Update app.py

app.py

@@ -11,92 +11,35 @@ from openai import OpenAI
 openai_api_key = os.getenv("OPENAI_API_KEY")
 openai = OpenAI(api_key=openai_api_key)
 
-# def download_audio(youtube_url):
-#     try:
-#         output_template = "/tmp/downloaded_audio.%(ext)s"
-
-#         # Remove any old files
-#         for f in glob.glob("/tmp/downloaded_audio.*"):
-#             os.remove(f)
-
-#         command = [
-#             "yt-dlp", "-f", "bestaudio",
-#             "--extract-audio", "--audio-format", "mp3",
-#             "--audio-quality", "0",
-#             "-o", output_template,
-#             youtube_url
-#         ]
-
-#         result = subprocess.run(command, capture_output=True, text=True)
-#         print("stdout:\n", result.stdout)
-#         print("stderr:\n", result.stderr)
-
-#         if result.returncode != 0:
-#             raise RuntimeError(f"yt-dlp failed: {result.stderr}")
-
-#         files = glob.glob("/tmp/downloaded_audio.*")
-#         if not files:
-#             raise FileNotFoundError("No audio file downloaded.")
-
-#         return files[0]
-#     except Exception as e:
-#         raise RuntimeError(f"Download error: {e}")
-
-from pytube import YouTube
-
-def clean_youtube_url(url):
-    match = re.search(r"(?:v=|shorts/)([a-zA-Z0-9_-]{11})", url)
-    video_id = match.group(1) if match else None
-    return f"https://www.youtube.com/watch?v={video_id}" if video_id else None
-
 def download_audio(youtube_url):
     try:
-        print(f"▶️ Original URL: {youtube_url}")
         output_template = "/tmp/downloaded_audio.%(ext)s"
 
-        # Cleanup old files
+        # Remove any old files
         for f in glob.glob("/tmp/downloaded_audio.*"):
             os.remove(f)
 
-        # ✅ Try yt-dlp first
         command = [
-            "yt-dlp",
-            "-f", "bestaudio",
+            "yt-dlp", "-f", "bestaudio",
             "--extract-audio", "--audio-format", "mp3",
             "--audio-quality", "0",
             "-o", output_template,
             youtube_url
         ]
-        print("📡 Running yt-dlp...")
+
         result = subprocess.run(command, capture_output=True, text=True)
-        print("📜 yt-dlp stdout:", result.stdout)
-        print("🐞 yt-dlp stderr:", result.stderr)
-
-        if result.returncode == 0:
-            files = glob.glob("/tmp/downloaded_audio.*")
-            if files:
-                print("✅ yt-dlp success.")
-                return files[0]
-
-        # 🔁 Fallback: try pytube with cleaned URL
-        print("🔁 yt-dlp failed. Trying pytube...")
-        clean_url = clean_youtube_url(youtube_url)
-        if not clean_url:
-            raise ValueError("Unable to extract video ID for pytube fallback.")
-
-        print(f"🧽 Cleaned URL for pytube: {clean_url}")
-        yt = YouTube(clean_url)
-        stream = yt.streams.filter(only_audio=True).first()
-        if not stream:
-            raise ValueError("No audio stream found via pytube.")
-
-        output_path = "/tmp/fallback_audio.mp4"
-        stream.download(filename=output_path)
-        print("✅ pytube download success.")
-        return output_path
+        print("stdout:\n", result.stdout)
+        print("stderr:\n", result.stderr)
+
+        if result.returncode != 0:
+            raise RuntimeError(f"yt-dlp failed: {result.stderr}")
+
+        files = glob.glob("/tmp/downloaded_audio.*")
+        if not files:
+            raise FileNotFoundError("No audio file downloaded.")
 
+        return files[0]
     except Exception as e:
-        print("❌ Final Download error:", e)
         raise RuntimeError(f"Download error: {e}")
 
 def transcribe_audio(file_path):