使用ITextSharp编辑PDF中的超链接和锚定
我正在使用iTextSharp库和C#.Net来拆分我的PDF文件 考虑一个名为sample.PDF的PDF文件，其中包含72页。此sample.pdf包含具有导航到其他页面的超链接的页面。例如：在第4页中有三个超链接，单击后可导航到相应的第24、27、28页。与第4页相同，有近12页有此超链接 现在使用iTextSharp库，我将这些PDF页面分割成72个单独的文件，并以1.PDF、2.PDF…72.PDF的名称保存。因此，在4.pdf中，当单击超链接时，我需要使pdf导航到24.pdf、27.pdf、28.pdf 请帮帮我。如何编辑和设置4.pdf中的超链接，使其导航到相应的pdf文件 谢谢,，使用ITextSharp编辑PDF中的超链接和锚定,pdf,hyperlink,itext,editing,Pdf,Hyperlink,Itext,Editing,我正在使用iTextSharp库和C#.Net来拆分我的PDF文件 考虑一个名为sample.PDF的PDF文件，其中包含72页。此sample.pdf包含具有导航到其他页面的超链接的页面。例如：在第4页中有三个超链接，单击后可导航到相应的第24、27、28页。与第4页相同，有近12页有此超链接 现在使用iTextSharp库，我将这些PDF页面分割成72个单独的文件，并以1.PDF、2.PDF…72.PDF的名称保存。因此，在4.pdf中，当单击超链接时，我需要使pdf导航到24.pdf、27
Ashok你想要什么是完全可能的。您需要使用低级PDF对象（PdfDictionary、PdfArray等） 每当有人需要使用这些对象时，我总是将它们引用到。在您的案例中，您需要检查第7章（特别是第3节）和第12章，第3节（文档级导航）和第5节（注释） 假设你已经读过，下面是你需要做的：
我的C语言说得不太好，所以我将把实际实现留给您。好的，根据@Mark Storer的内容，这里有一些起始代码。第一种方法创建了一个示例PDF，其中包含10个页面和第一个页面上的一些链接，这些链接可以跳转到PDF的不同部分，因此我们可以使用这些链接。第二个方法打开在第一个方法中创建的PDF，遍历每个注释，试图找出注释链接到哪个页面，并将其输出到跟踪窗口。代码是用VB编写的，但如果需要，可以很容易地转换成C。它的目标是iTextSharp 5.1.1.0 如果我有机会的话，我可能会尝试更进一步，并实际分割和重新链接的东西，但我现在没有时间
Option Explicit On
Option Strict On
Imports iTextSharp.text
Imports iTextSharp.text.pdf
Imports System.IO
Public Class Form1
''//Folder that we are working in
Private Shared ReadOnly WorkingFolder As String = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Desktop), "Hyperlinked PDFs")
''//Sample PDF
Private Shared ReadOnly BaseFile As String = Path.Combine(WorkingFolder, "Sample.pdf")
Private Shared Sub CreateSamplePdf()
''//Create our output directory if it does not exist
Directory.CreateDirectory(WorkingFolder)
''//Create our sample PDF
Using Doc As New iTextSharp.text.Document(PageSize.LETTER)
Using FS As New FileStream(BaseFile, FileMode.Create, FileAccess.Write, FileShare.Read)
Using writer = PdfWriter.GetInstance(Doc, FS)
Doc.Open()
''//Turn our hyperlinks blue
Dim BlueFont As Font = FontFactory.GetFont("Arial", 12, iTextSharp.text.Font.NORMAL, iTextSharp.text.BaseColor.BLUE)
''//Create 10 pages with simple labels on them
For I = 1 To 10
Doc.NewPage()
Doc.Add(New Paragraph(String.Format("Page {0}", I)))
''//On the first page add some links
If I = 1 Then
''//Go to pages relative to this page
Doc.Add(New Paragraph(New Chunk("First Page", BlueFont).SetAction(New PdfAction(PdfAction.FIRSTPAGE))))
Doc.Add(New Paragraph(New Chunk("Next Page", BlueFont).SetAction(New PdfAction(PdfAction.NEXTPAGE))))
Doc.Add(New Paragraph(New Chunk("Prev Page", BlueFont).SetAction(New PdfAction(PdfAction.PREVPAGE)))) ''//This one does not make sense but is here for completeness
Doc.Add(New Paragraph(New Chunk("Last Page", BlueFont).SetAction(New PdfAction(PdfAction.LASTPAGE))))
''//Go to a specific hard-coded page number
Doc.Add(New Paragraph(New Chunk("Go to page 5", BlueFont).SetAction(PdfAction.GotoLocalPage(5, New PdfDestination(0), writer))))
End If
Next
Doc.Close()
End Using
End Using
End Using
End Sub
Private Shared Sub ListPdfLinks()
''//Setup some variables to be used later
Dim R As PdfReader
Dim PageCount As Integer
Dim PageDictionary As PdfDictionary
Dim Annots As PdfArray
''//Open our reader
R = New PdfReader(BaseFile)
''//Get the page cont
PageCount = R.NumberOfPages
''//Loop through each page
For I = 1 To PageCount
''//Get the current page
PageDictionary = R.GetPageN(I)
''//Get all of the annotations for the current page
Annots = PageDictionary.GetAsArray(PdfName.ANNOTS)
''//Make sure we have something
If (Annots Is Nothing) OrElse (Annots.Length = 0) Then Continue For
''//Loop through each annotation
For Each A In Annots.ArrayList
''//I do not completely understand this but I think this turns an Indirect Reference into an actual object, but I could be wrong
''//Anyway, convert the itext-specific object as a generic PDF object
Dim AnnotationDictionary = DirectCast(PdfReader.GetPdfObject(A), PdfDictionary)
''//Make sure this annotation has a link
If Not AnnotationDictionary.Get(PdfName.SUBTYPE).Equals(PdfName.LINK) Then Continue For
''//Make sure this annotation has an ACTION
If AnnotationDictionary.Get(PdfName.A) Is Nothing Then Continue For
''//Get the ACTION for the current annotation
Dim AnnotationAction = DirectCast(AnnotationDictionary.Get(PdfName.A), PdfDictionary)
