more episodes 1 2 3 4

step1_transcribe.py

@@ -11,6 +11,7 @@ Usage:
 """
 
 import os
+import re
 import sys
 import json
 from pathlib import Path
@@ -113,6 +114,14 @@ def transcribe_video(video_path: Path) -> dict:
     return result
 
 
+def extract_episode_code(filename: str) -> str:
+    """Extract SxxExx code from filename (e.g., 'S01E01_The_Eye.mp4' -> 'S01E01')."""
+    match = re.search(r'(S\d{2}E\d{2})', filename, re.IGNORECASE)
+    if match:
+        return match.group(1).upper()
+    return None
+
+
 def process_video(video_path: Path, force: bool = False) -> Path:
     """
     Process a single video file.
@@ -121,6 +130,11 @@ def process_video(video_path: Path, force: bool = False) -> Path:
     progress = load_progress()
     filename = video_path.name
     
+    # Extract episode code for output naming (e.g., S01E01_The_Name.mp4 -> S01E01)
+    episode_code = extract_episode_code(filename)
+    if not episode_code:
+        raise ValueError(f"Could not extract episode code (SxxExx) from filename: {filename}")
+    
     # Check if already processed
     if not force and filename in progress and progress[filename].get("status") == "completed":
         output_path = Path(progress[filename]["output_file"])
@@ -130,6 +144,7 @@ def process_video(video_path: Path, force: bool = False) -> Path:
     
     print(f"\n{'='*50}")
     print(f"Processing: {filename}")
+    print(f"Episode code: {episode_code}")
     print(f"{'='*50}")
     
     try:
@@ -139,8 +154,8 @@ def process_video(video_path: Path, force: bool = False) -> Path:
         
         transcript_data = transcribe_video(video_path)
         
-        # Save to JSON
-        output_filename = video_path.stem + "_assemblyai.json"
+        # Save to JSON using episode code only (drop the name part)
+        output_filename = f"{episode_code}_assemblyai.json"
         output_path = OUTPUT_DIR / output_filename
         
         with open(output_path, 'w', encoding='utf-8') as f: