批量读取word表格内容，并整理到excel文件

import docx
import pandas as pd
import os
from win32com import client as wc
from openpyxl import load_workbook


def GetDesktopPath():
    """
    获取桌面
    -------
    TYPE
        DESCRIPTION.
    """
    return os.path.join(os.path.expanduser("~"), 'Desktop')
DesktopPath = GetDesktopPath()+'\\'


def convertdoc_docx(path):
    """
    doc 转化为 docx
    @param path:
    @return:
    """
    path_list = os.listdir(path)
    doc_list = [os.path.join(path, str(i)) for i in path_list if str(i).endswith('doc')]
    word = wc.Dispatch('Word.Application')
    for path in doc_list:
        #print(path)
        save_path = str(path).replace('doc', 'docx')
        doc = word.Documents.Open(path)
        doc.SaveAs(save_path, 12, False, "", True, "", False, False, False, False)
        doc.Close()
        #print('{} Save sucessfully '.format(save_path))
    word.Quit()


def get_data_from_path(doc_path):
    '''
    获取数据
     Generate Data form doc_path of word path
    :param doc_path:
    :return: col_keys 列键；
            col_values 列名；
    '''
    document = docx.Document(doc_path)
    col_keys = []       # 获取列名
    col_values = []     # 获取列值
    index_num = 0
    # 添加一个去重机制
    fore_str = ''
    for table in document.tables:
        for row_index, row in enumerate(table.rows):
            for col_index, cell in enumerate(row.cells):
                if fore_str != cell.text:
                    if index_num % 2==0:
                        col_keys.append(cell.text)
                    else:
                        col_values.append(cell.text)
                    fore_str = cell.text
                    index_num +=1
    
    # 完整展身份证号码、电话号码等
    col_values[5] = '\t'+col_values[5]
    #print(f'col keys is {col_keys}')
    #print(f'col values is {col_values}')
    return col_keys, col_values


if __name__ == '__main__':
    #注意你的路径
    word_paths = os.getcwd() # 'C:\\Users\\ABC\\Desktop\\word'
    convertdoc_docx(os.path.join(os.getcwd(), word_paths))
    wordlist_path = [os.path.join(word_paths, i) for i in os.listdir(word_paths) if str(i).endswith('.docx')]

    data_list = []
    columns_list = []
    
    for index, single_path in enumerate(wordlist_path):
        col_names, col_values = get_data_from_path(single_path)
        if index == 0:
            columns_list.append(col_names)
            #print(columns_list)
            data_list.append(col_values)
        else:
            data_list.append(col_values)

    # 输出
    df_data = pd.DataFrame(data_list, columns=columns_list[0])
    df_data.to_excel('result.xlsx',index=False)


    wb = load_workbook('result.xlsx')
    ws = wb[wb.sheetnames[0]]                  # 打开第一个sheet
    ws.column_dimensions['F'].width = 20.0     # 调整列整1宽
    ws.column_dimensions['G'].width = 30.0     # 调整列整1宽
    ws.column_dimensions['H'].width = 20.0     # 调整列整1宽
    ws.column_dimensions['j'].width = 30.0     # 调整列整1宽
    ws.column_dimensions['K'].width = 20.0     # 调整列整1宽
    #ws.row_dimensions[1].height = 40    	   # 调整行1高
    wb.save('result.xlsx')

关于docx 的安装

pip  install  -i  https://pypi.doubanio.com/simple/  --trusted-host pypi.doubanio.com  docx