Get pages of word document

Question

I\'m trying to get all pages of MSWord document via Microsoft.Office.Interop.Word (I\'m using C# in VS2012). What I would like to get is List< String > Pages, where inde

Answer 1

A bit of a simpler solution.

Pseudo code:

• Grab the page count.
• For each page:
  • Find the characters between this pages last character index and the last pages last character index.

Implementation:

    /// <summary>
    /// Reads each page of the word document into a string and returns the list of the page strings.
    /// </summary>
    public static IEnumerable<string> ReadPages(string filePath)
    {
        ICollection<string> pageStrings = new List<string>();
        Microsoft.Office.Interop.Word.Application app = new Microsoft.Office.Interop.Word.Application();
        Document doc = app.Documents.Open(filePath);

        long pageCount = doc.ComputeStatistics(Microsoft.Office.Interop.Word.WdStatistic.wdStatisticPages);
        int lastPageEnd = 0; // The document starts at 0.
        for ( long i = 0; i < pageCount; i++)
        {
            // The "range" of the page break. This actually is a range of 0 elements, both start and end are the 
            // location of the page break.
            Range pageBreakRange = app.Selection.GoToNext(Microsoft.Office.Interop.Word.WdGoToItem.wdGoToPage);
            string currentPageText = doc.Range(lastPageEnd, pageBreakRange.End).Text;
            lastPageEnd = pageBreakRange.End;
            pageStrings.Add(currentPageText);
        }
        return pageStrings;
    }

Answer 2

Eventually, I finished up with this, and it works (it's lame, it's ugly, but it does what it should):

public string[] GetPagesDoc(object Path)
    {
        List<string> Pages = new List<string>();

        // Get application object
        Microsoft.Office.Interop.Word.Application WordApplication = new Microsoft.Office.Interop.Word.Application();

        // Get document object
        object Miss = System.Reflection.Missing.Value;
        object ReadOnly = false;
        object Visible = false;
        Document Doc = WordApplication.Documents.Open(ref Path, ref Miss, ref ReadOnly, ref Miss, ref Miss, ref Miss, ref Miss, ref Miss, ref Miss, ref Miss, ref Miss, ref Visible, ref Miss, ref Miss, ref Miss, ref Miss);

        // Get pages count
        Microsoft.Office.Interop.Word.WdStatistic PagesCountStat = Microsoft.Office.Interop.Word.WdStatistic.wdStatisticPages;
        int PagesCount = Doc.ComputeStatistics(PagesCountStat, ref Miss);

        //Get pages
        object What = Microsoft.Office.Interop.Word.WdGoToItem.wdGoToPage;
        object Which = Microsoft.Office.Interop.Word.WdGoToDirection.wdGoToAbsolute;
        object Start;
        object End;
        object CurrentPageNumber;
        object NextPageNumber;

        for (int Index = 1; Index < PagesCount + 1; Index++)
        {
            CurrentPageNumber = (Convert.ToInt32(Index.ToString()));
            NextPageNumber = (Convert.ToInt32((Index+1).ToString()));

            // Get start position of current page
            Start = WordApplication.Selection.GoTo(ref What, ref Which, ref CurrentPageNumber, ref Miss).Start;

            // Get end position of current page                                
            End = WordApplication.Selection.GoTo(ref What, ref Which, ref NextPageNumber, ref Miss).End;

            // Get text
            if (Convert.ToInt32(Start.ToString()) != Convert.ToInt32(End.ToString()))
                Pages.Add(Doc.Range(ref Start, ref End).Text);
            else
                Pages.Add(Doc.Range(ref Start).Text);
        }
            return Pages.ToArray<string>();
    }