python提取word表格中数据

程序分析

今天文章介绍一个实战案例，与自动化办公相关；案例思想是源于前两天帮读者做了一个 demo ，需求大致将一上百个 word 中表格内容提取出来(所有word 中表格样式一样)，把提取到的内容自动存入 Excel 中。
原文地址 作者：zeroing

程序源码

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

path="C:\\Users\Lenovo\PycharmProjects\infoexarct\\table\\" #设置文件的目录

def doc_to_docx(path):
    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')
    wordlist_path=[]
    print("正在读取文件目录....")
    for doc_path in doc_list:
        doxc_path_save=doc_path.replace(path,"C:\\Users\Lenovo\PycharmProjects\infoexarct\\table\\temp\\")
        save_path = str(doxc_path_save).replace('doc','docx')
        doc = word.Documents.Open(doc_path)
        doc.SaveAs(save_path,12, False, "", True, "", False, False, False, False)
        doc.Close()
        wordlist_path.append(save_path)
        print('{} Save sucessfully '.format(save_path))
    word.Quit()
    print("文件转换已完成,开始分析文件....")

    return wordlist_path



def GetData_frompath(save_path):
    document = docx.Document(save_path)
    col_keys = [] # 获取列名
    col_values = [] # 获取列值
    index_num = 0
    for table in document.tables:
        for row_index,row in enumerate(table.rows):
            for col_index,cell in enumerate(row.cells):

                if (col_index==4 and row_index<7) :
                    continue
                # print(' pos index is ({},{})'.format(row_index, col_index))
                # print('cell text is {}'.format(cell.text))
                if row_index<7:
                    if index_num % 2==0:
                        col_keys.append(cell.text)
                    else:
                        col_values.append(cell.text)
                    fore_str = cell.text
                    index_num +=1
                else:
                    if col_index >0 :
                        break
                    else:
                        if index_num % 2 == 0:
                            col_keys.append(cell.text)
                        else:
                            col_values.append(cell.text)
                        fore_str = cell.text
                        index_num += 1

    col_keys.pop(3)
    col_values.pop(3)
    col_values[11] = '\t' + col_values[11]
    # print(f'col keys is {col_keys}')
    # print(f'col values is {col_values}')

    return  col_keys,col_values



def create_csv(wordlist_path):
    pd_data = []
    for index,single_path in enumerate(wordlist_path):
        col_names,col_values = GetData_frompath(single_path)
        print(f"已录入{index+1}名学生信息")
        if index == 0:
            pd_data.append(col_names)
            pd_data.append(col_values)
        else:
            pd_data.append(col_values)

    df = pd.DataFrame(pd_data)
    #csv_path="C:\\Users\Lenovo\PycharmProjects\infoexarct\\finsh.csv"
    # df.to_csv(csv_path, encoding='utf_8_sig',index=False,header=None)
    df.to_excel('data.xlsx', sheet_name='工作表1',index=False,header=None)
    print("程序执行结束.....")


wordlist_path=doc_to_docx(path)

create_csv(wordlist_path)

常见错误

from win32com import client as wc
word = wc.Dispatch(‘Word.Application’)

安装包 pip install pypiwin32
如果报错 DLL load failed while importing win32api:找不到指定的模块

那么我们可以找到自己安装的环境的脚本目录 ，一般在python安装环境的

运行一下命令 python pywin32_postinstall.py -install 就安装完成了
安装处理docx的包
pip install docx

报错 from exceptions import PendingDeprecationWarning
ModuleNotFoundError: No module named ‘exceptions’

python3.x版本移除了exceptions模块，但是docx包中引用了该模块

安装最新版python-docx模块即可
#1 pip install python-docx安装问题解决

modulenotfounderror: no module named 'xlwt’解决方案 python padans 输出excel出错