateadded:
-                dateadded_elem = ET.SubElement(episode_elem, "dateadded")
-                dateadded_elem.text = dateadded
-            
-            # Add lockdata
-            lockdata_elem = ET.SubElement(episode_elem, "lockdata")
-            lockdata_elem.text = "true"
-            
-            # Add comment with source at the bottom
-            comment = ET.Comment(f" Created by {self.manager_brand} - Source: {source} ")
-            episode_elem.append(comment)
-            
-            # Write the NFO file
-            tree = ET.ElementTree(episode_elem)
-            ET.indent(tree, space="  ", level=0)
-            tree.write(nfo_path, encoding='utf-8', xml_declaration=True)
-            
-            _log("INFO", f"✅ Created/updated episode NFO: {nfo_path.name}")
-            _log("INFO", f"   S{season_num:02d}E{episode_num:02d}, Aired: {aired}, DateAdded: {dateadded}, Source: {source}")
-            
-            return True
-            
-        except Exception as e:
-            _log("ERROR", f"Failed to create episode NFO {nfo_path}: {e}")
-            return False
-    
-    def extract_nfoguard_data(self, nfo_path: Path) -> Optional[Dict[str, str]]:
-        """Extract NFOGuard-managed data from existing NFO"""
-        if not nfo_path.exists():
-            return None
-        
-        try:
-            tree = ET.parse(nfo_path)
-            root = tree.getroot()
-            
-            if root.tag != "episodedetails":
-                return None
-            
-            # Look for NFOGuard fields
-            dateadded_elem = root.find("dateadded")
-            aired_elem = root.find("aired")
-            lockdata_elem = root.find("lockdata")
-            
-            # Only consider it NFOGuard-managed if it has dateadded and lockdata
-            if (dateadded_elem is not None and dateadded_elem.text and
-                lockdata_elem is not None and lockdata_elem.text == "true"):
-                
-                result = {
-                    "dateadded": dateadded_elem.text.strip(),
-                    "source": "existing_nfo"
-                }
-                
-                if aired_elem is not None and aired_elem.text:
-                    result["aired"] = aired_elem.text.strip()
-                
-                _log("DEBUG", f"Found NFOGuard data in {nfo_path.name}: {result}")
-                return result
-        
-        except (ET.ParseError, Exception) as e:
-            _log("WARNING", f"Error parsing NFO {nfo_path.name}: {e}")
-        
-        return None

core/nfo_manager.py

@@ -1,890 +0,0 @@
-#!/usr/bin/env python3
-"""
-NFO Manager for creating and managing metadata files
-Handles NFO creation for movies, TV shows, seasons, and episodes
-"""
-import os
-import xml.etree.ElementTree as ET
-from pathlib import Path
-from datetime import datetime
-from typing import Optional, Dict, Any, Tuple
-import re
-
-
-class NFOManager:
-    """Manages NFO file creation and updates"""
-    
-    def __init__(self, manager_brand: str = "NFOGuard", debug: bool = False):
-        self.manager_brand = manager_brand
-        self.debug = debug
-    
-    def parse_imdb_from_path(self, path: Path) -> Optional[str]:
-        """Extract IMDb ID from directory path or filename"""
-        # Look for various IMDb patterns in both directory and file names
-        path_str = str(path).lower()
-        
-        # Try [imdb-ttXXXXXXX] format first (most explicit)
-        match = re.search(r'\[imdb-?(tt\d+)\]', path_str)
-        if match:
-            return match.group(1)
-        
-        # Try standalone [ttXXXXXXX] format in brackets
-        match = re.search(r'\[(tt\d+)\]', path_str)
-        if match:
-            return match.group(1)
-        
-        # Try {imdb-ttXXXXXXX} format with curly braces
-        match = re.search(r'\{imdb-?(tt\d+)\}', path_str)
-        if match:
-            return match.group(1)
-        
-        # Try (imdb-ttXXXXXXX) format with parentheses
-        match = re.search(r'\(imdb-?(tt\d+)\)', path_str)
-        if match:
-            return match.group(1)
-        
-        # Try ttXXXXXXX at end of filename/dirname (common pattern)
-        match = re.search(r'[-_\s](tt\d+)$', path_str)
-        if match:
-            return match.group(1)
-        
-        return None
-    
-    def parse_imdb_from_path_with_nfo_fallback(self, path: Path, sonarr_client=None, shutdown_event=None) -> Optional[str]:
-        """
-        Enhanced IMDb detection that fallback to Sonarr ID lookup from NFO files
-        
-        1. First try to parse IMDb ID from directory path/name
-        2. If not found, scan NFO files in directory for Sonarr series ID
-        3. Use Sonarr API to lookup series and extract IMDb ID
-        """
-        # Primary: Try directory name first
-        imdb_id = self.parse_imdb_from_path(path)
-        if imdb_id:
-            return imdb_id
-        
-        # Check for shutdown signal before expensive operations
-        if shutdown_event and shutdown_event.is_set():
-            return None
-        
-        # Fallback: Check NFO files for Sonarr series ID
-        if not sonarr_client or not sonarr_client.enabled:
-            return None
-            
-        try:
-            # Look for episode NFO files in the directory (and subdirectories)
-            nfo_files = []
-            if path.is_dir():
-                # Check current directory and season subdirectories
-                nfo_files.extend(list(path.glob("*.nfo")))
-                for subdir in path.iterdir():
-                    if subdir.is_dir() and subdir.name.lower().startswith('season'):
-                        nfo_files.extend(list(subdir.glob("*.nfo")))
-            
-            # Extract Sonarr series ID from any NFO file
-            for nfo_file in nfo_files:
-                # Check for shutdown signal during NFO processing
-                if shutdown_event and shutdown_event.is_set():
-                    return None
-                    
-                try:
-                    tree = ET.parse(nfo_file)
-                    root = tree.getroot()
-                    
-                    # Look for Sonarr series ID
-                    for uniqueid in root.findall('.//uniqueid[@type="sonarr"]'):
-                        sonarr_id = uniqueid.text
-                        if sonarr_id and sonarr_id.isdigit():
-                            # Check for shutdown signal before API call
-                            if shutdown_event and shutdown_event.is_set():
-                                return None
-                                
-                            # Look up series in Sonarr to get IMDb ID
-                            series_data = sonarr_client.get_series_by_id(int(sonarr_id))
-                            if series_data:
-                                imdb_id = series_data.get('imdbId')
-                                if imdb_id:
-                                    return imdb_id.replace('tt', '') if imdb_id.startswith('tt') else imdb_id
-                                    
-                except Exception as e:
-                    continue  # Skip this NFO file and try the next one
-                    
-        except Exception as e:
-            pass  # Fallback failed, return None
-            
-        return None
-    
-    def parse_imdb_from_nfo(self, nfo_path: Path) -> Optional[str]:
-        """Extract IMDb ID from NFO file content"""
-        if not nfo_path.exists():
-            return None
-            
-        try:
-            root = self._parse_nfo_with_tolerance(nfo_path)
-            
-            # Check for <uniqueid type="imdb">ttXXXXXX</uniqueid>
-            imdb_uniqueid = root.find('.//uniqueid[@type="imdb"]')
-            if imdb_uniqueid is not None and imdb_uniqueid.text:
-                imdb_id = imdb_uniqueid.text.strip()
-                if imdb_id.startswith('tt'):
-                    return imdb_id
-                    
-            # Check for legacy <imdbid>ttXXXXXX</imdbid>
-            imdbid_elem = root.find('.//imdbid')
-            if imdbid_elem is not None and imdbid_elem.text:
-                imdb_id = imdbid_elem.text.strip()
-                if imdb_id.startswith('tt'):
-                    return imdb_id
-                    
-            # Check for legacy <imdb>ttXXXXXX</imdb>
-            imdb_elem = root.find('.//imdb')
-            if imdb_elem is not None and imdb_elem.text:
-                imdb_id = imdb_elem.text.strip()
-                if imdb_id.startswith('tt'):
-                    return imdb_id
-            
-            # Last resort: Check for TMDB ID as fallback identifier
-            # This handles movies that only have TMDB IDs in NFO files
-            tmdb_uniqueid = root.find('.//uniqueid[@type="tmdb"]')
-            if tmdb_uniqueid is not None and tmdb_uniqueid.text:
-                tmdb_id = tmdb_uniqueid.text.strip()
-                if tmdb_id.isdigit():
-                    print(f"⚠️ Found TMDB ID {tmdb_id} but no IMDb ID - using TMDB ID as fallback")
-                    # Return TMDB ID with prefix to distinguish from IMDb IDs
-                    return f"tmdb-{tmdb_id}"
-                    
-        except (ET.ParseError, Exception):
-            # Skip corrupted or non-XML files
-            pass
-            
-        return None
-    
-    def find_movie_imdb_id(self, movie_dir: Path) -> Optional[str]:
-        """Find IMDb ID from directory name, filenames, or NFO file"""
-        # First try directory name
-        imdb_id = self.parse_imdb_from_path(movie_dir)
-        if imdb_id:
-            return imdb_id
-            
-        # Try all files in the directory for IMDb ID patterns
-        for file_path in movie_dir.iterdir():
-            if file_path.is_file():
-                imdb_id = self.parse_imdb_from_path(file_path)
-                if imdb_id:
-                    return imdb_id
-                    
-        # Finally, try NFO file content (including TMDB fallback)
-        nfo_path = movie_dir / "movie.nfo"
-        imdb_id = self.parse_imdb_from_nfo(nfo_path)
-        if imdb_id:
-            return imdb_id
-            
-        return None
-    
-    def find_series_imdb_id(self, series_dir: Path) -> Optional[str]:
-        """Find IMDb ID from TV series directory name, filenames, or tvshow.nfo file"""
-        # First try directory name
-        imdb_id = self.parse_imdb_from_path(series_dir)
-        if imdb_id:
-            return imdb_id
-            
-        # Try all files in the directory for IMDb ID patterns
-        for file_path in series_dir.iterdir():
-            if file_path.is_file():
-                imdb_id = self.parse_imdb_from_path(file_path)
-                if imdb_id:
-                    return imdb_id
-                    
-        # Finally, try tvshow.nfo file content
-        nfo_path = series_dir / "tvshow.nfo"
-        imdb_id = self.parse_imdb_from_nfo(nfo_path)
-        if imdb_id:
-            return imdb_id
-            
-        return None
-    
-    def extract_nfoguard_dates_from_nfo(self, nfo_path: Path) -> Optional[Dict[str, str]]:
-        """Extract NFOGuard-managed dates from existing NFO file"""
-        if not nfo_path.exists():
-            return None
-            
-        try:
-            tree = ET.parse(nfo_path)
-            root = tree.getroot()
-            
-            # Look for NFOGuard fields
-            dateadded_elem = root.find('.//dateadded')
-            premiered_elem = root.find('.//premiered')
-            aired_elem = root.find('.//aired')  # For TV episodes
-            lockdata_elem = root.find('.//lockdata')
-            
-            # Consider it NFOGuard-managed ONLY if it has BOTH lockdata=true AND dateadded
-            # This prevents incomplete NFO files from being marked as "complete"
-            if (lockdata_elem is not None and lockdata_elem.text == "true" and
-                dateadded_elem is not None and dateadded_elem.text):
-                # Extract original source from NFOGuard comment, default to nfo_file_existing
-                source = "nfo_file_existing"
-                
-                # Parse XML content to find NFOGuard comment with source
-                nfo_content = nfo_path.read_text(encoding='utf-8')
-                import re
-                source_match = re.search(r'<!--\s*NFOGuard\s*-\s*Source:\s*([^-]+?)\s*-->', nfo_content)
-                if source_match:
-                    source = source_match.group(1).strip()
-                    print(f"🔍 Extracted original source from NFO comment: {source}")
-                
-                result = {
-                    "source": source
-                }
-                
-                if dateadded_elem is not None and dateadded_elem.text:
-                    result["dateadded"] = dateadded_elem.text.strip()
-                
-                if premiered_elem is not None and premiered_elem.text:
-                    result["released"] = premiered_elem.text.strip()
-                
-                if aired_elem is not None and aired_elem.text:
-                    result["aired"] = aired_elem.text.strip()
-                    
-                print(f"✅ Found NFOGuard data in NFO: dateadded={result.get('dateadded', 'None')}, source={source}, released={result.get('released', 'None')}, aired={result.get('aired', 'None')}")
-                return result
-                
-        except ET.ParseError as e:
-            # Handle malformed XML files gracefully (common with external NFO files)
-            print(f"🔍 NFO XML parse error (will try text fallback): {nfo_path.name}")
-            # Try text-based fallback for extracting NFOGuard data
-            return self._extract_nfoguard_data_text_fallback(nfo_path)
-        except Exception as e:
-            print(f"⚠️ Unexpected error reading NFO file {nfo_path.name}: {e}")
-            pass
-            
-        return None
-    
-    def _extract_nfoguard_data_text_fallback(self, nfo_path: Path) -> Optional[Dict[str, str]]:
-        """Text-based fallback for extracting NFOGuard data from malformed XML files"""
-        try:
-            content = nfo_path.read_text(encoding='utf-8', errors='ignore')
-            
-            # Look for NFOGuard elements using regex
-            import re
-            
-            # Check for lockdata=true first (NFOGuard marker)
-            if not re.search(r'<lockdata>true</lockdata>', content, re.IGNORECASE):
-                return None
-            
-            # Extract dateadded
-            dateadded_match = re.search(r'<dateadded>([^<]+)</dateadded>', content, re.IGNORECASE)
-            if not dateadded_match:
-                return None
-            
-            dateadded = dateadded_match.group(1).strip()
-            if not dateadded:
-                return None
-            
-            result = {
-                "dateadded": dateadded,
-                "source": "nfo_file_existing"  # Default source
-            }
-            
-            # Extract optional fields
-            premiered_match = re.search(r'<premiered>([^<]+)</premiered>', content, re.IGNORECASE)
-            if premiered_match:
-                result["released"] = premiered_match.group(1).strip()
-            
-            aired_match = re.search(r'<aired>([^<]+)</aired>', content, re.IGNORECASE)
-            if aired_match:
-                result["aired"] = aired_match.group(1).strip()
-            
-            # Extract source from NFOGuard comment
-            source_match = re.search(r'<!--\s*NFOGuard\s*-\s*Source:\s*([^-]+?)\s*-->', content)
-            if source_match:
-                result["source"] = source_match.group(1).strip()
-            
-            print(f"✅ Extracted NFOGuard data via text fallback: dateadded={result.get('dateadded', 'None')}, source={result['source']}")
-            return result
-            
-        except Exception as e:
-            print(f"⚠️ Text fallback extraction failed for {nfo_path.name}: {e}")
-            return None
-    
-    def extract_nfoguard_dates_from_episode_nfo(self, season_path: Path, season_num: int, episode_num: int) -> Optional[Dict[str, str]]:
-        """Extract NFOGuard-managed dates from existing episode NFO file"""
-        nfo_filename = f"s{season_num:02d}e{episode_num:02d}.nfo"
-        nfo_path = season_path / nfo_filename
-        
-        if not nfo_path.exists():
-            return None
-            
-        try:
-            tree = ET.parse(nfo_path)
-            root = tree.getroot()
-            
-            # Look for NFOGuard fields in episode NFO
-            dateadded_elem = root.find('.//dateadded')
-            aired_elem = root.find('.//aired')
-            lockdata_elem = root.find('.//lockdata')
-            
-            # Consider it NFOGuard-managed ONLY if it has BOTH lockdata=true AND dateadded
-            # This prevents incomplete episode NFO files from being marked as "complete"
-            if (lockdata_elem is not None and lockdata_elem.text == "true" and
-                dateadded_elem is not None and dateadded_elem.text):
-                # Extract original source from NFOGuard comment, default to episode_nfo_existing
-                source = "episode_nfo_existing"
-                
-                # Parse XML content to find NFOGuard comment with source
-                nfo_content = nfo_path.read_text(encoding='utf-8')
-                import re
-                source_match = re.search(r'<!--\s*NFOGuard\s*-\s*Source:\s*([^-]+?)\s*-->', nfo_content)
-                if source_match:
-                    source = source_match.group(1).strip()
-                    print(f"🔍 Extracted original source from episode NFO comment: {source}")
-                
-                result = {
-                    "source": source
-                }
-                
-                if dateadded_elem is not None and dateadded_elem.text:
-                    result["dateadded"] = dateadded_elem.text.strip()
-                
-                if aired_elem is not None and aired_elem.text:
-                    result["aired"] = aired_elem.text.strip()
-                    
-                print(f"✅ Found NFOGuard data in episode NFO S{season_num:02d}E{episode_num:02d}: dateadded={result.get('dateadded', 'None')}, source={source}, aired={result.get('aired', 'None')}")
-                return result
-                
-        except (ET.ParseError, Exception) as e:
-            print(f"⚠️ Error parsing episode NFO for NFOGuard data: {e}")
-            pass
-            
-        return None
-    
-    def _parse_nfo_with_tolerance(self, nfo_path: Path):
-        """Parse NFO file with tolerance for URLs appended after XML"""
-        try:
-            # First try normal parsing
-            tree = ET.parse(nfo_path)
-            return tree.getroot()
-        except ET.ParseError as e:
-            # If parsing fails, try to extract just the XML part
-            try:
-                with open(nfo_path, 'r', encoding='utf-8') as f:
-                    content = f.read()
-                
-                # Find the last </movie> tag and truncate after it
-                last_movie_end = content.rfind('</movie>')
-                if last_movie_end != -1:
-                    xml_content = content[:last_movie_end + 8]  # +8 for </movie>
-                    
-                    # Try parsing the truncated content
-                    root = ET.fromstring(xml_content)
-                    print(f"✅ Successfully parsed NFO after removing trailing content: {nfo_path.name}")
-                    return root
-                else:
-                    # Re-raise original error if we can't find </movie>
-                    raise e
-            except Exception:
-                # Re-raise original error if our fix attempt fails
-                raise e
-    
-    def create_movie_nfo(self, movie_dir: Path, imdb_id: str, dateadded: str, 
-                        released: Optional[str] = None, source: str = "unknown",
-                        lock_metadata: bool = True) -> None:
-        """Create or update movie.nfo file preserving existing content"""
-        nfo_path = movie_dir / "movie.nfo"
-        
-        # Debug output only if DEBUG=true in environment
-        import os
-        if os.environ.get("DEBUG", "false").lower() == "true":
-            print(f"🔍 create_movie_nfo called: imdb_id={imdb_id}, dateadded={dateadded}, released={released}, source={source}")
-            print(f"🔍 NFO path: {nfo_path}")
-            print(f"🔍 NFO exists: {nfo_path.exists()}")
-        
-        try:
-            # Try to load existing NFO file
-            if nfo_path.exists():
-                try:
-                    # Try to parse the XML, handling URLs appended after </movie>
-                    movie = self._parse_nfo_with_tolerance(nfo_path)
-                    
-                    # Ensure root element is <movie>
-                    if movie.tag != "movie":
-                        raise ValueError("Root element is not <movie>")
-                    
-                    # Only remove elements that are clearly NFOGuard-managed
-                    # Look for elements that have NFOGuard characteristics
-                    elements_to_remove = []
-                    
-                    # Remove lockdata=true (this is definitely NFOGuard)
-                    for lockdata in movie.findall("lockdata"):
-                        if lockdata.text == "true":
-                            elements_to_remove.append(lockdata)
-                    
-                    # Remove IMDb uniqueids that we manage
-                    for uniqueid in movie.findall("uniqueid[@type='imdb']"):
-                        elements_to_remove.append(uniqueid)
-                    
-                    # For dateadded/premiered/year, only remove if they appear to be NFOGuard-managed
-                    # (i.e., if lockdata=true exists, these are likely ours)
-                    has_nfoguard_lockdata = any(ld.text == "true" for ld in movie.findall("lockdata"))
-                    
-                    if has_nfoguard_lockdata:
-                        # This NFO was managed by NFOGuard, safe to remove our fields
-                        for tag in ["dateadded", "premiered", "year"]:
-                            existing = movie.find(tag)
-                            if existing is not None:
-                                # Store the value before removing (for premiered/year)
-                                if tag == "premiered" and not released:
-                                    print(f"🔍 Preserving existing premiered date: {existing.text}")
-                                    released = existing.text
-                                elements_to_remove.append(existing)
-                    else:
-                        # No NFOGuard lockdata found, be more conservative
-                        # Only remove dateadded if it looks like NFOGuard format (ISO timestamp)
-                        dateadded_elem = movie.find("dateadded")
-                        if dateadded_elem is not None and dateadded_elem.text:
-                            # NFOGuard uses ISO format like "2025-10-12 16:26:02"
-                            if re.match(r'\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}', dateadded_elem.text.strip()):
-                                elements_to_remove.append(dateadded_elem)
-                    
-                    # Remove all identified elements
-                    for elem in elements_to_remove:
-                        movie.remove(elem)
-                        
-                except (ET.ParseError, ValueError) as e:
-                    print(f"⚠️  Corrupted NFO detected: {nfo_path} - {str(e)[:100]}...")
-                    print(f"   Creating new clean NFO file to replace corrupted one")
-                    movie = ET.Element("movie")
-            else:
-                # Create new NFO structure
-                movie = ET.Element("movie")
-            
-            # Create all NFOGuard elements first, then append them in correct order
-            # This ensures they appear as a group at the bottom of the file
-            nfoguard_elements = []
-            
-            # Add IMDb uniqueid 
-            uniqueid = ET.Element("uniqueid", type="imdb", default="true")
-            uniqueid.text = imdb_id
-            nfoguard_elements.append(uniqueid)
-            
-            # Add premiered date if we have it
-            if released:
-                premiered_elem = ET.Element("premiered")
-                premiered_elem.text = released[:10] if len(released) >= 10 else released
-                nfoguard_elements.append(premiered_elem)
-                
-                # Extract year from premiered date for consistency
-                try:
-                    year_value = released[:4] if len(released) >= 4 else None
-                    if year_value and year_value.isdigit():
-                        year_elem = ET.Element("year")
-                        year_elem.text = year_value
-                        nfoguard_elements.append(year_elem)
-                except:
-                    pass  # Skip year if we can't extract it
-            
-            # Add dateadded - THIS IS CRITICAL FOR EMBY PLUGIN
-            if os.environ.get("DEBUG", "false").lower() == "true":
-                print(f"🔍 About to add dateadded: {dateadded} (type: {type(dateadded)})")
-            if dateadded:
-                dateadded_elem = ET.Element("dateadded")
-                dateadded_elem.text = dateadded
-                nfoguard_elements.append(dateadded_elem)
-                print(f"✅ Adding dateadded to NFO: {dateadded}")
-            else:
-                print(f"❌ dateadded is empty/None, not adding to NFO")
-            
-            # Add lockdata at the very end
-            if lock_metadata:
-                lockdata = ET.Element("lockdata")
-                lockdata.text = "true"
-                nfoguard_elements.append(lockdata)
-            
-            # Add NFOGuard comment as the very last element (appears at bottom)
-            nfoguard_comment = ET.Comment(f" NFOGuard - Source: {source} ")
-            nfoguard_elements.append(nfoguard_comment)
-            
-            # Now append all NFOGuard elements to the movie in one batch
-            # This ensures they appear as a contiguous block at the bottom
-            for elem in nfoguard_elements:
-                movie.append(elem)
-            
-            print(f"✅ Added {len(nfoguard_elements)} NFOGuard elements to bottom of NFO")
-            
-            # Write file with proper formatting
-            tree = ET.ElementTree(movie)
-            ET.indent(tree, space="  ", level=0)
-            
-            # Write directly to file (comment is already embedded in XML at bottom)
-            with open(nfo_path, 'w', encoding='utf-8') as f:
-                f.write('<?xml version="1.0" encoding="utf-8"?>\n')
-                tree.write(f, encoding='unicode', xml_declaration=False)
-            
-            print(f"✅ Successfully created/updated movie NFO: {nfo_path}")
-            print(f"   IMDb ID: {imdb_id}, Date Added: {dateadded}, Source: {source}")
-            
-        except Exception as e:
-            print(f"❌ Error creating/updating movie NFO {nfo_path}: {e}")
-    
-    def create_tvshow_nfo(self, series_dir: Path, imdb_id: str, tvdb_id: Optional[str] = None) -> None:
-        """Create or update tvshow.nfo file preserving existing content"""
-        nfo_path = series_dir / "tvshow.nfo"
-        
-        try:
-            # Try to load existing NFO file
-            if nfo_path.exists():
-                try:
-                    tree = ET.parse(nfo_path)
-                    tvshow = tree.getroot()
-                    
-                    # Ensure root element is <tvshow>
-                    if tvshow.tag != "tvshow":
-                        raise ValueError("Root element is not <tvshow>")
-                    
-                    # Remove existing NFOGuard-managed elements to avoid duplicates
-                    # These will be re-added at the bottom
-                    for tag in ["lockdata"]:
-                        existing = tvshow.find(tag)
-                        if existing is not None:
-                            tvshow.remove(existing)
-                    
-                    # Remove ALL existing uniqueid with type="imdb" regardless of attributes
-                    for uniqueid in tvshow.findall("uniqueid[@type='imdb']"):
-                        tvshow.remove(uniqueid)
-                        
-                except (ET.ParseError, ValueError) as e:
-                    print(f"⚠️  Corrupted TV show NFO detected: {nfo_path} - {str(e)[:100]}...")
-                    print(f"   Creating new clean tvshow.nfo file to replace corrupted one")
-                    tvshow = ET.Element("tvshow")
-            else:
-                # Create new NFO structure
-                tvshow = ET.Element("tvshow")
-            
-            # Add NFOGuard fields at the bottom
-            
-            # Add IMDb uniqueid at the end
-            imdb_uniqueid = ET.SubElement(tvshow, "uniqueid", type="imdb", default="true")
-            imdb_uniqueid.text = imdb_id
-            
-            # Add TVDB ID if available (preserve existing or add new)
-            if tvdb_id and not tvshow.find("uniqueid[@type='tvdb']"):
-                tvdb_uniqueid = ET.SubElement(tvshow, "uniqueid", type="tvdb")
-                tvdb_uniqueid.text = tvdb_id
-            
-            # Add lockdata at the very end
-            lockdata = ET.SubElement(tvshow, "lockdata")
-            lockdata.text = "true"
-            
-            # Add NFOGuard comment at the bottom
-            comment = ET.Comment(f" Created by {self.manager_brand} ")
-            tvshow.append(comment)
-            
-            # Write file with proper formatting
-            tree = ET.ElementTree(tvshow)
-            ET.indent(tree, space="  ", level=0)
-            tree.write(nfo_path, encoding='utf-8', xml_declaration=True)
-            
-            print(f"✅ Successfully created/updated TV show NFO: {nfo_path}")
-            print(f"   IMDb ID: {imdb_id}" + (f", TVDB ID: {tvdb_id}" if tvdb_id else ""))
-            
-        except Exception as e:
-            print(f"❌ Error creating/updating tvshow NFO {nfo_path}: {e}")
-    
-    def create_season_nfo(self, season_dir: Path, season_number: int) -> None:
-        """Create or update season.nfo file preserving existing content"""
-        nfo_path = season_dir / "season.nfo"
-        
-        try:
-            season_dir.mkdir(exist_ok=True)
-            
-            # Try to load existing NFO file
-            if nfo_path.exists():
-                try:
-                    tree = ET.parse(nfo_path)
-                    season = tree.getroot()
-                    
-                    # Ensure root element is <season>
-                    if season.tag != "season":
-                        raise ValueError("Root element is not <season>")
-                    
-                    # Remove existing NFOGuard-managed elements
-                    for tag in ["seasonnumber", "lockdata"]:
-                        existing = season.find(tag)
-                        if existing is not None:
-                            season.remove(existing)
-                        
-                except (ET.ParseError, ValueError) as e:
-                    print(f"⚠️  Corrupted season NFO detected: {nfo_path} - {str(e)[:100]}...")
-                    print(f"   Creating new clean season.nfo file to replace corrupted one")
-                    season = ET.Element("season")
-            else:
-                # Create new NFO structure
-                season = ET.Element("season")
-            
-            # Add NFOGuard fields at the bottom
-            seasonnumber = ET.SubElement(season, "seasonnumber")
-            seasonnumber.text = str(season_number)
-            
-            # Add lockdata at the end
-            lockdata = ET.SubElement(season, "lockdata")
-            lockdata.text = "true"
-            
-            # Add NFOGuard comment at the bottom
-            comment = ET.Comment(f" Created by {self.manager_brand} ")
-            season.append(comment)
-            
-            # Write file with proper formatting
-            tree = ET.ElementTree(season)
-            ET.indent(tree, space="  ", level=0)
-            tree.write(nfo_path, encoding='utf-8', xml_declaration=True)
-            
-            print(f"✅ Successfully created/updated season NFO: {nfo_path}")
-            print(f"   Season: {season_number}")
-            
-        except Exception as e:
-            print(f"❌ Error creating/updating season NFO {nfo_path}: {e}")
-    
-    def find_existing_episode_nfo(self, season_dir: Path, season_num: int, episode_num: int) -> Optional[Path]:
-        """Find any existing episode NFO file that matches season/episode"""
-        if not season_dir.exists():
-            return None
-        
-        # Look for NFO files in the season directory
-        for nfo_file in season_dir.glob("*.nfo"):
-                
-            # Check if this NFO contains the right season/episode
-            try:
-                tree = ET.parse(nfo_file)
-                root = tree.getroot()
-                
-                if root.tag == "episodedetails":
-                    # Check for season/episode elements
-                    season_elem = root.find("season")
-                    episode_elem = root.find("episode")
-                    
-                    if (season_elem is not None and episode_elem is not None and
-                        season_elem.text and episode_elem.text):
-                        try:
-                            file_season = int(season_elem.text)
-                            file_episode = int(episode_elem.text)
-                            
-                            if file_season == season_num and file_episode == episode_num:
-                                print(f"🔍 Found existing episode NFO: {nfo_file.name}")
-                                return nfo_file
-                        except ValueError:
-                            continue
-                            
-            except (ET.ParseError, Exception):
-                # Skip corrupted or non-XML files
-                continue
-                
-        return None
-    
-    def _get_target_episode_nfo_name(self, season_dir: Path, season_num: int, episode_num: int) -> str:
-        """Get target NFO filename - prefer existing NFO, then matching video file, fallback to short name"""
-        if not season_dir.exists():
-            return f"S{season_num:02d}E{episode_num:02d}.nfo"
-        
-        # First check if an NFO already exists for this episode
-        existing_nfo = self.find_existing_episode_nfo(season_dir, season_num, episode_num)
-        if existing_nfo:
-            print(f"📂 Existing NFO found, will preserve filename: {existing_nfo.name}")
-            return existing_nfo.name
-        
-        # Look for video files with matching season/episode
-        video_extensions = [".mkv", ".mp4", ".avi", ".mov", ".m4v", ".wmv", ".flv", ".webm"]
-        
-        for video_file in season_dir.iterdir():
-            if (video_file.is_file() and 
-                video_file.suffix.lower() in video_extensions):
-                
-                # Parse episode info from video filename
-                episode_info = self._parse_episode_from_filename(video_file.name)
-                if episode_info and episode_info == (season_num, episode_num):
-                    # Found matching video file - use its name for NFO
-                    target_nfo_name = f"{video_file.stem}.nfo"
-                    print(f"🎯 Target NFO will match video: {target_nfo_name}")
-                    return target_nfo_name
-        
-        # Fallback to short name if no matching video found
-        short_name = f"S{season_num:02d}E{episode_num:02d}.nfo"
-        print(f"⚠️  No matching video file found, using short name: {short_name}")
-        return short_name
-    
-    def _parse_episode_from_filename(self, filename: str) -> Optional[Tuple[int, int]]:
-        """Parse season and episode numbers from filename"""
-        # Try S##E## format first
-        match = re.search(r'[Ss](\d{1,2})[Ee](\d{1,2})', filename)
-        if match:
-            return int(match.group(1)), int(match.group(2))
-        
-        # Try ##x## format
-        match = re.search(r'(\d{1,2})x(\d{1,2})', filename)
-        if match:
-            return int(match.group(1)), int(match.group(2))
-        
-        return None
-    
-    def create_episode_nfo(self, season_dir: Path, season_num: int, episode_num: int,
-                          aired: Optional[str], dateadded: Optional[str], source: str,
-                          lock_metadata: bool = True, enhanced_metadata: Optional[Dict[str, Any]] = None) -> None:
-        """Create or update episode NFO file preserving existing content"""
-        # Get target NFO filename (prefer long name matching video file)
-        target_nfo_name = self._get_target_episode_nfo_name(season_dir, season_num, episode_num)
-        nfo_path = season_dir / target_nfo_name
-        
-        try:
-            # Check for existing NFO file at target location
-            source_nfo_path = nfo_path if nfo_path.exists() else None
-            
-            if source_nfo_path:
-                try:
-                    tree = ET.parse(source_nfo_path)
-                    episode = tree.getroot()
-                    
-                    # Ensure root element is <episodedetails>
-                    if episode.tag != "episodedetails":
-                        raise ValueError("Root element is not <episodedetails>")
-                    
-                    print(f"📝 Updating existing NFO: {nfo_path.name}")
-                    
-                    # Preserve existing content fields and store NFOGuard-managed fields for re-adding
-                    preserved_values = {}
-                    
-                    # Extract and preserve NFOGuard-managed fields (we'll re-add these at the bottom)
-                    nfoguard_fields = ["aired", "dateadded", "lockdata", "season", "episode"]
-                    for tag in nfoguard_fields:
-                        existing = episode.find(tag)
-                        if existing is not None:
-                            # Store the value before removing
-                            if tag == "aired" and not aired:
-                                aired = existing.text  # Preserve existing aired date
-                            preserved_values[tag] = existing.text
-                            episode.remove(existing)
-                    
-                    # Important: DO NOT remove content fields like title, plot, runtime, premiered, etc.
-                    # These should be preserved from the long-named NFO files
-                    
-                    # Debug: Show what fields are preserved after removing NFOGuard fields (if DEBUG enabled)
-                    if self.debug:
-                        preserved_fields = [elem.tag for elem in episode]
-                        if preserved_fields:
-                            print(f"   🔍 Content preserved after cleanup: {', '.join(preserved_fields)}")
-                        else:
-                            print(f"   ℹ️  NFO contains only NFOGuard metadata (no additional content fields)")
-                        
-                except (ET.ParseError, ValueError) as e:
-                    print(f"⚠️  Corrupted episode NFO detected: {nfo_path} - {str(e)[:100]}...")
-                    print(f"   Creating new clean episode NFO file to replace corrupted one")
-                    episode = ET.Element("episodedetails")
-            else:
-                # Create new NFO structure
-                episode = ET.Element("episodedetails")
-            
-            # Add enhanced metadata only if not already present (preserve existing from long-named NFO)
-            if enhanced_metadata:
-                if enhanced_metadata.get("title") and not episode.find("title"):
-                    title_elem = ET.SubElement(episode, "title")
-                    title_elem.text = enhanced_metadata["title"]
-                
-                if enhanced_metadata.get("overview") and not episode.find("plot"):
-                    plot_elem = ET.SubElement(episode, "plot")
-                    plot_elem.text = enhanced_metadata["overview"]
-                
-                if enhanced_metadata.get("runtime") and not episode.find("runtime"):
-                    runtime_elem = ET.SubElement(episode, "runtime")
-                    runtime_elem.text = str(enhanced_metadata["runtime"])
-            
-            # Add NFOGuard fields at the bottom
-            
-            # Basic episode info at the end
-            season_elem = ET.SubElement(episode, "season")
-            season_elem.text = str(season_num)
-            
-            episode_elem = ET.SubElement(episode, "episode")
-            episode_elem.text = str(episode_num)
-            
-            # Dates at the end
-            if aired:
-                aired_elem = ET.SubElement(episode, "aired")
-                # Convert datetime objects to strings
-                aired_str = str(aired)
-                aired_elem.text = aired_str[:10] if len(aired_str) >= 10 else aired_str
-            
-            # Debug logging for dateadded
-            print(f"🔍 DEBUG: dateadded value: {repr(dateadded)} (type: {type(dateadded)})")
-            if dateadded:
-                dateadded_elem = ET.SubElement(episode, "dateadded")
-                # Convert datetime objects to strings
-                dateadded_elem.text = str(dateadded)
-                print(f"✅ Added dateadded to episode NFO: {dateadded}")
-            else:
-                print(f"❌ dateadded is empty/None, not adding to episode NFO")
-            
-            # Add lockdata at the very end
-            if lock_metadata:
-                lockdata = ET.SubElement(episode, "lockdata")
-                lockdata.text = "true"
-            
-            # Add NFOGuard comment at the bottom
-            comment = ET.Comment(f" Created by {self.manager_brand} - Source: {source} ")
-            episode.append(comment)
-            
-            # Write file with proper formatting
-            tree = ET.ElementTree(episode)
-            ET.indent(tree, space="  ", level=0)
-            tree.write(nfo_path, encoding='utf-8', xml_declaration=True)
-            
-            print(f"✅ Successfully created/updated episode NFO: {nfo_path}")
-            print(f"   S{season_num:02d}E{episode_num:02d}, Aired: {aired}, Date Added: {dateadded}")
-            
-            # NFO file created/updated successfully
-            pass
-        except Exception as e:
-            print(f"❌ Error creating/updating episode NFO {nfo_path}: {e}")
-    
-    def set_file_mtime(self, file_path: Path, iso_timestamp) -> None:
-        """Set file modification time to match import date"""
-        try:
-            # Convert datetime objects to strings first
-            if hasattr(iso_timestamp, 'isoformat'):
-                iso_timestamp = iso_timestamp.isoformat()
-            elif not isinstance(iso_timestamp, str):
-                iso_timestamp = str(iso_timestamp)
-            
-            # Parse ISO timestamp
-            if iso_timestamp.endswith('Z'):
-                dt = datetime.fromisoformat(iso_timestamp.replace('Z', '+00:00'))
-            elif '+' in iso_timestamp or 'T' in iso_timestamp:
-                dt = datetime.fromisoformat(iso_timestamp)
-            elif ' ' in iso_timestamp:
-                # Handle space-separated datetime format (e.g., "2025-10-16 20:31:22")
-                dt = datetime.fromisoformat(iso_timestamp.replace(' ', 'T'))
-            else:
-                # Assume it's a simple date (e.g., "2025-10-16")
-                dt = datetime.fromisoformat(iso_timestamp + 'T00:00:00')
-            
-            # Convert to timestamp
-            timestamp = dt.timestamp()
-            
-            # Set both access and modification times
-            os.utime(file_path, (timestamp, timestamp))
-            print(f"✅ Updated file timestamp: {file_path.name} -> {iso_timestamp}")
-            
-        except Exception as e:
-            print(f"❌ Error setting mtime for {file_path}: {e}")
-    
-    def update_movie_files_mtime(self, movie_dir: Path, iso_timestamp: str) -> None:
-        """Update modification times for all video files in movie directory"""
-        video_exts = (".mkv", ".mp4", ".avi", ".mov", ".m4v")
-        updated_files = []
-        
-        for file_path in movie_dir.iterdir():
-            if file_path.is_file() and file_path.suffix.lower() in video_exts:
-                self.set_file_mtime(file_path, iso_timestamp)
-                updated_files.append(file_path.name)
-        
-        if updated_files:
-            print(f"✅ Updated {len(updated_files)} video file timestamps in {movie_dir.name}")
-        else:
-            print(f"⚠️  No video files found to update in {movie_dir.name}")

