文档检索——从Word、PPT、Excel文件中提取文本

本文提供了一种使用C#控制台程序将Office文档(如Word、Excel、PowerPoint)转换为纯文本的方法。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

要实现文档检索,首先需要得到纯文本形式的内容,其中一个办法是利用微软提供的类库,将文档另存为文本文件,缺点是需要运行环境

c#控制台程序代码如下:

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using Microsoft.Office.Core;
using Microsoft.Office.Interop.Word;
using Microsoft.Office.Interop.Excel;
using Microsoft.Office.Interop.PowerPoint;
using System.IO;

//Office文档转换为Text http://www.cnblogs.com/libsource

namespace OfficetoText
{
    class Program
    {
        static void Main(string[] args)
        {
            //接受两个参数 inputdocfilepath ouputtextfilepath
            if (args.Length != 2)
            {
                Console.WriteLine("参数输入不正确,应为 inputdocfilepath ouputtextfilepath");
                return;
            }
            string inputfilepath = args[0];
            string outputfilepath = args[1];
            if (!File.Exists(inputfilepath))
            {
                Console.WriteLine("指定的文件不存在");
                return;
            }
            FileConvert convert = FileConvertFactory.CreateFileConvert(inputfilepath);
            convert.Convert(inputfilepath, outputfilepath);
        }
    }
    public interface FileConvert
    {
        void Convert(string inputfilepath, string outputfilepath);
    }
    public class FileConvertFactory
    {
        private FileConvertFactory() { }
        public static FileConvert CreateFileConvert(string inputfilepath)
        {
            FileConvert fileConvert;
            string extension = Path.GetExtension(inputfilepath);
            switch (extension.ToLower())
            {
                case (".xls"):
                case (".xlsx"):
                    fileConvert = new ExcelFileConvert();
                    break;
                case (".ppt"):
                case (".pptx"):
                    fileConvert = new PPTFileConvert();
                    break;
                case (".doc"):
                case (".docx"):
                default:
                    fileConvert = new DocFileConvert();
                    break;
            }
            return fileConvert;
        }
    }
    public class DocFileConvert : FileConvert
    {
        public void Convert(string inputfilepath, string outputfilepath)
        {
            Microsoft.Office.Interop.Word.ApplicationClass wordApp = new Microsoft.Office.Interop.Word.ApplicationClass();
            object fileName = inputfilepath;
            object missing = Type.Missing;
            //打开文档
            Document doc = wordApp.Documents.Open(
                ref fileName, ref missing, ref missing, ref missing,
                ref missing, ref missing, ref missing, ref missing,
                ref missing, ref missing, ref missing, ref missing,
                ref missing, ref missing, ref missing, ref missing);
            object saveFormat = Microsoft.Office.Interop.Word.WdSaveFormat.wdFormatTextLineBreaks;
            //object saveEncoding = MsoEncoding.msoEncodingUTF8;
            fileName = outputfilepath;
            //保存为TXT文档
            doc.SaveAs(
                ref fileName, ref saveFormat, ref missing, ref missing,
                ref missing, ref missing, ref missing, ref missing,
                ref missing, ref missing, ref missing, ref missing,
                ref missing, ref missing, ref missing, ref missing);
            doc.Close(ref missing, ref missing, ref missing);
            wordApp.Quit(ref missing, ref missing, ref missing);
        }
    }
    public class ExcelFileConvert : FileConvert
    {
        public void Convert(string inputfilepath, string outputfilepath)
        {
            Microsoft.Office.Interop.Excel.ApplicationClass wordApp = new Microsoft.Office.Interop.Excel.ApplicationClass();
            object fileName = inputfilepath;
            object missing = Type.Missing;
            Workbook doc = wordApp.Workbooks.Open(
                inputfilepath, missing, missing, missing,
                 missing, missing, missing, missing,
                 missing, missing, missing, missing,
                 missing, missing, missing);
            object saveFormat = Microsoft.Office.Interop.Excel.XlFileFormat.xlUnicodeText;
            object saveResolution = XlSaveConflictResolution.xlLocalSessionChanges;
            doc.SaveAs(
                 outputfilepath, saveFormat, missing, missing,
                 missing, missing, XlSaveAsAccessMode.xlNoChange, saveResolution,
                 missing, missing, missing, missing);
            wordApp.Quit();
        }
    }
    public class PPTFileConvert : FileConvert
    {
        public void Convert(string inputfilepath, string outputfilepath)
        {
            Microsoft.Office.Interop.PowerPoint.ApplicationClass wordApp = new Microsoft.Office.Interop.PowerPoint.ApplicationClass();
            object fileName = inputfilepath;
            object missing = Type.Missing;
            Presentation doc = wordApp.Presentations.Open(
                inputfilepath, MsoTriState.msoCTrue, MsoTriState.msoCTrue, MsoTriState.msoFalse);
            object saveFormat = PpSaveAsFileType.ppSaveAsRTF;
            object saveResolution = XlSaveConflictResolution.xlLocalSessionChanges;
            string tempfile = Path.GetDirectoryName(outputfilepath) + DateTime.Now.ToFileTime() + "tmp.rtf";
            //保存为RTF文件
            doc.SaveAs(tempfile, PpSaveAsFileType.ppSaveAsRTF, MsoTriState.msoFalse);
            wordApp.Quit();
            //然后转换为txt文件
            DocFileConvert newConvert = new DocFileConvert();
            newConvert.Convert(tempfile, outputfilepath);
            File.Delete(tempfile);
        }
    }
}

转载于:https://www.cnblogs.com/libsource/archive/2010/07/02/1769943.html

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值