C#讀取word文檔文本

讀取word,首先得添加引用，不同的word版本對應着不同的引用

部分版本對應引用如下：

Microsoft Word 11.0 object library對應Office2003
Microsoft Word 12.0 object library對應Office2007
Microsoft Word 14.0 object library對應Office2010
Microsoft Word 15.0 object library對應Office2013

 

由於我電腦的版本是word 2007,故添加Microsoft Word 12.0 Object Library，添加方法，右擊項目解決方案，選擇 Add Reference,彈出對話框如下圖：

 

 

 
再使用下面兩個命名空間，如圖：

 

 

 

 完整代碼如下：

using System;

using System.Collections.Generic;

using System.Linq;

using System.Text;

using Office;

using Word;

namespace ReadWordText

{undefined

    class Program

    {undefined

        static void Main(string[] args)

        {undefined

 

            Application app = new Application();

            Document doc = null;

            object unknow = Type.Missing;

            object ReadOnly = false;//是否只能讀

            object encoding = Encoding.UTF8;//UTF8編碼

            app.Visible = false;

            string str = @"C:\Users\zxy\Desktop\讀取word文檔.doc";//文檔的路徑

            object file = str;

            try

            {undefined

                doc = app.Documents.Open(ref file,

               ref unknow, ref ReadOnly, ref unknow, ref unknow,

               ref unknow, ref unknow, ref unknow, ref unknow,

               ref unknow, ref encoding, ref unknow, ref unknow,

               ref unknow, ref unknow, ref unknow);

 

                //讀取第幾段內容（空白行、各級標題等均作為一段來算）  

                //string strParaghaph = doc.Paragraphs[4].Range.Text.Trim();

 

                //讀取第幾句內容(空白行、各級標題等都作為一句來算)

                // string strSentence = doc.Sentences[5].Text;

 

 

                //讀取整篇內容

                int sentencesLength = doc.Paragraphs.Count;//文檔的總段數

                for (int sen = 1; sen <= sentencesLength; sen++)

                {undefined

                    string strSence = doc.Paragraphs[sen].Range.Text;//獲取每段內容

                    Console.WriteLine(strSence);

                }

            

 

 

            }

            catch (Exception)

            {undefined

 

                Console.WriteLine("無法讀取到文本");

            }

           

          

            Console.ReadKey();

 

 

        }

    }

}