main.py

@@ -22,7 +22,7 @@ from utils.logging import _log
 
 # Import core components
 from core.database import NFOGuardDatabase
-from core.nfo_manager import NFOManager
+# from core.nfo_manager import NFOManager  # Phase 3: Removed - no longer needed
 from core.path_mapper import PathMapper
 
 # Import clients
@@ -93,20 +93,20 @@ def initialize_components():
     
     # Initialize core components
     db = NFOGuardDatabase(config=config)
-    nfo_manager = NFOManager(config.manager_brand, config.debug)
+    # nfo_manager = NFOManager(config.manager_brand, config.debug)  # Phase 3: Removed
     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 with nfo_manager for comprehensive IMDb detection
-    batcher = WebhookBatcher(nfo_manager)
+
+    # Initialize processors (nfo_manager=None for backward compatibility)
+    tv_processor = TVProcessor(db, None, path_mapper)
+    movie_processor = MovieProcessor(db, None, path_mapper)
+
+    # Initialize webhook batcher (no longer needs nfo_manager - Phase 3)
+    batcher = WebhookBatcher(nfo_manager=None)
     batcher.set_processors(tv_processor, movie_processor)
-    
+
     return {
         "db": db,
-        "nfo_manager": nfo_manager,
+        # "nfo_manager": nfo_manager,  # Phase 3: Removed
         "path_mapper": path_mapper,
         "tv_processor": tv_processor,
         "movie_processor": movie_processor,

nfoguard-web/api/web_routes.py

@@ -5,7 +5,7 @@ Provides endpoints for the web-based database manipulation interface
 import json
 from datetime import datetime, timezone
 from typing import List, Optional, Dict, Any
-from fastapi import HTTPException, Query
+from fastapi import HTTPException, Query, BackgroundTasks
 from pathlib import Path
 
 import sys
@@ -14,6 +14,10 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from api.models import *
 
 
+# Global status tracking for database population
+_populate_status = {"running": False, "completed": False}
+
+
 def map_source_to_description(source: str) -> str:
     """Map technical source codes to user-friendly descriptions"""
     if not source or source == "no_valid_date_source":
@@ -48,16 +52,24 @@ def map_source_to_description(source: str) -> str:
     elif "omdb:" in source_lower:
         return "OMDb Release"
     
+    # Sonarr sources
+    elif "sonarr:" in source_lower:
+        return "Sonarr API"
+
     # Manual and other sources
     elif "manual" in source_lower:
         return "Manual Entry"
     elif "digital_release" in source_lower:
         return "Digital Release"
+    elif "nfo_file_existing" in source_lower:
+        return "NFO File (Legacy)"
     elif "nfo:" in source_lower:
         return "NFO File"
     elif "webhook:" in source_lower:
         return "Webhook/API"
-    
+    elif "database" in source_lower:
+        return "Database"
+
     # Fallback for unknown patterns
     return source.title()
 
@@ -468,11 +480,18 @@ async def get_dashboard_stats(dependencies: dict):
         
         cursor.execute("SELECT COUNT(*) FROM episodes WHERE source = 'no_valid_date_source'")
         episodes_no_valid_source = db._get_first_value(cursor.fetchone())
-        
-        # Recent activity (last 7 days)
+
+        # Recent activity (last 7 days) - count items processed, not history events
         cursor.execute("""
-            SELECT COUNT(*) FROM processing_history 
-            WHERE processed_at > NOW() - INTERVAL '7 days'
+            SELECT COUNT(*) FROM (
+                SELECT imdb_id FROM movies
+                WHERE created_at > NOW() - INTERVAL '7 days'
+                   OR updated_at > NOW() - INTERVAL '7 days'
+                UNION
+                SELECT DISTINCT imdb_id FROM episodes
+                WHERE created_at > NOW() - INTERVAL '7 days'
+                   OR updated_at > NOW() - INTERVAL '7 days'
+            ) AS recent_items
         """)
         recent_activity = db._get_first_value(cursor.fetchone())
         
