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
DXM05218 分钟前
牟乃夏《ArcGIS Engine地理信息系统开发教程》学习笔记1
开发语言·经验分享·笔记·学习·arcgis·c#·arcgis engine
Wythzhfrey32 分钟前
51单片机Day03---让一个LED灯闪烁
c语言·单片机·嵌入式硬件·c#·51单片机
浅陌sss36 分钟前
C#容器源码分析 --- List
c#
前端Hardy1 小时前
HTML&CSS:卡片式提交框
css·html
前端Hardy1 小时前
HTML&CSS:超有趣的登录表单
javascript·css·html
CodeCraft Studio5 小时前
如何实现Microsoft Word (.docx) 格式到 FastReport .NET (.frx) 文件的转换
microsoft·word·.net
幻想趾于现实14 小时前
C# Winform 入门(15)之制作二维码和拼接(QR)
开发语言·c#·winform
霸道流氓气质14 小时前
Winform入门进阶企业级开发示例:http接口数据清洗转换、断线续传、mqtt数据传输实例详解(附代码资源下载)
http·c#·winform
今天吃了嘛o14 小时前
vue中根据html动态渲染内容2.0
vue.js·elementui·html
低头专研15 小时前
用 HTML 网页来管理 Markdown 标题序号
前端·html·markdown·markdown标题编号