Implement video transcoding, add dashboard UI, and cleanup repository

.gitignore

@@ -1,3 +1,6 @@
 __pycache__/
 *.pyc
 .env
+*.tar
+*.gz
+ta-organizerr.tar.gz

Dockerfile

@@ -1,6 +1,8 @@
 FROM python:3.11-slim
 WORKDIR /app
-COPY ta_symlink.py .
+COPY . .
+RUN apt-get update && apt-get install -y ffmpeg && rm -rf /var/lib/apt/lists/*
 RUN pip install --no-cache-dir requests flask
+RUN mkdir -p /app/data
 EXPOSE 5000
 CMD ["python", "ta_symlink.py"]

docker-compose.yml

@@ -3,8 +3,12 @@ services:
     build: /mnt/user/appdata/dockerbuildings
     container_name: ta-organizer
     volumes:
-      - /mnt/user/appdata/dockerbuildings/source:/app/source:ro
+      - /mnt/user/appdata/dockerbuildings/source:/app/source
       - /mnt/user/appdata/dockerbuildings/target:/app/target
+      - /mnt/user/appdata/dockerbuildings/data:/app/data
+    ports:
+      - "8002:5000"
     environment:
-      - SCAN_INTERVAL=${SCAN_INTERVAL:-60}
+      - SCAN_INTERVAL=60
+      - ALLOWED_IPS=127.0.0.1,192.168.1.0/24,10.0.0.0/8,172.16.0.0/12
     env_file: /mnt/user/appdata/dockerbuildings/.env

ta_symlink.py

@@ -1,4 +1,3 @@
-
 from pathlib import Path
 import os
 import requests
@@ -6,29 +5,266 @@ import re
 import sys
 import threading
 import time
-from flask import Flask, jsonify, render_template_string, request
+import ipaddress
+from flask import Flask, jsonify, render_template, request, abort
 
 # Load config from environment variables
 API_URL = os.getenv("API_URL", "http://localhost:8457/api")
 VIDEO_URL = os.getenv("VIDEO_URL", "http://localhost:8457/video/")
 API_TOKEN = os.getenv("API_TOKEN", "")
 SCAN_INTERVAL = int(os.getenv("SCAN_INTERVAL", 60)) # Default 60 minutes
+ALLOWED_IPS = [ip.strip() for ip in os.getenv("ALLOWED_IPS", "127.0.0.1").split(",")]
 SOURCE_DIR = Path("/app/source")
 TARGET_DIR = Path("/app/target")
 HEADERS = {"Authorization": f"Token {API_TOKEN}"}
 
 app = Flask(__name__)
 
+# Database setup
+import sqlite3
+from contextlib import contextmanager
+
+DB_PATH = Path("/app/data/videos.db")
+DB_PATH.parent.mkdir(parents=True, exist_ok=True)
+
+@contextmanager
+def get_db():
+    conn = sqlite3.connect(DB_PATH)
+    conn.row_factory = sqlite3.Row
+    try:
+        yield conn
+    finally:
+        conn.close()
+
+def init_db():
+    with get_db() as conn:
+        conn.execute("""
+            CREATE TABLE IF NOT EXISTS videos (
+                video_id TEXT PRIMARY KEY,
+                title TEXT,
+                channel TEXT,
+                published TEXT,
+                symlink TEXT,
+                status TEXT,
+                last_updated TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+            )
+        """)
+        conn.commit()
+
+init_db()
+
+# Global State
 processed_videos = []
+log_buffer = []
+log_lock = threading.Lock()
+transcode_log_buffer = []
+transcode_log_lock = threading.Lock()
 