@@ -1003,17 +1022,122 @@ async def delete_movie(dependencies: dict, imdb_id: str):
             print(f"⚠️ Failed to add processing history: {e}")
             
         return {"success": True, "status": "success", "message": f"Deleted movie {imdb_id}"}
-        
+
     except Exception as e:
         print(f"❌ Error deleting movie: {e}")
         raise HTTPException(status_code=500, detail=f"Failed to delete movie: {str(e)}")
 
 
+async def populate_database(background_tasks: BackgroundTasks, media_type: str = "both", dependencies: dict = None):
+    """
+    Populate NFOGuard database from Radarr/Sonarr sources
+
+    Args:
+        background_tasks: FastAPI background tasks
+        media_type: Type of media to populate ("movies", "tv", or "both")
+        dependencies: Dictionary with db, radarr_client, sonarr_client
+
+    Returns:
+        Status message indicating population has started
+    """
+    from core.database_populator import DatabasePopulator
+
+    db = dependencies["db"]
+    config = dependencies["config"]
+
+    # Get Radarr and Sonarr clients
+    from clients.radarr_client import RadarrClient
+    from clients.sonarr_client import SonarrClient
+
+    radarr_client = RadarrClient(config)
+    sonarr_client = SonarrClient(config)
+
+    if media_type not in ["both", "movies", "tv"]:
+        raise HTTPException(status_code=400, detail="media_type must be 'both', 'movies', or 'tv'")
+
+    # Create global status tracking
+    populate_status = {
+        "running": True,
+        "media_type": media_type,
+        "start_time": datetime.now().isoformat(),
+        "movies": {"status": "pending", "stats": None},
+        "tv": {"status": "pending", "stats": None},
+        "completed": False,
+        "error": None
+    }
+
+    # Store status globally so it can be queried
+    global _populate_status
+    _populate_status = populate_status
+
+    async def run_population():
+        """Background task to populate the database"""
+        try:
+            populator = DatabasePopulator(db, radarr_client, sonarr_client)
+
+            print(f"INFO: Starting database population: {media_type}")
+
+            if media_type == "movies":
+                populate_status["movies"]["status"] = "running"
+                movie_stats = populator.populate_movies()
+                populate_status["movies"]["status"] = "completed"
+                populate_status["movies"]["stats"] = movie_stats
+                print(f"INFO: Movie population completed: {movie_stats}")
+
+            elif media_type == "tv":
+                populate_status["tv"]["status"] = "running"
+                tv_stats = populator.populate_tv_episodes()
+                populate_status["tv"]["status"] = "completed"
+                populate_status["tv"]["stats"] = tv_stats
+                print(f"INFO: TV population completed: {tv_stats}")
+
+            elif media_type == "both":
+                populate_status["movies"]["status"] = "running"
+                movie_stats = populator.populate_movies()
+                populate_status["movies"]["status"] = "completed"
+                populate_status["movies"]["stats"] = movie_stats
+                print(f"INFO: Movie population completed: {movie_stats}")
+
+                populate_status["tv"]["status"] = "running"
+                tv_stats = populator.populate_tv_episodes()
+                populate_status["tv"]["status"] = "completed"
+                populate_status["tv"]["stats"] = tv_stats
+                print(f"INFO: TV population completed: {tv_stats}")
+
+            populate_status["completed"] = True
+            populate_status["running"] = False
+            print("INFO: Database population completed successfully")
+
+        except Exception as e:
+            print(f"ERROR: Database population failed: {e}")
+            populate_status["error"] = str(e)
+            populate_status["running"] = False
+            populate_status["completed"] = True
+
+    # Add task to background
+    background_tasks.add_task(run_population)
+
+    print(f"INFO: Database population started for: {media_type}")
+    return {
+        "status": "started",
+        "media_type": media_type,
+        "message": f"Database population started for {media_type}"
+    }
+
+
+async def get_populate_status():
+    """Get the current status of database population"""
+    global _populate_status
+    if '_populate_status' not in globals():
+        return {"running": False, "completed": False}
+    return _populate_status
+
+
 def register_web_routes(app, dependencies):
     """Register all web API routes with FastAPI app"""
     from fastapi import Request, Response
-    
-    # Dashboard and stats endpoints  
+
+    # Dashboard and stats endpoints
     @app.get("/api/dashboard")
     async def api_dashboard():
         return await get_dashboard_stats(dependencies)
@@ -1132,11 +1256,37 @@ def register_web_routes(app, dependencies):
         
         response.delete_cookie("nfoguard_session")
         return {"status": "logged_out", "message": "Session cleared"}
-    
+
+    # Database population endpoints
+    print("🔧 DEBUG: Registering /admin/populate-database endpoint...")
+
+    @app.post("/admin/populate-database")
+    async def api_populate_database(request: Request, background_tasks: BackgroundTasks):
+        """Populate database from Radarr/Sonarr"""
+        print(f"🔥 DEBUG: populate-database endpoint called!")
+        try:
+            data = await request.json()
+            media_type = data.get("media_type", "both")
+        except Exception:
+            # Fallback to query parameter if JSON parsing fails
+            media_type = request.query_params.get("media_type", "both")
+        return await populate_database(background_tasks, media_type, dependencies)
+
+    print("✅ DEBUG: /admin/populate-database registered")
+
+    @app.get("/api/populate/status")
+    async def api_populate_status():
+        """Get database population status"""
+        return await get_populate_status()
+
     # Health endpoint
     @app.get("/health")
     async def health_check():
         """Health check endpoint for container monitoring"""
         return {"status": "healthy", "service": "nfoguard-web"}
-    
-    print("✅ Web routes registered successfully")
+
+    print("✅ Web routes registered successfully")
+    print(f"📋 DEBUG: Registered routes count: {len(app.routes)}")
+    for route in app.routes:
+        if hasattr(route, 'path') and hasattr(route, 'methods'):
+            print(f"   - {route.methods} {route.path}")

nfoguard-web/main_web.py

@@ -33,7 +33,7 @@ def create_web_app() -> FastAPI:
     app = FastAPI(
         title="NFOGuard Web Interface",
         description="Web interface for NFOGuard media database management",
-        version="2.6.12-web",
+        version="2.9.0-fixes-only-files",
         docs_url="/docs" if web_config.web_debug else None,
         redoc_url="/redoc" if web_config.web_debug else None
     )

nfoguard-web/static/index.html

@@ -4,7 +4,7 @@
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <title>NFOGuard - Database Management</title>
-    <link rel="stylesheet" href="/static/css/styles.css?v=manual-scan-ui">
+    <link rel="stylesheet" href="/static/css/styles.css?v=2.10.0-skipped-imdb-edit-v2">
     <link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css" rel="stylesheet">
 </head>
 <body>
@@ -12,7 +12,7 @@
         <!-- Header -->
         <header class="app-header">
             <div class="header-content">
-                <h1><i class="fas fa-shield-alt"></i> NFOGuard</h1>
+                <h1><i class="fas fa-shield-alt"></i> NFOGuard <span style="font-size: 0.5em; color: #888;">v2.10.0-skipped-imdb-edit-v2</span></h1>
                 <p>Database Management & Reporting</p>
             </div>
             <div class="auth-status" id="auth-status" style="display: none;">
@@ -93,6 +93,17 @@
                             <small>Last 7 days</small>
                         </div>
                     </div>
+
+                    <div class="stat-card">
+                        <div class="stat-icon" style="background: linear-gradient(135deg, #f39c12 0%, #e67e22 100%);">
+                            <i class="fas fa-ban"></i>
+                        </div>
+                        <div class="stat-info">
+                            <h3 id="skipped-total">-</h3>
+                            <p>Skipped Items</p>
+                            <small id="skipped-breakdown">- movies, - episodes</small>
+                        </div>
+                    </div>
                 </div>
 
                 <div class="dashboard-charts">
@@ -127,6 +138,7 @@
                                 <option value="">All Movies</option>
                                 <option value="true">With Dates</option>
                                 <option value="false">Missing Dates</option>
+                                <option value="skipped">Skipped</option>
                             </select>
                             <select id="movies-filter-source">
                                 <option value="">All Sources</option>
@@ -139,16 +151,30 @@
                 </div>
                 
                 <div class="table-container">
-                    <table class="data-table" id="movies-table">
+                    <table class="data-table sortable-table" id="movies-table">
                         <thead>
                             <tr>
-                                <th>Title</th>
-                                <th>IMDb ID</th>
-                                <th>Movie Released</th>
-                                <th>Date Added to Library</th>
-                                <th>Source</th>
-                                <th>Date Type</th>
-                                <th>Video File</th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 0, 'text')" style="cursor: pointer;">
+                                    Title <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 1, 'text')" style="cursor: pointer;">
+                                    IMDb ID <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 2, 'date')" style="cursor: pointer;">
+                                    Movie Released <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 3, 'date')" style="cursor: pointer;">
+                                    Date Added to Library <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 4, 'text')" style="cursor: pointer;">
+                                    Source <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 5, 'text')" style="cursor: pointer;">
+                                    Date Type <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('movies-tbody', 6, 'text')" style="cursor: pointer;">
+                                    Video File <i class="fas fa-sort"></i>
+                                </th>
                                 <th>Actions</th>
                             </tr>
                         </thead>
@@ -184,6 +210,7 @@
                                 <option value="complete">Fully Dated</option>
                                 <option value="incomplete">Missing Dates</option>
                                 <option value="none">No Dates</option>
+                                <option value="skipped">Skipped</option>
                             </select>
                             <select id="series-filter-source">
                                 <option value="">All Sources</option>
@@ -196,14 +223,27 @@
                 </div>
                 
                 <div class="table-container">
-                    <table class="data-table" id="series-table">
+                    <table class="data-table sortable-table" id="series-table">
                         <thead>
                             <tr>
-                                <th>Series Title</th>
-                                <th>IMDb ID</th>
-                                <th>Episodes</th>
-                                <th>With Dates</th>
-                                <th>With Video</th>
+                                <th class="sortable" onclick="sortTable('series-tbody', 0, 'text')" style="cursor: pointer;">
+                                    Series Title <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('series-tbody', 1, 'text')" style="cursor: pointer;">
+                                    IMDb ID <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('series-tbody', 2, 'number')" style="cursor: pointer;">
+                                    Episodes <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('series-tbody', 3, 'number')" style="cursor: pointer;">
+                                    With Dates <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('series-tbody', 4, 'number')" style="cursor: pointer;">
+                                    With Video <i class="fas fa-sort"></i>
+                                </th>
+                                <th class="sortable" onclick="sortTable('series-tbody', 5, 'number')" style="cursor: pointer;">
+                                    Skipped <i class="fas fa-sort"></i>
+                                </th>
                                 <th>Actions</th>
                             </tr>
                         </thead>
@@ -443,6 +483,39 @@
                             <i class="fas fa-sync"></i> Refresh Stats
                         </button>
                     </div>
+
+                    <div class="tool-card">
+                        <h3><i class="fas fa-upload"></i> Populate Database</h3>
+                        <p>Bulk import data from Radarr/Sonarr into NFOGuard database</p>
+                        <form id="populate-form">
+                            <div class="form-group">
+                                <label>Media Type:</label>
+                                <select id="populate-media-type" required>
+                                    <option value="both">Movies & TV Shows</option>
+                                    <option value="movies">Movies Only</option>
+                                    <option value="tv">TV Shows Only</option>
+                                </select>
+                            </div>
+                            <button type="submit" class="btn btn-primary">
+                                <i class="fas fa-play"></i> Start Population
+                            </button>
+                        </form>
+                        <div id="populate-status" class="scan-status" style="display: none;">
+                            <div class="scan-progress">
+                                <div class="progress-bar">
+                                    <div class="progress-fill" id="populate-progress-bar"></div>
+                                </div>
+                                <div class="scan-info">
+                                    <span id="populate-current-operation">Running...</span>
+                                    <span id="populate-progress-text">In Progress</span>
+                                </div>
+                            </div>
+                            <div id="populate-results" class="stats-display" style="margin-top: 10px;"></div>
+                            <button class="btn btn-secondary btn-sm" onclick="stopPopulatePolling()">
+                                <i class="fas fa-times"></i> Hide Status
+                            </button>
+                        </div>
+                    </div>
                 </div>
             </div>
         </main>
@@ -654,6 +727,6 @@
     <!-- Toast Notifications -->
     <div class="toast-container" id="toast-container"></div>
 
-    <script src="/static/js/app.js?v=scheduled-scans-system"></script>
+    <script src="/static/js/app.js?v=2.10.0-skipped-imdb-edit-v2"></script>
 </body>
 </html>

processors/movie_processor.py

@@ -11,12 +11,12 @@ 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
+from utils.imdb_utils import find_imdb_in_directory  # Phase 3: Replaced NFOManager
 from utils.file_utils import find_media_path_by_imdb_and_title
 
 
@@ -68,9 +68,9 @@ def convert_utc_to_local(utc_iso_string: str) -> str:
 class MovieProcessor:
     """Handles movie processing"""
     
-    def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager, path_mapper: PathMapper):
+    def __init__(self, db: NFOGuardDatabase, nfo_manager, path_mapper: PathMapper):
+        # nfo_manager parameter kept for backward compatibility but no longer used (Phase 3)
         self.db = db
-        self.nfo_manager = nfo_manager
         self.path_mapper = path_mapper
         self.radarr = RadarrClient(
             os.environ.get("RADARR_URL", ""),
@@ -153,7 +153,7 @@ class MovieProcessor:
     
     def process_movie(self, movie_path: Path, webhook_mode: bool = False, force_scan: bool = False, scan_mode: str = "smart", shutdown_event=None) -> str:
         """Process a movie directory"""
-        imdb_id = self.nfo_manager.find_movie_imdb_id(movie_path)
+        imdb_id = find_imdb_in_directory(movie_path)  # Phase 3: Using imdb_utils instead of NFOManager
         if not imdb_id:
             _log("ERROR", f"No IMDb ID found in movie directory, filenames, or NFO file: {movie_path}")
             return "error"
@@ -225,106 +225,16 @@ class MovieProcessor:
             if released and hasattr(released, 'isoformat'):
                 released = released.isoformat()
             
