使用 itextsharp 从 PDF 中提取图像

Question

我正在尝试使用 itextsharp 从 pdf 中提取所有图像，但似乎无法克服这一障碍。

错误发生在 System.Drawing.Image ImgPDF = System.Drawing.Image.FromStream(MS); 行上，给出“参数无效”错误。

我认为当图像是位图而不是任何其他格式时它会起作用。

我有以下代码 - 抱歉，长度太长了；

    private void Form1_Load(object sender, EventArgs e)
    {
        FileStream fs = File.OpenRead(@"reader.pdf");
        byte[] data = new byte[fs.Length];
        fs.Read(data, 0, (int)fs.Length);

        List<System.Drawing.Image> ImgList = new List<System.Drawing.Image>();

        iTextSharp.text.pdf.RandomAccessFileOrArray RAFObj = null;
        iTextSharp.text.pdf.PdfReader PDFReaderObj = null;
        iTextSharp.text.pdf.PdfObject PDFObj = null;
        iTextSharp.text.pdf.PdfStream PDFStremObj = null;

        try
        {
            RAFObj = new iTextSharp.text.pdf.RandomAccessFileOrArray(data);
            PDFReaderObj = new iTextSharp.text.pdf.PdfReader(RAFObj, null);

            for (int i = 0; i <= PDFReaderObj.XrefSize - 1; i++)
            {
                PDFObj = PDFReaderObj.GetPdfObject(i);

                if ((PDFObj != null) && PDFObj.IsStream())
                {
                    PDFStremObj = (iTextSharp.text.pdf.PdfStream)PDFObj;
                    iTextSharp.text.pdf.PdfObject subtype = PDFStremObj.Get(iTextSharp.text.pdf.PdfName.SUBTYPE);

                    if ((subtype != null) && subtype.ToString() == iTextSharp.text.pdf.PdfName.IMAGE.ToString())
                    {
                        byte[] bytes = iTextSharp.text.pdf.PdfReader.GetStreamBytesRaw((iTextSharp.text.pdf.PRStream)PDFStremObj);

                        if ((bytes != null))
                        {
                            try
                            {
                                System.IO.MemoryStream MS = new System.IO.MemoryStream(bytes);

                                MS.Position = 0;
                                System.Drawing.Image ImgPDF = System.Drawing.Image.FromStream(MS);

                                ImgList.Add(ImgPDF);

                            }
                            catch (Exception)
                            {
                            }
                        }
                    }
                }
            }
            PDFReaderObj.Close();
        }
        catch (Exception ex)
        {
            throw new Exception(ex.Message);
        }



    } //Form1_Load

Answer 1

已解决...

即使我也遇到了“参数无效”的相同异常，并且经过了这么多
在 der_chirurg 提供的链接的帮助下工作
（http://kuujinbo.info/iTextSharp/CCITTFaxDecodeExtract.aspx）我解决了它
以下是代码：

using System.Drawing;
using System.Drawing.Imaging;
using System.IO;
using iTextSharp.text.pdf.parser;
using Dotnet = System.Drawing.Image;
using iTextSharp.text.pdf;

namespace PDF_Parsing
{
    partial class PDF_ImgExtraction
    {
        string imgPath;
        private void ExtractImage(string pdfFile)
        {
            PdfReader pdfReader = new PdfReader(files[fileIndex]);
            for (int pageNumber = 1; pageNumber <= pdfReader.NumberOfPages; pageNumber++)
            {
                PdfReader pdf = new PdfReader(pdfFile);
                PdfDictionary pg = pdf.GetPageN(pageNumber);
                PdfDictionary res = (PdfDictionary)PdfReader.GetPdfObject(pg.Get(PdfName.RESOURCES));
                PdfDictionary xobj = (PdfDictionary)PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT));
                foreach (PdfName name in xobj.Keys)
                {
                    PdfObject obj = xobj.Get(name);
                    if (obj.IsIndirect())
                    {
                        PdfDictionary tg = (PdfDictionary)PdfReader.GetPdfObject(obj);
                        string width = tg.Get(PdfName.WIDTH).ToString();
                        string height = tg.Get(PdfName.HEIGHT).ToString();
                        ImageRenderInfo imgRI = ImageRenderInfo.CreateForXObject(new Matrix(float.Parse(width), float.Parse(height)), (PRIndirectReference)obj, tg);
                        RenderImage(imgRI);
                    }
                }
            }
        }
        private void RenderImage(ImageRenderInfo renderInfo)
        {
            PdfImageObject image = renderInfo.GetImage();
            using (Dotnet dotnetImg = image.GetDrawingImage())
            {
                if (dotnetImg != null)
                {
                    using (MemoryStream ms = new MemoryStream())
                    {
                        dotnetImg.Save(ms, ImageFormat.Tiff);
                        Bitmap d = new Bitmap(dotnetImg);
                        d.Save(imgPath);
                    }
                }
            }
        }
    }
}

