NET CORE读取Excel.xlsx单元格图片的场景,一般是批量导入业务数据,例如:药品的图片,医师资格证,商品上架、商家营业资质、水果信息、用户头像等等
这里我截个图,图文并茂更好理解
特别声明:粘贴图片,直接复制在excel里,和在单元格嵌图片资源是两回事的。
上面这个图片是怎么来的呢?步骤如下:
没错,我讲的技术实现方案,是基于这样的嵌入单元格的图片。
代码的实现是:excel其实是一个压缩包,修改后缀xlsx变成zip,这里必须是新版的xlsx格式,老板的excel 我研究了,发现excel的压缩包的存储逻辑和新版本的excel不一样,自己可以修改后缀,解压出来看看。
解压完zip的包之后,开始读取指定的文件,图片路径都是固定的,excel里有你的业务id,根据当前行的图片所在位置,就可以在excel文件里找到对接的标识,通过标识找图片。excel解压出来的文件,都是xml,这时学习xml也是有必要的,要不然,你玩不明白。
处理完数据后,记得删除zip文件。其实你可以解压zip流,在内存中操作,操作完释放zip流,这里我为了简单直白,是解压到服务器指定位置的,方便处理完后删文件。
整体原理就是如此。
下面我上代码:新建一个 net core api 解决方案,引用一下 NPOI Nuget包。本地创建一个 .xlsx 格式的excel文件,当然你可以用其他 操作excel的Nuget包。
我直接把所有的代码整理好了,粘贴复制,直接可以使用,代码里有注释。
我是一个不爱说废话的程序员,一言不合就是反手扔代码。
using ICSharpCode.SharpZipLib.Zip;
using Microsoft.AspNetCore.Mvc;
using NPOI.HSSF.UserModel;
using NPOI.SS.UserModel;
using NPOI.XSSF.UserModel;
using System.Data;
using System.Xml;namespace ExcelOption.Controllers
{[ApiController][Route("[controller]")]public class ImportExcelController : ControllerBase{private readonly Microsoft.AspNetCore.Hosting.IHostingEnvironment _hostingEnvironment;public ImportExcelController(Microsoft.AspNetCore.Hosting.IHostingEnvironment hostingEnvironment){_hostingEnvironment = hostingEnvironment;}[HttpGet(Name = "dele")]public bool dele(){string zipFileName = "filezip" + ".zip";string xlsxFileName = "filexlsx" + ".xlsx";var mapPath = _hostingEnvironment.ContentRootPath;//业务逻辑处理完了就把原来的文件和解压的文件夹删除Directory.Delete(mapPath + @"\" + "filezip", true);System.IO.File.Delete(mapPath + @"\" + xlsxFileName);//File.Delete(mapPath + "\\" + xlsxFileName);System.IO.File.Delete(mapPath + @"\" + zipFileName);return true;}[HttpPost(Name = "ImportExcel_Img")]public bool ImportExcel_Img(IFormFileCollection files){if (files.Count > 0){var file = files[0];//读取导入的文件类型var fileExt = file.FileName.Substring(file.FileName.LastIndexOf('.')).ToLower();if (!fileExt.Equals(".xlsx")){//提示文件类型不正确return false;}//转换保存zipstring zipFileName = "filezip" + ".zip";string xlsxFileName = "filexlsx" + ".xlsx";var mapPath = _hostingEnvironment.ContentRootPath;//保存xlsx到服务器using (var stream = new FileStream(mapPath + xlsxFileName, FileMode.OpenOrCreate, FileAccess.ReadWrite)){file.CopyToAsync(stream);}//保存zip到服务器using (var stream = new FileStream(mapPath + zipFileName, FileMode.OpenOrCreate, FileAccess.ReadWrite)){file.CopyToAsync(stream);}var dt = ExcelHelper.ExcelToDataTable(mapPath + xlsxFileName);//解压,如果解压成功则根据xml处理 (应为方便我就放在ExcelHelper里面了)if (UnZipFile(mapPath + zipFileName, out string path)){//excel 图片信息List<o_ExcelImgModel> o_ExcelImgModelList = new List<o_ExcelImgModel>();//图片路径文件夹var mediaFolderPath = path + @"xl\media";//判断是否存在此文件夹如果有则处理(如果没有图片他是不会有这个文件夹的)if (System.IO.Directory.Exists(mediaFolderPath)){//解压成功获取xml 节点做处理var exclNode = GetXmlExclNodeList(path);var pictNode = GetXmlPictNodeList(path);//获取图片信息与地址foreach (var nl in exclNode){XmlElement sondNode = (XmlElement)nl;XmlNodeList descendDodeList = sondNode.ChildNodes;XmlNodeList picNodeList = descendDodeList[0].ChildNodes;XmlNodeList nvPicPrNodeList = picNodeList[0].ChildNodes;XmlElement cNvPrElement = (XmlElement)nvPicPrNodeList.Item(0);string name = cNvPrElement.GetAttribute("name").ToString();XmlNodeList blipFillNodeList = picNodeList[1].ChildNodes;XmlElement