-            # Create NFO with existing data and update files
-            if config.manage_nfo:
-                self.nfo_manager.create_movie_nfo(
-                    movie_path, imdb_id, dateadded, released, source, config.lock_metadata
-                )
-            
-            if config.fix_dir_mtimes and dateadded:
-                self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
+            # NFO file operations removed - database is now the single source of truth
+            # (Phase 1: Remove NFO file write operations)
             
             _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source}) [database-cached]")
             return "processed"
         else:
             _log("INFO", f"🔍 TIER 1 SKIP - {imdb_id}: Database incomplete, proceeding to Tier 2")
         
-        # TIER 2: Check if NFO file has NFOGuard data and cache it in database
-        nfo_path = movie_path / "movie.nfo"
-        _log("INFO", f"🔍 TIER 2 - Checking NFO file: {nfo_path}")
-        _log("INFO", f"🔍 TIER 2 - NFO exists: {nfo_path.exists()}")
-        
-        nfo_data = self.nfo_manager.extract_nfoguard_dates_from_nfo(nfo_path)
-        _log("INFO", f"🔍 TIER 2 - NFOGuard data extracted: {nfo_data}")
-        
-        if nfo_data:
-            _log("INFO", f"🚀 TIER 2 - Found NFOGuard data in NFO file: {nfo_data['dateadded']} (source: {nfo_data['source']})")
-            dateadded = nfo_data["dateadded"]
-            source = nfo_data["source"] 
-            released = nfo_data.get("released")
-            
-            # Cache NFO data in database for future lookups  
-            # Fixed parameter order: imdb_id, released, dateadded, source
-            self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
-            _log("INFO", f"✅ Cached NFO data in database for {imdb_id}")
-            
-            # 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-cached]")
-            return "processed"
-            
-        # TIER 2.5: Check for any existing valid date data in NFO (even without lockdata marker)
-        # Only use NFO dates if prioritize_nfo is enabled, otherwise check external APIs first
-        existing_nfo_data = self._extract_any_valid_dates_from_nfo(nfo_path)
-        if existing_nfo_data and config.manual_scan_prioritize_nfo:
-            _log("INFO", f"🔍 TIER 2.5 - Found existing date data in NFO (no lockdata): {existing_nfo_data['dateadded']} (source: {existing_nfo_data['source']})")
-            _log("INFO", f"⚡ MANUAL_SCAN_PRIORITIZE_NFO=True - Using NFO date for speed")
-            dateadded = existing_nfo_data["dateadded"]
-            source = existing_nfo_data["source"]
-            released = existing_nfo_data.get("released")
-            
-            # Cache existing data in database and add proper NFOGuard formatting
-            # Fixed parameter order: imdb_id, released, dateadded, source
-            self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
-            _log("INFO", f"✅ Cached existing NFO data in database for {imdb_id}")
-            
-            # Update NFO file to add NFOGuard formatting (lockdata, comment)
-            if config.manage_nfo:
-                self.nfo_manager.create_movie_nfo(
-                    movie_path, imdb_id, dateadded, released, source, config.lock_metadata
-                )
-                _log("INFO", f"✅ Added NFOGuard formatting to existing NFO for {imdb_id}")
-            
-            # 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}) [existing-nfo-enhanced]")
-            return "processed"
-        elif existing_nfo_data:
-            _log("INFO", f"🔍 TIER 2.5 - Found existing date data in NFO (no lockdata): {existing_nfo_data['dateadded']} (source: {existing_nfo_data['source']})")
-            _log("INFO", f"🎯 MANUAL_SCAN_PRIORITIZE_NFO=False - Will verify against external APIs first")
-            # Store NFO data as fallback but continue to TIER 3 to check external APIs
-            nfo_fallback_data = existing_nfo_data
-            
-        # 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 "processed"
-            
-        # TIER 3: No cached data found - proceed with API lookups and verification
+        # TIER 2: Query external APIs directly (NFO layer removed in Phase 2)
+        _log("INFO", f"🔍 TIER 2 - No database cache, querying external APIs")
         
         # Check for shutdown signal before expensive API operations
         if shutdown_event and shutdown_event.is_set():
@@ -362,18 +272,8 @@ class MovieProcessor:
             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.debug:
-            print(f"🔍 TIER3 - config.manage_nfo: {config.manage_nfo}")
-        if config.manage_nfo:
-            if config.debug:
-                print(f"🔍 TIER3 - Calling create_movie_nfo with final_dateadded: {final_dateadded}")
-            self.nfo_manager.create_movie_nfo(
-                movie_path, imdb_id, final_dateadded, released, final_source, config.lock_metadata
-            )
-        else:
-            if config.debug:
-                print(f"❌ TIER3 - manage_nfo is disabled, skipping NFO creation")
+        # NFO file operations removed - database is now the single source of truth
+        # (Phase 1: Remove NFO file write operations)
         
         # Skip remaining processing if no valid date found and file dates disabled
         if final_dateadded is None:
@@ -387,9 +287,8 @@ class MovieProcessor:
         
         _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)
+        # File mtime operations removed - database is now the single source of truth
+        # (Phase 1: Remove NFO file write operations)
         
         _log("DEBUG", f"Movie processing reached file mtime section: fix_dir_mtimes={config.fix_dir_mtimes}, dateadded={dateadded}")
         
@@ -407,76 +306,34 @@ class MovieProcessor:
         return "processed"
     
     def _process_movie_nfo_first(self, movie_path: Path, imdb_id: str, shutdown_event=None) -> str:
-        """Process movie for incomplete mode: Check NFO files first for missing dateadded elements"""
-        _log("INFO", f"🔍 NFO-FIRST MODE: Checking movie for missing dateadded in NFO file: {movie_path.name}")
-        
+        """Process movie for incomplete mode: Database-first then API (NFO checks removed in Phase 2)"""
+        _log("INFO", f"🔍 INCOMPLETE MODE: Checking movie for missing data: {movie_path.name}")
+
         # Check for shutdown signal
         if shutdown_event and shutdown_event.is_set():
-            _log("INFO", f"⚠️ SHUTDOWN SIGNAL RECEIVED - Stopping movie NFO-first processing: {movie_path.name}")
+            _log("INFO", f"⚠️ SHUTDOWN SIGNAL RECEIVED - Stopping movie processing: {movie_path.name}")
             return "shutdown"
-        
-        nfo_path = movie_path / "movie.nfo"
-        
-        # STEP 1: Check if NFO file exists and has dateadded
-        _log("DEBUG", f"STEP 1 - Checking NFO file for missing dateadded: {nfo_path}")
-        _log("INFO", f"🔍 NFO exists: {nfo_path.exists()}")
-        
-        if nfo_path.exists():
-            nfo_data = self.nfo_manager.extract_nfoguard_dates_from_nfo(nfo_path)
-            _log("INFO", f"🔍 NFOGuard data extracted: {nfo_data}")
-            
-            if nfo_data and nfo_data.get('dateadded'):
-                # NFO has dateadded - this movie is complete
-                _log("INFO", f"✅ NFO has dateadded={nfo_data['dateadded']}, movie marked as complete")
-                dateadded = nfo_data["dateadded"]
-                source = nfo_data["source"] 
-                released = nfo_data.get("released")
-                
-                # Cache NFO data in database for future lookups
-                self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
-                
-                # Update file mtimes if needed
-                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-complete]")
-                return "processed"
-            else:
-                # NFO exists but missing dateadded
-                _log("INFO", f"🔍 NFO exists but missing dateadded - needs DB/API lookup")
-        else:
-            # No NFO file found
-            _log("INFO", f"🔍 No NFO file found - needs DB/API lookup")
-        
-        # STEP 2: For movies missing dateadded in NFO, check database
-        _log("DEBUG", f"STEP 2 - Checking database for missing dateadded")
+
+        # STEP 1: Check database for existing data (Phase 2: NFO check removed)
+        _log("DEBUG", f"STEP 1 - Checking database for existing data")
         existing = self.db.get_movie_dates(imdb_id)
-        
+
         if existing and existing.get("dateadded") and existing.get("source") != "no_valid_date_source":
-            # Found in database - use cached data and will add to NFO
-            _log("INFO", f"✅ Database has dateadded={existing['dateadded']} - will add to NFO")
+            # Found in database - data is complete
+            _log("INFO", f"✅ Database has dateadded={existing['dateadded']}")
             dateadded, source, released = existing["dateadded"], existing["source"], existing.get("released")
-            
-            # Convert datetime objects to strings for NFO manager
+
+            # Convert datetime objects to strings
             if hasattr(dateadded, 'isoformat'):
                 dateadded = dateadded.isoformat()
             if released and hasattr(released, 'isoformat'):
                 released = released.isoformat()
-            
-            # Create NFO with database data
-            if config.manage_nfo:
-                self.nfo_manager.create_movie_nfo(
-                    movie_path, imdb_id, dateadded, released, source, config.lock_metadata
-                )
-            
-            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-to-nfo]")
+
+            _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source}) [database-cached]")
             return "processed"
-        
-        # STEP 3: For movies still missing dateadded, query APIs
-        _log("DEBUG", f"STEP 3 - Querying APIs for missing dateadded")
+
+        # STEP 2: Database incomplete or missing, query APIs
+        _log("DEBUG", f"STEP 2 - Querying APIs for missing data")
         
         # Check for shutdown signal before API calls
         if shutdown_event and shutdown_event.is_set():
@@ -487,19 +344,10 @@ class MovieProcessor:
         is_tmdb_fallback = imdb_id.startswith("tmdb-")
         
         if is_tmdb_fallback:
-            # TMDB fallback processing
+            # TMDB fallback processing - use file modification time
             _log("INFO", f"🔍 TMDB fallback processing for {imdb_id}")
-            
-            # Check for existing TMDB NFO date data
-            tmdb_data = self._extract_dates_from_tmdb_nfo(nfo_path)
-            if tmdb_data and tmdb_data.get('dateadded'):
-                dateadded = tmdb_data['dateadded']
-                released = tmdb_data.get('released')
-                source = "tmdb_nfo"
-            else:
-                # Use file modification time as fallback for TMDB
-                dateadded, source, released = self._get_file_mtime_date(movie_path)
-                _log("INFO", f"Using file mtime as fallback for TMDB movie: {dateadded}")
+            dateadded, source, released = self._get_file_mtime_date(movie_path)
+            _log("INFO", f"Using file mtime for TMDB movie: {dateadded}")
         else:
             # Standard IMDb processing
             # Try to get digital release date from external APIs
@@ -511,116 +359,22 @@ class MovieProcessor:
                 released = digital_date  # For movies, digital release is often the key date
                 _log("INFO", f"Got digital release date from APIs: {dateadded} (source: {source})")
             else:
-                # Check Radarr NFO for premiered date
-                radarr_premiered = self._get_radarr_nfo_premiered_date(movie_path)
-                if radarr_premiered:
-                    dateadded = radarr_premiered
-                    source = "radarr_nfo"
-                    released = radarr_premiered
-                    _log("INFO", f"Got premiered date from Radarr NFO: {dateadded}")
-                else:
-                    # Last resort: file modification time
-                    dateadded, source, released = self._get_file_mtime_date(movie_path)
-                    _log("INFO", f"Using file mtime as last resort: {dateadded}")
+                # Last resort: file modification time
+                dateadded, source, released = self._get_file_mtime_date(movie_path)
+                _log("INFO", f"Using file mtime as fallback: {dateadded}")
         
-        # Save to database and create NFO
+        # Save to database only (NFO operations removed in Phase 1)
         if dateadded:
             self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
             
-            if config.manage_nfo:
-                self.nfo_manager.create_movie_nfo(
-                    movie_path, imdb_id, dateadded, released, source, config.lock_metadata
-                )
-            
-            if config.fix_dir_mtimes and dateadded:
-                self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
-            
-            _log("INFO", f"🔍 NFO-FIRST COMPLETE: {movie_path.name} (source: {source})")
+            _log("INFO", f"🔍 INCOMPLETE MODE COMPLETE: {movie_path.name} (source: {source})")
             return "processed"
         else:
             _log("WARNING", f"Could not determine dateadded for movie: {movie_path.name}")
             return "error"
     
-    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 _extract_any_valid_dates_from_nfo(self, nfo_path: Path) -> Optional[Dict[str, str]]:
-        """Extract any valid date information from NFO file, even without NFOGuard markers"""
-        if not nfo_path.exists():
-            return None
-            
-        try:
-            import xml.etree.ElementTree as ET
-            tree = ET.parse(nfo_path)
-            root = tree.getroot()
-            
-            # Look for dateadded element (indicates previously processed by NFOGuard or similar)
-            dateadded_elem = root.find('.//dateadded')
-            premiered_elem = root.find('.//premiered')
-            
-            if dateadded_elem is not None and dateadded_elem.text:
-                dateadded = dateadded_elem.text.strip()
-                
-                # Try to determine source from NFOGuard comment if present
-                source = "existing_nfo_data"
-                try:
-                    nfo_content = nfo_path.read_text(encoding='utf-8')
-                    import re
-                    # Look for NFOGuard comment pattern
-                    source_match = re.search(r'<!--.*?NFOGuard.*?Source:\s*([^-\s]+).*?-->', nfo_content, re.DOTALL | re.IGNORECASE)
-                    if source_match:
-                        source = source_match.group(1).strip()
-                        _log("DEBUG", f"Found source in NFOGuard comment: {source}")
-                    else:
-                        # Try to infer source from dateadded format/content
-                        if "tmdb" in nfo_content.lower() or (premiered_elem and premiered_elem.text):
-                            source = "tmdb:digital"
-                        elif "radarr" in nfo_content.lower():
-                            source = "radarr:db.history.import"
-                        else:
-                            source = "existing_nfo_data"
-                        _log("DEBUG", f"Inferred source from NFO content: {source}")
-                except Exception as e:
-                    _log("DEBUG", f"Could not determine source from NFO content: {e}")
-                
-                result = {
-                    "dateadded": dateadded,
-                    "source": source
-                }
-                
-                if premiered_elem is not None and premiered_elem.text:
-                    result["released"] = premiered_elem.text.strip()
-                
-                _log("INFO", f"✅ Found existing date data in NFO: dateadded={dateadded}, source={source}")
-                return result
-                
-        except (ET.ParseError, Exception) as e:
-            _log("DEBUG", f"Error parsing NFO for existing date data: {e}")
-            
-        return None
-    
+    # NFO helper methods removed in Phase 2 - database is the single source of truth
+
     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}")
@@ -687,14 +441,7 @@ class MovieProcessor:
                 # When using digital release date, store it as both dateadded and released
                 return digital_date, digital_source, digital_date
             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}")
-                    # When using Radarr NFO premiered date, store it as both dateadded and released
-                    return radarr_premiered, "radarr:nfo.premiered", radarr_premiered
+                _log("WARNING", f"⚠️ Movie {imdb_id}: No import date OR digital release date found")
         
         else:  # digital_then_import
             # Try digital release first
@@ -753,32 +500,8 @@ class MovieProcessor:
             _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
-    
+    # _get_radarr_nfo_premiered_date() removed in Phase 2 - no longer reading NFO files
+
     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:

processors/tv_processor.py

@@ -11,13 +11,12 @@ 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.async_nfo_manager import AsyncNFOManager
 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
+from utils.imdb_utils import parse_imdb_from_path  # Phase 3: Replaced NFOManager
 from utils.file_utils import (
     find_media_path_by_imdb_and_title,
     find_episodes_on_disk,
@@ -32,10 +31,9 @@ from utils.async_file_utils import (
 class TVProcessor:
     """Handles TV series processing"""
     
