在python中突出显示更改的单词

我找到了一个比较 Excel 电子表格并突出显示更改的函数。如何以仅突出显示更改的单词的方式修改脚本？

您可以在下面看到我想应用的逻辑。

数据框 1

数据帧 2

数据帧 3

原始脚本在 GitHub 上，链接在这里。作为输出，我想将所有内容保存在 1 个工作簿中，如下面的代码所示。唯一需要进行的更改是以某种方式标记所有更改的单词并将它们导出到 DataFrame 3 (dfDiff)。

import pandas as pd
from pathlib import Path
import os


def excel_diff(path_OLD, path_NEW, index_col):
    df_OLD = pd.read_excel(path_OLD, index_col=index_col).fillna(0)
    df_NEW = pd.read_excel(path_NEW, index_col=index_col).fillna(0)

    # Perform Diff
    dfDiff = df_NEW.copy()
    droppedRows = []
    newRows = []

    cols_OLD = df_OLD.columns
    cols_NEW = df_NEW.columns
    sharedCols = list(set(cols_OLD).intersection(cols_NEW))

    for row in dfDiff.index:
        if (row in df_OLD.index) and (row in df_NEW.index):
            for col in sharedCols:
                value_OLD = df_OLD.loc[row, col]
                value_NEW = df_NEW.loc[row, col]
                if value_OLD == value_NEW:
                    dfDiff.loc[row, col] = df_NEW.loc[row, col]
                else:
                    dfDiff.loc[row, col] = ('{}→{}').format(value_OLD, value_NEW)
        else:
            newRows.append(row)

    for row in df_OLD.index:
        if row not in df_NEW.index:
            droppedRows.append(row)
            dfDiff = dfDiff.append(df_OLD.loc[row, :])

    dfDiff = dfDiff.sort_index().fillna('')
    print(dfDiff)
    print('\nNew Rows:     {}'.format(newRows))
    print('Dropped Rows: {}'.format(droppedRows))

    # Save output and format
    # fname = '{} vs {}.xlsx'.format(path_OLD.stem, path_NEW.stem)
    fname = (os.path.dirname(os.path.abspath(__file__)) + '/uploads/differences.xlsx'.format(path_OLD.stem, path_NEW.stem))
    writer = pd.ExcelWriter(fname, engine='xlsxwriter')

    dfDiff.to_excel(writer, sheet_name='differences', index=True)
    df_NEW.to_excel(writer, sheet_name=path_NEW.stem, index=True)
    df_OLD.to_excel(writer, sheet_name=path_OLD.stem, index=True)

    # get xlsxwriter objects
    workbook = writer.book
    worksheet = writer.sheets['differences']
    worksheet.hide_gridlines(2)
    worksheet.set_default_row(15)

    # define formats
    grey_fmt = workbook.add_format({'font_color': '#E0E0E0'})
    highlight_fmt = workbook.add_format({'font_color': '#ff6666', 'bg_color': '#ffff00'})
    new_fmt = workbook.add_format({'font_color': '#32CD32', 'bold': True})

    # set format over range
    ## highlight changed cells
    worksheet.conditional_format('A1:ZZ1000', {'type': 'text',
                                               'criteria': 'containing',
                                               'value': '→',
                                               'format': highlight_fmt})

    # highlight new/changed rows
    for row in range(dfDiff.shape[0]):
        if row + 1 in newRows:
            worksheet.set_row(row + 1, 15, new_fmt)
        if row + 1 in droppedRows:
            worksheet.set_row(row + 1, 15, grey_fmt)

    # save
    writer.save()
    print('\nDone.')


def main():
    path_OLD = Path(os.path.dirname(os.path.abspath(__file__)) + '/uploads/old_content.xlsx')
    path_NEW = Path(os.path.dirname(os.path.abspath(__file__)) + '/uploads/new_content.xlsx')

    # get index col from data
    df = pd.read_excel(path_NEW)
    index_col = df.columns[0]
    print('\nIndex column: {}\n'.format(index_col))
    excel_diff(path_OLD, path_NEW, index_col)


main()