Build a Python Utility That Detects Duplicate Records Across Multiple Excel Sheets

import pandas as pd
from pathlib import Path

def find_duplicate_records_across_sheets(file_path: str, key_columns: list, sheet_names: list) -> dict:
    """
    Detect duplicate records across multiple Excel sheets based on specified key columns.
    
    Args:
        file_path: Path to the Excel file
        key_columns: List of column names to check for duplicates
        sheet_names: List of sheet names to compare
    
    Returns:
        Dictionary with duplicate records per sheet pair
    """
    xls = pd.ExcelFile(file_path)
    duplicates = {}
    
    for i, sheet1 in enumerate(sheet_names):
        df1 = pd.read_excel(xls, sheet_name=sheet1)
        for j, sheet2 in enumerate(sheet_names):
            if i >= j:
                continue
            df2 = pd.read_excel(xls, sheet_name=sheet2)
            merged = df1.merge(df2, on=key_columns, how='inner', suffixes=(f'_{sheet1}', f'_{sheet2}'))
            if not merged.empty:
                duplicates[f'{sheet1}_vs_{sheet2}'] = merged
    
    return duplicates

if __name__ == "__main__":
    sample_file = Path("sample_data.xlsx")
    if sample_file.exists():
        result = find_duplicate_records_across_sheets(
            "sample_data.xlsx", 
            key_columns=["ID"], 
            sheet_names=["Sheet1", "Sheet2", "Sheet3"]
        )
        for pair, records in result.items():
            print(f"Duplicate records in {pair}:")
            print(records.to_string(index=False))
            print()
    else:
        print("Create sample_data.xlsx with multiple sheets for testing.")