我们有一个C#Windows服务,当前通过使用第三方组件读取PDF上的二维条码来处理所有PDF,然后更新数据库并将文档存储在文档存储库中。
有没有办法在读取条形码后将文件剪切并将其存储为另一个文件?
例如,如果有10页文档,则应分成10个不同的文件。
感谢。
答案 0 :(得分:6)
我遇到了同样的问题,您可以使用itextsharp component工具拆分文档
public Split(String[] args)
{
if (args.Length != 4)
{
Console.Error.WriteLine("This tools needs 4 parameters:\njava Split srcfile destfile1 destfile2 pagenumber");
}
else
{
try
{
int pagenumber = int.Parse(args[3]);
// we create a reader for a certain document
PdfReader reader = new PdfReader(args[0]);
// we retrieve the total number of pages
int n = reader.NumberOfPages;
Console.WriteLine("There are " + n + " pages in the original file.");
if (pagenumber < 2 || pagenumber > n)
{
throw new DocumentException("You can't split this document at page " + pagenumber + "; there is no such page.");
}
// step 1: creation of a document-object
Document document1 = new Document(reader.GetPageSizeWithRotation(1));
Document document2 = new Document(reader.GetPageSizeWithRotation(pagenumber));
// step 2: we create a writer that listens to the document
PdfWriter writer1 = PdfWriter.GetInstance(document1, new FileStream(args[1], FileMode.Create));
PdfWriter writer2 = PdfWriter.GetInstance(document2, new FileStream(args[2], FileMode.Create));
// step 3: we open the document
document1.Open();
PdfContentByte cb1 = writer1.DirectContent;
document2.Open();
PdfContentByte cb2 = writer2.DirectContent;
PdfImportedPage page;
int rotation;
int i = 0;
// step 4: we add content
while (i < pagenumber - 1)
{
i++;
document1.SetPageSize(reader.GetPageSizeWithRotation(i));
document1.NewPage();
page = writer1.GetImportedPage(reader, i);
rotation = reader.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb1.AddTemplate(page, 0, -1f, 1f, 0, 0, reader.GetPageSizeWithRotation(i).Height);
}
else
{
cb1.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
}
while (i < n)
{
i++;
document2.SetPageSize(reader.GetPageSizeWithRotation(i));
document2.NewPage();
page = writer2.GetImportedPage(reader, i);
rotation = reader.GetPageRotation(i);
if (rotation == 90 || rotation == 270)
{
cb2.AddTemplate(page, 0, -1f, 1f, 0, 0, reader.GetPageSizeWithRotation(i).Height);
}
else
{
cb2.AddTemplate(page, 1f, 0, 0, 1f, 0, 0);
}
Console.WriteLine("Processed page " + i);
}
// step 5: we close the document
document1.Close();
document2.Close();
}
catch(Exception e)
{
Console.Error.WriteLine(e.Message);
Console.Error.WriteLine(e.StackTrace);
}
}
}
答案 1 :(得分:3)
您可以使用像PDFSharp这样的PDF库,读取文件,遍历每个页面,将它们添加到新的PDF文档中并将它们保存在文件系统中。然后,您也可以删除或保留原文。
这是相当多的代码,但非常简单,这些示例应该让你开始。
答案 2 :(得分:2)
上一个问题部分回答 - 如何分割pdf文档,如果您知道条形码的位置,那么您可以轻松地拆分文档:
How can I split up a PDF file into pages (preferably C#)
该推荐是一个名为PDFSharp和sample demonstrating PDF splitting的库。
答案 3 :(得分:1)
public int ExtractPages(string sourcePdfPath, string DestinationFolder)
{
int p = 0;
try
{
iTextSharp.text.Document document;
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(new iTextSharp.text.pdf.RandomAccessFileOrArray(sourcePdfPath), new ASCIIEncoding().GetBytes(""));
if (!Directory.Exists(sourcePdfPath.ToLower().Replace(".pdf", "")))
{
Directory.CreateDirectory(sourcePdfPath.ToLower().Replace(".pdf", ""));
}
else
{
Directory.Delete(sourcePdfPath.ToLower().Replace(".pdf", ""), true);
Directory.CreateDirectory(sourcePdfPath.ToLower().Replace(".pdf", ""));
}
for (p = 1; p <= reader.NumberOfPages; p++)
{
using (MemoryStream memoryStream = new MemoryStream())
{
document = new iTextSharp.text.Document();
iTextSharp.text.pdf.PdfWriter writer = iTextSharp.text.pdf.PdfWriter.GetInstance(document, memoryStream);
