itextsharp.ExtractImagesFromPDF.zip

从PDF中提取图片的项目实例，用VS2008可以直接运行。

using System;
using System.Drawing.Imaging;
using System.IO;
using iTextSharp.text.pdf;

namespace itextsharp.ExtractImagesFromPDF
{
    public class PDFParser
    {
        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）;

                    // recursively search pages forms and groups for images.
                    Pdfobject obj = FindImageInPDFDictionary（pg）;
                    if （obj != null）
                    {

                        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）;
                                System.Drawing.Imaging.ImageCodecInfo jpegEncoder = GetImageEncoder（“JPEG“）;
                                img.Save（path jpegEncoder parms）;
                            }
                        }
                    }
                }
            }
            catch
            {
                throw;
            }
            finally
            {
                pdf.Close（）;
                raf.Close（）;
            }


        }

        private static Pdfobject FindImageInPDFDictionary（PdfDictionary pg）
        {
            PdfDictionary res = （PdfDictionary）PdfReader.GetPdfobject（pg.Get（PdfName.RESOURCES））;


            PdfDictionary xob

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----
     目录           0  2012-02-16 19:30  itextsharp.ExtractImagesFromPDF\
     文件        2735  2012-02-16 19:24  itextsharp.ExtractImagesFromPDF\itextsharp.ExtractImagesFromPDF.csproj
     文件         168  2012-02-11 14:55  itextsharp.ExtractImagesFromPDF\itextsharp.ExtractImagesFromPDF.csproj.user
     文件        5126  2012-02-16 19:21  itextsharp.ExtractImagesFromPDF\Program.cs
     目录           0  2012-02-16 19:17  itextsharp.ExtractImagesFromPDF\Properties\
     文件        1384  2012-02-11 14:37  itextsharp.ExtractImagesFromPDF\Properties\AssemblyInfo.cs