 # Utility functions
+def log(msg):
+    """Logs a message to stdout and the in-memory buffer."""
+    print(msg, flush=True)
+    with log_lock:
+        log_buffer.append(msg)
+        if len(log_buffer) > 1000:
+            log_buffer.pop(0)
+
+def tlog(msg):
+    """Logs a message to the transcode log buffer."""
+    print(f"[TRANSCODE] {msg}", flush=True)
+    with transcode_log_lock:
+        transcode_log_buffer.append(msg)
+        if len(transcode_log_buffer) > 500:
+            transcode_log_buffer.pop(0)
+
+def detect_encoder():
+    """Detect best available hardware encoder."""
+    import subprocess
+    try:
+        result = subprocess.run(['ffmpeg', '-hide_banner', '-encoders'], 
+                              capture_output=True, text=True)
+        encoders = result.stdout
+        
+        if 'h264_nvenc' in encoders:
+            return 'h264_nvenc'
+        elif 'h264_vaapi' in encoders:
+            return 'h264_vaapi'
+        elif 'h264_videotoolbox' in encoders:
+            return 'h264_videotoolbox'
+        else:
+            return 'libx264'
+    except:
+        return 'libx264'
+
+def probe_codecs(filepath):
+    """Probe video and audio codecs using ffprobe."""
+    import subprocess
+    try:
+        # Get video codec
+        v_result = subprocess.run([
+            'ffprobe', '-v', 'error', '-select_streams', 'v:0',
+            '-show_entries', 'stream=codec_name', '-of', 'csv=p=0', filepath
+        ], capture_output=True, text=True)
+        video_codec = v_result.stdout.strip()
+        
+        # Get audio codec
+        a_result = subprocess.run([
+            'ffprobe', '-v', 'error', '-select_streams', 'a:0',
+            '-show_entries', 'stream=codec_name', '-of', 'csv=p=0', filepath
+        ], capture_output=True, text=True)
+        audio_codec = a_result.stdout.strip()
+        
+        return video_codec, audio_codec
+    except Exception as e:
+        tlog(f"Error probing {filepath}: {e}")
+        return None, None
+
+def transcode_video(filepath, encoder='libx264'):
+    """Transcode a video file to H.264/AAC."""
+    import subprocess
+    
+    original_path = Path(filepath)
+    
+    # Try to resolve symlink first (don't check if it exists, broken symlinks still exist as links)
+    if original_path.is_symlink():
+        try:
+            actual_file = Path(os.readlink(original_path)).resolve()
+            tlog(f"Following symlink: {filepath} -> {actual_file}")
+            
+            # Translate host path to container path
+            # Host: /mnt/user/tubearchives/bp/... → Container: /app/source/...
+            actual_file_str = str(actual_file)
+            if actual_file_str.startswith("/mnt/user/tubearchives/bp"):
+                container_path = actual_file_str.replace("/mnt/user/tubearchives/bp", "/app/source", 1)
+                tlog(f"Translated path: {actual_file} -> {container_path}")
+                filepath = container_path
+            else:
+                filepath = str(actual_file)
+        except Exception as e:
+            tlog(f"Error resolving symlink: {e}")
+            return False
+    elif not original_path.exists():
+        tlog(f"File not found: {filepath}")
+        return False
+    
+    # Now check if the actual file exists
+    if not Path(filepath).exists():
+        tlog(f"Source file not found: {filepath}")
+        return False
+    
+    video_codec, audio_codec = probe_codecs(filepath)
+    
+    if video_codec == 'h264' and audio_codec == 'aac':
+        tlog(f"Already H.264/AAC: {filepath}")
+        return True
+    
+    temp_file = f"{filepath}.temp.mp4"
+    
+    try:
+        # Determine transcode strategy
+        if video_codec == 'h264':
+            tlog(f"Audio-only transcode: {filepath}")
+            cmd = [
+                'ffmpeg', '-v', 'error', '-stats', '-i', filepath,
+                '-c:v', 'copy',
+                '-c:a', 'aac', '-b:a', '192k',
+                '-movflags', '+faststart',
+                '-y', temp_file
+            ]
+        else:
+            tlog(f"Full transcode using {encoder}: {filepath}")
+            if encoder == 'h264_nvenc':
+                cmd = [
+                    'ffmpeg', '-v', 'error', '-stats', '-i', filepath,
+                    '-c:v', 'h264_nvenc', '-preset', 'fast', '-cq', '23',
+                    '-c:a', 'aac', '-b:a', '192k',
+                    '-movflags', '+faststart',
+                    '-y', temp_file
+                ]
+            elif encoder == 'h264_vaapi':
+                cmd = [
+                    'ffmpeg', '-v', 'error', '-stats',
+                    '-hwaccel', 'vaapi', '-hwaccel_output_format', 'vaapi',
+                    '-i', filepath,
+                    '-vf', 'format=nv12,hwupload',
+                    '-c:v', 'h264_vaapi', '-b:v', '5M',
+                    '-c:a', 'aac', '-b:a', '192k',
+                    '-movflags', '+faststart',
+                    '-y', temp_file
+                ]
+            else:  # libx264
+                cmd = [
+                    'ffmpeg', '-v', 'error', '-stats', '-i', filepath,
+                    '-c:v', 'libx264', '-crf', '23', '-preset', 'medium',
+                    '-c:a', 'aac', '-b:a', '192k',
+                    '-movflags', '+faststart',
+                    '-y', temp_file
+                ]
+        
+        result = subprocess.run(cmd, capture_output=True, text=True)
+        
+        if result.returncode == 0:
+            # Replace original
+            Path(filepath).unlink()
+            Path(temp_file).rename(filepath)
+            tlog(f"✅ Success: {filepath}")
+            return True
+        else:
+            # Check if it's a GPU error and retry with CPU
+            if encoder in ['h264_nvenc', 'h264_vaapi', 'h264_videotoolbox'] and 'libcuda' in result.stderr or 'Cannot load' in result.stderr:
+                tlog(f"⚠️ GPU encoding failed, retrying with CPU (libx264)...")
+                
+                # Retry with libx264
+                if video_codec == 'h264':
+                    cpu_cmd = [
+                        'ffmpeg', '-v', 'error', '-stats', '-i', filepath,
+                        '-c:v', 'copy',
+                        '-c:a', 'aac', '-b:a', '192k',
+                        '-movflags', '+faststart',
+                        '-y', temp_file
+                    ]
+                else:
+                    cpu_cmd = [
+                        'ffmpeg', '-v', 'error', '-stats', '-i', filepath,
+                        '-c:v', 'libx264', '-crf', '23', '-preset', 'medium',
+                        '-c:a', 'aac', '-b:a', '192k',
+                        '-movflags', '+faststart',
+                        '-y', temp_file
+                    ]
+                
+                cpu_result = subprocess.run(cpu_cmd, capture_output=True, text=True)
+                
+                if cpu_result.returncode == 0:
+                    Path(filepath).unlink()
+                    Path(temp_file).rename(filepath)
+                    tlog(f"✅ Success (CPU): {filepath}")
+                    return True
+                else:
+                    tlog(f"❌ Failed (CPU): {filepath}")
+                    tlog(f"Error: {cpu_result.stderr}")
+                    if Path(temp_file).exists():
+                        Path(temp_file).unlink()
+                    return False
+            else:
+                tlog(f"❌ Failed: {filepath}")
+                tlog(f"Error: {result.stderr}")
+                if Path(temp_file).exists():
+                    Path(temp_file).unlink()
+                return False
+            
+    except Exception as e:
+        tlog(f"❌ Exception: {e}")
+        if Path(temp_file).exists():
+            Path(temp_file).unlink()
+        return False
+
 def sanitize(text):
     text = text.encode("ascii", "ignore").decode()
     text = re.sub(r'[\/:*?"<>|]', "_", text)
     return text.strip()
 
 def fetch_all_metadata():
-    print("📥 Fetching all video metadata...", flush=True)
+    log("📥 Fetching all video metadata...")
     video_map = {}
     page = 1
     while True:
@@ -67,20 +303,16 @@ def fetch_all_metadata():
                 if current is not None and last is not None and current >= last:
                     break
             else:
-                # Fallback if no pagination info, just stop if empty data (handled above) or arbitrary limit?
-                # If we got data but no pagination, maybe it's a single page result?
-                # But we loop until no data.
                 pass
 
