C# 读取Word文本框中的文本、图片和表格（附VB.NET代码）

待我称王封你为后i 2022-11-06 14:00 298阅读 0赞

# 【概述】 #

Word中可插入文本框，在文本框中可添加文本、图片、表格等内容。本篇文章通过C\#程序代码介绍如何来读取文本框中的文本、图片和表格等内容。附VB.NET代码，有需要可作参考。

# 【程序环境】 #

程序中所需必要的程序集文件[Spire.Doc.dll][]，及其他相关dll文件（见下文）。

用于测试的Word源文档如图：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70][]

# 【程序代码】 #

### **1.****读取文本框中的文本** ###

所需程序集:

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 1][]

【C\#】

using Spire.Doc;
    using Spire.Doc.Documents;
    using Spire.Doc.Fields;
    using System;
    using System.IO;
    using System.Text;
    
    namespace ExtractText
    {
        class Program
        {
            static void Main(string[] args)
            {
                //加载Word源文档
                Document doc = new Document();
                doc.LoadFromFile("test.docx");
    
                //获取文本框
                TextBox textbox = doc.TextBoxes[0];
    
                //创建StringBuilder类的对象
                StringBuilder sb = new StringBuilder();
    
                //遍历文本框中的对象，获取文本
                foreach (object obj in textbox.Body.ChildObjects)
                {
                    if (obj is Paragraph)
                    {
                        String text = ((Paragraph)obj).Text;
                        sb.AppendLine(text);
                    }
                }
    
                //保存写入的txt文档到指定路径
                File.WriteAllText("ExtractedText.txt", sb.ToString());
                System.Diagnostics.Process.Start("ExtractedText.txt");
            }
        }
    }

【vb.net】

Imports Spire.Doc
    Imports Spire.Doc.Documents
    Imports Spire.Doc.Fields
    Imports System.IO
    Imports System.Text
    
    Namespace ExtractText
    	Class Program
    		Private Shared Sub Main(args As String())
    			'加载Word源文档
    			Dim doc As New Document()
    			doc.LoadFromFile("test.docx")
    
    			'获取文本框
    			Dim textbox As TextBox = doc.TextBoxes(0)
    
    			'创建StringBuilder类的对象
    			Dim sb As New StringBuilder()
    
    			'遍历文本框中的对象，获取文本
    			For Each obj As Object In textbox.Body.ChildObjects
    				If TypeOf obj Is Paragraph Then
    					Dim text As [String] = DirectCast(obj, Paragraph).Text
    					sb.AppendLine(text)
    				End If
    			Next
    
    			'保存写入的txt文档到指定路径
    			File.WriteAllText("ExtractedText.txt", sb.ToString())
    			System.Diagnostics.Process.Start("ExtractedText.txt")
    		End Sub
    	End Class
    End Namespace

文本读取结果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 2][]

### **2.****读取文本框中的图片** ###

所需程序集:

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 3][]

【C\#】

using Spire.Doc;
    using Spire.Doc.Documents;
    using Spire.Doc.Fields;
    using System;
    
    namespace ExtractImg
    {
        class Program
        {
            static void Main(string[] args)
            {
                //加载Word源文档
                Document doc = new Document();
                doc.LoadFromFile("test.docx");
    
                //获取文本框
                TextBox textbox = doc.TextBoxes[0];    
    
                int index = 0 ;
                //遍历文本框中所有段落
                for (int i = 0 ; i < textbox.Body.Paragraphs.Count;i++)
                {
                    Paragraph paragraph = textbox.Body.Paragraphs[i];
                    //遍历段落中的所有子对象
                    for (int j = 0; j < paragraph.ChildObjects.Count; j++)
                    {
                        object obj = paragraph.ChildObjects[j];
                        
                        //判定对象是否为图片
                        if (obj is DocPicture)
                        {
                            //获取图片
                            DocPicture picture = (DocPicture) obj;
                            String imageName = String.Format("Image-{0}.png", index);
                            picture.Image.Save(imageName, System.Drawing.Imaging.ImageFormat.Png);
                            index++;
                        }
                    }
                }
                     
            }
        }
    }

【vb.net】

Imports Spire.Doc
    Imports Spire.Doc.Documents
    Imports Spire.Doc.Fields
    
    Namespace ExtractImg
    	Class Program
    		Private Shared Sub Main(args As String())
    			'加载Word源文档
    			Dim doc As New Document()
    			doc.LoadFromFile("test.docx")
    
