我已成功使用pdfsharp从pdf中提取图像。图像是CCITFFaxDecode。但是在创建的tiff图像中,图像会旋转。知道可能出现什么问题吗?
这是我使用的代码:
byte[] data = xObject.Stream.Value;
Tiff tiff = BitMiracle.LibTiff.Classic.Tiff.Open("D:\\clip_TIFF.tif", "w");
tiff.SetField(TiffTag.IMAGEWIDTH, (uint)(width));
tiff.SetField(TiffTag.IMAGELENGTH, (uint)(height));
tiff.SetField(TiffTag.COMPRESSION, (uint)BitMiracle.LibTiff.Classic.Compression.CCITTFAX4);
tiff.SetField(TiffTag.BITSPERSAMPLE, (uint)(bpp));
tiff.WriteRawStrip(0,data,data.Length);
tiff.Close();
答案 0 :(得分:0)
通过这是完整的代码,它从pdf中提取图像,但旋转它。抱歉代码的长度。
PdfDocument document = PdfReader.Open("D:\\Sample.pdf");
PdfDictionary resources =document.pages.Elements.GetDictionary("/Resources");
PdfDictionary xObjects = resources.Elements.GetDictionary("/XObject");
if (xObjects != null)
{
ICollection<PdfItem> items = xObjects.Elements.Values;
// Iterate references to external objects
foreach (PdfItem item in items)
{
PdfReference reference = item as PdfReference;
if (reference != null)
{
PdfDictionary xObject = reference.Value as PdfDictionary;
// Is external object an image?
if (xObject != null && xObject.Elements.GetString("/Subtype") == "/Image")
{
string filter = xObject.Elements.GetName("/Filter");
if (filter.Equals("/CCITTFaxDecode"))
{
int width = xObject.Elements.GetInteger(PdfImage.Keys.Width);
int height = xObject.Elements.GetInteger(PdfImage.Keys.Height);
int bpp = xObject.Elements.GetInteger(PdfImage.Keys.BitsPerComponent);
byte[] data = xObject.Stream.Value;
Tiff tiff = BitMiracle.LibTiff.Classic.Tiff.Open("D:\\sample.tif", "w");
tiff.SetField(TiffTag.IMAGEWIDTH, (uint)(width));
tiff.SetField(TiffTag.IMAGELENGTH, (uint)(height));
tiff.SetField(TiffTag.COMPRESSION, (uint)BitMiracle.LibTiff.Classic.Compression.CCITTFAX4);
tiff.SetField(TiffTag.BITSPERSAMPLE, (uint)(bpp));
tiff.SetField(TiffTag.STRIPOFFSETS, 187);
tiff.WriteRawStrip(0,data,data.Length);
tiff.Close();
}
}
}
}
}
答案 1 :(得分:0)
由于问题仍然被标记为w / iTextSharp可能会添加一些代码,即使它看起来不像你在这里使用库。从iText [Sharp] 5开始添加PDF解析支持。
没有包含您正在使用的图片类型的测试PDF,但是found one here(请参阅附件)。这是ASP.NET
(HTTP handler
.ashx)中使用该测试PDF文档的非常简单工作示例,可以帮助您:
<%@ WebHandler Language="C#" Class="CCITTFaxDecodeExtract" %>
using System;
using System.Collections.Generic;
using System.IO;
using System.Web;
using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using Dotnet = System.Drawing.Image;
using System.Drawing.Imaging;
public class CCITTFaxDecodeExtract : IHttpHandler {
public void ProcessRequest (HttpContext context) {
HttpServerUtility Server = context.Server;
HttpResponse Response = context.Response;
string file = Server.MapPath("~/app_data/CCITTFaxDecode.pdf");
PdfReader reader = new PdfReader(file);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
MyImageRenderListener listener = new MyImageRenderListener();
for (int i = 1; i <= reader.NumberOfPages; i++) {
parser.ProcessContent(i, listener);
}
for (int i = 0; i < listener.Images.Count; ++i) {
string path = Server.MapPath("~/app_data/" + listener.ImageNames[i]);
using (FileStream fs = new FileStream(
path, FileMode.Create, FileAccess.Write
))
{
fs.Write(listener.Images[i], 0, listener.Images[i].Length);
}
}
}
public bool IsReusable { get { return false; } }
/*
* see: TextRenderInfo & RenderListener classes here:
* http://api.itextpdf.com/itext/
*
* and Google "itextsharp extract images"
*/
public class MyImageRenderListener : IRenderListener {
public void RenderText(TextRenderInfo renderInfo) { }
public void BeginTextBlock() { }
public void EndTextBlock() { }
public List<byte[]> Images = new List<byte[]>();
public List<string> ImageNames = new List<string>();
public void RenderImage(ImageRenderInfo renderInfo) {
PdfImageObject image = renderInfo.GetImage();
PdfName filter = image.Get(PdfName.FILTER) as PdfName;
if (filter == null) {
PdfArray pa = (PdfArray) image.Get(PdfName.FILTER);
for (int i = 0; i < pa.Size; ++i) {
filter = (PdfName) pa[i];
}
}
if (PdfName.CCITTFAXDECODE.Equals(filter)) {
using (Dotnet dotnetImg = image.GetDrawingImage()) {
if (dotnetImg != null) {
ImageNames.Add(string.Format(
"{0}.tiff", renderInfo.GetRef().Number)
);
using (MemoryStream ms = new MemoryStream()) {
dotnetImg.Save(
ms, ImageFormat.Tiff);
Images.Add(ms.ToArray());
}
}
}
}
}
}
}
如果正在旋转图像,see this thread on the iText mailing list;也许PDF文档中的某些页面已被轮换。