fix: resolve Spotify URL to text title at start of task to fix fallback for both yt-dlp and Tubidy search

apps/musicseerr/tasks.py

@@ -227,6 +227,40 @@ def send_telegram_notification(chat_id: int, text: str):
         logger.error(f"Failed to send Telegram notification: {e}")
 
 
+def extract_spotify_track_title(url: str, proxy_url: str) -> str:
+    """
+    Fetches the Spotify track page and extracts the track name and artists from the title tag.
+    """
+    proxies = {"http": proxy_url, "https": proxy_url} if proxy_url else None
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+    }
+    logger.info(f"Extracting track title from Spotify page: {url}")
+    try:
+        response = requests.get(url, headers=headers, proxies=proxies, timeout=15)
+        if response.status_code == 200:
+            soup = BeautifulSoup(response.text, "html.parser")
+            title_tag = soup.find("title")
+            if title_tag:
+                title_text = title_tag.text
+                # Format is typically "Song Name - song and lyrics by Artist1, Artist2 | Spotify"
+                # Or "Song Name - song by Artist | Spotify"
+                if " - song " in title_text:
+                    parts = title_text.split(" - song ", 1)
+                    song_name = parts[0].strip()
+                    artist_part = parts[1].split(" by ", 1)
+                    if len(artist_part) > 1:
+                        artists = artist_part[1].split(" | Spotify", 1)[0].strip()
+                        return f"{artists} - {song_name}"
+                    return song_name
+                elif " | Spotify" in title_text:
+                    return title_text.split(" | Spotify")[0].strip()
+                return title_text.strip()
+    except Exception as e:
+        logger.warning(f"Failed to extract Spotify track title: {e}")
+    return ""
+
+
 def symlink_existing_tracks(temp_dir: str):
     """
     Finds all audio files recursively in /remote-music/music, extracts artist and title,
@@ -311,6 +345,15 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
             logger.error(f"Failed to resolve proxy hostname: {e}")
             
     try:
+        download_successful = False
+        
+        # If query is a Spotify track URL, resolve it to a text title first for fallback options
+        resolved_title = ""
+        if "spotify.com/track/" in query.lower():
+            resolved_title = extract_spotify_track_title(query, resolved_proxy_url)
+            if resolved_title:
+                logger.info(f"[{task_id}] Pre-resolved Spotify URL to text title: '{resolved_title}'")
+                
         is_tubidy = "tubidy" in query.lower()
         is_spotify = "spotify.com" in query.lower()
         is_youtube = "youtube.com" in query.lower() or "youtu.be" in query.lower()
@@ -333,6 +376,7 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
             result = subprocess.run(cmd, cwd=temp_dir, env=env, capture_output=True, text=True)
             if result.returncode == 0:
                 logger.info(f"[{task_id}] spotDL download succeeded.")
+                download_successful = True
             else:
                 logger.warning(f"[{task_id}] spotDL failed: {result.stderr or result.stdout}. Falling back to yt-dlp.")
                 # Clear state for P2 fallback
@@ -348,9 +392,12 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
                 env["http_proxy"] = resolved_proxy_url
                 env["https_proxy"] = resolved_proxy_url
                 
-            # If not a link, treat as search query
+            # If not a link or if resolved from Spotify track URL, treat as search query
             search_query = query
-            if not query.startswith("http"):
+            if resolved_title:
+                search_query = f"ytsearch1:{resolved_title}"
+                logger.info(f"[{task_id}] Using resolved Spotify track title for yt-dlp search: '{search_query}'")
+            elif not query.startswith("http"):
                 search_query = f"ytsearch1:{query}"
                 
             cmd = [
@@ -368,6 +415,7 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
             result = subprocess.run(cmd, cwd=temp_dir, env=env, capture_output=True, text=True)
             if result.returncode == 0:
                 logger.info(f"[{task_id}] yt-dlp download succeeded.")
+                download_successful = True
             else:
                 logger.warning(f"[{task_id}] yt-dlp failed: {result.stderr or result.stdout}. Falling back to Tubidy Search.")
                 
@@ -393,18 +441,23 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
             # Download file stream
             download_file_stream(mp3_url, dest_path, resolved_proxy_url)
             logger.info(f"[{task_id}] Tubidy download completed.")
+            download_successful = True
             
             # Tag metadata
             tag_mp3(dest_path, filename)
             logger.info(f"[{task_id}] Tubidy ID3 tagging complete.")
             
         # Priority 4: Tubidy Search Fallback (if spotDL and yt-dlp failed and no files are present)
-        downloaded_files = os.listdir(temp_dir)
+        if not download_successful and not is_tubidy:
-        if not downloaded_files and not is_tubidy:
             jobs_dict[task_id]["priority_used"] = "Tubidy-Search"
             logger.info(f"[{task_id}] Attempting Fallback Priority 4: Tubidy Search Scraper for '{query}'")
             
-            search_results = search_tubidy(query, resolved_proxy_url)
+            search_query = query
+            if resolved_title:
+                search_query = resolved_title
+                logger.info(f"[{task_id}] Using pre-resolved Spotify track title for Tubidy search: '{search_query}'")
+            
+            search_results = search_tubidy(search_query, resolved_proxy_url)
             if search_results:
                 first_result = search_results[0]
                 logger.info(f"[{task_id}] Found Tubidy match: '{first_result['title']}' (ID: {first_result['id']})")
@@ -430,14 +483,18 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
                     # Tag metadata
                     tag_mp3(dest_path, filename)
                     logger.info(f"[{task_id}] Tubidy fallback ID3 tagging complete.")
+                    download_successful = True
                 except Exception as e:
                     logger.error(f"[{task_id}] Tubidy fallback download failed: {e}")
                     raise Exception(f"All download options (spotDL, yt-dlp, Tubidy) failed. Last error: {e}")
             else:
-                logger.error(f"[{task_id}] No Tubidy search results found for query '{query}'")
+                logger.error(f"[{task_id}] No Tubidy search results found for query '{search_query}'")
                 raise Exception("All download options (spotDL, yt-dlp, Tubidy) failed. No Tubidy search results found.")
             
         # Verify files and move to /remote-music/music
+        if not download_successful:
+            raise Exception("Ingestion finished but no download was successful.")
+            
         downloaded_files = os.listdir(temp_dir)
         actual_files = [f for f in downloaded_files if not os.path.islink(os.path.join(temp_dir, f))]
         
@@ -450,7 +507,7 @@ def run_download_task(task_id: str, query: str, proxy_url: str, jobs_dict: dict,
                     send_telegram_notification(chat_id, f"✅ Successfully ingested request: '{query}'\n\n(All tracks already existed - skipped duplicates)")
                 return
             else:
-                raise Exception("Ingestion finished but no files were found in local temp folder.")
+                raise Exception("Ingestion finished successfully but no files were found in local temp folder.")
             
         os.makedirs("/remote-music/music", exist_ok=True)
         moved_files = []