由于数据方提供的数据在excel文件中不止有文字内容还包含图片信息,于是编写相关测试代码,读取excel文件内容及图片信息.
本文使用的是 NPOI-2.6.2 版本,此版本持.Net4.7.2;.NetStandard2.0;.NetStandard2.1;.Net6.0+。
测试文档内容,如下图:
保存后的图片:
打开图片显示正常:
编写读取数据方法,代码如:
static public DataTable ReadExcel(string filePath, string _sDirImg)
{
using (FileStream file = new FileStream(filePath, FileMode.Open, FileAccess.Read))
{
IWorkbook workbook = null;
string sExt = Path.GetExtension(filePath).ToLower();
if (sExt == ".xlsx")
{
workbook = new XSSFWorkbook(file);//新版本的Excel(.xlsx)
}
else
{
workbook = new HSSFWorkbook(file);//老版本的Excel(.xls)
}
// 读取第一个 Sheet
ISheet sheet = workbook.GetSheetAt(0);
if (sExt == ".xlsx")
{
fnReadImageXSSF(sheet, _sDirImg);//新版本的Excel(.xlsx)
}
else
{
fnReadImageHSSF(sheet, _sDirImg);//老版本的Excel(.xls)
}
// 创建 DataTable
DataTable dataTable = new DataTable(sheet.SheetName);
// 读取表头
IRow headerRow = sheet.GetRow(0);
for (int i = 0; i < headerRow.LastCellNum; i++)
{
ICell cell = headerRow.GetCell(i);
dataTable.Columns.Add(cell.ToString(), typeof(string));
}
// 读取数据行
for (int rowNum = 1; rowNum <= sheet.LastRowNum; rowNum++)
{
IRow row = sheet.GetRow(rowNum);
DataRow dataRow = dataTable.NewRow();
for (int i = 0; i < row.LastCellNum; i++)
{
ICell cell = row.GetCell(i);
if (null == cell) continue;
dataRow[i] = cell.ToString();
}
dataTable.Rows.Add(dataRow);
}
return dataTable;
}
}
编写对应不同版本的excel文件,读取图片方法,读取excel .xlsx文件内图片:
/// <summary>
/// 读取excel .xlsx文件内图片
/// </summary>
/// <param name="sheet"></param>
/// <param name="_sDirImg"></param>
static public void fnReadImageXSSF(ISheet sheet, string _sDirImg)
{
// 读取图像信息
foreach (XSSFShape shape in ((XSSFDrawing)sheet.DrawingPatriarch).GetShapes())
{
if (shape is XSSFPicture)
{
XSSFPicture picture = (XSSFPicture)shape;
// 获取图片所在单元格的行号和列号
int rowIndex = picture.GetPreferredSize().Row1;
int colIndex = picture.GetPreferredSize().Col1;
// 获取图像文件格式
string imageFormat = picture.PictureData.MimeType switch
{
"image/jpeg" => "jpeg",
"image/png" => "png",
"image/gif" => "gif",
"image/bmp" => "bmp",
_ => "jpg"
};
// 保存图像文件
string outputFileName = _sDirImg + $"{rowIndex}-{colIndex}-{Guid.NewGuid()}.{imageFormat}";
using (FileStream imageFile = new FileStream(outputFileName, FileMode.Create))
{
imageFile.Write(picture.PictureData.Data, 0, picture.PictureData.Data.Length);
}
Console.WriteLine($"Saved image: {outputFileName}");
}
}
}
读取excel .xls文件内图片,代码如下:
/// <summary>
/// 读取excel .xls文件内图片
/// </summary>
/// <param name="sheet"></param>
/// <param name="_sDirImg"></param>
static public void fnReadImageHSSF(ISheet sheet, string _sDirImg)
{
// 读取图像信息
foreach (HSSFShape shape in ((HSSFPatriarch)sheet.DrawingPatriarch).Children)
{
if (shape is HSSFPicture)
{
HSSFPicture picture = (HSSFPicture)shape;
// 获取图片所在单元格的行号和列号
int rowIndex = picture.GetPreferredSize().Row1;
int colIndex = picture.GetPreferredSize().Col1;
// 获取图像文件格式
string imageFormat = picture.PictureData.MimeType switch
{
"image/jpeg" => "jpeg",
"image/png" => "png",
"image/gif" => "gif",
"image/bmp" => "bmp",
_ => "jpg"
};
// 保存图像文件
string outputFileName = _sDirImg + $"{rowIndex}-{colIndex}-{Guid.NewGuid()}.{imageFormat}";
using (FileStream imageFile = new FileStream(outputFileName, FileMode.Create))
{
imageFile.Write(picture.PictureData.Data, 0, picture.PictureData.Data.Length);
}
Console.WriteLine($"Saved image: {outputFileName}");
}
}
}
正常处理应该是读取到图片保存成功后,处理datatable图片列的相关地址,如:uploads/xxx/xx.jpg ,返回保存在服务器上的地址,以便前端访问或保存到数据库等,本文并没有处理,有需要的伙伴自行处理吧,希望本文对你有帮助。