writer.SetPdfVersion(iTextSharp.text.pdf.PdfWriter.PDF_VERSION_1_2);
writer.CompressionLevel = iTextSharp.text.pdf.PdfStream.BEST_COMPRESSION;
writer.SetFullCompression();
document.SetPageSize(reader.GetPageSize(p));
document.NewPage();
document.Open();
document.AddDocListener(writer);
iTextSharp.text.pdf.PdfContentByte cb = writer.DirectContent;
iTextSharp.text.pdf.PdfImportedPage pageImport = writer.GetImportedPage(reader, p);
int rot = reader.GetPageRotation(p);
if (rot == 90 || rot == 270)
{
cb.AddTemplate(pageImport, 0, -1.0F, 1.0F, 0, 0, reader.GetPageSizeWithRotation(p).Height);
}
else
{
cb.AddTemplate(pageImport, 1.0F, 0, 0, 1.0F, 0, 0);
}
document.Close();
document.Dispose();
File.WriteAllBytes(DestinationFolder + "/" + p + ".pdf", memoryStream.ToArray());
}
}
reader.Close();
reader.Dispose();
}
catch
{
}
finally
{
GC.Collect();
}
return p - 1;
}
在任何地方调用此函数并传递源和目标文件夹路径
答案 4 :(得分:0)
此代码基于PDFsharp库
http://www.pdfsharp.com/PDFsharp/
如果您想按书签分割,则此处为代码。
public static void SplitPDFByBookMark(string fileName)
{
string sInFile = fileName;
PdfReader pdfReader = new PdfReader(sInFile);
try
{
IList<Dictionary<string, object>> bookmarks = SimpleBookmark.GetBookmark(pdfReader);
for (int i = 0; i < bookmarks.Count; ++i)
{
IDictionary<string, object> BM = (IDictionary<string, object>)bookmarks[0];
IDictionary<string, object> nextBM = i == bookmarks.Count - 1 ? null : bookmarks[i + 1];
string startPage = BM["Page"].ToString().Split(' ')[0].ToString();
string startPageNextBM = nextBM == null ? "" + (pdfReader.NumberOfPages + 1) : nextBM["Page"].ToString().Split(' ')[0].ToString();
SplitByBookmark(pdfReader, int.Parse(startPage), int.Parse(startPageNextBM), bookmarks[i].Values.ToArray().GetValue(0).ToString() + ".pdf", fileName);
}
}
catch (Exception ex)
{
throw ex;
}
}
private static void SplitByBookmark(PdfReader reader, int pageFrom, int PageTo, string outPutName, string inPutFileName)
{
Document document = new Document();
FileStream fs = new System.IO.FileStream(System.IO.Path.GetDirectoryName(inPutFileName) + '\\' + outPutName, System.IO.FileMode.Create);
try
{
PdfWriter writer = PdfWriter.GetInstance(document, fs);
document.Open();
PdfContentByte cb = writer.DirectContent;
//holds pdf data
PdfImportedPage page;
if (pageFrom == PageTo && pageFrom == 1)
{
document.NewPage();
page = writer.GetImportedPage(reader, pageFrom);
cb.AddTemplate(page, 0, 0);
pageFrom++;
fs.Flush();
document.Close();
fs.Close();
}
else
{
while (pageFrom < PageTo)
{
document.NewPage();
page = writer.GetImportedPage(reader, pageFrom);
cb.AddTemplate(page, 0, 0);
pageFrom++;
fs.Flush();
document.Close();
fs.Close();
}
}
}
catch (Exception ex)
{
throw ex;
}
finally
{
if (document.IsOpen())
document.Close();
if (fs != null)
fs.Close();
}
}
答案 5 :(得分:0)
itextsharp
您可以从nuget安装SplitPDFByBookMark()
并将此代码复制并粘贴到c#app中调用my_dataframe.loc[my_dataframe['is_true'], [new_col_one, new_col_two]] =
my_dataframe.loc[my_dataframe['is_true'], 'col_with_values'].str.extract(some_regex,expand=True)
方法并传递pdf文件名。
这段代码将搜索你的书签并完成!
答案 6 :(得分:0)
GroupDocs.Merger允许将源文档拆分为多个结果文档。通过指定页码数组或开始/结束页码并设置不同的 PageSplitOptions 模式,可以以不同的方式执行文档拆分。 让我们看看如何将文档拆分为几个一页的文档(按确切的页码):
string filePath = @"c:\sample.docx";
string filePathOut = @"c:\output\document_{0}.{1}";
PageSplitOptions splitOptions = new PageSplitOptions(filePathOut, new int[] { 3, 6, 8 });
using (Merger merger = new Merger(filePath))
{
merger.Split(splitOptions);
}
此代码段将产生:
文档名称 页码
document_0 3
document_1 6
document_2 8
了解更多here。
披露:我是GroupDocs的一名开发人员。