从word文件中提取图像

Question

我一直在尝试使用以下 C# 代码从 doc 文件中提取图像，但它不起作用：

object missing = System.Reflection.Missing.Value;            
            Microsoft.Office.Interop.Word.Application oWord = new Microsoft.Office.Interop.Word.Application();
            Microsoft.Office.Interop.Word.Document oDoc = new Microsoft.Office.Interop.Word.Document();
            oWord.Visible = false;
            object str1 = "C:\\doc.doc";
            oDoc = oWord.Documents.Open(ref str1, 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);

            if (oDoc.InlineShapes.Count > 0)            {


                for (int j = 0; j < oDoc.InlineShapes.Count; j++)
                {  

                    oWord.ActiveDocument.Select();
                    oDoc.ActiveWindow.Selection.CopyAsPicture();

                    IDataObject data = Clipboard.GetDataObject();                    

                    if (data.GetDataPresent(typeof(System.Drawing.Bitmap)))
                    {
                        object bm = data.GetData(DataFormats.Bitmap);

                        Bitmap bmp;
                        bmp = (Bitmap)data.GetData(typeof(System.Drawing.Bitmap));

                        bmp.Save("C:\\test.bmp");
                    }



                }

任何人都可以提供从 word 文件中提取图像的正确代码吗？

Answer 1

using System;
using System.Drawing;
using System.IO;
using System.Threading;
using Page = System.Web.UI.Page;
using Microsoft.Office.Interop.Word;
using Microsoft.VisualBasic.Devices;
public partial class ReadIMG : System.Web.UI.Page
{   
    private Application m_word;
    private int m_i;
    protected void Page_Load(object sender, EventArgs e)
    {
        object missing = Type.Missing;
        object FileName = Server.MapPath("~/LectureOrig/Word.docx");
        object readOnly = true;
        m_word = new Application();
        m_word.Documents.Open(ref FileName,
                                ref missing, ref readOnly, 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);
        try
        {
            for (int i = 1; i <= m_word.ActiveDocument.InlineShapes.Count; i++)
            {
                m_i = i;
               // CopyFromClipboardShape();
                Thread thread = new Thread(CopyFromClipbordInlineShape);
                thread.SetApartmentState(ApartmentState.STA);
                thread.Start();
                thread.Join();
            }
        }
        finally
        {
            object save = false;
            m_word.Quit(ref save, ref missing, ref missing);
            m_word = null;
        }
    }
    protected void CopyFromClipbordInlineShape()
    {   
        InlineShape inlineShape = m_word.ActiveDocument.InlineShapes[m_i];
        inlineShape.Select();
        m_word.Selection.Copy();
        Computer computer = new Computer();
        //Image img = computer.Clipboard.GetImage();
        if (computer.Clipboard.GetDataObject() != null)
        {
            System.Windows.Forms.IDataObject data = computer.Clipboard.GetDataObject();
            if (data.GetDataPresent(System.Windows.Forms.DataFormats.Bitmap))
            {
                Image image = (Image)data.GetData(System.Windows.Forms.DataFormats.Bitmap, true);                
                image.Save(Server.MapPath("~/ImagesGet/image.gif"), System.Drawing.Imaging.ImageFormat.Gif);
                image.Save(Server.MapPath("~/ImagesGet/image.jpg"), System.Drawing.Imaging.ImageFormat.Jpeg);

            }
            else
            {
                LabelMessage.Text="The Data In Clipboard is not as image format";
            }
        }
        else
        {
            LabelMessage.Text="The Clipboard was empty";
        }
    }

代码复制自How To Extract images from Doc (Word) file in C#?

Answer 2

如果是 .docx 文件，则还有另一种选择：

1. 将文件重命名为 .zip
2. 提取内容
3. 在提取的文件夹 word/media 中查找以下目录

是的，它不是按照发布的方式执行此操作的 C# 方法，但如果您正在寻找的话，即使编写代码来执行上述 3 个步骤也将是一种自动化该过程的方法。

Answer 3

这是本地/非网页版本。

此代码大部分复制自： http://www.csharphelp.com/2007/05/save-picture-from-clipboard-to-file-using-c/ - 加上Ekk答案中的几行。

InlineShape inlineShape = m_word.ActiveDocument.InlineShapes[m_i];
inlineShape.Select();
m_word.Selection.Copy();
if (Clipboard.GetDataObject() != null)
{
    IDataObject data = Clipboard.GetDataObject();

    if (data.GetDataPresent(DataFormats.Bitmap))
    {
        Image image = (Image)data.GetData(DataFormats.Bitmap,true);

        image.Save("image.bmp",System.Drawing.Imaging.ImageFormat.Bmp);
        image.Save("image.jpg",System.Drawing.Imaging.ImageFormat.Jpeg);
        image.Save("image.gif",System.Drawing.Imaging.ImageFormat.Gif);
    }
    else
    {
        MessageBox.Show("The Data In Clipboard is not as image format");
    }
}
else
{
    MessageBox.Show("The Clipboard was empty");
}

Answer 4

我使用 spire 库时遇到了同样的问题，我得到了解决方案，我给出了该库使用的链接，只需在 Visual Studio 中添加该 dll 文件并复制以下代码：

enter code here



        if (file.ShowDialog() == DialogResult.OK) //if there is a file choosen by the user  
        {
            object path = file.FileName; //get the path of the file  
            object readOnly = true;

            Spire.Doc.Document document = new Spire.Doc.Document(file.FileName);
            int index = 1;

            //Get Each Section of Document  
            foreach (Spire.Doc.Section section in document.Sections)
            {
                //Get Each Paragraph of Section  
                foreach (Spire.Doc.Documents.Paragraph paragraph in section.Paragraphs)
                {
                    StringBuilder sb = new StringBuilder();
                    sb.AppendLine(paragraph.Text);//storing the text of word in string builder
                    Console.WriteLine(sb);
                    //Get Each Document Object of Paragraph Items  
                    foreach (DocumentObject docObject in paragraph.ChildObjects)
                    {
                        //If Type of Document Object is Picture, Extract.  
                        if (docObject.DocumentObjectType == DocumentObjectType.Picture)
                        {
                            DocPicture pic = docObject as DocPicture;

                            String imgName = String.Format(@"E:\C#\OnlineExam\Question\{0}.png", index);

                            //Save Image  
                            pic.Image.Save(imgName, System.Drawing.Imaging.ImageFormat.Png);
                            index++;
                        }
                    }
                }
            }}

您可以从此链接找到 dll 文件