-            print(f"   - Page {page} fetched. Total videos so far: {len(video_map)}", flush=True)
+            log(f"   - Page {page} fetched. Total videos so far: {len(video_map)}")
             page += 1
             
         except Exception as e:
-            print(f"❌ Error fetching page {page}: {e}", flush=True)
-            # If a page fails, maybe we should stop or retry? For now, let's stop to avoid infinite loops on auth error
+            log(f"❌ Error fetching page {page}: {e}")
             break
             
-    print(f"✅ Metadata fetch complete. Found {len(video_map)} videos.", flush=True)
+    log(f"✅ Metadata fetch complete. Found {len(video_map)} videos.")
     return video_map
 
 def cleanup_old_folders():
@@ -88,7 +320,7 @@ def cleanup_old_folders():
     Scans TARGET_DIR for folders containing '+00:00'.
     Safely deletes them ONLY if they contain no real files (only symlinks or empty).
     """
-    print("🧹 Starting cleanup. Scanning ONLY for folders containing '+00:00'...", flush=True)
+    log("🧹 Starting cleanup. Scanning ONLY for folders containing '+00:00'...")
     cleaned_count = 0
     skipped_count = 0
     
@@ -123,15 +355,86 @@ def cleanup_old_folders():
                             item.unlink()
                         # Remove directory
                         video_dir.rmdir()
-                        print(f"   [DELETED] {video_dir.name}", flush=True)
+                        log(f"   [DELETED] {video_dir.name}")
                         cleaned_count += 1
                     except Exception as e:
-                        print(f"   ❌ Failed to delete {video_dir.name}: {e}", flush=True)
+                        log(f"   ❌ Failed to delete {video_dir.name}: {e}")
                 else:
-                    print(f"   ⚠️ SKIPPING {video_dir.name} - {reason}", flush=True)
+                    log(f"   ⚠️ SKIPPING {video_dir.name} - {reason}")
                     skipped_count += 1
                     
-    print(f"🧹 Cleanup complete. Removed: {cleaned_count}, Skipped: {skipped_count}", flush=True)
+    log(f"🧹 Cleanup complete. Removed: {cleaned_count}, Skipped: {skipped_count}")
+
+def check_orphaned_links():
+    """
+    Scans TARGET_DIR for video.mp4 symlinks and checks if they point to valid files.
+    For orphaned links, parses the folder structure to extract metadata.
+    Stores results in database.
+    """
+    log("🔍 Checking for orphaned symlinks...")
+    orphaned = []
+    total_checked = 0
+    
+    if not TARGET_DIR.exists():
+        log("⚠️ Target directory does not exist")
+        return orphaned
+
+    with get_db() as conn:
+        for channel_dir in TARGET_DIR.iterdir():
+            if not channel_dir.is_dir():
+                continue
+                
+            channel_name = channel_dir.name
+                
+            for video_dir in channel_dir.iterdir():
+                if not video_dir.is_dir():
+                    continue
+                    
+                folder_name = video_dir.name
+                
+                # Look for video files
+                for video_file in video_dir.glob("video.*"):
+                    total_checked += 1
+                    
+                    if video_file.is_symlink():
+                        try:
+                            # Check if the symlink target exists
+                            target = Path(os.readlink(video_file))
+                            
+                            if not target.exists():
+                                # Parse folder name: "YYYY-MM-DD - Title"
+                                parts = folder_name.split(" - ", 1)
+                                published = parts[0] if len(parts) > 0 else "unknown"
+                                title = parts[1] if len(parts) > 1 else folder_name
+                                
+                                # Try to extract video ID from symlink target path
+                                video_id = target.stem if target.stem else "unknown"
+                                
+                                orphaned.append({
+                                    "video_id": video_id,
+                                    "path": str(video_file),
+                                    "target": str(target),
+                                    "folder": folder_name,
+                                    "channel": channel_name,
+                                    "title": title,
+                                    "published": published
+                                })
+                                
+                                # Store in DB
+                                conn.execute("""
+                                    INSERT OR REPLACE INTO videos 
+                                    (video_id, title, channel, published, symlink, status)
+                                    VALUES (?, ?, ?, ?, ?, 'missing')
+                                """, (video_id, title, channel_name, published, str(video_file)))
+                                
+                                log(f"   ⚠️ BROKEN: {folder_name} -> {target}")
+                        except Exception as e:
+                            log(f"   ❌ ERROR: {folder_name}: {e}")
+                            
+        conn.commit()
+                        
+    log(f"✅ Check complete. Scanned {total_checked} files, found {len(orphaned)} orphaned symlinks.")
+    return orphaned
 
 # Main logic
 
@@ -149,116 +452,231 @@ def process_videos():
     new_links = 0
     verified_links = 0
     