-    def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager, path_mapper: PathMapper):
+    def __init__(self, db: NFOGuardDatabase, nfo_manager, path_mapper: PathMapper):
+        # nfo_manager parameter kept for backward compatibility but no longer used (Phase 3)
         self.db = db
-        self.nfo_manager = nfo_manager
-        self.async_nfo_manager = AsyncNFOManager(config.manager_brand, config.debug)
         self.path_mapper = path_mapper
         self.sonarr = SonarrClient(
             os.environ.get("SONARR_URL", ""),
@@ -147,7 +145,7 @@ class TVProcessor:
     
     def process_series(self, series_path: Path, force_scan: bool = False, scan_mode: str = "smart") -> str:
         """Process a TV series directory"""
-        imdb_id = self.nfo_manager.parse_imdb_from_path(series_path)
+        imdb_id = parse_imdb_from_path(series_path)  # Phase 3: Using imdb_utils
         if not imdb_id:
             _log("ERROR", f"No IMDb ID found in series path: {series_path}")
             return "error"
@@ -193,19 +191,8 @@ class TVProcessor:
             if (season, episode) in disk_episodes:
                 episode_count += 1
                 
-                # Create NFO
-                if config.manage_nfo:
-                    season_dir = series_path / config.get_season_dir_name(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)
+                # NFO file operations removed - database is now the single source of truth
+                # (Phase 1: Remove NFO file write operations)
                 
                 # Save to database
                 try:
@@ -259,64 +246,12 @@ class TVProcessor:
                 # Not in database or incomplete - needs NFO check
                 episodes_needing_nfo_check.append((season, episode))
         
-        _log("INFO", f"Database cache hits: {db_cache_hits}/{len(disk_episodes)} episodes. Need NFO check: {len(episodes_needing_nfo_check)}")
-        
-        # TIER 2: Check NFO files for NFOGuard dates and cache them in database
-        nfo_cache_hits = 0
-        episodes_needing_lookup = []
-        
-        if episodes_needing_nfo_check:
-            _log("DEBUG", f"TIER 2 - Checking NFO files for NFOGuard dates for {len(episodes_needing_nfo_check)} episodes")
-            
-            for (season, episode) in episodes_needing_nfo_check:
-                # Look for existing NFO files for this episode
-                season_dir = series_path / config.get_season_dir_name(season)
-                episode_files = disk_episodes[(season, episode)]
-                
-                nfo_found = False
-                for episode_file in episode_files:
-                    # Try to find matching NFO file
-                    nfo_path = episode_file.with_suffix('.nfo')
-                    if nfo_path.exists():
-                        # Extract NFOGuard data from episode NFO
-                        nfo_data = self.nfo_manager.extract_nfoguard_dates_from_nfo(nfo_path)
-                        if nfo_data:
-                            aired = nfo_data.get('aired') 
-                            dateadded = nfo_data.get('dateadded')
-                            source = nfo_data.get('source', 'nfo_cache')
-                            
-                            _log("DEBUG", f"S{season:02d}E{episode:02d}: NFO data found - aired={aired}, dateadded={dateadded}, source={source}")
-                            
-                            # Skip incomplete NFO files with "unknown" source or no useful dates
-                            if source == "unknown" and not dateadded and not aired:
-                                _log("INFO", f"S{season:02d}E{episode:02d}: Ignoring incomplete NFO file with source 'unknown' and no dates")
-                                break  # Break out of NFO search to mark episode as needing API lookup
-                            
-                            # Apply fallback logic if NFO has aired but no dateadded
-                            if not dateadded and aired:
-                                dateadded = aired
-                                source = f"{source}_aired_fallback" if source != 'nfo_cache' else 'nfo_aired_fallback'
-                                _log("DEBUG", f"S{season:02d}E{episode:02d}: NFO has aired but no dateadded, using aired as fallback: {dateadded}")
-                            
-                            if dateadded:
-                                episode_dates[(season, episode)] = (aired, dateadded, source)
-                                nfo_cache_hits += 1
-                                nfo_found = True
-                                
-                                # Cache NFO data in database for future lookups
-                                self.db.upsert_episode_date(imdb_id, season, episode, aired, dateadded, source, True)
-                                _log("DEBUG", f"NFO cache hit for S{season:02d}E{episode:02d}: {dateadded} - cached in DB")
-                                break
-                
-                if not nfo_found:
-                    # No NFO data found - needs API lookup
-                    episodes_needing_lookup.append((season, episode))
-            
-            _log("INFO", f"NFO cache hits: {nfo_cache_hits}/{len(episodes_needing_nfo_check)} episodes. Need API lookup: {len(episodes_needing_lookup)}")
-        
-        # TIER 3: Only call Sonarr API for episodes not in database or NFO files
+        _log("INFO", f"TIER 1 - Database cache hits: {db_cache_hits}/{len(disk_episodes)} episodes. Need API lookup: {len(episodes_needing_nfo_check)}")
+
+        # TIER 2: Query Sonarr API for episodes not in database (NFO layer removed in Phase 2)
+        episodes_needing_lookup = episodes_needing_nfo_check  # Renamed for clarity
         if episodes_needing_lookup:
-            _log("DEBUG", f"TIER 3 - Querying Sonarr for {len(episodes_needing_lookup)} episodes missing from database and NFO files")
+            _log("DEBUG", f"TIER 2 - Querying Sonarr for {len(episodes_needing_lookup)} episodes missing from database")
             sonarr_episodes = self._get_sonarr_episodes(imdb_id, episodes_needing_lookup)
             
             # Process episodes that needed lookup
@@ -385,77 +320,35 @@ class TVProcessor:
         return episode_dates
     
     def _gather_episode_dates_nfo_first(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 dates for incomplete mode: Check NFO files first for missing dateadded elements"""
-        _log("INFO", f"🔍 NFO-FIRST MODE: Checking {len(disk_episodes)} episodes for missing dateadded in NFO files")
+        """Gather episode dates for incomplete mode: Database-first then API (NFO checks removed in Phase 2)"""
+        _log("INFO", f"🔍 INCOMPLETE MODE: Checking {len(disk_episodes)} episodes for missing data")
         episode_dates = {}
-        episodes_needing_db_check = []
         episodes_needing_api_lookup = []
-        
-        # STEP 1: Check each NFO file to determine if dateadded is missing
-        _log("DEBUG", f"STEP 1 - Checking NFO files for missing dateadded elements")
-        nfo_complete_count = 0
-        
+
+        # STEP 1: Check database for all episodes (NFO check removed in Phase 2)
+        _log("DEBUG", f"STEP 1 - Checking database for {len(disk_episodes)} episodes")
+        db_hits = 0
+
         for (season, episode) in disk_episodes:
-            season_dir = series_path / config.get_season_dir_name(season)
-            episode_files = disk_episodes[(season, episode)]
-            
-            nfo_has_dateadded = False
-            nfo_data = None
-            
-            # Look for NFO file for this episode
-            for episode_file in episode_files:
-                nfo_path = episode_file.with_suffix('.nfo')
-                if nfo_path.exists():
-                    # Extract NFOGuard data from episode NFO
-                    nfo_data = self.nfo_manager.extract_nfoguard_dates_from_nfo(nfo_path)
-                    if nfo_data and nfo_data.get('dateadded'):
-                        # NFO has dateadded - this episode is complete
-                        aired = nfo_data.get('aired')
-                        dateadded = nfo_data.get('dateadded') 
-                        source = nfo_data.get('source', 'nfo_cache')
-                        episode_dates[(season, episode)] = (aired, dateadded, source)
-                        nfo_complete_count += 1
-                        nfo_has_dateadded = True
-                        _log("DEBUG", f"S{season:02d}E{episode:02d}: NFO has dateadded={dateadded}, marked as complete")
-                        break
-            
-            if not nfo_has_dateadded:
-                # NFO missing or missing dateadded - needs further processing
-                if nfo_data:
-                    # NFO exists but missing dateadded
-                    _log("DEBUG", f"S{season:02d}E{episode:02d}: NFO exists but missing dateadded - needs DB/API lookup")
-                else:
-                    # No NFO file found
-                    _log("DEBUG", f"S{season:02d}E{episode:02d}: No NFO file found - needs DB/API lookup")
-                episodes_needing_db_check.append((season, episode))
-        
-        _log("INFO", f"NFO files with dateadded: {nfo_complete_count}/{len(disk_episodes)} episodes. Need DB check: {len(episodes_needing_db_check)}")
-        
-        # STEP 2: For episodes missing dateadded in NFO, check database
-        if episodes_needing_db_check:
-            _log("DEBUG", f"STEP 2 - Checking database for {len(episodes_needing_db_check)} episodes missing dateadded")
-            db_hits = 0
-            
-            for (season, episode) in episodes_needing_db_check:
-                db_result = self.db.get_episode_date(imdb_id, season, episode)
-                
-                if db_result and db_result.get('dateadded'):
-                    # Found in database - use cached data and will add to NFO later
-                    aired = db_result.get('aired')
-                    dateadded = db_result.get('dateadded')
-                    source = db_result.get('source', 'database_cache')
-                    episode_dates[(season, episode)] = (aired, dateadded, source)
-                    db_hits += 1
-                    _log("DEBUG", f"S{season:02d}E{episode:02d}: Database has dateadded={dateadded} - will add to NFO")
-                else:
-                    # Not in database or incomplete - needs API lookup
-                    episodes_needing_api_lookup.append((season, episode))
-            
-            _log("INFO", f"Database hits: {db_hits}/{len(episodes_needing_db_check)} episodes. Need API lookup: {len(episodes_needing_api_lookup)}")
-        
-        # STEP 3: For episodes still missing dateadded, query Sonarr
+            db_result = self.db.get_episode_date(imdb_id, season, episode)
+
+            if db_result and db_result.get('dateadded'):
+                # Found in database - use cached data
+                aired = db_result.get('aired')
+                dateadded = db_result.get('dateadded')
+                source = db_result.get('source', 'database_cache')
+                episode_dates[(season, episode)] = (aired, dateadded, source)
+                db_hits += 1
+                _log("DEBUG", f"S{season:02d}E{episode:02d}: Database has dateadded={dateadded}")
+            else:
+                # Not in database or incomplete - needs API lookup
+                episodes_needing_api_lookup.append((season, episode))
+
+        _log("INFO", f"Database hits: {db_hits}/{len(disk_episodes)} episodes. Need API lookup: {len(episodes_needing_api_lookup)}")
+
+        # STEP 2: For episodes missing from database, query Sonarr
         if episodes_needing_api_lookup:
-            _log("DEBUG", f"STEP 3 - Querying Sonarr for {len(episodes_needing_api_lookup)} episodes missing from NFO and database")
+            _log("DEBUG", f"STEP 2 - Querying Sonarr for {len(episodes_needing_api_lookup)} episodes missing from database")
             sonarr_episodes = self._get_sonarr_episodes(imdb_id, episodes_needing_api_lookup)
             
             for (season, episode) in episodes_needing_api_lookup:
@@ -503,7 +396,7 @@ class TVProcessor:
                 
                 episode_dates[(season, episode)] = (aired, dateadded, source)
         
-        _log("INFO", f"🔍 NFO-FIRST COMPLETE: {len(episode_dates)} episodes processed")
+        _log("INFO", f"🔍 INCOMPLETE MODE COMPLETE: {len(episode_dates)} episodes processed")
         for (s, e), (aired, dateadded, source) in episode_dates.items():
             _log("INFO", f"   S{s:02d}E{e:02d}: aired={aired}, dateadded={dateadded}, source={source}")
         
@@ -648,18 +541,8 @@ class TVProcessor:
         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)
+                # NFO file operations removed - database is now the single source of truth
+                # (Phase 1: Remove NFO file write operations)
                 
                 # Save to database
                 try:
@@ -728,16 +611,8 @@ class TVProcessor:
         
         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)
+        # NFO file operations removed - database is now the single source of truth
+        # (Phase 1: Remove NFO file write operations)
         
         # Save to database
         self.db.upsert_episode_date(imdb_id, season_num, episode_num, aired, dateadded, source, True)
@@ -765,7 +640,7 @@ class TVProcessor:
         Returns:
             Dictionary with processing results
         """
-        imdb_id = self.nfo_manager.parse_imdb_from_path(series_path)
+        imdb_id = parse_imdb_from_path(series_path)  # Phase 3: Using imdb_utils
         if not imdb_id:
             return {"status": "error", "reason": f"No IMDb ID found in series path: {series_path}"}
         
@@ -787,25 +662,8 @@ class TVProcessor:
         
         for (season, episode), (aired, dateadded, source) in episode_dates.items():
             if (season, episode) in disk_episodes:
-                season_dir = series_path / config.get_season_dir_name(season)
-                
-                # Prepare NFO creation data
-                if config.manage_nfo:
-                    episode_data_list.append({
-                        'season_dir': season_dir,
-                        'season': season,
-                        'episode': episode,
-                        'aired': aired,
-                        'dateadded': dateadded,
-                        'source': source,
-                        'lock_metadata': config.lock_metadata
-                    })
-                
-                # Prepare mtime operations
-                if config.fix_dir_mtimes and dateadded:
-                    video_files = disk_episodes[(season, episode)]
-                    for video_file in video_files:
-                        mtime_operations.append((video_file, dateadded))
+                # NFO file operations removed - database is now the single source of truth
+                # (Phase 1: Remove NFO file write operations)
                 
