Update app.py

app.py

@@ -49,21 +49,47 @@ def parse_filename_to_ms(filename):
     return (h * 3600000) + (m * 60000) + (s * 1000) + ms
 
 def parse_srt(content: str):
-    blocks = content.replace('\r\n', '\n').replace('\r', '\n').strip().split('\n\n')
+    # Normalize line endings
+    content = content.replace('\r\n', '\n').replace('\r', '\n')
+    
+    # Split by blocks (2 or more newlines) - Robust against triple newlines
+    blocks = re.split(r'\n\s*\n', content.strip())
+    
     parsed = []
     for block in blocks:
-        lines = block.split('\n')
-        if len(lines) >= 2:
-            time_line = lines[1]
-            if '-->' in time_line:
-                start_str = time_line.split('-->')[0].strip()
-                text = " ".join(lines[2:]) if len(lines) > 2 else "[BLANK]"
-                parsed.append({
-                    "id": lines[0],
-                    "time": time_line,
-                    "startTimeMs": parse_srt_time_to_ms(start_str),
-                    "text": text
-                })
+        # Clean lines
+        lines = [l.strip() for l in block.split('\n') if l.strip()]
+        if len(lines) < 2:
+            continue
+            
+        # Robustly find timestamp line
+        time_line_index = -1
+        for idx, line in enumerate(lines):
+            if '-->' in line:
+                time_line_index = idx
+                break
+        
+        if time_line_index != -1:
+            time_line = lines[time_line_index]
+            
+            # Determine ID (usually line before time)
+            if time_line_index > 0:
+                s_id = lines[time_line_index - 1]
+            else:
+                s_id = str(len(parsed) + 1)
+            
+            # Extract Text (everything after time)
+            text_lines = lines[time_line_index + 1:]
+            text = " ".join(text_lines) if text_lines else "[BLANK]"
+            
+            start_str = time_line.split('-->')[0].strip()
+            
+            parsed.append({
+                "id": s_id,
+                "time": time_line,
+                "startTimeMs": parse_srt_time_to_ms(start_str),
+                "text": text
+            })
     return parsed
 
 def compress_image(image_bytes, quality=70, max_width=800):