-    try:
-        for channel_path in SOURCE_DIR.iterdir():
-            if not channel_path.is_dir():
-                continue
-            for video_file in channel_path.glob("*.*"):
-                video_id = video_file.stem
-                
-                # 2. Lookup in local map
-                meta = video_map.get(video_id)
-                if not meta:
-                    continue
-                sanitized_channel_name = sanitize(meta["channel_name"])
-                channel_dir = TARGET_DIR / sanitized_channel_name
-                channel_dir.mkdir(parents=True, exist_ok=True)
-                sanitized_title = sanitize(meta["title"])
-                folder_name = f"{meta['published']} - {sanitized_title}"
-                video_dir = channel_dir / folder_name
-                video_dir.mkdir(parents=True, exist_ok=True)
-                actual_file = next(channel_path.glob(f"{video_id}.*"), None)
-                if not actual_file:
-                    continue
-                host_path_root = Path("/mnt/user/tubearchives/bp")
-                host_source_path = host_path_root / actual_file.relative_to(SOURCE_DIR)
-                dest_file = video_dir / f"video{actual_file.suffix}"
-                try:
-                    if dest_file.exists():
-                        if dest_file.is_symlink():
-                            current_target = Path(os.readlink(dest_file))
-                            if current_target.resolve() != host_source_path.resolve():
-                                dest_file.unlink()
-                                os.symlink(host_source_path, dest_file)
-                                print(f"   [FIX] Relinked: {folder_name}", flush=True)
-                                new_links += 1
-                            else:
-                                verified_links += 1
-                    else:
-                        os.symlink(host_source_path, dest_file)
-                        print(f"   [NEW] Linked: {folder_name}", flush=True)
-                        new_links += 1
-                except Exception:
-                    pass
-                processed_videos.append({
-                    "video_id": video_id,
-                    "title": meta["title"],
-                    "channel": meta["channel_name"],
-                    "published": meta["published"],
-                    "symlink": str(dest_file)
-                })
-    except Exception as e:
-        return str(e)
+    with get_db() as conn:
+        # Clear existing "linked" videos (we'll repopulate)
+        conn.execute("DELETE FROM videos WHERE status = 'linked'")
         
-    print(f"✅ Scan complete. Processed {len(processed_videos)} videos.", flush=True)
-    print(f"   - New/Fixed Links: {new_links}", flush=True)
-    print(f"   - Verified Links:  {verified_links}", flush=True)
+        try:
+            for channel_path in SOURCE_DIR.iterdir():
+                if not channel_path.is_dir():
+                    continue
+                for video_file in channel_path.glob("*.*"):
+                    video_id = video_file.stem
+                    
+                    # Lookup in local map
+                    meta = video_map.get(video_id)
+                    if not meta:
+                        continue
+                    sanitized_channel_name = sanitize(meta["channel_name"])
+                    channel_dir = TARGET_DIR / sanitized_channel_name
+                    channel_dir.mkdir(parents=True, exist_ok=True)
+                    sanitized_title = sanitize(meta["title"])
+                    folder_name = f"{meta['published']} - {sanitized_title}"
+                    video_dir = channel_dir / folder_name
+                    video_dir.mkdir(parents=True, exist_ok=True)
+                    actual_file = next(channel_path.glob(f"{video_id}.*"), None)
+                    if not actual_file:
+                        continue
+                    host_path_root = Path("/mnt/user/tubearchives/bp")
+                    host_source_path = host_path_root / actual_file.relative_to(SOURCE_DIR)
+                    dest_file = video_dir / f"video{actual_file.suffix}"
+                    try:
+                        if dest_file.exists():
+                            if dest_file.is_symlink():
+                                current_target = Path(os.readlink(dest_file))
+                                if current_target.resolve() != host_source_path.resolve():
+                                    dest_file.unlink()
+                                    os.symlink(host_source_path, dest_file)
+                                    log(f"   [FIX] Relinked: {folder_name}")
+                                    new_links += 1
+                                else:
+                                    verified_links += 1
+                        else:
+                            os.symlink(host_source_path, dest_file)
+                            log(f"   [NEW] Linked: {folder_name}")
+                            new_links += 1
+                    except Exception:
+                        pass
+                    
+                    # Store in database
+                    conn.execute("""
+                        INSERT OR REPLACE INTO videos 
+                        (video_id, title, channel, published, symlink, status)
+                        VALUES (?, ?, ?, ?, ?, 'linked')
+                    """, (video_id, meta["title"], meta["channel_name"], 
+                          meta["published"], str(dest_file)))
+                    
+                    processed_videos.append({
+                        "video_id": video_id,
+                        "title": meta["title"],
+                        "channel": meta["channel_name"],
+                        "published": meta["published"],
+                        "symlink": str(dest_file)
+                    })
+        except Exception as e:
+            conn.rollback()
+            return str(e)
+        
+        conn.commit()
+            
+    log(f"✅ Scan complete. Processed {len(processed_videos)} videos.")
+    log(f"   - New/Fixed Links: {new_links}")
+    log(f"   - Verified Links:  {verified_links}")
     return None
 
 def scheduler():
-    print(f"🕒 Background scheduler started. Scanning every {SCAN_INTERVAL} minutes.", flush=True)
+    log(f"🕒 Background scheduler started. Scanning every {SCAN_INTERVAL} minutes.")
     while True:
-        print("🔄 Running scheduled scan...", flush=True)
+        log("🔄 Running scheduled scan...")
         process_videos()
         time.sleep(SCAN_INTERVAL * 60)
 
 # Flask routes
+
+@app.before_request
+def limit_remote_addr():
+    # Skip check for local requests if needed, but generally good to enforce
+    client_ip = request.remote_addr
+    try:
+        ip_obj = ipaddress.ip_address(client_ip)
+        allowed = False
+        for allowed_ip in ALLOWED_IPS:
+            if not allowed_ip: continue
+            if "/" in allowed_ip:
+                if ip_obj in ipaddress.ip_network(allowed_ip, strict=False):
+                    allowed = True
+                    break
+            else:
+                if ip_obj == ipaddress.ip_address(allowed_ip):
+                    allowed = True
+                    break
+        if not allowed:
+            log(f"⛔ Access denied for IP: {client_ip}")
+            abort(403)
+    except ValueError as e:
+        log(f"⛔ Invalid IP format: {client_ip}, Error: {e}")
+        abort(403)
+
 @app.route("/")
 def index():
-    return render_template_string('''
-    <html>
-    <head><title>TA Organizerr</title></head>
-    <body>
-        <h1>TA Organizerr</h1>
-        <form method="post" action="/process">
-            <button type="submit">Process Videos</button>
-        </form>
-        <h2>Processed Videos</h2>
-        <ul>
-        {% for v in videos %}
-            <li>{{v.published}} - {{v.title}} ({{v.channel}}) <br>Symlink: {{v.symlink}}</li>
-        {% endfor %}
-        </ul>
-    </body>
-    </html>
-    ''', videos=processed_videos)
+    return render_template('dashboard.html')
 
