Question

在我的asp.net应用程序中，我想从PDF文件中提取所有图像。

我尝试了这段代码，但这不起作用：

using System;
using System.Collections;
using System.Configuration;
using System.Data;
using System.Linq;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.HtmlControls;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Xml.Linq;
using System.IO;
using System.Drawing.Imaging;
using iTextSharp.text;
using iTextSharp.text.pdf;

namespace WebPages2.Site
{
    public partial class PDFImageReader : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {

        }
        protected void ctrlUploadButton_Click(object sender, EventArgs e)
        {
            string path = this.ctrlFileUpload.FileName;
            string outputPath = this.Server.MapPath("~/Image");

            ExtractImagesFromPDF(path, outputPath);
        }
        #region ExtractImagesFromPDF
        public static void ExtractImagesFromPDF(string sourcePdf, string outputPath)
        {
            // NOTE:  This will only get the first image it finds per page.
            PdfReader pdf = new PdfReader(sourcePdf);

            RandomAccessFileOrArray raf = new iTextSharp.text.pdf.RandomAccessFileOrArray(sourcePdf);

            try
            {
                for (int pageNumber = 1; pageNumber <= pdf.NumberOfPages; pageNumber++)
                {
                    PdfDictionary pg = pdf.GetPageN(pageNumber);
                    PdfDictionary res =
                      (PdfDictionary)PdfReader.GetPdfObject(pg.Get(PdfName.RESOURCES));
                    PdfDictionary xobj =
                      (PdfDictionary)PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT));
                    if (xobj != null)
                    {
                        foreach (PdfName name in xobj.Keys)
                        {
                            PdfObject obj = xobj.Get(name);
                            if (obj.IsIndirect())
                            {
                                PdfDictionary tg = (PdfDictionary)PdfReader.GetPdfObject(obj);
                                PdfName type =
                                  (PdfName)PdfReader.GetPdfObject(tg.Get(PdfName.SUBTYPE));
                                if (PdfName.IMAGE.Equals(type))
                                {

                                    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))
                                    {
                                        using (System.IO.MemoryStream memStream = new System.IO.MemoryStream(bytes))
                                        {
                                            memStream.Position = 0;
                                            System.Drawing.Image img = System.Drawing.Image.FromStream(memStream);
                                            // must save the file while stream is open.

                                            if (!Directory.Exists(outputPath))
                                                Directory.CreateDirectory(outputPath);

                                            string path = Path.Combine(outputPath, String.Format(@"{0}.jpg", pageNumber));
                                            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);
                                            // GetImageEncoder is found below this method
                                            System.Drawing.Imaging.ImageCodecInfo jpegEncoder = GetImageEncoder("JPEG");
                                            img.Save(path, jpegEncoder, parms);
                                            //WebPages2.Classes.MessageBox.Show(path);

                                            break;

                                        }
                                    }
                                }
                            }
                        }
                    }
                }
            }

            catch
            {
                throw;
            }
            finally
            {
                pdf.Close();
            }


        }
        #endregion

        #region GetImageEncoder
        public static System.Drawing.Imaging.ImageCodecInfo GetImageEncoder(string imageType)
        {
            imageType = imageType.ToUpperInvariant();



            foreach (ImageCodecInfo info in ImageCodecInfo.GetImageEncoders())
            {
                if (info.FormatDescription == imageType)
                {
                    return info;
                }
            }

            return null;
        }
        #endregion
    }
}

所以我什么都没得到;浏览后，当我点击上传按钮时，我的页面中没有发生任何事情，我没有收到任何错误。

Answer 1

您需要调试代码。在适当的位置插入断点并检查代码的执行部分。

Answer 2

你的问题可能就在这里：

PdfName type = (PdfName)PdfReader.GetPdfObject(tg.Get  (PdfName.SUBTYPE));
   if (PdfName.IMAGE.Equals(type))

我猜测if是解析为false，因此其余的代码没有运行。

从pdf文件中提取所有图像

2 个答案: