Update app.py

app.py

@@ -133,8 +133,6 @@ import asyncio
 #     return None
 
 
-download_cache = {}
-
 async def download_scene_files(scene: SceneDto):
     tasks = []
 
@@ -154,37 +152,83 @@ async def download_scene_files(scene: SceneDto):
     downloaded_files = await asyncio.gather(*tasks)
     return downloaded_files
 
+# async def download_file_from_url(url: str, retries: int = 3, delay: float = 2.0) -> str | None:
+#     """
+#     Downloads a file from a URL and returns the path to a temporary file.
+#     If download fails after `retries` attempts, returns None instead of raising an error.
+#     Caches successful downloads to avoid repeated requests.
+#     """
+#     if url in download_cache:
+#         #print(f"{url} is got from cache")
+#         return download_cache[url]
+    
+#     for attempt in range(1, retries + 1):
+#         try:
+#             async with httpx.AsyncClient(timeout=60.0) as client:
+#                 response = await client.get(url)
+#                 response.raise_for_status()
+
+#             temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
+#             temp_file.write(response.content)
+#             temp_file.close()
+            
+#             #print(f"{url} is downloaded and saved in cache")
+            
+#             download_cache[url] = temp_file.name
+#             return temp_file.name
+
+#         except Exception as e:
+#             #print(f"Attempt {attempt} failed for {url}: {e}")
+#             if attempt < retries:
+#                 await asyncio.sleep(delay)
+
+#     #print(f"All {retries} attempts failed for {url}, skipping...")
+#     return None
+
+import os
+import httpx
+import asyncio
+
+CACHE_DIR = "audio_cache"
+os.makedirs(CACHE_DIR, exist_ok=True)  # create if not exists folder stores permanently on disk
+
+download_cache = {}  # in-memory map: url -> local file
+
 async def download_file_from_url(url: str, retries: int = 3, delay: float = 2.0) -> str | None:
     """
-    Downloads a file from a URL and returns the path to a temporary file.
-    If download fails after `retries` attempts, returns None instead of raising an error.
-    Caches successful downloads to avoid repeated requests.
+    Downloads a file from a URL and stores it in a permanent cache folder.
+    Returns the local file path. Reuses already downloaded files.
     """
     if url in download_cache:
-        #print(f"{url} is got from cache")
         return download_cache[url]
-    
+
+    # determine local file path in cache folder
+    filename = url.split("/")[-1]  # simple filename from URL
+    local_path = os.path.join(CACHE_DIR, filename)
+
+    # check if file already exists on disk
+    if os.path.exists(local_path):
+        download_cache[url] = local_path
+        return local_path
+
+    # download if not cached
     for attempt in range(1, retries + 1):
         try:
             async with httpx.AsyncClient(timeout=60.0) as client:
                 response = await client.get(url)
                 response.raise_for_status()
 
-            temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
-            temp_file.write(response.content)
-            temp_file.close()
-            
-            #print(f"{url} is downloaded and saved in cache")
-            
-            download_cache[url] = temp_file.name
-            return temp_file.name
+            # save to permanent cache folder
+            with open(local_path, "wb") as f:
+                f.write(response.content)
+
+            download_cache[url] = local_path
+            return local_path
 
         except Exception as e:
-            #print(f"Attempt {attempt} failed for {url}: {e}")
             if attempt < retries:
                 await asyncio.sleep(delay)
 
-    #print(f"All {retries} attempts failed for {url}, skipping...")
     return None
 
 #-----------------------------------------------------------
@@ -643,10 +687,10 @@ async def get_results(task_id: str):
     if result and all(k in result for k in ("fileName", "duration", "audioPath")):
         #clearing cache
         print(f"all fields are available {result}")
-        for file_path in download_cache.values():
-            if os.path.exists(file_path):
-                os.remove(file_path)
-        download_cache.clear()
+        # for file_path in download_cache.values():
+        #     if os.path.exists(file_path):
+        #         os.remove(file_path)
+        # download_cache.clear()
         
         return {"status": "completed", **result}
     else: