将 docx 文件合并在一起，包括页眉、页脚和图片

Question

我必须将多个 DOCX 文件（使用 DocX Package 创建）合并到一个大文件中。我已经成功合并多个文件，但无法合并页眉和页脚（它们在文件、页面之间有所不同）。我已经尝试过 DocX 包 和 MS Office COM Interop，它只是不想合并标头/页脚。它们被跳过。

有谁可以提供可行的解决方案吗？可以是任何东西（包括使用 PDFCreator COM、Interop 或 DocX 转换为 PDF）。

我还尝试过 C# 中的 PDFCreator Sample，它可以很好地将一个文档转换为 PDF，但我不知道如何向它提供多个文档，以便它创建一个大 PDF。因此，如果有人可以提供一种好的（免费）方式，我们将不胜感激。

这就是我使用的：

internal static class DocumentsMerging {
    private static object missing = Type.Missing;
    private static ApplicationClass wordApplication { get; set; }
    private static void addDocument(object path, Document doc, bool firstDocument) {
        object subDocPath = path;
        var subDoc = wordApplication.Documents.Open(ref subDocPath, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing);
        try {
            if (!firstDocument) {
                insertPageBreak(doc);
            }
            object docStart = doc.Content.End - 1;
            object docEnd = doc.Content.End;
            object start = subDoc.Content.Start;
            object end = subDoc.Content.End;
            Range rng = doc.Range(ref docStart, ref docEnd);
            rng.FormattedText = subDoc.Range(ref start, ref end);
            //if (!lastDocument) {
            //}
        } finally {
            subDoc.Close(ref missing, ref missing, ref missing);
        }
    }
    public static bool deleteFile(string fileName) {
        if (File.Exists(fileName)) {
            try {
                File.Delete(fileName);
                if (File.Exists(fileName)) {
                    return false;
                }
                return true;
            } catch (IOException) {
                DialogResult result = MessageBox.Show(new Form {TopMost = true}, "Plik " + fileName + " jest w użyciu lub nie masz uprawnień do zapisania raportu w tym miejscu. Czy chcesz spróbować ponownie?", "Błąd zapisu (000002)", MessageBoxButtons.YesNo, MessageBoxIcon.Stop);
                if (result == DialogResult.No) {
                    return false;
                }
                if (deleteFile(fileName)) {
                    return true;
                }
            } catch (Exception e) {
                MessageBox.Show(new Form {TopMost = true}, "Plik " + fileName + " nie może zostać skasowany. Błąd " + Environment.NewLine + Environment.NewLine + e, "Błąd zapisu (000003)", MessageBoxButtons.YesNo, MessageBoxIcon.Stop);
                return false;
            }
        } else {
            return true;
        }
        return false;
    }
    public static void documentsMerge(object fileName, List<string> arrayList) {
        // object fileName = Path.Combine(Environment.CurrentDirectory, @"NewDocument.doc");
        bool varTest = deleteFile(fileName.ToString());
        if (varTest) {
            try {
                wordApplication = new ApplicationClass();
                var doc = wordApplication.Documents.Add(ref missing, ref missing, ref missing, ref missing);
                try {
                    doc.Activate();
                    int count = 0;
                    foreach (var alItem in arrayList) {
                        addDocument(alItem, doc, count == 0);
                        count++;
                    }
                    // addDocument(@"D:\Projects\WordTests\ConsoleApplication1\Documents\Doc1.doc", doc ) ; //, false);
                    // addDocument(@"D:\Projects\WordTests\ConsoleApplication1\Documents\Doc2.doc", doc ) ; //, true);
                    doc.SaveAs(ref fileName, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing);
                } finally {
                    doc.Close(ref missing, ref missing, ref missing);
                }
            } finally {
                wordApplication.Quit(ref missing, ref missing, ref missing);
            }
        } else {
            return;
        }
    }
    private static void insertPageBreak(Document doc) {
        object docStart = doc.Content.End - 1;
        object docEnd = doc.Content.End;
        Range rng = doc.Range(ref docStart, ref docEnd);
       // object pageBreak = WdBreakType.wdPageBreak;
        object pageBreak = WdBreakType.wdSectionBreakNextPage;

        rng.InsertBreak(ref pageBreak);
    }
}

Answer 1

看看这个 http://devpinoy.org/blogs/keithrull/archive/2007/05/23/how-to-merge-multiple-microsoft-word-documents-in-c.aspx

更改此行:

object pageBreak = Word.WdBreakType.wdPageBreak;

到此

object pageBreak = Word.WdBreakType.wdSectionBreakNextPage;

从第二个文档获取标题和页脚。

添加整个方法以及在源发生变化时如何调用它。

班级：

using System;
using Word = Microsoft.Office.Interop.Word;
using System.Configuration;

namespace KeithRull.Utilities.OfficeInterop
{
  public class MsWord
  {
    /// <summary>
    /// This is the default Word Document Template file. I suggest that you point this to the location
    /// of your Ms Office Normal.dot file which is usually located in your Ms Office Templates folder.
    /// If it does not exist, what you could do is create an empty word document and save it as Normal.dot.
    /// </summary>
    private static string defaultWordDocumentTemplate = @"Normal.dot";

