PDF To TIFF

找到的几种PDF To Tiff方法：

 

一：使用Ghostscript，开源项目，注意Win32和Win64版本。

免费，生成的大小适度的图片清晰度一般。当然可以设置生成很大的清晰文件。

下载地址：http://sourceforge.net/projects/ghostscript/files/

下载后解压，只需要Bin中的文件：

gswin32c.exe

gsdll32.dll

gswin32.exe

gsdll32.lib

通过命令行调用：

gswin32c.exe -dSAFER -dBATCH -dNOPAUSE -r100 -dNOTRANSPARENCY -sDEVICE=tiff12nc -sCompression=lzw -dAdjustWidth=0 -dMaxStripSize=999999999  -sOutputFile=D:\Work\Test\PDF\abc.tif  D:\Work\Test\PDF\abc.PDF

另外，gswin32c.exe还可以将PDF转为其他格式的图片文件。

如JPG：gswin32c.exe -dSAFER -dBATCH -dNOPAUSE -r100 -sDEVICE=jpeg -dGraphicsAlphaBits=4 -sOutputFile=D:\Work\Test\PDF\abc%d.jpg  D:\Work\Test\PDF\abc.PDF

参数设置参见压缩包中的doc\Use.htm

 

二、oakdoc的PDF to TIFF Converter，收费软件。分GUI、Command、COMPONENT版本。

下载地址：http://www.oakdoc.com/products/pdftotiff.html

GUI网上有破解版。试用版生成的图片上有水印。

收费，价格低，生成的文件小且清晰。支持PDF目录 -> Tif目录的批量操作。

Command版只需要pdftotiff.exe

通过命令行调用：

pdftotiff.exe  -i "D:\Work\Test\PDF" -o "D:\Work\Test\Tif" -x 96 -y 96 -q 75 -c 4 -e \"LZW\" -a

参数设置参见压缩包中的help\index.htm

 

三、Adobe的Professional版，收费。有破解版。
首先，使用Acrobat.CAcroPDDoc将PDF页面CopyToClipboard
然后，从Clipboard.GetData(DataFormats.Bitmap)读取出Image
最后，将Image合并到一个Tif文件中。

 

private static List<Image> PDFToImage(string InputFilename)
{
    List<Image> imgs = new List<Image>();

    Acrobat.CAcroPDPage pdfPage = null;
    Acrobat.CAcroPoint pdfPoint = null;
    Acrobat.CAcroRect pdfRect = null;
    Acrobat.CAcroPDDoc pdfDoc = (Acrobat.CAcroPDDoc)Microsoft.VisualBasic.Interaction.CreateObject("AcroExch.PDDoc", "");
    //pdfDoc = new Acrobat.AcroPDDocClass();

    //Type AcroApp = Type.GetTypeFromCLSID(new System.Guid("{85DE1C45-2C66-101B-B02E-04021C009402}"));
    //Type AcrobatType = Type.GetTypeFromCLSID(new System.Guid("{72498821-3203-101B-B02E-04021C009402}"));
    //Type AcroPD = Type.GetTypeFromCLSID(new System.Guid("{FF76CB60-2EC8-101B-B02E-04021C009402}"));
    //Acrobat.CAcroApp oApp = (Acrobat.CAcroApp)Activator.CreateInstance(AcroApp);
    //Acrobat.CAcroAVDoc avdoc = (Acrobat.CAcroAVDoc)Activator.CreateInstance(AcrobatType);
    //Acrobat.CAcroPDDoc pdfDoc = (Acrobat.CAcroPDDoc)Activator.CreateInstance(AcroPD);

    bool llRet = pdfDoc.Open(InputFilename);

    if (!llRet)
    {
        throw new FileNotFoundException();
    }
    int pageCount = pdfDoc.GetNumPages();
    for (int i = 0; i < pageCount; i++)
    {
        pdfPage = (Acrobat.CAcroPDPage)pdfDoc.AcquirePage(i);
        pdfPoint = (Acrobat.CAcroPoint)pdfPage.GetSize();
        pdfRect = (Acrobat.CAcroRect)Microsoft.VisualBasic.Interaction.CreateObject("AcroExch.Rect", "");
        pdfRect.Left = 0;
        pdfRect.right = pdfPoint.x;
        pdfRect.Top = 0;
        pdfRect.bottom = pdfPoint.y;

        pdfPage.CopyToClipboard(pdfRect, 0, 0, 100);

        IDataObject loClipboardData = Clipboard.GetDataObject();
        if (loClipboardData.GetDataPresent(DataFormats.Bitmap))
        {
            //Get Image
            Bitmap pdfBitmap = (Bitmap)loClipboardData.GetData(DataFormats.Bitmap);
            imgs.Add(pdfBitmap);
        }
    }
    pdfDoc.Close();