''//Test if it is a named actions such as /FIRST, /LAST, etc
If AnnotationAction.Get(PdfName.S).Equals(PdfName.NAMED) Then
Trace.Write("GOTO:")
If AnnotationAction.Get(PdfName.N).Equals(PdfName.FIRSTPAGE) Then
Trace.WriteLine(1)
ElseIf AnnotationAction.Get(PdfName.N).Equals(PdfName.NEXTPAGE) Then
Trace.WriteLine(Math.Min(I + 1, PageCount)) ''//Any links that go past the end of the document should just go to the last page
ElseIf AnnotationAction.Get(PdfName.N).Equals(PdfName.LASTPAGE) Then
Trace.WriteLine(PageCount)
ElseIf AnnotationAction.Get(PdfName.N).Equals(PdfName.PREVPAGE) Then
Trace.WriteLine(Math.Max(I - 1, 1)) ''//Any links the go before the first page should just go to the first page
End If
''//Otherwise see if its a GOTO page action
ElseIf AnnotationAction.Get(PdfName.S).Equals(PdfName.GOTO) Then
''//Make sure that it has a destination
If AnnotationAction.GetAsArray(PdfName.D) Is Nothing Then Continue For
''//Once again, not completely sure if this is the best route but the ACTION has a sub DESTINATION object that is an Indirect Reference.
''//The code below gets that IR, asks the PdfReader to convert it to an actual page and then loop through all of the pages
''//to see which page the IR points to. Very inneficient but I could not find a way to get the page number based on the IR.
''//AnnotationAction.GetAsArray(PdfName.D) gets the destination
''//AnnotationAction.GetAsArray(PdfName.D).ArrayList(0) get the indirect reference part of the destination (.ArrayList(1) has fitting options)
''//DirectCast(AnnotationAction.GetAsArray(PdfName.D).ArrayList(0), PRIndirectReference) turns it into a PRIndirectReference
''//The full line gets us an actual page object (actually I think it could be any type of pdf object but I have not tested that).
''//BIG NOTE: This line really should have a bunch more sanity checks in place
Dim AnnotationReferencedPage = PdfReader.GetPdfObject(DirectCast(AnnotationAction.GetAsArray(PdfName.D).ArrayList(0), PRIndirectReference))
Trace.Write("GOTO:")
''//Re-loop through all of the pages in the main document comparing them to this page
For J = 1 To PageCount
If AnnotationReferencedPage.Equals(R.GetPageN(J)) Then
Trace.WriteLine(J)
Exit For
End If
Next
End If
Next
Next
End Sub
Private Sub Form1_Load(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles MyBase.Load
CreateSamplePdf()
ListPdfLinks()
Me.Close()
End Sub
End Class
下面的此功能使用iTextSharp来：
/// <summary>Inspects PDF files for internal links.
/// </summary>
public static void FindPdfDocsWithInternalLinks()
{
foreach (var fi in PdfFiles) {
try {
var reader = new PdfReader(fi.FullName);
// Pagination
for(var i = 1; i <= reader.NumberOfPages; i++) {
var pageDict = reader.GetPageN(i);
var annotArray = (PdfArray)PdfReader.GetPdfObject(pageDict.Get(PdfName.ANNOTS));
if (annotArray == null) continue;
if (annotArray.Length <= 0) continue;
// check every annotation on the page
foreach (var annot in annotArray.ArrayList) {
var annotDict = (PdfDictionary)PdfReader.GetPdfObject(annot);
if (annotDict == null) continue;
var subtype = annotDict.Get(PdfName.SUBTYPE).ToString();
if (subtype != "/Link") continue;
var linkDict = (PdfDictionary)annotDict.GetDirectObject(PdfName.A);
if (linkDict == null) continue;
// if it makes it this far, its an Anchor annotation
// so we can grab it's URI
var sUri = linkDict.Get(PdfName.URI).ToString();
if (String.IsNullOrEmpty(sUri)) continue;
}
}
reader.Close();
}
catch (InvalidPdfException e)
{
if (!fi.FullName.Contains("_vti_cnf"))
Console.WriteLine("\r\nInvalid PDF Exception\r\nFilename: " + fi.FullName + "\r\nException:\r\n" + e);
continue;
}
catch (NullReferenceException e)
{
if (!fi.FullName.Contains("_vti_cnf"))
Console.WriteLine("\r\nNull Reference Exception\r\nFilename: " + fi.Name + "\r\nException:\r\n" + e);
continue;
}
}
// DO WHATEVER YOU WANT HERE
}
///检查PDF文件的内部链接。
///
公共静态void FindPdfDocsWithInternalLinks（）
{
foreach（Pdfiles中的var fi）{
试一试{
变量读取器=新的PDF读取器（fi.FullName）；
//分页
对于（var i=1；i Hi，Mark感谢您的帮助。我正在分析文档。您能提供一个示例代码吗？因为我需要尽快完成并交付。@MarkStorer-步骤1.1是我丢失的地方，PDF参考没有多大帮助，因为iTextSharp的对象和糟糕的文档。我可以找到所有的子类型=/link
注释ns，但有不同的类型，它们的键/元素也不同。我在这里编辑并扩展了这个问题：