Signed-off-by: mbrucedogs <mbrucedogs@gmail.com>

karaoke_downloader/download_planner.py

@@ -20,12 +20,12 @@ from karaoke_downloader.cache_manager import (
 from karaoke_downloader.fuzzy_matcher import (
     create_song_key,
     create_video_key,
+    extract_artist_title,
     get_similarity_function,
     is_exact_match,
     is_fuzzy_match,
     normalize_title,
 )
-from karaoke_downloader.id3_utils import extract_artist_title
 from karaoke_downloader.youtube_utils import get_channel_info
 
 # Constants

karaoke_downloader/downloader.py

@@ -472,6 +472,13 @@ class KaraokeDownloader:
                 )
 
         undownloaded = not_on_server
+        
+        # Apply limit to undownloaded list before scanning
+        if limit is not None:
+            original_count = len(undownloaded)
+            undownloaded = undownloaded[:limit]
+            print(f"\n🎯 Limited to first {limit} songs (was {original_count} total)")
+        
         print(f"\n🎯 {len(undownloaded)} songs need to be downloaded.")
         if not undownloaded:
             print("🎵 All songlist songs already downloaded.")

karaoke_downloader/fuzzy_matcher.py

@@ -33,9 +33,46 @@ def normalize_title(title):
 
 def extract_artist_title(video_title):
     """Extract artist and title from video title."""
+    # Handle "Title - Artist" format
     if " - " in video_title:
         parts = video_title.split(" - ", 1)
         return parts[0].strip(), parts[1].strip()
+    
+    # Handle "Title Karaoke | Artist Karaoke Version" format
+    if " | " in video_title and "karaoke" in video_title.lower():
+        parts = video_title.split(" | ", 1)
+        title_part = parts[0].strip()
+        artist_part = parts[1].strip()
+        
+        # Clean up the parts
+        title = title_part.replace("Karaoke", "").strip()
+        artist = artist_part.replace("Karaoke Version", "").strip()
+        
+        return artist, title
+    
+    # Handle "Title Artist KARAOKE" format
+    if "karaoke" in video_title.lower():
+        # Try to find the artist by looking for common patterns
+        title_lower = video_title.lower()
+        
+        # Look for patterns like "Title Artist KARAOKE"
+        # This is a simplified approach - we'll need to improve this
+        words = video_title.split()
+        if len(words) >= 3:
+            # Assume the last word before "KARAOKE" is part of the artist
+            for i, word in enumerate(words):
+                if "karaoke" in word.lower():
+                    if i >= 2:
+                        # Everything before the last word before KARAOKE is title
+                        # Everything after is artist
+                        title = " ".join(words[:i-1])
+                        artist = " ".join(words[i-1:])
+                        return artist, title
+        
+        # If we can't parse it, return empty artist and full title
+        return "", video_title
+    
+    # Default: return empty artist and full title
     return "", video_title
 
 

karaoke_downloader/id3_utils.py

@@ -31,17 +31,7 @@ def clean_channel_name(channel_name: str) -> str:
     return "Unknown"
 
 
-def extract_artist_title(video_title):
+from karaoke_downloader.fuzzy_matcher import extract_artist_title
-    title = (
-        video_title.replace("(Karaoke Version)", "").replace("(Karaoke)", "").strip()
-    )
-    if " - " in title:
-        parts = title.split(" - ", 1)
-        if len(parts) == 2:
-            artist = parts[0].strip()
-            song_title = parts[1].strip()
-            return artist, song_title
-    return "Unknown Artist", title
 
 
 def add_id3_tags(file_path, video_title, channel_name):