Pandas

[nourou4them]

import pandas as pd
import getpass

def compare_excel_files(file1_path, file2_path):
    # Read Excel files
    df1 = pd.read_excel(file1_path)
    df2 = pd.read_excel(file2_path)

    # Initialize list to store differences
    differences = []

    # Iterate over rows in file 1
    for index, row in df1.iterrows():
        a_value_file1 = row['A']
        # Check if value in column A from file 1 exists in column A of file 2
        if a_value_file1 in df2['A'].values:
            # Get corresponding row in file 2
            corresponding_row_file2 = df2[df2['A'] == a_value_file1].iloc[0]
            # Check for differences in other columns
            diff_row = {'A': a_value_file1}
            for col in df1.columns:
                if col != 'A':
                    value_file1 = row[col]
                    value_file2 = corresponding_row_file2[col]
                    if value_file1 == value_file2:
                        diff_row[col] = f"{value_file1} (OK)"
                    else:
                        diff_row[col] = f"{value_file1} (File 1) vs {value_file2} (File 2)"
            # Add row to differences list if there are differences
            if any('(File' in value for value in diff_row.values()):
                differences.append(diff_row)

    return len(df1), len(df2), pd.DataFrame(differences)

def write_output_to_txt(output_path, num_lines_file1, num_lines_file2, differences, file1_name, file2_name, username):
    with open(output_path, 'w') as file:
        file.write(f"Username: {username}\n")
        file.write(f"Input File 1: {file1_name}\n")
        file.write(f"Input File 2: {file2_name}\n")
        file.write(f"Number of lines in File 1: {num_lines_file1}\n")
        file.write(f"Number of lines in File 2: {num_lines_file2}\n\n")

        if not differences.empty:
            file.write("Differences between files:\n")
            file.write(differences.to_string(index=False))
        else:
            file.write("No differences found between files.")

if __name__ == "__main__":
    # Input file paths
    file1_path = input("Enter path to the first Excel file: ")
    file2_path = input("Enter path to the second Excel file: ")

    file1_name = file1_path.split('/')[-1]  # Extracting file name with extension
    file2_name = file2_path.split('/')[-1]  # Extracting file name with extension

    # Analyze files and get differences
    num_lines_file1, num_lines_file2, differences = compare_excel_files(file1_path, file2_path)

    # Output to txt file
    output_path = input("Enter the path to save the output txt file: ")
    username = getpass.getuser()  # Get username of the user running the program
    write_output_to_txt(output_path, num_lines_file1, num_lines_file2, differences, file1_name, file2_name, username)

    print("Analysis complete. Output saved to", output_path)