Python办公自动化｜光速对比并提取两份Word/Excel中的不同元素

import pandas as pd
import numpy as np
df1 = pd.read_excel('data1.xlsx')
df2 = pd.read_excel('data2.xlsx')

rows,cols=np.where(comparison_values==False)
for item in zip(rows,cols):
    df1.iloc[item[0], item[1]] = '{} --> {}'.format(df1.iloc[item[0], item[1]],df2.iloc[item[0], item[1]])
df1.to_excel('diff.xlsx',index=False,header=True)

def getText(wordname):
    '''
    提取文字
    '''
    d = Document(wordname)
    texts = []
    for para in d.paragraphs:
        texts.append(para.text)
    return texts

def is_Chinese(word):
    '''
    识别中文
    '''
    for ch in word:
        if '\u4e00' <= ch <= '\u9fff':
            return True
    return False

def msplit(s, seperators = ',|\.|\?|，|。|？|！|、'):
    '''
    根据标点符号分句
    '''
    return re.split(seperators, s)

def readDocx(docfile):
    '''
    读取文档
    '''
    print(f"======正在读取{docfile}======")
    paras = getText(docfile)
    segs = []
    for p in paras:
        temp = []
        for s in msplit(p):
            if len(s) > 2:
                temp.append(s.replace(' ', ""))
        if len(temp) > 0:
            segs.append(temp)
    return segs

def comparsion(doc1,doc2,p,s):
    if doc1 == doc2:
        print('两个word完全一致')
    else:
        if doc1[p][s] != doc2[p][s]:
            print(f"第{p+1}段，第{s+1}句不相同: {doc1[p][s]} ----> {doc2[p][s]}")