-@app.route("/process", methods=["POST"])
-def process():
-    error = process_videos()
-    if error:
-        return f"Error: {error}", 500
-    return render_template_string('''
-    <html>
-    <head><title>TA Organizerr</title></head>
-    <body>
-        <h1>TA Organizerr</h1>
-        <form method="post" action="/process">
-            <button type="submit">Process Videos</button>
-        </form>
-        <h2>Processed Videos</h2>
-        <ul>
-        {% for v in videos %}
-            <li>{{v.published}} - {{v.title}} ({{v.channel}}) <br>Symlink: {{v.symlink}}</li>
-        {% endfor %}
-        </ul>
-    </body>
-    </html>
-    ''', videos=processed_videos)
+@app.route("/api/status")
+def api_status():
+    with get_db() as conn:
+        # Get all videos from DB
+        videos = []
+        for row in conn.execute("SELECT * FROM videos ORDER BY channel, published DESC"):
+            videos.append({
+                "video_id": row["video_id"],
+                "title": row["title"],
+                "channel": row["channel"],
+                "published": row["published"],
+                "symlink": row["symlink"],
+                "status": row["status"]
+            })
+        
+        # Calculate stats
+        total = len(videos)
+        linked = sum(1 for v in videos if v["status"] == "linked")
+        missing = sum(1 for v in videos if v["status"] == "missing")
+        
+        return jsonify({
+            "total_videos": total,
+            "verified_links": linked,
+            "missing_count": missing,
+            "videos": videos
+        })
 
-@app.route("/api/videos")
-def api_videos():
-    return jsonify(processed_videos)
+@app.route("/api/logs")
+def api_logs():
+    start = request.args.get('start', 0, type=int)
+    with log_lock:
+        return jsonify({
+            "logs": log_buffer[start:],
+            "next_index": len(log_buffer)
+        })
+
+@app.route("/api/scan", methods=["POST"])
+def api_scan():
+    # Run in background to avoid blocking
+    threading.Thread(target=process_videos).start()
+    return jsonify({"status": "started"})
+
+@app.route("/api/cleanup", methods=["POST"])
+def api_cleanup():
+    threading.Thread(target=cleanup_old_folders).start()
+    return jsonify({"status": "started"})
+
+@app.route("/api/check-orphans", methods=["POST"])
+def api_check_orphans():
+    orphaned = check_orphaned_links()
+    return jsonify({"status": "complete", "orphaned": orphaned, "count": len(orphaned)})
+
+@app.route("/transcode")
+def transcode_page():
+    return render_template('transcoding.html')
+
+@app.route("/api/transcode/videos")
+def api_transcode_videos():
+    """Get all videos that need transcoding."""
+    page = request.args.get('page', 1, type=int)
+    per_page = request.args.get('per_page', 100, type=int)
+    offset = (page - 1) * per_page
+    
+    with get_db() as conn:
+        # Get total count
+        total = conn.execute("SELECT COUNT(*) as count FROM videos WHERE status = 'missing'").fetchone()['count']
+        
+        videos = []
+        for row in conn.execute(
+            "SELECT * FROM videos WHERE status = 'missing' LIMIT ? OFFSET ?",
+            (per_page, offset)
+        ):
+            videos.append({
+                "video_id": row["video_id"],
+                "title": row["title"],
+                "channel": row["channel"],
+                "published": row["published"],
+                "symlink": row["symlink"]
+            })
+        
+        return jsonify({
+            "videos": videos,
+            "total": total,
+            "page": page,
+            "per_page": per_page,
+            "pages": (total + per_page - 1) // per_page
+        })
+
+@app.route("/api/transcode/start", methods=["POST"])
+def api_transcode_start():
+    """Start transcoding a video."""
+    data = request.get_json()
+    filepath = data.get('filepath')
+    
+    if not filepath:
+        return jsonify({"error": "No filepath provided"}), 400
+    
+    encoder = detect_encoder()
+    tlog(f"🖥️  Selected encoder: {encoder}")
+    
+    # Run in background
+    def run_transcode():
+        transcode_video(filepath, encoder)
+    
+    threading.Thread(target=run_transcode).start()
+    return jsonify({"message": "Transcode started", "encoder": encoder})
+
+@app.route("/api/transcode/logs")
+def api_transcode_logs():
+    """Get transcode logs."""
+    start = request.args.get('start', 0, type=int)
+    with transcode_log_lock:
+        return jsonify({
+            "logs": transcode_log_buffer[start:],
+            "next_index": len(transcode_log_buffer)
+        })
 