Answer 2

您需要检查流的 /Filter 以查看给定图像使用的图像格式。它可能是标准图像格式：

• DCTDecode (jpeg)
• JPXDecode (jpeg 2000)
• JBIG2Decode（jbig 是仅限黑白格式）
• CCITTFaxDecode（传真格式，PDF 支持第 3 组和第 4 组）

除此之外，您还需要获取原始字节（如您所愿），并使用图像流的宽度、高度、每个组件的位数、颜色组件的数量（可以是 CMYK、索引、RGB 或某些奇怪的东西）以及其他一些定义来构建图像在 ISO PDF 规范（免费提供）。

因此，在某些情况下，您的代码可以工作，但在其他情况下，它会因您提到的异常而失败。

PS：当出现异常时，请每次都包含堆栈跟踪。上面加点糖好吗？

Answer 3

使用这两种方法对我来说是这样的：

    public static List<System.Drawing.Image> ExtractImagesFromPDF(byte[] bytes)
    {
        var imgs = new List<System.Drawing.Image>();
        var pdf = new PdfReader(bytes);

        try
        {
            for (int pageNumber = 1; pageNumber <= pdf.NumberOfPages; pageNumber++)
            {
                PdfDictionary pg = pdf.GetPageN(pageNumber);
                List<PdfObject> objs = FindImageInPDFDictionary(pg);

                foreach (var obj in objs)
                {
                    if (obj != null)
                    {
                        int XrefIndex = Convert.ToInt32(((PRIndirectReference)obj).Number.ToString(System.Globalization.CultureInfo.InvariantCulture));
                        PdfObject pdfObj = pdf.GetPdfObject(XrefIndex);
                        PdfStream pdfStrem = (PdfStream)pdfObj;
                        var pdfImage = new PdfImageObject((PRStream)pdfStrem);
                        var img = pdfImage.GetDrawingImage();

                        imgs.Add(img);
                    }
                }
            }
        }
        finally
        {
            pdf.Close();
        }

        return imgs;
    }

    private static List<PdfObject> FindImageInPDFDictionary(PdfDictionary pg)
    {
        var res = (PdfDictionary)PdfReader.GetPdfObject(pg.Get(PdfName.RESOURCES));
        var xobj = (PdfDictionary)PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT));
        var pdfObgs = new List<PdfObject>();

        if (xobj != null)
        {
            foreach (PdfName name in xobj.Keys)
            {
                PdfObject obj = xobj.Get(name);
                if (obj.IsIndirect())
                {
                    var tg = (PdfDictionary)PdfReader.GetPdfObject(obj);
                    var type = (PdfName)PdfReader.GetPdfObject(tg.Get(PdfName.SUBTYPE));

                    if (PdfName.IMAGE.Equals(type)) // image at the root of the pdf
                    {
                        pdfObgs.Add(obj);
                    }
                    else if (PdfName.FORM.Equals(type)) // image inside a form
                    {
                        FindImageInPDFDictionary(tg).ForEach(o => pdfObgs.Add(o));
                    }
                    else if (PdfName.GROUP.Equals(type)) // image inside a group
                    {
                        FindImageInPDFDictionary(tg).ForEach(o => pdfObgs.Add(o));
                    }
                }
            }
        }

        return pdfObgs;
    }

Answer 4

在较新版本的 iTextSharp 中，ImageRenderInfo.CreateForXObject 的第一个参数不再是 Matrix 而是 GraphicsState。 @der_chirurg 的方法应该有效。我使用以下链接中的信息对自己进行了测试，效果非常好：

http://www.thevalvepage.com/swmonkey/2014/11/26/extract-images-from-pdf-files-using-itextsharp/

Answer 5

要提取所有页面上的所有图像，无需实现不同的过滤器。 iTextSharp 有一个图像渲染器，它将所有图像保存为其原始图像类型。

只需执行此处找到的以下操作： http://kuujinbo.info/iTextSharp/CCITTFaxDecodeExtract.aspx不需要实现 HttpHandler...

