使用 RegexBasedLocationExtractionStrategy 定位字符串并使用 iTextSharp 的 PDFstamper 标记图像。标记所有位置的问题

Question

我正在尝试使用 Itext7 的 RegexBasedLocationExtractionStrategy 循环遍历所述 PDF 中的所有页面来定位 PDF 中的字符串模式。例如，我正在搜索的字符串是“Conrad Noll IV，#6272795”。我想要做的是，每次我找到这个字符串的 x 和 7 坐标时，我都会使用这些坐标，从 x 坐标中减去几个点，这样我就可以在它旁边标记一个“X”（png 图像） .

这是我尝试过的代码/模块。

    Imports iTextSharp.text
    Imports System.IO
    Imports System.IO.Path
    Imports System.Text.RegularExpressions
    Imports iTextSharp.text.pdf.parser
    Imports System.Linq
    Imports iText
    Imports iText.Kernel.Pdf.Canvas.Parser.Listener
    Imports iText.Kernel.Pdf.Canvas.Parser
    Imports iText.Kernel.Pdf

    Module Module1
    Dim signedFolder = "C:\Users\xborja\Desktop\Original PDF's\Signed PDFs\"
    Sub Main()

    If Not Directory.Exists(signedFolder) Then
        Directory.CreateDirectory(signedFolder)
    End If
    Dim src = "C:\Users\xborja\Desktop\Original PDF's Before Merge\TP067389.CRUZ.pdf"
    Dim pattern = "Conrad Noll IV, #6272795"
    Dim inputfile As Stream = New FileStream(src, FileMode.Open, FileAccess.Read, FileShare.Read)
    Dim inputImage As Stream = New FileStream("C:\Users\user\source\repos\addImagePdf\addImagePdf\CN signature.png", FileMode.Open, FileAccess.Read, FileShare.Read)
    Dim xmarkImage As Stream = New FileStream("C:\Users\user\Desktop\xmark.png", FileMode.Open, FileAccess.Read, FileShare.Read)
    Dim finalPDF As String = signedFolder & GetFileNameWithoutExtension(src) & " signed.pdf"
    Dim outputPdf As Stream = New FileStream(finalPDF, FileMode.Create, FileAccess.Write, FileShare.None)
    Dim pdfReader = New iText.Kernel.Pdf.PdfReader(src)
    Dim pdfReader2 = New pdf.PdfReader(inputfile)
    Dim pdfDoc As iText.Kernel.Pdf.PdfDocument = New iText.Kernel.Pdf.PdfDocument(pdfReader)
    Dim pageCount = pdfDoc.GetNumberOfPages
    Dim pagecount2 = pdfReader2.NumberOfPages
    Dim extractionStrategy As RegexBasedLocationExtractionStrategy = New RegexBasedLocationExtractionStrategy(pattern)
    Dim locationList As IList(Of IPdfTextLocation) = New List(Of IPdfTextLocation)
    Dim parser As PdfCanvasProcessor = New PdfCanvasProcessor(extractionStrategy)

    Dim stamper = New pdf.PdfStamper(pdfReader2, outputPdf)

    Dim pdfContentByte = Nothing
    Dim image As Image = Image.GetInstance(inputImage)
    Dim xmark As Image = Image.GetInstance(xmarkImage)

    Dim xy = Nothing
    Dim counter = 0

    Console.WriteLine(pagecount2)

    For page1 = 1 To pagecount2

        parser.ProcessPageContent(pdfDoc.GetPage(page1)) ' THIS has to be outside the for each
        For Each location As IPdfTextLocation In extractionStrategy.GetResultantLocations
            parser.ProcessPageContent(pdfDoc.GetPage(page1))
            pdfContentByte = stamper.GetOverContent(page1)
            If location IsNot Nothing Then
                counter += 1
                Dim xP = Math.Round(location.GetRectangle.GetX)
                Dim yP = Math.Round(location.GetRectangle.GetY)


                xmark.SetAbsolutePosition(xP - 18, yP)
                pdfContentByte.addimage(xmark)
                stamper.Close()

                Console.WriteLine(pattern & " " & xP & " " & yP & " located on page " & page1 & " and counter is " & counter)

