VB.net

Had a bit of fun (?) at work writing a VB console application that simply opens up a word document and checks all headers and footers in the document for a specified list of keywords.

The only real gotcha is that you need to install the Primary Interop Assemblies for you version of office (and add them to your project references). Microsoft have a very strong com API for scripting their applications (Word, Excel, Powerpoint, Outlook etc).

Not much has changed since I last used it several years ago (VB.net) - I did not look into advancements in C#.

Module Module1
    'Print debug messages
    Const debug = False
    'If no parameters are specified, scan this document
    Const default_file = "c:\mydoc.doc"
    'The keywords we want to match on
    Const keywords = "c:\keywords.txt"
    'The logfile we want to write our results to
    Const logfile = "c:\headerfooter.log"
    Dim alKeywords As New ArrayList()

    Sub Main()
        loadKeywords()
        If Command().Length = 0 Then
            Console.WriteLine("No Params Passsed")
            scanDocument("c:\mydoc.doc")
        Else
            Console.WriteLine(Command())
            scanDocument(Command())
        End If
        Console.ReadLine()
    End Sub
    Sub loadKeywords()
        'Read keywords into global string arraylist

        Dim fs As New FileStream("c:\keywords.txt", FileMode.Open, FileAccess.Read)
        'declaring a FileStream to open the file named file.doc with access mode of reading
        Dim d As New StreamReader(fs)
        'creating a new StreamReader and passing the filestream object fs as argument
        d.BaseStream.Seek(0, SeekOrigin.Begin)
        'Seek method is used to move the cursor to different positions in a file, in this code, to
        'the beginning
        While d.Peek() > -1
            'peek method of StreamReader object tells how much more data is left in the file
            Dim strKeyword As String
            strKeyword = d.ReadLine()

            If debug Then
                Console.WriteLine(strKeyword)
            End If

            alKeywords.Add(strKeyword)
            'displaying text from doc file in the RichTextBox
        End While
        d.Close()
    End Sub
    Sub scanDocument(ByVal sFile As String)
        Dim oApp As Word.Application
        Dim oDoc As Word.Document
        Dim oSec As Word.Section
        Dim oPageStart As Word.Range
        Dim iPage As Integer, iTotalPages As Integer, iSection As Integer
        Dim sHeader As String, sFooter As String

        Const wdStatisticPages = 2
        Const wdGotoPage = 1
        Const wdGotoAbsolute = 1
        Const wdHeaderFooterFirstPage = 2
        Const wdHeaderFooterPrimary = 1

        'Open the document
        oApp = New Word.Application
        oDoc = oApp.Documents.Open(sFile)
        iTotalPages = oDoc.ComputeStatistics(wdStatisticPages)

        'Retrieve the headers and footers on each page
        With oDoc

            iSection = 0

            For iPage = 1 To iTotalPages

                'Go to the page represented by the page number iPage and
                'retrieve its section
                oPageStart = oDoc.GoTo(What:=wdGotoPage, _
                                           Which:=wdGotoAbsolute, Count:=iPage)
                oSec = oPageStart.Sections(1)

                'If this is a different section than the one in the previous
                'iteration and it has a first page header/.footer, then
                'retrieve the first page header/footer for this section.
                'Otherwise, retrieve the primary header/footer for this section
                If (iSection < oSec.Index) And _
                   (oSec.PageSetup.DifferentFirstPageHeaderFooter) Then
                    sHeader = oSec.Headers(wdHeaderFooterFirstPage).Range.Text
                    sFooter = oSec.Footers(wdHeaderFooterFirstPage).Range.Text
                Else
                    sHeader = oSec.Headers(wdHeaderFooterPrimary).Range.Text
                    sFooter = oSec.Footers(wdHeaderFooterPrimary).Range.Text
                End If

                iSection = oSec.Index
                If debug Then
                    Console.WriteLine("Page " & iPage & ", Section " & iSection & _
                            ":" & vbCrLf)
                    Console.WriteLine("   Header: " & sHeader)
                    Console.WriteLine("   Footer: " & sFooter)
                End If

                checkText(sHeader, sHeader, sFooter, iPage, iSection)
                checkText(sFooter, sHeader, sFooter, iPage, iSection)
            Next

        End With

        'Make Word visible to compare the document with the results in the
        'debug window
        'oApp.Visible = True
        oDoc.Close()
        oApp.Quit()
    End Sub
    Sub checkText(ByVal sText As String, ByVal sHeader As String, ByVal sFooter As String, ByVal iPage As Integer, ByVal iSection As Integer)

        Dim i As Integer

        For i = 0 To (alKeywords.Count() - 1)
            If sText.ToUpper.Contains(alKeywords.Item(i).ToString().ToUpper()) Then
                log("Match in document " & Command() & " Text: " & sText)
                log(" Match Keyword: " & alKeywords.Item(i).ToString() & " Page: " & iPage & " Section: " & iSection)
            End If
        Next
    End Sub

    Sub log(ByVal sTest As String)
        Console.WriteLine(sTest)
    End Sub
End Module