asp.net core openxml读取word内容

安装包

OpenXMLSDK-MOT

System.IO.Packaging

asp.net core openxml读取word内容_第1张图片

编写代码测试

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

namespace WordReader
{
    internal class Program
    {
        static void Main(string[] args)
        {
            //不支持doc,需要将doc转化为docx
            var fileName = "xxxx.docx";
            var res = TextFromWord(fileName);
            Console.WriteLine(res);
            Console.WriteLine("完成~~");
        }

        public static string TextFromWord(string filename)
        {
            StringBuilder textBuilder = new StringBuilder();
            using (WordprocessingDocument wDoc = WordprocessingDocument.Open(filename, false))
            {
                var parts = wDoc.MainDocumentPart.Document.Descendants().FirstOrDefault();
                if (parts != null)
                {
                    foreach (var node in parts.ChildElements)
                    {
                        if (node is Paragraph)
                        {
                            ProcessParagraph((Paragraph)node, textBuilder);
                            textBuilder.AppendLine("");
                        }

                        if (node is Table)
                        {
                            ProcessTable((Table)node, textBuilder);
                        }
                    }
                }
            }
            return textBuilder.ToString();
        }

        private static void ProcessTable(Table node, StringBuilder textBuilder)
        {
            foreach (var row in node.Descendants<TableRow>())
            {
                var rowCount = row.Descendants<TableCell>().Count();
                Console.WriteLine(rowCount);
                textBuilder.Append("| ");
                foreach (var cell in row.Descendants<TableCell>())
                {
                    foreach (var para in cell.Descendants<Paragraph>())
                    {
                        ProcessParagraph(para, textBuilder);
                    }
                    textBuilder.Append(" | ");
                }
                textBuilder.AppendLine("");
            }
        }

        private static void ProcessParagraph(Paragraph node, StringBuilder textBuilder)
        {
            foreach (var text in node.Descendants<Text>())
            {
                textBuilder.Append(text.InnerText);
            }
        }
    }
}

你可能感兴趣的:(dotnet,asp.net,word,c#)