            End If

        Next location

    Next page1

End Sub

End Module

如您所见，我正在同时使用 2 个不同的阅读器，因为每个阅读器都有不同的参数，因此我尝试将两者结合使用来做一些棘手的事情。

当我运行它并向自己打印结果时，它显示了我正在搜索的字符串的正确 X 和 Y 位置数量以及正确的页数，但 itextsharp.pdfstamper 仅标记一个位置，这是第一个它找到的位置。

xmark.SetAbsolutePosition(xP - 18, yP) 是我设置的，这样当它找到 x y 坐标时，x 减去 8 从而将我的 X 图像直接移动到它的右侧，所以它看起来像名称已签出。

代码会读取所有页面，打印出搜索字符串的所有位置，但只标记其中一个，这是有原因的吗？

Answer 1

添加标记后关闭内循环内的PdfStamper：

For page1 = 1 To pagecount2
    ...
    For Each location As IPdfTextLocation In extractionStrategy.GetResultantLocations
        ...
        If location IsNot Nothing Then
            ...
            xmark.SetAbsolutePosition(xP - 18, yP)
            pdfContentByte.addimage(xmark)
            stamper.Close()
            ...
        End If
    Next location
Next page1

因此，在添加第一个标记后，压模完成其输出，然后不再接受任何更改。在循环之后移动 Close 调用：

For page1 = 1 To pagecount2
    ...
    For Each location As IPdfTextLocation In extractionStrategy.GetResultantLocations
        ...
        If location IsNot Nothing Then
            ...
            xmark.SetAbsolutePosition(xP - 18, yP)
            pdfContentByte.addimage(xmark)
            ' stamper.Close()
            ...
        End If
    Next location
Next page1
stamper.Close()

Answer 2

您可以将所有内容保留在 Itext 中，而不使用 itextsharp，而是使用此代码：

Imports System.IO
Imports System.IO.Path
Imports System.Text.RegularExpressions
Imports iTextSharp.text.pdf.parser
Imports System.Linq
Imports iText
Imports iText.Kernel.Pdf.Canvas.Parser.Listener
Imports iText.Kernel.Pdf.Canvas.Parser
Imports iText.Kernel.Pdf
Imports iText.Layout
Imports iText.IO.Image
Imports iText.Layout.Element
Imports iText.Layout.Properties

Module Module1
    Dim signedFolder = "C:\Users\Desktop\Original PDF's\Signed PDFs\"
    Sub Main()

        If Not Directory.Exists(signedFolder) Then
            Directory.CreateDirectory(signedFolder)
        End If
        Dim src = "C:\Users\Desktop\Original PDF's Before Merge\TP067389.CRUZ.pdf"
        Dim pattern = "Conrad Noll IV, #6272795"

        Dim xmarkImage = "C:\Users\Desktop\xmark.png"
        Dim finalPDF As String = signedFolder & GetFileNameWithoutExtension(src) & " signed.pdf"

        Dim pdfDoc As PdfDocument = New iText.Kernel.Pdf.PdfDocument(New PdfReader(src), New PdfWriter(finalPDF))
        Dim document As Document = New Document(pdfDoc)


        Dim pageCount = pdfDoc.GetNumberOfPages


        Dim extractionStrategy As RegexBasedLocationExtractionStrategy = New RegexBasedLocationExtractionStrategy(pattern)
        Dim locationList As IList(Of IPdfTextLocation) = New List(Of IPdfTextLocation)
        Dim parser As PdfCanvasProcessor = New PdfCanvasProcessor(extractionStrategy)

        Dim xmark As ImageData = ImageDataFactory.Create(xmarkImage)

        Dim counter = 0

        Dim xp = Nothing
        Dim yp = Nothing


        For page1 = 1 To pageCount

            parser.ProcessPageContent(pdfDoc.GetPage(page1))

            For Each location As IPdfTextLocation In extractionStrategy.GetResultantLocations
                parser.ProcessPageContent(pdfDoc.GetPage(page1))
                If location IsNot Nothing Then
                    counter += 1

                    xp = CType(Math.Round(location.GetRectangle.GetX), Single)
                    yp = CType(Math.Round(location.GetRectangle.GetY), Single)

                    Dim xmimage As Image = New Image(xmark).SetFixedPosition(page1, xp - 16, yp)
                    document.Add(xmimage)

                    locationList.Add(location)
                    Console.WriteLine(pattern & " " & xp & " " & yp & " located on page " & page1)



                End If
            Next location
        Next page1
        document.Close()






    End Sub


End Module