vb.net - 使用 VB 使用 Acrobat SDK (Interop.Acrobat.dll) 从 pdf 中提取注释。网

Question

我正在使用 Acrobat SDK 从 pdf 文件中提取文本。

这工作得很好。

我的代码并没有从评论中提取文本。

是否可以使用 Acrobat SDK 从评论/注释中提取文本？

我知道我可以使用 iTextSharp 并且效果很好，但我只想使用一个库。

下面的代码：

Public Shared Function AdobePdfParse(strFileName As String, strTxtFromFile As String) As String
    'Note: A Reference to the Adobe Library must be set in Tools|References!
    'Note! This only works with Acrobat Pro installed on your PC, will not work with Reader
    Dim AcroApp As CAcroApp, AcroAVDoc As CAcroAVDoc, AcroPDDoc As CAcroPDDoc
    Dim AcroHiliteList As CAcroHiliteList, AcroTextSelect As CAcroPDTextSelect
    Dim PageNumber, PageContent, i, j, iNumPages
    Dim strResult As String

    AcroApp = CreateObject("AcroExch.App")
    AcroAVDoc = CreateObject("AcroExch.AVDoc")
    If AcroAVDoc.Open(strFileName, vbNull) <> True Then Exit Function

    AcroPDDoc = AcroAVDoc.GetPDDoc
    iNumPages = AcroPDDoc.GetNumPages

    Dim intfirst As Integer = 1

    For i = 0 To iNumPages - 1
        PageNumber = AcroPDDoc.AcquirePage(i)
        PageContent = CreateObject("AcroExch.HiliteList")
        If PageContent.Add(0, 9000) <> True Then Exit Function
        AcroTextSelect = PageNumber.CreatePageHilite(PageContent)
        ' The next line is needed to avoid errors with protected PDFs that can't be read
        On Error Resume Next
        For j = 0 To AcroTextSelect.GetNumText - 1
            strTxtFromFile = strTxtFromFile & AcroTextSelect.GetText(j)
        Next (j)
    Next i

    AcroAVDoc.Close(bNoSave:=0)
    AcroApp = Nothing
    AcroAVDoc = Nothing

    'Return sbTxtFromFile
    Return strTxtFromFile

End Function

标签： vb.netparsingtextacrobat-sdk