 if __name__ == "__main__":
     # Start scheduler in background thread

templates/dashboard.html

@@ -0,0 +1,305 @@
+<!DOCTYPE html>
+<html lang="en" data-bs-theme="dark">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>TA Organizerr Dashboard</title>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
+    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap-icons@1.10.0/font/bootstrap-icons.css">
+    <style>
+        .log-box {
+            height: 300px;
+            overflow-y: scroll;
+            font-family: monospace;
+            font-size: 0.9em;
+            background-color: #1e1e1e;
+            color: #00ff00;
+            border: 1px solid #444;
+            padding: 10px;
+        }
+
+        .status-dot {
+            height: 10px;
+            width: 10px;
+            background-color: #bbb;
+            border-radius: 50%;
+            display: inline-block;
+        }
+
+        .status-green {
+            background-color: #28a745;
+        }
+
+        .status-yellow {
+            background-color: #ffc107;
+        }
+
+        .status-red {
+            background-color: #dc3545;
+        }
+    </style>
+</head>
+
+<body>
+    <div class="container-fluid p-4">
+        <header class="d-flex justify-content-between align-items-center mb-4">
+            <h1><i class="bi bi-folder2-open"></i> TA Organizerr</h1>
+            <div>
+                <a href="/transcode" class="btn btn-outline-primary me-2">
+                    <i class="bi bi-film"></i> Transcode
+                </a>
+                <span class="badge bg-secondary" id="connection-status">Connecting...</span>
+            </div>
+        </header>
+
+        <!-- Stats Row -->
+        <div class="row mb-4">
+            <div class="col-md-3">
+                <div class="card text-bg-primary mb-3">
+                    <div class="card-header">Total Videos</div>
+                    <div class="card-body">
+                        <h2 class="card-title" id="stat-total">0</h2>
+                    </div>
+                </div>
+            </div>
+            <div class="col-md-3">
+                <div class="card text-bg-success mb-3">
+                    <div class="card-header">Linked & Verified</div>
+                    <div class="card-body">
+                        <h2 class="card-title" id="stat-linked">0</h2>
+                    </div>
+                </div>
+            </div>
+            <div class="col-md-3">
+                <div class="card text-bg-warning mb-3">
+                    <div class="card-header">New / Fixed</div>
+                    <div class="card-body">
+                        <h2 class="card-title" id="stat-new">0</h2>
+                    </div>
+                </div>
+            </div>
+            <div class="col-md-3">
+                <div class="card text-bg-danger mb-3">
+                    <div class="card-header">Missing / Error</div>
+                    <div class="card-body">
+                        <h2 class="card-title" id="stat-error">0</h2>
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <!-- Controls & Logs -->
+        <div class="row mb-4">
+            <div class="col-md-4">
+                <div class="card h-100">
+                    <div class="card-header">Control Panel</div>
+                    <div class="card-body d-grid gap-2">
+                        <button class="btn btn-primary btn-lg" onclick="triggerScan()">
+                            <i class="bi bi-arrow-repeat"></i> SCAN NOW
+                        </button>
+                        <button class="btn btn-danger" onclick="triggerCleanup()">
+                            <i class="bi bi-trash"></i> CLEAN OLD FOLDERS (+00:00)
+                        </button>
+                        <button class="btn btn-warning" onclick="checkOrphans()">
+                            <i class="bi bi-search"></i> CHECK ORPHANED LINKS
+                        </button>
+                        <hr>
+                        <small class="text-muted">Next scheduled scan in: <span id="next-scan">--</span> min</small>
+                        <div id="orphan-results" class="mt-2"></div>
+                    </div>
+                </div>
+            </div>
+            <div class="col-md-8">
+                <div class="card h-100">
+                    <div class="card-header d-flex justify-content-between">
+                        <span>Live Logs</span>
+                        <button class="btn btn-sm btn-outline-secondary" onclick="clearLogs()">Clear</button>
+                    </div>
+                    <div class="card-body p-0">
+                        <div class="log-box" id="log-container">
+                            <div>Waiting for logs...</div>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <div class="card">
+            <div class="card-header d-flex justify-content-between align-items-center">
+                <span>Video Matrix</span>
+                <div class="d-flex gap-2">
+                    <select class="form-select form-select-sm" id="status-filter" style="width: 150px;">
+                        <option value="">All Status</option>
+                        <option value="linked">Linked</option>
+                        <option value="missing">Missing</option>
+                    </select>
+                    <select class="form-select form-select-sm" id="channel-filter" style="width: 200px;">
+                        <option value="">All Channels</option>
+                    </select>
+                    <input type="text" class="form-control form-control-sm" id="search-input"
+                        placeholder="Search videos..." style="width: 200px;">
+                </div>
+            </div>
+            <div class="card-body p-0 table-responsive" style="max-height: 500px;">
+                <table class="table table-striped table-hover mb-0">
+                    <thead class="table-dark sticky-top">
+                        <tr>
+                            <th>Status</th>
+                            <th>Published</th>
+                            <th>Channel</th>
+                            <th>Title</th>
+                            <th>Video ID</th>
+                            <th>Symlink Path</th>
+                        </tr>
+                    </thead>
+                    <tbody id="video-table-body">
