使用 Open XML SDK 实现 html 富文本转换为 docx 格式示例 _网页播放器

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
    }
}

下例使用 html2openxml 将 html 转 docx

using system;
using system.io;
using documentformat.openxml;
using documentformat.openxml.packaging;
using documentformat.openxml.wordprocessing;
using htmltoopenxml;

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());

            // 使用html2openxml将html内容转换为docx元素
            var converter = new htmlconverter(mainpart);
            converter.imageprocessing = imageprocessing.automaticdownload;
            var paragraphs = converter.parse(htmlcontent);
            
            foreach (var paragraph in paragraphs)
            {
                body.append(paragraph);
            }

            doc.save();
        }

        console.writeline("html to docx conversion complete.");
    }
}

带内联式 css 样式。

using system;
using system.io;
using system.text;
using documentformat.openxml;
using documentformat.openxml.packaging;
using documentformat.openxml.wordprocessing;
using htmltoopenxml;

class program
{
    static void main()
    {
        string htmlcontent = "<p style=\"color: blue; font-size: 14px;\">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());

            // 使用html2openxml将html内容转换为docx元素
            var converter = new htmlconverter(mainpart);
            converter.imageprocessing = imageprocessing.automaticdownload;
            var paragraphs = converter.parse(htmlcontent);

            foreach (var paragraph in paragraphs)
            {
                body.append(paragraph);
            }

            doc.save();
        }

        console.writeline("html to docx conversion complete.");
    }
}

带 css 样式应用

using system;
using system.io;
using system.text;
using documentformat.openxml;
using documentformat.openxml.packaging;
using documentformat.openxml.wordprocessing;
using htmltoopenxml;

class program
{
    static void main()
    {
        string htmlcontent = "<p class=\"my-paragraph\">this is <strong>bold</strong> and <em>italic</em> text.</p>";
        string externalcss = ".my-paragraph { color: blue; font-size: 14px; }";

        // 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());

            // 将外部css样式转化为内联样式
            htmlcontent = applyexternalcsstohtml(htmlcontent, externalcss);

            // 使用html2openxml将html内容转换为docx元素
            var converter = new htmlconverter(mainpart);
            converter.imageprocessing = imageprocessing.automaticdownload;
            var paragraphs = converter.parse(htmlcontent);

            foreach (var paragraph in paragraphs)
            {
                body.append(paragraph);
            }

            doc.save();
        }

        console.writeline("html to docx conversion complete.");
    }

    static string applyexternalcsstohtml(string htmlcontent, string externalcss)
    {
        // 解析外部css文件并将其应用于html内容
        // 这里需要将css规则应用到html标记的内联样式中
        // 在此示例中，我们简单地将css类名替换为内联样式
        // 你可能需要更复杂的css处理逻辑，取决于外部css文件的内容和结构

        // 将样式规则拆分为每个类
        var cssrules = externalcss.split('}');

        foreach (var rule in cssrules)
        {
            if (!string.isnullorwhitespace(rule))
            {
                // 提取类名和样式属性
                var parts = rule.split('{');
                var classname = parts[0].trim();
                var style = parts[1].trim();

                // 将类名替换为内联样式
                htmlcontent = htmlcontent.replace($"class=\"{classname}\"", $"style=\"{style}\"");
            }
        }

        return htmlcontent;
    }
}