    			'获取文本框
    			Dim textbox As TextBox = doc.TextBoxes(0)
    
    			Dim index As Integer = 0
    			'遍历文本框中所有段落
    			For i As Integer = 0 To textbox.Body.Paragraphs.Count - 1
    				Dim paragraph As Paragraph = textbox.Body.Paragraphs(i)
    				'遍历段落中的所有子对象
    				For j As Integer = 0 To paragraph.ChildObjects.Count - 1
    					Dim obj As Object = paragraph.ChildObjects(j)
    
    					'判定对象是否为图片
    					If TypeOf obj Is DocPicture Then
    						'获取图片
    						Dim picture As DocPicture = DirectCast(obj, DocPicture)
    						Dim imageName As [String] = [String].Format("Image-{0}.png", index)
    						picture.Image.Save(imageName, System.Drawing.Imaging.ImageFormat.Png)
    						index += 1
    					End If
    				Next
    			Next
    
    		End Sub
    	End Class
    End Namespace

图片读取结果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 4][]

### **3.****读取文本框中的表格** ###

所需程序集:

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 5][]

【C\#】

using Spire.Doc;
    using Spire.Doc.Documents;
    using Spire.Doc.Fields;
    using System.IO;
    using System.Text;
    
    namespace ExtractTable
    {
        class Program
        {
            static void Main(string[] args)
            {
                //加载Word文档
                Document doc = new Document();
                doc.LoadFromFile("test.docx");
    
                //获取文本框
                TextBox textbox = doc.TextBoxes[0];
    
                //获取文本框中表格
                Table table = textbox.Body.Tables[0] as Table;
    
                StringBuilder sb = new StringBuilder();
    
                //遍历表格中的段落并提取文本
                foreach (TableRow row in table.Rows)
                {
                    foreach (TableCell cell in row.Cells)
                    {
                        foreach (Paragraph paragraph in cell.Paragraphs)
                        {
                            sb.AppendLine(paragraph.Text);
                        }
                    }
                }
                File.WriteAllText("ExtractedTable.txt", sb.ToString());
            }
        }
    }

【vb.net】

Imports Spire.Doc
    Imports Spire.Doc.Documents
    Imports Spire.Doc.Fields
    Imports System.IO
    Imports System.Text
    
    Namespace ExtractTable
    	Class Program
    		Private Shared Sub Main(args As String())
    			'加载Word文档
    			Dim doc As New Document()
    			doc.LoadFromFile("test.docx")
    
    			'获取文本框
    			Dim textbox As TextBox = doc.TextBoxes(0)
    
    			'获取文本框中表格
    			Dim table As Table = TryCast(textbox.Body.Tables(0), Table)
    
    			Dim sb As New StringBuilder()
    
    			'遍历表格中的段落并提取文本
    			For Each row As TableRow In table.Rows
    				For Each cell As TableCell In row.Cells
    					For Each paragraph As Paragraph In cell.Paragraphs
    						sb.AppendLine(paragraph.Text)
    					Next
    				Next
    			Next
    			File.WriteAllText("ExtractedTable.txt", sb.ToString())
    		End Sub
    	End Class
    End Namespace

表格数据读取结果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 6][]

## 【总结】 ##

以上是本文关于通过C\#程序读取Word中的文本框的方法。所附VB.NET代码供参考。

另推荐阅读《[Java 读取Word文本框中的文本、图片和表格][Java _Word]》

（本文完，如需**转载**，请**务必注明出处**！！）

[Spire.Doc.dll]: https://www.e-iceblue.cn/Downloads/Free-Spire-Doc-NET.html
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70]: /images/20221023/eb17e2f67f5f41f0be30a05fc63783f1.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 1]: /images/20221023/6793ae2b1230461baa4fef19c5fa2001.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 2]: /images/20221023/abe069735a564d0990240986f36d6301.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 3]: /images/20221023/a5857361567249608a09de4a3ef04286.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 4]: /images/20221023/3d0d1324a92947cb820579cce67dc681.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 5]: /images/20221023/33f50dd676764f86b4a4feae02a5867b.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VpY2VibHVl_size_16_color_FFFFFF_t_70 6]: /images/20221023/937dc552ac52427e85b83846372303e5.png
[Java _Word]: https://blog.csdn.net/Eiceblue/article/details/114397998?spm=1001.2014.3001.5501