Answer 6

我在 github 上添加了库，提取 PDF 中的图像并压缩它们。

当您要开始使用非常强大的 ITextSharp 库时，这可能很有用。

链接如下： https://github.com/rock-walker/PdfCompression

Answer 7

这对我有用，我认为这是一个简单的解决方案：

编写一个自定义 RenderListener 并实现其 RenderImage 方法，如下所示

    public void RenderImage(ImageRenderInfo info)
    {
        PdfImageObject image = info.GetImage();
        Parser.Matrix matrix = info.GetImageCTM();
        var fileType = image.GetFileType();
        ImageFormat format;
        switch (fileType)
        {//you may add more types here
            case "jpg":
            case "jpeg":
                format = ImageFormat.Jpeg;
                break;
            case "pnt":
                format = ImageFormat.Png;
                break;
            case "bmp":
                format = ImageFormat.Bmp;
                break;
            case "tiff":
                format = ImageFormat.Tiff;
                break;
            case "gif":
                format = ImageFormat.Gif;
                break;
            default:
                format = ImageFormat.Jpeg;
                break;
        }

        var pic = image.GetDrawingImage();
        var x = matrix[Parser.Matrix.I31];
        var y = matrix[Parser.Matrix.I32];
        var width = matrix[Parser.Matrix.I11];
        var height = matrix[Parser.Matrix.I22];
        if (x < <some value> && y < <some value>)
        {
            return;//ignore these images
        }

        pic.Save(<path and name>, format);
}

Answer 8

我过去使用过这个库，没有任何问题。

http://www.winnovative-software.com/PdfImgExtractor.aspx

private void btnExtractImages_Click(object sender, EventArgs e)
{
    if (pdfFileTextBox.Text.Trim().Equals(String.Empty))
    {
        MessageBox.Show("Please choose a source PDF file", "Choose PDF file", MessageBoxButtons.OK);
        return;
    }

    // the source pdf file
    string pdfFileName = pdfFileTextBox.Text.Trim();

    // start page number
    int startPageNumber = int.Parse(textBoxStartPage.Text.Trim());
    // end page number
    // when it is 0 the extraction will continue up to the end of document
    int endPageNumber = 0;
    if (textBoxEndPage.Text.Trim() != String.Empty)
        endPageNumber = int.Parse(textBoxEndPage.Text.Trim());

    // create the PDF images extractor object
    PdfImagesExtractor pdfImagesExtractor = new PdfImagesExtractor();

    pdfImagesExtractor.LicenseKey = "31FAUEJHUEBQRl5AUENBXkFCXklJSUlQQA==";

    // the demo output directory
    string outputDirectory = Path.Combine(Application.StartupPath, @"DemoFiles\Output");

    Cursor = Cursors.WaitCursor;

    // set the handler to be called when an image was extracted
    pdfImagesExtractor.ImageExtractedEvent += pdfImagesExtractor_ImageExtractedEvent;

    try
    {
        // start images counting
        imageIndex = 0;

        // call the images extractor to raise the ImageExtractedEvent event when an images is extracted from a PDF page
        // the pdfImagesExtractor_ImageExtractedEvent handler below will be executed for each extracted image
        pdfImagesExtractor.ExtractImagesInEvent(pdfFileName, startPageNumber, endPageNumber);

        // Alternatively you can use the ExtractImages() and ExtractImagesToFile() methods
        // to extracted the images from a PDF document in memory or to image files in a directory

        // uncomment the line below to extract the images to an array of ExtractedImage objects
        //ExtractedImage[] pdfPageImages = pdfImagesExtractor.ExtractImages(pdfFileName, startPageNumber, endPageNumber);

        // uncomment the lines below to extract the images to image files in a directory
        //string outputDirectory = System.IO.Path.Combine(Application.StartupPath, @"DemoFiles\Output");
        //pdfImagesExtractor.ExtractImagesToFile(pdfFileName, startPageNumber, endPageNumber, outputDirectory, "pdfimage");
    }
    catch (Exception ex)
    {
        // The extraction failed
        MessageBox.Show(String.Format("An error occurred. {0}", ex.Message), "Error");
        return;
    }
    finally
    {
        // uninstall the event handler
        pdfImagesExtractor.ImageExtractedEvent -= pdfImagesExtractor_ImageExtractedEvent;

        Cursor = Cursors.Arrow;
    }

    try
    {
        System.Diagnostics.Process.Start(outputDirectory);
    }
    catch (Exception ex)
    {
        MessageBox.Show(string.Format("Cannot open output folder. {0}", ex.Message));
        return;
    }
}

/// <summary>
/// The ImageExtractedEvent event handler called after an image was extracted from a PDF page.
/// The event is raised when the ExtractImagesInEvent() method is used
/// </summary>
/// <param name="args">The handler argument containing the extracted image and the PDF page number</param>
void pdfImagesExtractor_ImageExtractedEvent(ImageExtractedEventArgs args)
{
    // get the image object and page number from even handler argument
    Image pdfPageImageObj = args.ExtractedImage.ImageObject;
    int pageNumber = args.ExtractedImage.PageNumber;

    // save the extracted image to a PNG file
    string outputPageImage = Path.Combine(Application.StartupPath, @"DemoFiles\Output", 
        "pdfimage_" + pageNumber.ToString() + "_" + imageIndex++ + ".png");
    pdfPageImageObj.Save(outputPageImage, ImageFormat.Png);

    args.ExtractedImage.Dispose();
}