Update server.py

server.py

@@ -172,6 +172,7 @@ def compress_video(input_path: str, output_path: str) -> Dict:
 async def load_progress_file() -> Dict:
     """Load compression progress from JSON file in HF dataset."""
     try:
+        print("Attempting to load progress file from dataset...")
         # Try to download existing progress file
         progress_path = hf_hub_download(
             repo_id=HF_DATASET_REPO,
@@ -186,10 +187,12 @@ async def load_progress_file() -> Dict:
         
         with open(progress_path, 'r') as f:
             progress = json.load(f)
-        print(f"✓ Loaded progress file: {len(progress.get('compressed', []))} files already processed")
+        compressed_count = len(progress.get('compressed', []))
+        failed_count = len(progress.get('failed', []))
+        print(f"✓ Loaded progress: {compressed_count} compressed, {failed_count} failed")
         return progress
     except Exception as e:
-        print(f"No existing progress file found, starting fresh: {e}")
+        print(f"⊘ No existing progress file or load failed: {str(e)[:100]}")
         return {"compressed": [], "failed": [], "last_updated": datetime.now().isoformat()}
 
 
@@ -233,16 +236,26 @@ async def scan_and_compress_videos():
         compressed_files = {item["path"] for item in progress.get("compressed", [])}
         failed_files = {item["path"] for item in progress.get("failed", [])}
         
+        print(f"Current state: {len(compressed_files)} compressed, {len(failed_files)} failed")
+        
         print("\n" + "="*80)
         print("SCANNING FOR LARGE VIDEOS")
         print("="*80)
         
-        # List all files in ready_videos
-        files = list_repo_files(
-            repo_id=HF_DATASET_REPO,
-            repo_type="dataset",
-            token=HF_TOKEN
-        )
+        try:
+            # List all files in ready_videos
+            print("Connecting to Hugging Face dataset...")
+            files = list_repo_files(
+                repo_id=HF_DATASET_REPO,
+                repo_type="dataset",
+                token=HF_TOKEN
+            )
+            print(f"✓ Found {len(files)} total files in dataset")
+        except Exception as e:
+            print(f"✗ Error listing files: {e}")
+            compression_state["last_error"] = str(e)
+            compression_state["is_polling"] = False
+            return
         
         # Find unprocessed video files
         video_files = []
@@ -272,7 +285,7 @@ async def scan_and_compress_videos():
                     continue
         
         compression_state["total_found"] = len(video_files)
-        print(f"Found {len(video_files)} unprocessed video files")
+        print(f"\n✓ Found {len(video_files)} unprocessed video files")
         
         if not video_files:
             print("✓ All videos already processed!")
@@ -389,15 +402,26 @@ async def scan_and_compress_videos():
 
 @app.on_event("startup")
 async def startup_event():
-    """Start initial compression scan after 15 seconds."""
-    async def delayed_scan():
-        await asyncio.sleep(15)
-        print("\n" + "="*80)
-        print("STARTING COMPRESSION SCAN (15 seconds after startup)")
-        print("="*80)
-        await scan_and_compress_videos()
+    """Start compression scan on server startup."""
+    print("\n" + "="*80)
+    print("STARTUP EVENT TRIGGERED")
+    print("="*80)
+    
+    # Check if ffmpeg/ffprobe are available
+    try:
+        result = subprocess.run(["ffmpeg", "-version"], capture_output=True, timeout=5)
+        if result.returncode == 0:
+            print("✓ ffmpeg is available")
+        else:
+            print("✗ ffmpeg check failed")
+    except FileNotFoundError:
+        print("✗ WARNING: ffmpeg not found in PATH - compression will fail")
+    except Exception as e:
+        print(f"✗ Error checking ffmpeg: {e}")
     
-    asyncio.create_task(delayed_scan())
+    # Schedule scan immediately instead of with delay
+    print("Starting compression scan immediately...")
+    await scan_and_compress_videos()
 
 
 @app.get("/")