### Python 脚本用于 Excel 文件中的行比较 为了实现两个 Excel 文件之间的行比较，可以利用 `pandas` 库读取 Excel 数据并执行对比操作。下面是一个完整的解决方案： #### 1. 准备工作 确保安装了必要的库： ```bash pip install pandas openpyxl ``` #### 2. 编写 Python 脚本进行行比较 创建名为 `compare_excel_rows.py` 的脚本来加载两个 Excel 文件，并逐行列出差异。 ```python import sys import pandas as pd def load_excel(file_path): """Load an Excel file into a DataFrame.""" try: df = pd.read_excel(file_path, engine='openpyxl') return df.fillna('') # Replace NaN with empty string for comparison purposes except Exception as e: print(f"Error loading {file_path}: {e}") sys.exit(1) def compare_dataframes(df1, df2): """Compare two DataFrames and find differences row by row.""" diff_df = pd.DataFrame() if not df1.equals(df2): # Check overall equality first ne_stacked = (df1 != df2).stack() # Find non-equal elements changed = ne_stacked[ne_stacked] difference_locations = list(zip(*changed.index.labels)) modified_values = [] for loc in difference_locations: old_value = df1.iloc[loc].astype(str) new_value = df2.iloc[loc].astype(str) modified_values.append({ 'Row': loc[0], 'Column': df1.columns[loc[1]], 'Old Value': old_value, 'New Value': new_value }) diff_df = pd.DataFrame(modified_values) return diff_df if __name__ == "__main__": if len(sys.argv) != 3: print("Usage: py -3 compare_excel_rows.py <first_file.xlsx> <second_file.xlsx>") sys.exit(1) file1 = sys.argv[1] file2 = sys.argv[2] df_first = load_excel(file1)[^1] df_second = load_excel(file2)[^1] result = compare_dataframes(df_first, df_second) if not result.empty: print("\nDifferences found:") print(result.to_string(index=False)) else: print("No differences detected between the files.") ``` 此脚本会接受两个命令行参数——即要比较的两个 Excel 文件名，并输出它们之间存在的任何不同之处。如果发现不一致，则显示具体的更改位置及其旧值和新值。