数据预处理之抽取文本信息

# coding=utf-8

import os, fnmatch  # fnmatch 匹配后缀名的包
from win32com import client as wc
from win32com.client import Dispatch, gencache


def Files2txt(filePath, savePath=‘‘):
    try:
        # 切分文件目录和文件名
        dirs, filename = os.path.split(filePath)
        # 修改转化后的文件名
        typename = os.path.splitext(filename)[-1].lower()
        new_name = TranType(filename, typename)
        # 文件转化后的保存路径
        if savePath == ‘‘:
            savePath = dirs
        else:
            savePath = savePath
        new_save_path = os.path.join(savePath, new_name)
        print(‘保存路径：‘, new_save_path)
        # 加载处理应用
        manyapp = wc.Dispatch(‘Word.Application‘)
        mytxt = manyapp.Documents.Open(filePath)
        mytxt.SaveAs(new_save_path, 4)
        mytxt.Close()
        print(‘处理完成,请查看！‘)
    except Exception as e:
        print(‘程序出错了！‘)

def TranType(filename, typename):
    ‘‘‘
    根据文件后缀修改文件名
    1、文件名  2、文件类型后缀
    返回修改后的新的文件名
    ‘‘‘
    new_name = ‘‘
    if typename == ‘.pdf‘:
        if fnmatch.fnmatch(filename, ‘*.pdf‘):
            new_name = filename[:-4] + ‘.txt‘
        else:
            return
    elif typename == ‘.doc‘ or typename == ‘.docx‘:
        if fnmatch.fnmatch(filename, ‘*.doc‘):
            new_name = filename[:-4] + ‘.txt‘
        elif fnmatch.fnmatch(filename, ‘*.docx‘):
            new_name = filename[:-5] + ‘.txt‘
        else:
            return
    else:
        print(‘警告：\n 您输入【‘, typename, ‘】不合法，工具仅支持pdf/doc/docx格式，请输入正确的格式。‘)
        return
    return new_name


if __name__ == ‘__main__‘:
    filepath1 = os.path.abspath(r‘D:\Python\study\test\抽取文本信息\智联范本.docx‘)
    Files2txt(filepath1)