使用 Open XML SDK 实现 html 富文本转换为 docx 格式示例

使用 Open XML SDK 实现 html 富文本转换为 docx 格式文档相对复杂。下面是一个示例。手动检测 <strong>和 <em> 标签并应用相应的文本格式。

using System;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

class Program
{
    static void Main()
    {
        string htmlContent = "<p>This is <strong>bold</strong> and <em>italic</em> text.</p>";

        // 创建一个新的docx文档
        using (WordprocessingDocument doc = WordprocessingDocument.Create("output.docx", WordprocessingDocumentType.Document))
        {
            MainDocumentPart mainPart = doc.AddMainDocumentPart();
            mainPart.Document = new Document();
            Body body = mainPart.Document.AppendChild(new Body());

            // 解析HTML并创建docx段落
            string[] paragraphs = htmlContent.Split(new[] { "<p>", "</p>" }, StringSplitOptions.RemoveEmptyEntries);
            foreach (string paragraphContent in paragraphs)
            {
                Paragraph paragraph = new Paragraph();
                Run run = new Run();

                string[] tags = paragraphContent.Split(new[] { "<strong>", "</strong>", "<em>", "</em>" }, StringSplitOptions.None);
                foreach (string tag in tags)
                {
                    RunProperties runProperties = new RunProperties();
                    if (tag.Contains("<strong>"))
                    {
                        runProperties.Bold = new Bold();
                    }
                    if (tag.Contains("<em>"))
                    {
                        runProperties.Italic = new Italic();
                    }

                    run.Append(runProperties);
                    run.Append(new Text(tag));
                }

                paragraph.Append(run);
                body.Append(paragraph);
            }
        }

        Console.WriteLine("HTML to docx conversion complete.");
    }
}

需要根据 HTML 标记的不同来创建相应的 docx元素，例如将<p>标签映射到docx段落，将<strong>标签映射到粗体等。

using System;
using System.IO;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

class Program
{
    static void Main()
    {
        string htmlContent = "<p>This is <strong>bold</strong> and <em>italic</em> text.</p>";

        // 创建一个新的docx文档
        using (WordprocessingDocument doc = WordprocessingDocument.Create("output.docx", WordprocessingDocumentType.Document))
        {
            MainDocumentPart mainPart = doc.AddMainDocumentPart();
            mainPart.Document = new Document();
            Body body = mainPart.Document.AppendChild(new Body());

            // 解析HTML内容并创建相应的docx元素
            ProcessHtmlContent(htmlContent, body);

            doc.Save();
        }

        Console.WriteLine("HTML to docx conversion complete.");
    }

    static void ProcessHtmlContent(string htmlContent, OpenXmlElement parentElement)
    {
        // 解析HTML内容并将其映射到docx元素
        // 这里需要根据HTML标记的不同来创建相应的docx元素
        // 例如，<p>标签可以映射到段落，<strong>可以映射到粗体文本等

        // 示例：将HTML段落转换为docx段落
        if (htmlContent.StartsWith("<p>") && htmlContent.EndsWith("</p>"))
        {
            string paragraphText = htmlContent.Substring(3, htmlContent.Length - 7);
            Paragraph paragraph = new Paragraph(new Run(new Text(paragraphText)));
            parentElement.Append(paragraph);
        }

        // 添加更多的HTML标记处理逻辑以满足你的需求
    }
}