c# 将html转化到word

c# 将html转化到word

1)HtmlToWordConverter.cs

cs 复制代码
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;
using HtmlAgilityPack;
using System.Collections.Generic;

namespace ConsoleApp9
{
    public class HtmlToWordConverter
    {
        public void ConvertHtmlToWord(List<string> bodyStrings, string titleString, string docxFilePath)
        {
            using (WordprocessingDocument wordDocument = WordprocessingDocument.Create(docxFilePath, WordprocessingDocumentType.Document))
            {
                MainDocumentPart mainPart = wordDocument.AddMainDocumentPart();
                mainPart.Document = new Document();
                Body body = mainPart.Document.AppendChild(new Body());

                // Add centered title
                if (!string.IsNullOrEmpty(titleString))
                {
                    Paragraph titleParagraph = new Paragraph();
                    Run titleRun = new Run(new Text(titleString));
                    titleParagraph.AppendChild(new ParagraphProperties(new Justification() { Val = JustificationValues.Center }));
                    titleParagraph.Append(titleRun);
                    body.Append(titleParagraph);
                }

                // Convert each bodyString to Word content
                foreach (string bodyString in bodyStrings)
                {
                    HtmlDocument htmlDoc = new HtmlDocument();
                    htmlDoc.LoadHtml(bodyString);

                    ConvertHtmlNodesToWord(htmlDoc.DocumentNode.ChildNodes, body);
                }
            }
        }

        private void ConvertHtmlNodesToWord(HtmlNodeCollection nodes, OpenXmlElement parent)
        {
            foreach (HtmlNode node in nodes)
            {
                switch (node.Name)
                {
                    case "p": // Paragraph
                        Paragraph para = new Paragraph();
                        Run run = new Run();
                        ConvertHtmlToRun(node.ChildNodes, run);
                        para.Append(run);
                        parent.Append(para);
                        break;

                    case "h1": // Heading 1
                    case "h2": // Heading 2
                    case "h3": // Heading 3
                    case "h4": // Heading 4
                    case "h5": // Heading 5
                    case "h6": // Heading 6
                        Paragraph heading = new Paragraph();
                        Run runHeading = new Run();
                        RunProperties runPropHeading = new RunProperties();

                        // Set heading style based on HTML heading level
                        int headingLevel = int.Parse(node.Name.Substring(1)); // Extract the number from "h1" to "1"
                        if (headingLevel >= 1 && headingLevel <= 6)
                        {
                            runPropHeading.Append(new Bold());
                            runPropHeading.Append(new FontSize() { Val = new StringValue((24 - (headingLevel - 1) * 2).ToString()) });
                            runPropHeading.Append(new DocumentFormat.OpenXml.Wordprocessing.Color() { Val = "2E74B5" }); // You can adjust the color as needed
                        }
                        runHeading.Append(runPropHeading);
                        ConvertHtmlToRun(node.ChildNodes, runHeading);
                        heading.Append(runHeading);
                        parent.Append(heading);
                        break;

                    // Add more cases for other HTML elements like tables, lists, etc. as needed

                    default:
                        break;
                }

                if (node.HasChildNodes)
                {
                    ConvertHtmlNodesToWord(node.ChildNodes, parent);
                }
            }
        }

        private void ConvertHtmlToRun(HtmlNodeCollection nodes, Run run)
        {
            foreach (HtmlNode node in nodes)
            {
                switch (node.Name)
                {
                    case "#text": // Text node
                        run.AppendChild(new Text(node.InnerText));
                        break;

                    case "strong": // Strong (bold) text
                        RunProperties runPropStrong = new RunProperties(new Bold());
                        run.AppendChild(runPropStrong);
                        ConvertHtmlToRun(node.ChildNodes, run);
                        break;

                    case "em": // Emphasized (italic) text
                        RunProperties runPropEm = new RunProperties(new Italic());
                        run.AppendChild(runPropEm);
                        ConvertHtmlToRun(node.ChildNodes, run);
                        break;

                    // Add more cases for other HTML formatting elements as needed

                    default:
                        ConvertHtmlToRun(node.ChildNodes, run);
                        break;
                }
            }
        }
    }
}

2)Program.cs

cs 复制代码
using System;
using System.Collections.Generic;

namespace ConsoleApp9
{
    class Program
    {
        static void Main(string[] args)
        {
            List<string> bodyStrings = new List<string>{
            @"<h1>内容1</h1>
            <p>第一段内容</p>
            <p>第二段内容</p>",
            @"<h1>内容2</h1>
            <p>第一段内容</p>
            <p>第二段内容</p>"};

            string titleString = "HTML测试";
            string docxFilePath = AppDomain.CurrentDomain.BaseDirectory + "tests.docx";

            HtmlToWordConverter converter = new HtmlToWordConverter();
            converter.ConvertHtmlToWord(bodyStrings, titleString, docxFilePath);

            Console.WriteLine("生成word成功");
        }
    }
}
相关推荐
CallZhang21011 小时前
Vision Master的C#脚本与opencv联合编程
opencv·计算机视觉·c#·视觉检测
AI视觉网奇12 小时前
kafka 冲突解决 kafka安装
c#·linq
hqwest12 小时前
C#WPF实战出真汁07--【系统设置】--菜品类型设置
开发语言·c#·wpf·grid设计·stackpanel布局
萘柰奈13 小时前
Unity进阶--C#补充知识点--【Unity跨平台的原理】Mono与IL2CPP
unity·c#·游戏引擎
程序设计实验室13 小时前
StarBlog v1.3.0 新版本,一大波更新以及迁移服务器部署
c#·aspnetcore·starblog番外
淡海水14 小时前
【原理】Struct 和 Class 辨析
开发语言·c++·c#·struct·class
淡海水14 小时前
【原理】Unity GC 对比 C# GC
unity·c#·gc·垃圾回收
张人玉14 小时前
C#读取文件, IO 类属性及使用示例
microsoft·c#
前端老鹰16 小时前
CSS backdrop-filter:给元素背景添加模糊与色调的高级滤镜
前端·css·html
咕白m62519 小时前
通过 C# 高效提取 PDF 文本的完整指南
后端·c#