c# - 从 PDF 的特定页面中提取图像

Question

我想从 PDF 文件中提取图像。我尝试使用以下代码，它从 PDF 中完美地提取了一个 jpeg 图像。问题是如何从特定页面中提取图像，例如第 1 页或来自其他页面。我不想阅读整个 PDF 来搜索图像。

有什么建议吗？

提取图片的代码:

private void List<System.Drawing.Image> ExtractImages(String PDFSourcePath)
        {
            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(PDFSourcePath);
                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);
                                    pictureBox1.Image = ImgPDF;
                                    MS.Close();
                                    MS.Flush();

                                }
                                catch (Exception)
                                {

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

Answer 1

我目前没有可用的 iTextSharp 4.0，因此此代码针对 5.2，但它也应该适用于旧版本。这段代码几乎是直接电梯from this post here ，因此请参阅该帖子以及对其他问题的回复。正如我在上面的评论中所说，您的代码正在从文档的角度查看所有图像，而我链接到的代码是逐页查看。

请阅读其他帖子中的所有评论，尤其是this one这解释了这 ONLY 适用于 JPG 图像。 PDF 支持许多不同类型的图像，因此除非您知道您只处理 JPG，否则您将需要添加更多代码。参见 this post和 this post一些提示。

        string testFile = System.IO.Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Desktop), "Doc1.pdf");
        string outputPath = Environment.GetFolderPath(Environment.SpecialFolder.Desktop);
        int pageNum = 1;

        PdfReader pdf = new PdfReader(testFile);
        PdfDictionary pg = pdf.GetPageN(pageNum);
        PdfDictionary res = (PdfDictionary)PdfReader.GetPdfObject(pg.Get(PdfName.RESOURCES));
        PdfDictionary xobj = (PdfDictionary)PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT));
        if (xobj == null) { return; }
        foreach (PdfName name in xobj.Keys) {
            PdfObject obj = xobj.Get(name);
            if (!obj.IsIndirect()) { continue; }
            PdfDictionary tg = (PdfDictionary)PdfReader.GetPdfObject(obj);
            PdfName type = (PdfName)PdfReader.GetPdfObject(tg.Get(PdfName.SUBTYPE));
            if (!type.Equals(PdfName.IMAGE)) { continue; }
            int XrefIndex = Convert.ToInt32(((PRIndirectReference)obj).Number.ToString(System.Globalization.CultureInfo.InvariantCulture));
            PdfObject pdfObj = pdf.GetPdfObject(XrefIndex);
            PdfStream pdfStrem = (PdfStream)pdfObj;
            byte[] bytes = PdfReader.GetStreamBytesRaw((PRStream)pdfStrem);
            if (bytes == null) { continue; }
            using (System.IO.MemoryStream memStream = new System.IO.MemoryStream(bytes)) {
                memStream.Position = 0;
                System.Drawing.Image img = System.Drawing.Image.FromStream(memStream);
                if (!Directory.Exists(outputPath))
                    Directory.CreateDirectory(outputPath);

                string path = Path.Combine(outputPath, String.Format(@"{0}.jpg", pageNum));
                System.Drawing.Imaging.EncoderParameters parms = new System.Drawing.Imaging.EncoderParameters(1);
                parms.Param[0] = new System.Drawing.Imaging.EncoderParameter(System.Drawing.Imaging.Encoder.Compression, 0);
                var jpegEncoder = ImageCodecInfo.GetImageEncoders().ToList().Find(x => x.FormatID == ImageFormat.Jpeg.Guid);
                img.Save(path, jpegEncoder, parms);

            }
        }