我正在解析 C# 中的 .doc 文件以提取文本。
问题是 .doc 文件包含表格、形状和图像，以及我的文本。我使用 Microsoft Interop Word 库来提取文本。当我提取文本时，我还会得到形状和图像上的标签，以及表格的列和行内的数据。
我不需要表格或图像中的形状或数据标签。如何从我的 .doc 文件中删除这些形状、它们的标签、图像和表格？
这是代码。
public void ReadMsWord()
{
// variable to store file path
string filePath = null;
// open dialog box to select file
OpenFileDialog file = new OpenFileDialog();
// dilog box title name
file.Title = "Word File";
// set initial directory of computer system
file.InitialDirectory = "c:\\";
// set restore directory
file.RestoreDirectory = true;
// execute if block when dialog result box click ok button
if (file.ShowDialog() == DialogResult.OK)
{
// store selected file path
filePath = file.FileName.ToString();
}
try
{
// create word application
Microsoft.Office.Interop.Word.Application word = new Microsoft.Office.Interop.Word.ApplicationClass();
// create object of missing value
object miss = System.Reflection.Missing.Value;
// create object of selected file path
object path = filePath;
// set file path mode
object readOnly = false;
// open document
Microsoft.Office.Interop.Word.Document docs = word.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 miss, ref miss, ref miss, ref miss, ref miss);
// select whole data from active window document
docs.ActiveWindow.Selection.WholeStory();
// handover the data to cllipboard
docs.ActiveWindow.Selection.Copy();
// clipboard create reference of idataobject interface which transfer the data
IDataObject data = Clipboard.GetDataObject();
//set data into richtextbox control in text format
string t = "";
string[] y = {};
t = data.GetData(DataFormats.Text).ToString();
y = t.Split('\n');
string check = "";
string check1 = "";
string A = "";
//int i = 0;
for (int i = 0; i < y.Length - 1; i++)
{
if (!Regex.IsMatch(y[i], @"^([A|B|C|D]| )")&&(y[i].Length>15))
{
//@"^\d+"
//int j = i + 1;
// while (!Regex.IsMatch(asdf[j], @"^[A|B|C]"))
// {
check = check + '\n'+'\n' + y[i];
//i++;
}
}
for (int i = 0; i < y.Length - 1; i++)
{
if (Regex.IsMatch(y[i], @"^[A |B |C |D ]"))
{
//@"^\d+"
//int j = i + 1;
// while (!Regex.IsMatch(asdf[j], @"^[A|B|C]"))
// {
check1 = check1 + '\n' + '\n' + y[i];
//i++;
}
}
@theGhostofc 的代码这是我正在使用的代码，它给出异常类型不匹配类型
private void button1_Click(object sender, EventArgs e)
{
string filePath = null;
// open dialog box to select file
OpenFileDialog file = new OpenFileDialog();
// dilog box title name
file.Title = "Word File";
// set initial directory of computer system
file.InitialDirectory = "c:\\";
// set restore directory
file.RestoreDirectory = true;
// execute if block when dialog result box click ok button
if (file.ShowDialog() == DialogResult.OK)
{
// store selected file path
filePath = file.FileName.ToString();
}
try
{
// create word application
Microsoft.Office.Interop.Word.Application word = new
Microsoft.Office.Interop.Word.Application();
// create object of missing value
object miss = System.Reflection.Missing.Value;
// create object of selected file path
object path = filePath;
// set file path mode
object readOnly = false;
// open document
Microsoft.Office.Interop.Word.Document docs = word.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 miss,
ref miss, ref miss, ref miss,
ref miss);
foreach (Microsoft.Office.Interop.Word.Table tbl in docs.Tables)
{
tbl.Delete();
}
foreach (Microsoft.Office.Interop.Word.Shape shp in docs.Shapes)
{
shp.Delete();
}
foreach (Microsoft.Office.Interop.Word.InlineShape ilshp in
docs.InlineShapes)
{
if (ilshp.Type ==
Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapePicture)
ilshp.Delete();
}
docs.Close(ref path,ref readOnly,ref miss);
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
@theghostofc 的代码
private void button1_Click(object sender, EventArgs e)
{
// variable to store file path
string filePath = null;
// open dialog box to select file
OpenFileDialog file = new OpenFileDialog();
// dilog box title name
file.Title = "Word File";
// set initial directory of computer system
file.InitialDirectory = "c:\\";
// set restore directory
file.RestoreDirectory = true;
// execute if block when dialog result box click ok button
if (file.ShowDialog() == DialogResult.OK)
{
// store selected file path
filePath = file.FileName.ToString();
}
Microsoft.Office.Interop.Word.Application word = new Microsoft.Office.Interop.Word.ApplicationClass();
// create object of missing value
object miss = System.Reflection.Missing.Value;
// create object of selected file path
object path = filePath;
// set file path mode
object readOnly = false;
// open document
Microsoft.Office.Interop.Word.Document docs = word.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 miss,
ref miss, ref miss, ref miss, ref miss);
try
{
// create word application
foreach (Microsoft.Office.Interop.Word.Table tbl in docs.Tables)
{
tbl.Delete();
}
foreach (Microsoft.Office.Interop.Word.Shape shp in docs.Shapes)
{
shp.Delete();
}
foreach (Microsoft.Office.Interop.Word.InlineShape ilshp in docs.InlineShapes)
{
if (ilshp.Type == Microsoft.Office.Interop.Word.WdInlineShapeType.wdInlineShapePicture)
ilshp.Delete();
}
object saveOption = Microsoft.Office.Interop.Word.WdSaveOptions.wdDoNotSaveChanges;
object originalFormat = Microsoft.Office.Interop.Word.WdOriginalFormat.wdOriginalDocumentFormat;
object routeDocument = false;
docs.Close(ref saveOption, ref originalFormat, ref routeDocument);
// docs.Close(ref miss, ref miss, ref miss);
docs = null;
GC.Collect();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
}
这是代码，请告诉我这两种方法都要求参数docs.Save()和docs.Close(). 我已经将参数传递给docs.Close()但我不知道应该传递什么参数docs.Save() 所以我没有docs.Save()在我的代码中使用所以请明确定义我这些东西我会很高兴你