    Marshal.ReleaseComObject(pdfPage);
    Marshal.ReleaseComObject(pdfRect);
    Marshal.ReleaseComObject(pdfDoc);

    return imgs;
}

  

/// <summary>
/// Combine some file into 1 tif multipage file
/// if black and write image, we use CCITT4 compression
/// else we use the LZW compression
/// </summary>
/// <param name="InputFilenames">the files to be combined, canbe (bmp, jpg, gif, png, tif)</param>
/// <param name="OutputFilename">the output filename</param>
public static void CombineTif(string[] InputFilenames, string OutputFilename)
{
    //get ImageCodecInfo, generate tif format
    ImageCodecInfo info = null;
    foreach (ImageCodecInfo ice in ImageCodecInfo.GetImageEncoders())
    {
        if (ice.MimeType == "image/tiff")
        {
            info = ice;
            break;
        }
    }

    /*
    * define the encoderparameter, 
    * when the 1st page, will be EncoderValue.MultiFrame.
    * when the other pages, will be EncoderValue.FrameDimensionPage.
    * when all pages saved, will be the EncoderValue.Flush.
    */
    EncoderParameters ep = new EncoderParameters(2);

    /*
    * when the 1st file, 1st frame, will be true.
    * from the 1st file, 2nd frame, will be false.
    */
    bool b11 = true;

    Image img = null;

    //create a image instance from the 1st image
    for (int nLoopfile = 0; nLoopfile < InputFilenames.Length; nLoopfile++)
    {
        //get image from src file
        Image img_src = Image.FromFile(InputFilenames[nLoopfile]);

        Guid guid = img_src.FrameDimensionsList[0];
        System.Drawing.Imaging.FrameDimension dimension = new System.Drawing.Imaging.FrameDimension(guid);

        //get the frames from src file
        for (int nLoopFrame = 0; nLoopFrame < img_src.GetFrameCount(dimension); nLoopFrame++)
        {
            img_src.SelectActiveFrame(dimension, nLoopFrame);

            /*
            * if black and write image, we use CCITT4 compression
            * else we use the LZW compression
            */
            if (img_src.PixelFormat == PixelFormat.Format1bppIndexed)
            {
                ep.Param[0] = new EncoderParameter(Encoder.Compression, Convert.ToInt32(EncoderValue.CompressionCCITT4));
            }
            else
            {
                ep.Param[0] = new EncoderParameter(Encoder.Compression, Convert.ToInt32(EncoderValue.CompressionLZW));
            }

            if (b11)
            {
                //1st file, 1st frame, create the master image
                img = img_src;

                ep.Param[1] = new EncoderParameter(Encoder.SaveFlag, Convert.ToInt32(EncoderValue.MultiFrame));
                img.Save(OutputFilename, info, ep);

                b11 = false;
                continue;
            }

            ep.Param[1] = new EncoderParameter(Encoder.SaveFlag, Convert.ToInt32(EncoderValue.FrameDimensionPage));
            img.SaveAdd(img_src, ep);
        }
    }
    ep.Param[1] = new EncoderParameter(Encoder.SaveFlag, Convert.ToInt32(EncoderValue.Flush));
    img.SaveAdd(ep);
}

  

其他方法：
XpdfRasterizerNet可以将PDF输出为BMP文件，带水印，需要regsvr32注册XpdfRasterizer.dll，没有进一步使用。
含以下DLL：XpdfRasterizer.dll、XpdfRasterizerNet.dll、O2S.Components.PDFRender4NET.dll、O2S.Components.PDFView4NET.dll

 

    XpdfRasterizerNet.XpdfRasterizerClass rast = new XpdfRasterizerNet.XpdfRasterizerClass();
    rast.loadFile(pdffile);
    for (int page = 1; page <= rast.numPages; page++)
    {
        string jpgfile = fileName + page.ToString() + ".bmp";
        rast.writePageBitmap(page, dpi, rast.imageRGB, rast.imageFileBMP, jpgfile);
    }
    rast.closeFile();

 

 Java中的PDFBox有J#版，不过没有最终完成，没有实现page.convertToImage方法。

 

    PDDocument doc = PDDocument.load(@"D:\Work\Test\PDF\abc.pdf");
    List pages = doc.getDocumentCatalog().getAllPages();
    Iterator iter = pages.iterator();
    while (iter.hasNext())
    {
        PDPage page = (PDPage)iter.next();
        BufferedImage image = page.convertToImage();//error
        File file = new java.io.File(@"D:\Work\Test\PDF\abc.tif");
        ImageIO.write(image, "tiff", file);
        //OutputStream os = new FileOutputStream(file);
        //JPEGImageEncoder encoder = JPEGCodec.createJPEGEncoder(os);
        //encoder.encode(image);
    }