我必须将多个 PDF 合并为一个 PDF。
我正在使用 iText.sharp 库,并收集转换后的代码并尝试使用它(从此处)实际代码是 C# 语言,我将其转换为 VB.NET。
Private Function MergeFiles(ByVal sourceFiles As List(Of Byte())) As Byte()
Dim mergedPdf As Byte() = Nothing
Using ms As New MemoryStream()
Using document As New Document()
Using copy As New PdfCopy(document, ms)
document.Open()
For i As Integer = 0 To sourceFiles.Count - 1
Dim reader As New PdfReader(sourceFiles(i))
' loop over the pages in that document
Dim n As Integer = reader.NumberOfPages
Dim page As Integer = 0
While page < n
page = page + 1
copy.AddPage(copy.GetImportedPage(reader, page))
End While
Next
End Using
End Using
mergedPdf = ms.ToArray()
End Using
End Function
Run Code Online (Sandbox Code Playgroud)
我现在收到以下错误:
已添加具有相同密钥的项目。
我做了一些调试,并将问题跟踪到以下几行:
copy.AddPage(copy.GetImportedPage(reader,
copy.AddPage(copy.GetImportedPage(reader, page)))
Run Code Online (Sandbox Code Playgroud)
为什么会发生这个错误?
我有一个控制台,可以监视指定文件夹中的各个文件夹,然后需要将该文件夹中的所有 pdf 合并为一个 pdf。我将文件路径数组作为字符串传递,并传递我想要的输出文件。
这是我使用的功能。
Public Shared Function MergePdfFiles(ByVal pdfFiles() As String, ByVal outputPath As String) As Boolean
Dim result As Boolean = False
Dim pdfCount As Integer = 0 'total input pdf file count
Dim f As Integer = 0 'pointer to current input pdf file
Dim fileName As String
Dim reader As iTextSharp.text.pdf.PdfReader = Nothing
Dim pageCount As Integer = 0
Dim pdfDoc As iTextSharp.text.Document = Nothing 'the output pdf document
Dim writer As PdfWriter = Nothing
Dim cb As PdfContentByte = Nothing
Dim page As PdfImportedPage = Nothing
Dim rotation As Integer = 0
Try
pdfCount = pdfFiles.Length
If pdfCount > 1 Then
'Open the 1st item in the array PDFFiles
fileName = pdfFiles(f)
reader = New iTextSharp.text.pdf.PdfReader(fileName)
'Get page count
pageCount = reader.NumberOfPages
pdfDoc = New iTextSharp.text.Document(reader.GetPageSizeWithRotation(1), 18, 18, 18, 18)
writer = PdfWriter.GetInstance(pdfDoc, New FileStream(outputPath, FileMode.OpenOrCreate))
With pdfDoc
.Open()
End With
'Instantiate a PdfContentByte object
cb = writer.DirectContent
'Now loop thru the input pdfs
While f < pdfCount
'Declare a page counter variable
Dim i As Integer = 0
'Loop thru the current input pdf's pages starting at page 1
While i < pageCount
i += 1
'Get the input page size
pdfDoc.SetPageSize(reader.GetPageSizeWithRotation(i))
'Create a new page on the output document
pdfDoc.NewPage()
'If it is the 1st page, we add bookmarks to the page
'Now we get the imported page
page = writer.GetImportedPage(reader, i)
'Read the imported page's rotation
rotation = reader.GetPageRotation(i)
'Then add the imported page to the PdfContentByte object as a template based on the page's rotation
If rotation = 90 Then
cb.AddTemplate(page, 0, -1.0F, 1.0F, 0, 0, reader.GetPageSizeWithRotation(i).Height)
ElseIf rotation = 270 Then
cb.AddTemplate(page, 0, 1.0F, -1.0F, 0, reader.GetPageSizeWithRotation(i).Width + 60, -30)
Else
cb.AddTemplate(page, 1.0F, 0, 0, 1.0F, 0, 0)
End If
End While
'Increment f and read the next input pdf file
f += 1
If f < pdfCount Then
fileName = pdfFiles(f)
reader = New iTextSharp.text.pdf.PdfReader(fileName)
pageCount = reader.NumberOfPages
End If
End While
'When all done, we close the document so that the pdfwriter object can write it to the output file
pdfDoc.Close()
result = True
End If
Catch ex As Exception
Return False
End Try
Return result
End Function
Run Code Online (Sandbox Code Playgroud)