                 # Save to database
                 try:
@@ -815,27 +673,10 @@ class TVProcessor:
                     _log("ERROR", f"S{season:02d}E{episode:02d}: Database write failed: {e}")
                     # Continue processing other episodes
         
-        # Process NFOs and mtimes concurrently
+        # NFO and mtime operations removed - database is now the single source of truth
+        # (Phase 1: Remove NFO file write operations)
         results = {}
         
-        if episode_data_list:
-            _log("INFO", f"Creating {len(episode_data_list)} episode NFOs concurrently")
-            nfo_results = await self.async_nfo_manager.async_batch_create_episode_nfos(
-                episode_data_list,
-                max_concurrent=config.max_concurrent
-            )
-            results['nfo_created'] = sum(nfo_results)
-            results['nfo_failed'] = len(nfo_results) - sum(nfo_results)
-        
-        if mtime_operations:
-            _log("INFO", f"Setting mtimes for {len(mtime_operations)} files concurrently")
-            mtime_results = await self.async_nfo_manager.async_batch_set_file_mtimes(
-                mtime_operations,
-                max_concurrent=10
-            )
-            results['mtime_updated'] = sum(mtime_results)
-            results['mtime_failed'] = len(mtime_results) - sum(mtime_results)
-        
         _log("INFO", f"Completed async processing TV series: {series_path.name}")
         
         return {
@@ -892,7 +733,7 @@ class TVProcessor:
     
     def process_webhook_episodes(self, series_path: Path, webhook_episodes: List[Dict[str, Any]]) -> None:
         """Process only the specific episodes mentioned in a webhook (targeted mode)"""
-        imdb_id = self.nfo_manager.parse_imdb_from_path(series_path)
+        imdb_id = parse_imdb_from_path(series_path)  # Phase 3: Using imdb_utils
         if not imdb_id:
             _log("ERROR", f"No IMDb ID found in series path: {series_path}")
             return
@@ -942,18 +783,8 @@ class TVProcessor:
             aired, dateadded, source = self._get_webhook_episode_date(imdb_id, season_num, episode_num, series_metadata, webhook_episode)
             enhanced_metadata = self._get_episode_metadata(series_metadata, season_num, episode_num, season_dir) if series_metadata else self._get_episode_metadata(None, season_num, episode_num, season_dir)
             
-            # Create NFO
-            if config.manage_nfo:
-                self.nfo_manager.create_episode_nfo(
-                    season_dir,
-                    season_num, episode_num, aired, dateadded, source, config.lock_metadata,
-                    enhanced_metadata
-                )
-            
-            # Update file mtimes
-            if config.fix_dir_mtimes and dateadded:
-                for episode_file in episode_files:
-                    self.nfo_manager.set_file_mtime(episode_file, dateadded)
+            # NFO file operations removed - database is now the single source of truth
+            # (Phase 1: Remove NFO file write operations)
             
             # Save to database
             self.db.upsert_episode_date(imdb_id, season_num, episode_num, aired, dateadded, source, True)
@@ -1208,17 +1039,13 @@ class TVProcessor:
                 dateadded = episode_data.get('dateadded')
                 
                 # Get IMDb ID
-                imdb_id = self.nfo_manager.parse_imdb_from_path(series_path)
+                imdb_id = parse_imdb_from_path(series_path)  # Phase 3: Using imdb_utils
                 if not imdb_id:
                     return {"status": "error", "reason": "No IMDb ID found"}
                 
-                # Create NFO if needed
-                nfo_success = True
-                if config.manage_nfo:
-                    season_dir = series_path / config.get_season_dir_name(season)
-                    nfo_success = await self.async_nfo_manager.async_create_episode_nfo(
-                        season_dir, season, episode, aired, dateadded, "webhook", config.lock_metadata
-                    )
+                # NFO file operations removed - database is now the single source of truth
+                # (Phase 1: Remove NFO file write operations)
+                nfo_success = True  # Always True since we're not creating NFOs anymore
                 
                 # Update database
                 self.db.upsert_episode_date(imdb_id, season, episode, aired, dateadded, "webhook", True)

processors/tv_series_processor.py

@@ -19,8 +19,8 @@ from core.logging import _log, convert_utc_to_local
 
 class TVSeriesProcessor:
     """Clean TV series processor with video filename matching"""
-    
-    def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager, 
+
+    def __init__(self, db: NFOGuardDatabase, nfo_manager: NFOManager,
                  path_mapper: PathMapper, sonarr_client: SonarrClient):
         self.db = db
         self.nfo_manager = nfo_manager  # Keep for series/season NFOs
@@ -28,6 +28,19 @@ class TVSeriesProcessor:
         self.path_mapper = path_mapper
         self.sonarr = sonarr_client
         self.external_manager = ExternalClientManager()
+
+        # Initialize Sonarr database client for high-performance queries
+        self.sonarr_db = None
+        try:
+            from clients.sonarr_db_client import SonarrDbClient
+            self.sonarr_db = SonarrDbClient.from_env()
+            if self.sonarr_db:
+                _log("INFO", "✅ SONARR DB MODE: Direct database access enabled")
+            else:
+                _log("INFO", "⚠️ SONARR API MODE: Using API (configure SONARR_DB_TYPE for better performance)")
+        except Exception as e:
+            _log("WARNING", f"Sonarr DB client initialization failed, using API: {e}")
+            self.sonarr_db = None
     
     def process_series_manual_scan(self, series_path: Path) -> bool:
         """Process a TV series during manual scan"""
@@ -219,15 +232,66 @@ class TVSeriesProcessor:
         return False
     
     def _get_episode_dates_from_sonarr(self, imdb_id: str, season_num: int, episode_num: int) -> Tuple[Optional[str], Optional[str], str]:
-        """Get episode dates from Sonarr API with proper fallback"""
+        """Get episode dates from Sonarr (DB first, then API fallback)"""
         aired = None
         dateadded = None
         source = "no_data_found"
-        
+
+        # TIER 1: Try Sonarr database (high performance)
+        if self.sonarr_db:
+            try:
+                # Find series by IMDb
+                series = self.sonarr_db.get_series_by_imdb(imdb_id)
+                if series:
+                    series_id = series['id']
+
+                    # Get all episodes for series
+                    episodes = self.sonarr_db.get_all_episodes_for_series(series_id)
+
+                    # Find target episode
+                    target_episode = None
+                    for ep in episodes:
+                        if ep['season'] == season_num and ep['episode'] == episode_num:
+                            target_episode = ep
+                            break
+
+                    if target_episode:
+                        # Get air date
+                        aired = target_episode.get('air_date')
+
+                        # Try to get import date from history
+                        episode_id = target_episode['id']
+                        import_date, import_source = self.sonarr_db.get_episode_import_date(episode_id)
+
+                        if import_date:
+                            dateadded = import_date
+                            source = import_source
+                            _log("INFO", f"✅ DB: Found import date for S{season_num:02d}E{episode_num:02d}: {dateadded}")
+                            return aired, dateadded, source
+
+                        # Fallback to episode file date
+                        file_date = self.sonarr_db.get_episode_file_date(series_id, season_num, episode_num)
+                        if file_date:
+                            dateadded = file_date
+                            source = "sonarr:db.file.dateAdded"
+                            _log("INFO", f"✅ DB: Using file date for S{season_num:02d}E{episode_num:02d}: {dateadded}")
+                            return aired, dateadded, source
+
+                        # Use air date as fallback
+                        if aired:
+                            dateadded = convert_utc_to_local(aired)
+                            source = "sonarr:db.airDate"
+                            _log("WARNING", f"⚠️ DB: No import date, using air date for S{season_num:02d}E{episode_num:02d}: {dateadded}")
+                            return aired, dateadded, source
+
+            except Exception as e:
+                _log("WARNING", f"Sonarr DB query failed for S{season_num:02d}E{episode_num:02d}, falling back to API: {e}")
+
+        # TIER 2: Fall back to Sonarr API
         if not self.sonarr.enabled:
             _log("WARNING", "Sonarr not enabled, cannot get episode dates")
             return aired, dateadded, source
-        
+
         try:
             # Find series in Sonarr using lookup endpoint first
             series = self.sonarr.series_by_imdb(imdb_id)
@@ -239,25 +303,25 @@ class TVSeriesProcessor:
                 if not series:
                     _log("WARNING", f"Series not found via direct search either for IMDb: {imdb_id}")
                     # Fall through to external API fallback
-            
+
             if series:
                 # Get episodes for series
                 episodes = self.sonarr.episodes_for_series(series["id"])
                 target_episode = None
-                
+
                 for episode in episodes:
-                    if (episode.get("seasonNumber") == season_num and 
+                    if (episode.get("seasonNumber") == season_num and
                         episode.get("episodeNumber") == episode_num):
                         target_episode = episode
                         break
-                
+
                 if not target_episode:
                     _log("WARNING", f"Episode S{season_num:02d}E{episode_num:02d} not found in Sonarr")
                     # Don't return here - fall through to external API fallback
                 else:
                     # Get airdate
                     aired = target_episode.get("airDateUtc")
-                    
+
                     # Try to get import history
                     episode_id = target_episode.get("id")
                     if episode_id:
@@ -266,17 +330,17 @@ class TVSeriesProcessor:
                             # Sonarr import dates are already in local timezone despite 'Z' suffix
                             # Remove 'Z' and use as-is to avoid double timezone conversion
                             dateadded = import_date.replace('Z', '') if 'Z' in import_date else import_date
-                            source = "sonarr:history.import"
-                            _log("INFO", f"Found import date for S{season_num:02d}E{episode_num:02d}: {dateadded} (no timezone conversion)")
+                            source = "sonarr:api.history.import"
+                            _log("INFO", f"✅ API: Found import date for S{season_num:02d}E{episode_num:02d}: {dateadded}")
                             return aired, dateadded, source
-                    
+
                     # Fallback to airdate if no import history
                     if aired:
                         dateadded = convert_utc_to_local(aired)
-                        source = "sonarr:episode.airDateUtc"
-                        _log("WARNING", f"No import history for S{season_num:02d}E{episode_num:02d}, using airdate: {dateadded}")
+                        source = "sonarr:api.episode.airDateUtc"
+                        _log("WARNING", f"⚠️ API: No import history for S{season_num:02d}E{episode_num:02d}, using airdate: {dateadded}")
                         return aired, dateadded, source
-        
+
         except Exception as e:
             _log("ERROR", f"Sonarr API error for S{season_num:02d}E{episode_num:02d}: {e}")
         

start_web.py

@@ -29,7 +29,7 @@ def create_web_app() -> FastAPI:
     app = FastAPI(
         title="NFOGuard Web Interface",
         description="Web interface for NFOGuard media database management",
-        version="2.7.0-web",
+        version="2.9.0-fixes-only-files",
         docs_url=None,  # Disable docs in production
         redoc_url=None
     )
@@ -94,7 +94,7 @@ def setup_static_files(app: FastAPI) -> None:
                 "status": "healthy",
                 "service": "nfoguard-web",
                 "timestamp": time.time(),
-                "version": "2.8.0-web"
+                "version": "2.9.0-fixes-only-files"
             }
         except Exception as e:
             from fastapi import HTTPException

static/index.html

@@ -382,6 +382,39 @@
                             <i class="fas fa-sync"></i> Refresh Stats
                         </button>
                     </div>
+
+                    <div class="tool-card">
+                        <h3><i class="fas fa-upload"></i> Populate Database</h3>
+                        <p>Bulk import data from Radarr/Sonarr into NFOGuard database</p>
+                        <form id="populate-form">
+                            <div class="form-group">
+                                <label>Media Type:</label>
+                                <select id="populate-media-type" required>
+                                    <option value="both">Movies & TV Shows</option>
+                                    <option value="movies">Movies Only</option>
+                                    <option value="tv">TV Shows Only</option>
+                                </select>
+                            </div>
+                            <button type="submit" class="btn btn-primary">
+                                <i class="fas fa-play"></i> Start Population
+                            </button>
+                        </form>
+                        <div id="populate-status" class="scan-status" style="display: none;">
+                            <div class="scan-progress">
+                                <div class="progress-bar">
+                                    <div class="progress-fill" id="populate-progress-bar"></div>
+                                </div>
+                                <div class="scan-info">
+                                    <span id="populate-current-operation">Running...</span>
+                                    <span id="populate-progress-text">In Progress</span>
+                                </div>
+                            </div>
+                            <div id="populate-results" class="stats-display" style="margin-top: 10px;"></div>
+                            <button class="btn btn-secondary btn-sm" onclick="stopPopulatePolling()">
+                                <i class="fas fa-times"></i> Hide Status
+                            </button>
+                        </div>
+                    </div>
                 </div>
             </div>
         </main>

static/js/app.js

@@ -77,6 +77,7 @@ function initializeEventListeners() {
     document.getElementById('edit-form').addEventListener('submit', handleEditSubmit);
     document.getElementById('bulk-update-form').addEventListener('submit', handleBulkUpdate);
     document.getElementById('manual-scan-form').addEventListener('submit', handleManualScan);
+    document.getElementById('populate-form').addEventListener('submit', handlePopulateDatabase);
 }
 
