update : tasks sch

core/nfo_manager.py

@@ -249,12 +249,64 @@ class NFOManager:
                 print(f"✅ Found NFOGuard data in NFO: dateadded={result.get('dateadded', 'None')}, source={source}, released={result.get('released', 'None')}, aired={result.get('aired', 'None')}")
                 return result
                 
-        except (ET.ParseError, Exception) as e:
-            print(f"⚠️ Error parsing NFO for NFOGuard data: {e}")
+        except ET.ParseError as e:
+            # Handle malformed XML files gracefully (common with external NFO files)
+            print(f"🔍 NFO XML parse error (will try text fallback): {nfo_path.name}")
+            # Try text-based fallback for extracting NFOGuard data
+            return self._extract_nfoguard_data_text_fallback(nfo_path)
+        except Exception as e:
+            print(f"⚠️ Unexpected error reading NFO file {nfo_path.name}: {e}")
             pass
             
         return None
     
+    def _extract_nfoguard_data_text_fallback(self, nfo_path: Path) -> Optional[Dict[str, str]]:
+        """Text-based fallback for extracting NFOGuard data from malformed XML files"""
+        try:
+            content = nfo_path.read_text(encoding='utf-8', errors='ignore')
+            
+            # Look for NFOGuard elements using regex
+            import re
+            
+            # Check for lockdata=true first (NFOGuard marker)
+            if not re.search(r'<lockdata>true</lockdata>', content, re.IGNORECASE):
+                return None
+            
+            # Extract dateadded
+            dateadded_match = re.search(r'<dateadded>([^<]+)</dateadded>', content, re.IGNORECASE)
+            if not dateadded_match:
+                return None
+            
+            dateadded = dateadded_match.group(1).strip()
+            if not dateadded:
+                return None
+            
+            result = {
+                "dateadded": dateadded,
+                "source": "nfo_file_existing"  # Default source
+            }
+            
+            # Extract optional fields
+            premiered_match = re.search(r'<premiered>([^<]+)</premiered>', content, re.IGNORECASE)
+            if premiered_match:
+                result["released"] = premiered_match.group(1).strip()
+            
+            aired_match = re.search(r'<aired>([^<]+)</aired>', content, re.IGNORECASE)
+            if aired_match:
+                result["aired"] = aired_match.group(1).strip()
+            
+            # Extract source from NFOGuard comment
+            source_match = re.search(r'<!--\s*NFOGuard\s*-\s*Source:\s*([^-]+?)\s*-->', content)
+            if source_match:
+                result["source"] = source_match.group(1).strip()
+            
+            print(f"✅ Extracted NFOGuard data via text fallback: dateadded={result.get('dateadded', 'None')}, source={result['source']}")
+            return result
+            
+        except Exception as e:
+            print(f"⚠️ Text fallback extraction failed for {nfo_path.name}: {e}")
+            return None
+    
     def extract_nfoguard_dates_from_episode_nfo(self, season_path: Path, season_num: int, episode_num: int) -> Optional[Dict[str, str]]:
         """Extract NFOGuard-managed dates from existing episode NFO file"""
         nfo_filename = f"s{season_num:02d}e{episode_num:02d}.nfo"