    /// <summary>
    /// A function that merges Microsoft Word Documents that uses the default template
    /// </summary>
    /// <param name="filesToMerge">An array of files that we want to merge</param>
    /// <param name="outputFilename">The filename of the merged document</param>
    /// <param name="insertPageBreaks">Set to true if you want to have page breaks inserted after each document</param>
    public static void Merge(string[] filesToMerge, string outputFilename, bool insertPageBreaks)
    {
        Merge(filesToMerge, outputFilename, insertPageBreaks, defaultWordDocumentTemplate);
    }

    /// <summary>
    /// A function that merges Microsoft Word Documents that uses a template specified by the user
    /// </summary>
    /// <param name="filesToMerge">An array of files that we want to merge</param>
    /// <param name="outputFilename">The filename of the merged document</param>
    /// <param name="insertPageBreaks">Set to true if you want to have page breaks inserted after each document</param>
    /// <param name="documentTemplate">The word document you want to use to serve as the template</param>
    public static void Merge(string[] filesToMerge, string outputFilename, bool insertPageBreaks, string documentTemplate)
    {
        object defaultTemplate = documentTemplate;
        object missing = System.Type.Missing;
        object pageBreak = Word.WdBreakType.wdSectionBreakNextPage;
        object outputFile = outputFilename;

        // Create  a new Word application
        Word._Application wordApplication = new Word.Application( );

        try
        {
            // Create a new file based on our template
            Word.Document wordDocument = wordApplication.Documents.Add(
                                          ref missing
                                        , ref missing
                                        , ref missing
                                        , ref missing);

            // Make a Word selection object.
            Word.Selection selection = wordApplication.Selection;

            //Count the number of documents to insert;
            int documentCount = filesToMerge.Length;

            //A counter that signals that we shoudn't insert a page break at the end of document.
            int breakStop = 0;

            // Loop thru each of the Word documents
            foreach (string file in filesToMerge)
            {
                breakStop++;
                // Insert the files to our template
                selection.InsertFile(
                                            file
                                        , ref missing
                                        , ref missing
                                        , ref missing
                                        , ref missing);

                //Do we want page breaks added after each documents?
                if (insertPageBreaks && breakStop != documentCount)
                {
                    selection.InsertBreak(ref pageBreak);
                }
            }

            // Save the document to it's output file.
            wordDocument.SaveAs(
                            ref outputFile
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing
                        , ref missing);

            // Clean up!
            wordDocument = null;
        }
        catch (Exception ex)
        {
            //I didn't include a default error handler so i'm just throwing the error
            throw ex;
        }
        finally
        {
            // Finally, Close our Word application
            wordApplication.Quit(ref missing, ref missing, ref missing);
        }
    }
}
}

和电话：

using System;
using KeithRull.Utilities.OfficeInterop;

namespace WordDocMerge2
{
  class Program
  {
    static void Main(string[] args)
    {
        try
        {
            string document1 = @"D:\Visual Studio Projects\31.docx";
            string document2 = @"D:\Visual Studio Projects\33.docx";
            string document3 = @"D:\Visual Studio Projects\32.docx";

            string[] documentsToMerge = { document1, document2, document3 };

            string outputFileName = String.Format("D:\\Visual Studio Projects\\{0}.docx", Guid.NewGuid( ));

            MsWord.Merge(documentsToMerge, outputFileName, true);

        }
        catch (Exception ex)
        {
            //messageLabel.Text = ex.Message;
        }
    }
}
}

Answer 2

由于 最新版本的 DocX 合并工作正常。因此，现在可以直接使用 DocX，而不是使用 Interop。唯一需要知道的页眉/页脚取自第一个文档（模板），因为页眉/页脚是按文档而不是按页面设置的。

public static void documentsMerge(object fileName, List<string> arrayList) {

        bool varTest = deleteFile(fileName.ToString());
        if (varTest)
        {
            using (DocX documentToCreate = DocX.Load(arrayList[0]))
            {


                foreach (var alItem in arrayList.Skip(1))
                {
                    documentToCreate.InsertParagraph().InsertPageBreakAfterSelf();
                    DocX documentToMergeIn = DocX.Load(alItem);
                    documentToCreate.InsertDocument(documentToMergeIn);
                }
                documentToCreate.SaveAs(fileName.ToString());
            }
        }
    }

Answer 3

从 http://powertools.codeplex.com/ C# 代码开始，稍微修改一下，使其执行以下操作你想要页眉和页脚。

Eric White 的博客解释包含有关代码如何工作的评论。

Answer 4

您是否尝试过在 xml 级别进行合并？ Docx 是内含 Xml 文件的 zip 文件。

您可以使用 XDocument 合并 XML。