picElement = (XmlElement)blipFillNodeList.Item(0);string id = picElement.GetAttribute("r:embed").ToString();foreach (XmlNode xn in pictNode){XmlElement xe = (XmlElement)xn;if (xe.GetAttribute("Id").ToString() == id){var pathOfPicture = xe.GetAttribute("Target").ToString().Replace("..", "").Replace("/", @"\");pathOfPicture = path + @"xl\" + pathOfPicture;o_ExcelImgModelList.Add(new o_ExcelImgModel(){ID = id,Name = name,PathOfPicture = pathOfPicture});break;}}}//图片对应dt的哪一列,存到dt然后再循环dt去处理(这个是小编的思维,如果有更好的做法可以随缘发挥)foreach (var item in o_ExcelImgModelList){//item.PathOfPicture 图片路径取到了,此时你可以存储了}}//现在dt某一列存放了图片的绝对路径就可以通过table去处理了//循环表插入数据及上传foreach (DataRow item in dt.Rows){//此时你excel转换的 dataTable表的图片字段的 值是:"_xlfn.DISPIMG(\"ID_CD49305586E940EF8F78CD3B54A4BCD3\",1)"item["用户名"].ToString(); //"zhao1"//var kkl= item["IMG"].ToString(); // "_xlfn.DISPIMG(\"ID_CD49305586E940EF8F78CD3B54A4BCD3\",1)"var breakApart = item["IMG"].ToString().Split('\\', '"')[1];var imgPath= o_ExcelImgModelList.FirstOrDefault(x => x.Name == breakApart);//获取图片然后做上传逻辑,这个自己实现我就不多讲了}}else{//解压时报直接返回,这个返回啥类型或者啥数据自己定义就好我这边demo 随缘来个bool意思下return false;}//业务逻辑处理完了就把原来的文件和解压的文件夹删除Directory.Delete(mapPath + "\\" + "filezip", true);System.IO.File.Delete(mapPath + "\\" + xlsxFileName);//File.Delete(mapPath + "\\" + xlsxFileName);System.IO.File.Delete(mapPath + "\\" + zipFileName);}return true;}public static string MidStrEx(string sourse, string startstr, string endstr){string result = string.Empty;int startindex, endindex;try{startindex = sourse.IndexOf(startstr);if (startindex == -1)return result;string tmpstr = sourse.Substring(startindex + startstr.Length);endindex = tmpstr.IndexOf(endstr);if (endindex == -1)return result;result = tmpstr.Remove(endindex);}catch (Exception ex){Console.Write("MidStrEx Err:" + ex.Message);}return result;}/// <summary>/// Xml图片表格位置及路径ID/// </summary>private const string _XmlExcel = @"xl\cellimages.xml";/// <summary>/// Xml图片路径/// </summary>private const string _XmlPict = @"xl\_rels\cellimages.xml.rels";/// <summary>/// 获取图片路径 Xml节点/// </summary>/// <param name="path">解压后的文件夹路径</param>/// <returns></returns>private XmlNodeList GetXmlPictNodeList(string path){XmlDocument doc = new XmlDocument();doc.Load(path + _XmlPict);XmlNode root = doc.DocumentElement;return root.ChildNodes;}/// <summary>/// 获取图片表格位置及路径ID Xml节点/// </summary>/// <param name="path">解压后的文件夹路径</param>/// <returns></returns>private XmlNodeList GetXmlExclNodeList(string path){XmlDocument doc = new XmlDocument();doc.Load(path + _XmlExcel);XmlNode root = doc.DocumentElement;return root.ChildNodes;}/// <summary>/// 解压文件/// </summary>/// <param name="zipFilePath">压缩文件路径</param>/// <param name="path">返回压缩文件夹路径</param>/// <param name="unZipDir">解压文件存放路径,为空时默认与压缩文件同一级目录下,跟压缩文件同名的文件夹</param>/// <returns></returns>private bool UnZipFile(string zipFilePath, out string path, string unZipDir = null){if (zipFilePath == string.Empty){path = null;return false;}if (!System.IO.File.Exists(zipFilePath)){path = null;return false;}//解压文件夹为空时默认与压缩文件同一级目录下,跟压缩文件同名的文件夹 if (string.IsNullOrWhiteSpace(unZipDir))unZipDir = zipFilePath.Replace(Path.GetFileName(zipFilePath), Path.GetFileNameWithoutExtension(zipFilePath));if (!unZipDir.EndsWith("\\"))unZipDir += "\\";if (!Directory.Exists(unZipDir))Directory.CreateDirectory(unZipDir);try{using (ZipInputStream s = new ZipInputStream(System.IO.File.OpenRead(zipFilePath))){ZipEntry theEntry;while ((theEntry = s.GetNextEntry()) != null){string directoryName = Path.GetDirectoryName(theEntry.Name);string fileName = Path.GetFileName(theEntry.Name);if (directoryName.Length > 0){Directory.CreateDirectory(unZipDir + directoryName);}if (!directoryName.EndsWith("\\"))directoryName += "\\";if (fileName != String.Empty){using (FileStream streamWriter = System.IO.File.Create(unZipDir + theEntry.Name)){int size = 2048;byte[] data = new byte[2048];while (true){size = s.Read(data, 0, data.Length);if (size > 0){streamWriter.Write(data, 0, size);}else{break;}}}}}}}catch{path = null;return false;}path = unZipDir;return true;}}/// <summary>/// excel 图片信息/// </summary>public class o_ExcelImgModel{/// <summary>/// ID/// </summary>public string ID { get; set; }/// <summary>/// 上传图片生成的id/// </summary>public string Name { get; set; }/// <summary>/// 图片文件绝对路径/// </summary>public string PathOfPicture { get; set; }}public class ExcelHelper{private static IWorkbook workbook = null;private static FileStream fs = null;/// <summary>/// 将excel中的数据导入到DataTable中/// </summary>/// <param name="fileName">excel文件路径</param>/// <param name="sheetName">excel工作薄sheet的名称</param>/// <param name="isFirstRowColumn">第一行是否是DataTable的列名</param>/// <returns>返回的DataTable</returns>public static DataTable ExcelToDataTable(string fileName, string sheetName = null, bool isFirstRowColumn = true){ISheet sheet = null;DataTable data = new DataTable();int startRow = 0;try{fs = new FileStream(fileName, FileMode.Open, FileAccess.Read);if (fileName.IndexOf(".xlsx") > 0) // 2007版本workbook = new XSSFWorkbook(fs);else if (fileName.IndexOf(".xls") > 0) // 2003版本workbook = new HSSFWorkbook(fs);if (sheetName != null){sheet = workbook.GetSheet(sheetName);if (sheet == null) //如果没有找到指定的sheetName对应的sheet,则尝试获取第一个sheet{sheet = workbook.GetSheetAt(0);}}else{sheet = workbook.GetSheetAt(0);}if (sheet != null){IRow firstRow = sheet.GetRow(0);int cellCount = firstRow.LastCellNum; //一行最后一个cell的编号 即总的列数if (isFirstRowColumn){for (int i = firstRow.FirstCellNum; i < cellCount; ++i){ICell cell = firstRow.GetCell(i);if (cell != null){string cellValue = cell.StringCellValue;if (cellValue != null){DataColumn column = new DataColumn(cellValue);data.Columns.Add(column);}}}startRow = sheet.FirstRowNum + 1;}else{for (int i = firstRow.FirstCellNum; i < cellCount; i++){DataColumn column = new DataColumn(i.ToString());data.Columns.Add(column);}startRow = sheet.FirstRowNum;}//最后一列的标号int rowCount = sheet.LastRowNum;for (int i = startRow; i <= rowCount; ++i){IRow row = sheet.GetRow(i);if (row == null) continue; //没有数据的行默认是null DataRow dataRow = data.NewRow();for (int j = row.FirstCellNum; j < cellCount; ++j){if (row.GetCell(j) != null) //同理,没有数据的单元格都默认是nulldataRow[j] = row.GetCell(j).ToString();}data.Rows.Add(dataRow);}}return data;}catch (Exception ex){Console.WriteLine("Exception: " + ex.Message);return null;}}}
}
如果你看完了,就点赞转发一下呗,给小编打打气。我发技术文章的目的就是给自己的技术生涯留下点痕迹、或者蛛丝马迹,毕竟互联网是有记忆的,将来我五六十、七八十了,希望我长命百岁,还能搜到我曾经年轻时分享的技术文章,或者我的后代能看到他爸爸?爷爷 or 姥爷?太爷爷 爷爷留下来的【财富】