+                        <!-- Rows injected by JS -->
+                    </tbody>
+                </table>
+            </div>
+        </div>
+    </div>
+
+    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
+    <script>
+        // Poll for status every 2 seconds
+        setInterval(fetchStatus, 2000);
+        // Poll for logs every 1 second
+        setInterval(fetchLogs, 1000);
+
+        let lastLogIndex = 0;
+
+        async function fetchStatus() {
+            try {
+                const res = await fetch('/api/status');
+                const data = await res.json();
+
+                document.getElementById('connection-status').textContent = 'Connected';
+                document.getElementById('connection-status').className = 'badge bg-success';
+
+                // Update stats
+                document.getElementById('stat-total').textContent = data.total_videos;
+                document.getElementById('stat-linked').textContent = data.verified_links;
+                document.getElementById('stat-error').textContent = data.missing_count || 0;
+
+                // Update table if changed (simple check, can be optimized)
+                updateTable(data.videos);
+
+            } catch (e) {
+                document.getElementById('connection-status').textContent = 'Disconnected';
+                document.getElementById('connection-status').className = 'badge bg-danger';
+            }
+        }
+
+        async function fetchLogs() {
+            try {
+                const res = await fetch('/api/logs?start=' + lastLogIndex);
+                const data = await res.json();
+                if (data.logs && data.logs.length > 0) {
+                    const logBox = document.getElementById('log-container');
+                    data.logs.forEach(line => {
+                        const div = document.createElement('div');
+                        div.textContent = line;
+                        logBox.appendChild(div);
+                    });
+                    logBox.scrollTop = logBox.scrollHeight;
+                    lastLogIndex = data.next_index;
+                }
+            } catch (e) { console.error(e); }
+        }
+
+        async function triggerScan() {
+            if (!confirm("Start a full library scan? This may take a moment.")) return;
+            await fetch('/api/scan', { method: 'POST' });
+            alert("Scan started! Watch the logs.");
+        }
+
+        async function triggerCleanup() {
+            if (!confirm("Are you sure you want to delete all folders containing '+00:00'?\n\nSafety check: Real files will NOT be deleted.")) return;
+            await fetch('/api/cleanup', { method: 'POST' });
+            alert("Cleanup started! Watch the logs.");
+        }
+
+        async function checkOrphans() {
+            const resultsDiv = document.getElementById('orphan-results');
+            resultsDiv.innerHTML = '<div class="spinner-border spinner-border-sm" role="status"></div> Checking...';
+
+            const res = await fetch('/api/check-orphans', { method: 'POST' });
+            const data = await res.json();
+
+            if (data.count === 0) {
+                resultsDiv.innerHTML = '<div class="alert alert-success p-2 mb-0 mt-2">✅ No orphaned links found!</div>';
+            } else {
+                resultsDiv.innerHTML = `<div class="alert alert-warning p-2 mb-0 mt-2">⚠️ Found ${data.count} orphaned links. Check logs for details.</div>`;
+            }
+
+            setTimeout(() => { resultsDiv.innerHTML = ''; }, 10000);
+        }
+
+        function clearLogs() {
+            document.getElementById('log-container').innerHTML = '';
+        }
+
+        function updateTable(videos) {
+            const tbody = document.getElementById('video-table-body');
+            const search = document.getElementById('search-input').value.toLowerCase();
+            const channelFilter = document.getElementById('channel-filter').value;
+            const statusFilter = document.getElementById('status-filter').value;
+
+            // Build unique channel list for dropdown
+            const channels = [...new Set(videos.map(v => v.channel))].sort();
+            const channelDropdown = document.getElementById('channel-filter');
+            const currentValue = channelDropdown.value;
+
+            // Only update dropdown if channel list changed
+            if (channelDropdown.options.length !== channels.length + 1) {
+                channelDropdown.innerHTML = '<option value="">All Channels</option>';
+                channels.forEach(ch => {
+                    const opt = document.createElement('option');
+                    opt.value = ch;
+                    opt.textContent = ch;
+                    channelDropdown.appendChild(opt);
+                });
+                channelDropdown.value = currentValue;
+            }
+
+            // Clear and rebuild table
+            tbody.innerHTML = '';
+
+            videos.forEach(v => {
+                // Apply filters
+                if (search && !v.title.toLowerCase().includes(search) && !v.video_id.includes(search)) return;
+                if (channelFilter && v.channel !== channelFilter) return;
+                if (statusFilter && v.status !== statusFilter) return;
+
+                const tr = document.createElement('tr');
+                let statusColor = v.status === 'linked' ? 'status-green' : 'status-red';
+
+                tr.innerHTML = `
+                    <td><span class="status-dot ${statusColor}"></span></td>
+                    <td>${v.published}</td>
+                    <td>${v.channel}</td>
+                    <td>${v.title}</td>
+                    <td><code>${v.video_id}</code></td>
+                    <td class="text-truncate" style="max-width: 300px;">${v.symlink || '-'}</td>
+                `;
+                tbody.appendChild(tr);
+            });
+        }
+
+        document.getElementById('search-input').addEventListener('input', () => {
+            fetchStatus();
+        });
+
+        document.getElementById('channel-filter').addEventListener('change', () => {
+            fetchStatus();
+        });
+
+        document.getElementById('status-filter').addEventListener('change', () => {
+            fetchStatus();
+        });
+    </script>
+</body>
+
+</html>

