使用C#高效提取Word文档中的图片和文本的代码实现

Install-Package Spire.Doc

using Spire.Doc;
using System;
using System.IO;
using System.Text;

public class WordTextExtractor
{
    public static string ExtractAllText(string filePath)
    {
        // 确保文件存在
        if (!File.Exists(filePath))
        {
            Console.WriteLine($"错误：文件 '{filePath}' 不存在。");
            return string.Empty;
        }

        try
        {
            // 加载Word文档
            Document document = new Document();
            document.LoadFromFile(filePath);

            // 获取文档中的所有文本
            string fullText = document.GetText();

            // 返回提取到的文本
            return fullText;
        }
        catch (Exception ex)
        {
            Console.WriteLine($"提取文本时发生错误：{ex.Message}");
            return string.Empty;
        }
    }

    public static void Main(string[] args)
    {
        string docPath = "Sample.docx"; // 替换为您的Word文档路径
        string extractedText = ExtractAllText(docPath);

        if (!string.IsNullOrEmpty(extractedText))
        {
            Console.WriteLine("--- 提取到的文本内容 ---");
            Console.WriteLine(extractedText);
            // 您也可以将文本保存到文件
            File.WriteAllText("ExtractedText.txt", extractedText, Encoding.UTF8);
            Console.WriteLine("\n文本已保存到 ExtractedText.txt");
        }
    }
}

using Spire.Doc;
using Spire.Doc.Documents;
using Spire.Doc.Fields;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.IO;

public class WordImageExtractor
{
    public static void ExtractImages(string filePath, string outputPath)
    {
        if (!File.Exists(filePath))
        {
            Console.WriteLine($"错误：文件 '{filePath}' 不存在。");
            return;
        }

        if (!Directory.Exists(outputPath))
        {
            Directory.CreateDirectory(outputPath);
        }

        try
        {
            Document document = new Document();
            document.LoadFromFile(filePath);

            int imageCount = 0;
            // 遍历文档中的所有Section
            foreach (Section section in document.Sections)
            {
                // 遍历Section中的所有Paragraph
                foreach (Paragraph paragraph in section.Paragraphs)
                {
                    // 遍历Paragraph中的所有DocumentObject
                    foreach (DocumentObject obj in paragraph.ChildObjects)
                    {
                        // 判断是否为图片对象（DocPicture）或包含图片的ShapeObject
                        if (obj.DocumentObjectType == DocumentObjectType.Picture)
                        {
                            DocPicture picture = obj as DocPicture;
                            if (picture != null && picture.Image != null)
                            {
                                string imageName = $"Image_{imageCount++}.png";
                                string imagePath = Path.Combine(outputPath, imageName);
                                picture.Image.Save(imagePath, ImageFormat.Png);
                                Console.WriteLine($"已提取图片: {imagePath}");
                            }
                        }
                    }
                }
            }

            if (imageCount == 0)
            {
                Console.WriteLine("文档中未找到任何图片。");
            }
        }
        catch (Exception ex)
        {
            Console.WriteLine($"提取图片时发生错误：{ex.Message}");
        }
    }

    public static void Main(string[] args)
    {
        string docPath = "SampleWithImages.docx"; // 替换为您的Word文档路径
        string outputDir = "ExtractedImages";
        ExtractImages(docPath, outputDir);
    }
}