c#怎么实现读取word文档

引用spire.doc.dll

提取word文档的文字兆罩渗到txt文件：

using Spire.Doc

using Spire.Doc.Documents

using System.IO

namespace ReadText

{

    class Program

    {

        static void Main(string[] args)

        {

            //创建Document对象

            Document doc = new Document()

            //加载Word文档

            doc.LoadFromFile("input.docx")

            //创建StringBuilder对象

            StringBuilder sb = new StringBuilder()

            //遍历Word文档中每一个section

            foreach (Section section in doc.Sections)

            {

                //遍历section中每一个段落

                foreach (Paragraph paragraph in section.Paragraphs)

                {

                    //提取Word的每一行文字存入StringBuilder对象

                    sb.AppendLine(paragraph.Text)

                }

            }

            //写入txt文档

            File.WriteAllText("output.txt", sb.ToString())

        }

    }

}

提取word文档中图片，保存到本地：

using Spire.Doc

using Spire.Doc.Fields

using Spire.Doc.Documents

namespace ReadImage

{

    class Program

    {

        static void Main(string[] args)

        {      

            //创建Document对象并加载Word文档

            Document doc = new Document()

            doc.LoadFromFile(@"Image.doc")

            int index = 0

            //遍历Word文档中每一个section

            foreach (Section section in doc.Sections)

            {

                //遍历section中的每个段落

                foreach (Paragraph paragraph in section.Paragraphs)

      闷信          {

                    //遍历段落中的每个DocumentObject

                    foreach (DocumentObject docObject in paragraph.ChildObjects)

                    {

           族脊             //判断DocumentObject是否为图片

                        if (docObject.DocumentObjectType == DocumentObjectType.Picture)

                        {

                            //保存图片到指定路径并设置图片格式

                            DocPicture picture = docObject as DocPicture

                            String imageName = String.Format(@"images\Image-{0}.png", index)

                            picture.Image.Save(imageName, System.Drawing.Imaging.ImageFormat.Png)

                            index++

                        }

                    }

                }

            }

        }

    }

}

你是指在扩展名是docx的Word文件提取xml文件？可以用WinRAR打开docx文件，然后在里面的Word文件蚂备夹中找到document.xlm文件弊慧解压闷卜毁出来。

---