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提取图像，例如第1页或其他页面。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);
}
}
答案 0 :(得分：9)
我目前没有iTextSharp 4.0可用，所以这段代码的目标是5.2，但它也应该适用于较旧的代码。此代码几乎是直接提升from this post here，因此请查看该帖子以及针对其他问题的回复。正如我在上面的评论中所说，您的代码正在查看文档透视图中的所有图像，而我链接的代码逐页进行。
请阅读其他帖子中的所有评论，尤其是this one，其中说明此 ONLY 适用于JPG图片。 PDF支持很多不同类型的图像，除非你知道你只处理JPG，否则你需要添加更多代码。有关提示，请参阅this post和this post。
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);
}
}
答案 1 :(得分：2)
以下是我用于从PDF中提取图像的代码。它对我来说完全没问题。
// Required: iTextSharp.dll
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 ExtractPdfImage
{
string imgPath = @"c:\extractedImg.png";
private void ExtractImage(string pdfFile)
{
const int pageNumber = 1;
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);
}
}
}
}
}
}
答案 2 :(得分：0)
以下代码可以从特定页面中提取图像。
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)
{
const int pageNumber = 1;//Page number to extract the image from
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);
}
}
}
}
}
}