Get pages of word document
13,700
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>();
}
Author by
user3166379
Updated on July 25, 2022Comments
-
user3166379 almost 2 years
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 index is the number of page. I understand (at least I think so) that there is no direct way to do that. So I came up with something like that:
List<String> Pages = new List<String>(); int NumberOfPreviousPage = -1; int NumberOfPage = -1; string InnerText = ""; for (int i = 0; i < Doc.Paragraphs.Count; i++) { Paragraph CurrentParagraph = Doc.Paragraphs[i + 1]; InnerText = CurrentParagraph.Range.Text; NumberOfPage = CurrentParagraph.Range.get_Information(WdInformation.wdActiveEndPageNumber); if (NumberOfPage == NumberOfPreviousPage) Pages[Pages.Count - 1] += String.Format("\r\n{0}", InnerText); else { Pages.Add(InnerText); NumberOfPreviousPage = NumberOfPage; } }
But, when algorithm gets to paragraph, which starts on one page and ends on another, it decides that paragraph should be on next page. I want to split this paragraph between pages, but I don't know how to detect where I have to do the split.