templates/transcoding.html

@@ -0,0 +1,213 @@
+<!DOCTYPE html>
+<html lang="en" data-bs-theme="dark">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Transcode Manager - TA Organizerr</title>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
+    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap-icons@1.10.0/font/bootstrap-icons.css">
+    <style>
+        .codec-badge {
+            font-family: monospace;
+            font-size: 0.8em;
+        }
+
+        .codec-ok {
+            background-color: #28a745;
+        }
+
+        .codec-warn {
+            background-color: #ffc107;
+            color: #000;
+        }
+
+        .codec-bad {
+            background-color: #dc3545;
+        }
+    </style>
+</head>
+
+<body>
+    <div class="container-fluid p-4">
+        <header class="d-flex justify-content-between align-items-center mb-4">
+            <h1><i class="bi bi-film"></i> Transcode Manager</h1>
+            <a href="/" class="btn btn-secondary"><i class="bi bi-arrow-left"></i> Back to Dashboard</a>
+        </header>
+
+        <div class="alert alert-info d-flex justify-content-between align-items-center">
+            <div>
+                <strong>ℹ️ Info:</strong> This page shows videos with broken/missing source files. Click "Find Missing
+                Videos" to scan for orphaned symlinks, then transcode them to restore compatibility.
+            </div>
+            <button class="btn btn-primary" onclick="findMissing()">
+                <i class="bi bi-search"></i> Find Missing Videos
+            </button>
+        </div>
+
+        <div class="card mb-4">
+            <div class="card-header d-flex justify-content-between align-items-center">
+                <h5>Transcode Queue</h5>
+                <div id="pagination-info" class="text-muted"></div>
+            </div>
+            <div class="card-body">
+                <table class="table table-striped">
+                    <thead>
+                        <tr>
+                            <th style="width: 15%;">Channel</th>
+                            <th style="width: 10%;">Published</th>
+                            <th style="width: 30%;">Title</th>
+                            <th style="width: 30%;">Symlink Path</th>
+                            <th style="width: 15%;">Actions</th>
+                        </tr>
+                    </thead>
+                    <tbody id="transcode-table">
+                        <tr>
+                            <td colspan="5" class="text-center">
+                                <div class="spinner-border" role="status"></div> Loading...
+                            </td>
+                        </tr>
+                    </tbody>
+                </table>
+                <nav>
+                    <ul class="pagination justify-content-center" id="pagination">
+                    </ul>
+                </nav>
+            </div>
+        </div>
+
+        <div class="card">
+            <div class="card-header">Transcoding Log</div>
+            <div class="card-body">
+                <div id="transcode-log"
+                    style="height: 300px; overflow-y: scroll; font-family: monospace; font-size: 0.9em; background-color: #1e1e1e; color: #00ff00; padding: 10px;">
+                    <div>Waiting for transcode jobs...</div>
+                </div>
+            </div>
+        </div>
+    </div>
+
+    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
+    <script>
+        let transcodeLogIndex = 0;
+        let currentPage = 1;
+
+        async function findMissing() {
+            const tbody = document.getElementById('transcode-table');
+            tbody.innerHTML = '<tr><td colspan="7" class="text-center"><div class="spinner-border" role="status"></div> Scanning for orphaned symlinks...</td></tr>';
+
+            try {
+                const res = await fetch('/api/check-orphans', { method: 'POST' });
+                const data = await res.json();
+                alert(`Found ${data.count} videos with broken/missing source files.`);
+                currentPage = 1;
+                loadVideos();
+            } catch (e) {
+                alert("Scan failed: " + e);
+                loadVideos();
+            }
+        }
+
+        async function loadVideos(page = 1) {
+            try {
+                const res = await fetch(`/api/transcode/videos?page=${page}&per_page=100`);
+                const data = await res.json();
+
+                const tbody = document.getElementById('transcode-table');
+                tbody.innerHTML = '';
+
+                if (data.videos.length === 0) {
+                    tbody.innerHTML = '<tr><td colspan="5" class="text-center">No missing videos found. Click "Find Missing Videos" to scan.</td></tr>';
+                    return;
+                }
+
+                data.videos.forEach(v => {
+                    const tr = document.createElement('tr');
+
+                    tr.innerHTML = `
+                        <td>${v.channel}</td>
+                        <td>${v.published}</td>
+                        <td class="text-truncate" style="max-width: 200px;" title="${v.title}">${v.title}</td>
+                        <td class="text-truncate" style="max-width: 250px;" title="${v.symlink}"><small>${v.symlink}</small></td>
+                        <td>
+                            <button class="btn btn-sm btn-primary" onclick="transcode('${v.symlink}')">
+                                <i class="bi bi-play"></i> Transcode
+                            </button>
+                        </td>
+                    `;
+                    tbody.appendChild(tr);
+                });
+
+                // Update pagination info
+                document.getElementById('pagination-info').textContent =
+                    `Showing ${data.videos.length} of ${data.total} videos (Page ${data.page}/${data.pages})`;
+
+                // Render pagination
+                const pagination = document.getElementById('pagination');
+                pagination.innerHTML = '';
+
+                if (data.pages > 1) {
+                    // Previous button
+                    const prevLi = document.createElement('li');
+                    prevLi.className = `page-item ${data.page === 1 ? 'disabled' : ''}`;
+                    prevLi.innerHTML = `<a class="page-link" href="#" onclick="loadVideos(${data.page - 1}); return false;">Previous</a>`;
+                    pagination.appendChild(prevLi);
+
+                    // Page numbers (show max 5 pages around current)
+                    const startPage = Math.max(1, data.page - 2);
+                    const endPage = Math.min(data.pages, data.page + 2);
+
+                    for (let i = startPage; i <= endPage; i++) {
+                        const li = document.createElement('li');
+                        li.className = `page-item ${i === data.page ? 'active' : ''}`;
+                        li.innerHTML = `<a class="page-link" href="#" onclick="loadVideos(${i}); return false;">${i}</a>`;
+                        pagination.appendChild(li);
+                    }
+
+                    // Next button
+                    const nextLi = document.createElement('li');
+                    nextLi.className = `page-item ${data.page === data.pages ? 'disabled' : ''}`;
+                    nextLi.innerHTML = `<a class="page-link" href="#" onclick="loadVideos(${data.page + 1}); return false;">Next</a>`;
+                    pagination.appendChild(nextLi);
+                }
+            } catch (e) {
+                console.error(e);
+            }
+        }
+
+        async function transcode(filepath) {
+            if (!confirm("Start transcoding this video? This may take a while.")) return;
+
+            const res = await fetch('/api/transcode/start', {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' },
+                body: JSON.stringify({ filepath })
+            });
+
+            const data = await res.json();
+            alert(data.message || "Transcode started! Check the log below.");
+        }
+
+        async function fetchLogs() {
+            try {
+                const res = await fetch('/api/transcode/logs?start=' + transcodeLogIndex);
+                const data = await res.json();
+                if (data.logs && data.logs.length > 0) {
+                    const logBox = document.getElementById('transcode-log');
+                    data.logs.forEach(line => {
+                        const div = document.createElement('div');
+                        div.textContent = line;
+                        logBox.appendChild(div);
+                    });
+                    logBox.scrollTop = logBox.scrollHeight;
+                    transcodeLogIndex = data.next_index;
+                }
+            } catch (e) { console.error(e); }
+        }
+
+        loadVideos();
+        setInterval(fetchLogs, 1000);
+    </script>
+</body>
+
+</html>