 // API calls
@@ -1742,3 +1743,186 @@ async function bulkDeleteSelected() {
         showToast(`❌ Failed to delete ${failCount} episode(s)`, 'error');
     }
 }
+
+// ---------------------------
+// Database Population Functions
+// ---------------------------
+
+async function handlePopulateDatabase(event) {
+    event.preventDefault();
+
+    const mediaType = document.getElementById('populate-media-type').value;
+
+    // Validate input
+    if (!mediaType) {
+        showToast('❌ Please select media type', 'error');
+        return;
+    }
+
+    // Confirm with user
+    const confirmMsg = `Are you sure you want to populate the database with ${mediaType}? This will query Radarr/Sonarr and may take several minutes.`;
+    if (!confirm(confirmMsg)) {
+        return;
+    }
+
+    try {
+        // Show populate status
+        showPopulateStatus();
+
+        // Start the population
+        showToast('🚀 Starting database population...', 'info');
+        const response = await fetch(`/admin/populate-database?media_type=${mediaType}`, {
+            method: 'POST',
+            credentials: 'include'
+        });
+
+        if (!response.ok) {
+            throw new Error(`HTTP ${response.status}: ${response.statusText}`);
+        }
+
+        const result = await response.json();
+
+        if (result.status === 'started') {
+            showToast('✅ Population started successfully', 'success');
+            // Start polling for status
+            startPopulatePolling();
+        } else {
+            showToast(`ℹ️ ${result.message || 'Population completed'}`, 'info');
+            hidePopulateStatus();
+        }
+
+    } catch (error) {
+        console.error('Database population failed:', error);
+        showToast(`❌ Population failed: ${error.message}`, 'error');
+        hidePopulateStatus();
+    }
+}
+
+function showPopulateStatus() {
+    const populateStatus = document.getElementById('populate-status');
+    const progressBar = document.getElementById('populate-progress-bar');
+    const operationText = document.getElementById('populate-current-operation');
+    const progressText = document.getElementById('populate-progress-text');
+    const resultsDiv = document.getElementById('populate-results');
+
+    populateStatus.style.display = 'block';
+    progressBar.style.width = '0%';
+    operationText.textContent = 'Initializing...';
+    progressText.textContent = '0%';
+    resultsDiv.innerHTML = '';
+}
+
+function hidePopulateStatus() {
+    const populateStatus = document.getElementById('populate-status');
+    if (populateStatus) {
+        populateStatus.style.display = 'none';
+    }
+}
+
+function startPopulatePolling() {
+    // Poll every 2 seconds for populate status
+    window.populatePollingInterval = setInterval(async () => {
+        try {
+            const response = await fetch('/api/populate/status');
+            if (!response.ok) {
+                throw new Error('Failed to get populate status');
+            }
+
+            const status = await response.json();
+            updatePopulateProgress(status);
+
+            // Stop polling if population is complete
+            if (!status.running && status.completed) {
+                stopPopulatePolling();
+                showToast('✅ Database population completed!', 'success');
+            }
+
+        } catch (error) {
+            console.error('Failed to poll populate status:', error);
+            // Don't show error toast repeatedly, just stop polling
+            stopPopulatePolling();
+        }
+    }, 2000);
+}
+
+function stopPopulatePolling() {
+    if (window.populatePollingInterval) {
+        clearInterval(window.populatePollingInterval);
+        window.populatePollingInterval = null;
+    }
+}
+
+function updatePopulateProgress(status) {
+    const progressBar = document.getElementById('populate-progress-bar');
+    const operationText = document.getElementById('populate-current-operation');
+    const progressText = document.getElementById('populate-progress-text');
+    const resultsDiv = document.getElementById('populate-results');
+
+    if (status.error) {
+        progressBar.style.width = '100%';
+        progressBar.style.backgroundColor = '#e74c3c';
+        operationText.textContent = 'Error occurred';
+        progressText.textContent = 'Failed';
+        resultsDiv.innerHTML = `<p style="color: #e74c3c;">Error: ${status.error}</p>`;
+        return;
+    }
+
+    if (!status.running && status.completed) {
+        progressBar.style.width = '100%';
+        operationText.textContent = 'Population completed';
+        progressText.textContent = '100%';
+
+        // Display results
+        let resultsHTML = '<h4>Population Results:</h4>';
+
+        if (status.movies && status.movies.stats) {
+            const m = status.movies.stats;
+            resultsHTML += `
+                <div style="margin: 10px 0;">
+                    <strong>Movies:</strong><br>
+                    Total: ${m.total || 0} | Added: ${m.added || 0} | Skipped: ${m.skipped || 0} | Errors: ${m.errors || 0}<br>
+                    Duration: ${m.duration ? m.duration.toFixed(2) : 0}s
+                </div>
+            `;
+        }
+
+        if (status.tv && status.tv.stats) {
+            const t = status.tv.stats;
+            resultsHTML += `
+                <div style="margin: 10px 0;">
+                    <strong>TV Shows:</strong><br>
+                    Series: ${t.total_series || 0} | Episodes: ${t.total_episodes || 0}<br>
+                    Added: ${t.added || 0} | Skipped: ${t.skipped || 0} | Errors: ${t.errors || 0}<br>
+                    Duration: ${t.duration ? t.duration.toFixed(2) : 0}s
+                </div>
+            `;
+        }
+
+        resultsDiv.innerHTML = resultsHTML;
+        return;
+    }
+
+    // Update progress based on status
+    let totalProgress = 0;
+    let progressDetails = '';
+
+    if (status.movies && status.movies.status === 'running') {
+        totalProgress = 50;
+        progressDetails = 'Processing movies...';
+    } else if (status.movies && status.movies.status === 'completed') {
+        totalProgress = 50;
+        progressDetails = 'Movies completed, processing TV...';
+    }
+
+    if (status.tv && status.tv.status === 'running') {
+        totalProgress = 75;
+        progressDetails = 'Processing TV shows...';
+    } else if (status.tv && status.tv.status === 'completed') {
+        totalProgress = 100;
+        progressDetails = 'Completed';
+    }
+
+    progressBar.style.width = `${totalProgress}%`;
+    operationText.textContent = progressDetails;
+    progressText.textContent = `${totalProgress}%`;
+}

utils/imdb_utils.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+IMDb ID Extraction Utilities
+Parses IMDb IDs from directory/file names (no file I/O)
+Phase 3: Replaces NFOManager for IMDb ID extraction only
+"""
+import re
+from pathlib import Path
+from typing import Optional
+
+
+def parse_imdb_from_path(path: Path) -> Optional[str]:
+    """
+    Extract IMDb ID from directory path or filename using regex patterns.
+    Does NOT read any files - only parses the path string.
+
+    Supported patterns:
+    - [imdb-tt1234567]
+    - [tt1234567]
+    - {imdb-tt1234567}
+    - (imdb-tt1234567)
+    - -tt1234567 (at end)
+    - _tt1234567 (at end)
+
+    Args:
+        path: Path object to parse
+
+    Returns:
+        IMDb ID (e.g., "tt1234567") or None if not found
+    """
+    path_str = str(path).lower()
+
+    # Try [imdb-ttXXXXXXX] format first (most explicit)
+    match = re.search(r'\[imdb-?(tt\d+)\]', path_str)
+    if match:
+        return match.group(1)
+
+    # Try standalone [ttXXXXXXX] format in brackets
+    match = re.search(r'\[(tt\d+)\]', path_str)
+    if match:
+        return match.group(1)
+
+    # Try {imdb-ttXXXXXXX} format with curly braces
+    match = re.search(r'\{imdb-?(tt\d+)\}', path_str)
+    if match:
+        return match.group(1)
+
+    # Try (imdb-ttXXXXXXX) format with parentheses
+    match = re.search(r'\(imdb-?(tt\d+)\)', path_str)
+    if match:
+        return match.group(1)
+
+    # Try ttXXXXXXX at end of filename/dirname (common pattern)
+    match = re.search(r'[-_\s](tt\d+)$', path_str)
+    if match:
+        return match.group(1)
+
+    return None
+
+
+def find_imdb_in_directory(directory: Path) -> Optional[str]:
+    """
+    Find IMDb ID from directory name or filenames within the directory.
+    Does NOT read file contents - only checks filenames.
+
+    Args:
+        directory: Directory path to search
+
+    Returns:
+        IMDb ID or None if not found
+    """
+    # First try directory name itself
+    imdb_id = parse_imdb_from_path(directory)
+    if imdb_id:
+        return imdb_id
+
+    # Try all filenames in the directory
+    if directory.is_dir():
+        for file_path in directory.iterdir():
+            if file_path.is_file():
+                imdb_id = parse_imdb_from_path(file_path)
+                if imdb_id:
+                    return imdb_id
+
+    return None

utils/logging.py

@@ -96,19 +96,21 @@ def _setup_file_logging():
     # Clear any existing handlers to avoid duplicates
     logger.handlers.clear()
     
+    # Try to set up file logging
+    file_logging_enabled = False
     try:
         file_handler = SafeRotatingFileHandler(
             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)
+        file_logging_enabled = True
     except Exception as e:
-        # If RotatingFileHandler fails, fall back to regular FileHandler
-        print(f"Warning: Could not setup rotating file handler ({e}), using regular file handler")
+        # If RotatingFileHandler fails, try regular FileHandler
         try:
             file_handler = logging.FileHandler(log_dir / "nfoguard.log")
             formatter = TimezoneAwareFormatter(
@@ -116,8 +118,20 @@ def _setup_file_logging():
             )
             file_handler.setFormatter(formatter)
             logger.addHandler(file_handler)
+            file_logging_enabled = True
         except Exception as e2:
-            print(f"Error: Could not setup any file logging: {e2}")
+            # File logging not available (e.g., read-only filesystem)
+            # Fall back to console-only logging silently
+            pass
+
+    # If file logging failed, ensure console handler is added
+    if not file_logging_enabled:
+        console_handler = logging.StreamHandler()
+        formatter = TimezoneAwareFormatter(
+            '[%(asctime)s] %(levelname)s: %(message)s'
+        )
+        console_handler.setFormatter(formatter)
+        logger.addHandler(console_handler)
     
     return logger
 

webhooks/webhook_batcher.py

@@ -10,12 +10,14 @@ from concurrent.futures import ThreadPoolExecutor
 
 from config.settings import config
 from utils.logging import _log
+from utils.imdb_utils import find_imdb_in_directory, parse_imdb_from_path  # Phase 3: Replaced NFOManager
 
 
 class WebhookBatcher:
     """Batches webhook events to avoid processing storms"""
-    
+
     def __init__(self, nfo_manager=None):
+        # nfo_manager parameter kept for backward compatibility but no longer used (Phase 3)
         self.pending: Dict[str, Dict] = {}
         self.timers: Dict[str, threading.Timer] = {}
         self.processing: Set[str] = set()
@@ -24,8 +26,6 @@ class WebhookBatcher:
         # Will be set by the application when processors are available
         self.tv_processor = None
         self.movie_processor = None
-        # NFO manager for comprehensive IMDb detection
-        self.nfo_manager = nfo_manager
     
     def set_processors(self, tv_processor, movie_processor):
         """Set the processor instances"""
@@ -84,56 +84,40 @@ class WebhookBatcher:
             # 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
-                
-                # Use comprehensive IMDb detection (directory, filenames, NFO files)
-                if self.nfo_manager:
-                    detected_imdb = self.nfo_manager.find_movie_imdb_id(path_obj)
-                    imdb_match = False
-                    if detected_imdb:
-                        # Compare with and without 'tt' prefix for flexibility
-                        if detected_imdb == expected_imdb or detected_imdb.replace('tt', '') == expected_imdb.replace('tt', ''):
-                            imdb_match = True
-                    
-                    if not imdb_match:
-                        _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} not found via comprehensive detection in path {path_str}")
-                        _log("ERROR", f"Detected IMDb: {detected_imdb}, Expected: {expected_imdb}")
-                        _log("ERROR", f"This prevents processing wrong movies due to batch corruption")
-                        return
-                    _log("DEBUG", f"Batch validation passed: IMDb {expected_imdb} matches detected {detected_imdb}")
-                else:
-                    # Fallback to simple string search if nfo_manager not available
-                    if expected_imdb not in path_str.lower():
-                        _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} not found in path {path_str} (fallback mode)")
-                        _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 (fallback mode)")
+
+                # Use imdb_utils for IMDb detection (Phase 3: no NFO reading)
+                detected_imdb = find_imdb_in_directory(path_obj)
+                imdb_match = False
+                if detected_imdb:
+                    # Compare with and without 'tt' prefix for flexibility
+                    if detected_imdb == expected_imdb or detected_imdb.replace('tt', '') == expected_imdb.replace('tt', ''):
+                        imdb_match = True
+
+                if not imdb_match:
+                    _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} but found {detected_imdb} in {path_str}")
+                    _log("ERROR", f"Detected IMDb: {detected_imdb}, Expected: {expected_imdb}")
+                    _log("ERROR", f"This prevents processing wrong movies due to batch corruption")
+                    return
+                _log("DEBUG", f"Batch validation passed: IMDb {expected_imdb} matches detected {detected_imdb}")
             
             # CRITICAL: Validate that the path contains the expected IMDb ID for TV shows
             if media_type == 'tv':
                 expected_imdb = key.replace('tv:', '') if key.startswith('tv:') else key
-                
-                # Use comprehensive IMDb detection (directory, filenames, tvshow.nfo files)
-                if self.nfo_manager:
-                    detected_imdb = self.nfo_manager.find_series_imdb_id(path_obj)
-                    imdb_match = False
-                    if detected_imdb:
-                        # Compare with and without 'tt' prefix for flexibility
-                        if detected_imdb == expected_imdb or detected_imdb.replace('tt', '') == expected_imdb.replace('tt', ''):
-                            imdb_match = True
-                    
-                    if not imdb_match:
-                        _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} not found via comprehensive detection in TV path {path_str}")
-                        _log("ERROR", f"Detected TV IMDb: {detected_imdb}, Expected: {expected_imdb}")
-                        _log("ERROR", f"This prevents processing wrong TV series due to batch corruption")
-                        return
-                    _log("DEBUG", f"TV batch validation passed: IMDb {expected_imdb} matches detected {detected_imdb}")
-                else:
-                    # Fallback to simple string search if nfo_manager not available
-                    if expected_imdb not in path_str.lower():
-                        _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} not found in TV path {path_str} (fallback mode)")
-                        _log("ERROR", f"This prevents processing wrong TV series due to batch corruption")
-                        return
-                    _log("DEBUG", f"TV batch validation passed: IMDb {expected_imdb} found in path (fallback mode)")
+
+                # Use imdb_utils for IMDb detection (Phase 3: no NFO reading)
+                detected_imdb = parse_imdb_from_path(path_obj)
+                imdb_match = False
+                if detected_imdb:
+                    # Compare with and without 'tt' prefix for flexibility
+                    if detected_imdb == expected_imdb or detected_imdb.replace('tt', '') == expected_imdb.replace('tt', ''):
+                        imdb_match = True
+
+                if not imdb_match:
+                    _log("ERROR", f"BATCH VALIDATION FAILED: Expected IMDb {expected_imdb} but found {detected_imdb} in TV {path_str}")
+                    _log("ERROR", f"Detected TV IMDb: {detected_imdb}, Expected: {expected_imdb}")
+                    _log("ERROR", f"This prevents processing wrong TV series due to batch corruption")
+                    return
+                _log("DEBUG", f"TV batch validation passed: IMDb {expected_imdb} matches detected {detected_imdb}")
                 
                 if not self.tv_processor:
                     _log("ERROR", "TV processor not available")