在C#中用winform开发百度智能云OCR文字识别技术增值税发票识别助手

当前位置：网站建设 > 技术支持

在C#中用winform开发百度智能云OCR文字识别技术增值税发票识别助手

资料来源：网络整理时间：2023/2/14 1:14:29 共计：3631 浏览

首先本小工具使用C# winfrom 实现，其中主要是使用了百度智能云OCR文字识别技术，调用期官网接口，很简单，搭配NPOI Execl操作类库，

利用Spire.pdf类库，把pdf格式发票，转换为png图片格式。自动识别图片、pdf格式发票，发票可以用高拍仪、手机拍照、扫面件等都可以识别。

其他说明：本程序借助百度智能云API作为基础的发票识别技术。

发票识别助手共分5个功能模块，操作相对很简单，第一步点击添加发票按钮，选择要识别的发票信息。注意说明：目前图片格式支持jpg、png、bmp，图片的长和宽要求最短边大于10px，

最长边小于2048px;图像编码后大小必须小于4M，建议不要超过1M；第二步点击识别发票按钮，系统开始识别发票信息，识别完成后，发票信息会自动生成；

介绍一下关键的代码：

一、获取百度云API token，这个是官方给的，直接拿过来用就可以了。

public static class AccessToken

    {
        // 百度云中开通对应服务应用的 API Key 建议开通应用的时候多选服务
        private static String clientId = ConfigurationManager.AppSettings.Get("APIKey");
        // 百度云中开通对应服务应用的 Secret Key
        private static String clientSecret = ConfigurationManager.AppSettings.Get("SecretKey");

        public static String getAccessToken()
        {
            String authHost = "https://aip.baidubce.com/oauth/2.0/token";
            HttpClient client = new HttpClient();
            List<KeyValuePair<String, String>> paraList = new List<KeyValuePair<string, string>>();
            paraList.Add(new KeyValuePair<string, string>("grant_type", "client_credentials"));
            paraList.Add(new KeyValuePair<string, string>("client_id", clientId));
            paraList.Add(new KeyValuePair<string, string>("client_secret", clientSecret));

            HttpResponseMessage response = client.PostAsync(authHost, new FormUrlEncodedContent(paraList)).Result;
            String result = response.Content.ReadAsStringAsync().Result;
            // Console.WriteLine(result);

            AccessTokenInfo tokenInfo = JsonConvert.DeserializeObject<AccessTokenInfo>(result);

            return tokenInfo.access_token;
        }
    }

    public class AccessTokenInfo
    {
        public string refresh_token { get; set; }
        public string expires_in { get; set; }
        public string session_key { get; set; }
        public string access_token { get; set; }
        public string scope { get; set; }
        public string session_secret { get; set; }
    }

二、增值税票识别请求过程和参数传递，也是官方给的例子，自己按照需求修改一下就可以了。

// 增值税发票识别
        public static string vatInvoice(string fileName)
        {
            string host = "https://aip.baidubce.com/rest/2.0/ocr/v1/vat_invoice?access_token=" + token;
            Encoding encoding = Encoding.Default;
            System.Net.HttpWebRequest request = (HttpWebRequest)WebRequest.Create(host);
            request.Method = "post";
            request.KeepAlive = true;
            // 图片的base64编码
            string base64 = getFileBase64(fileName);
            String str = "image=" + UrlEncode(base64);
            byte[] buffer = encoding.GetBytes(str);
            request.ContentLength = buffer.Length;
            request.GetRequestStream().Write(buffer, 0, buffer.Length);
            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
            StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.UTF8);
            string result = reader.ReadToEnd();
            return result;
        }

        public static String getFileBase64(String fileName)
        {
            FileStream filestream = new FileStream(fileName, FileMode.Open, System.IO.FileAccess.Read, FileShare.ReadWrite);
            byte[] arr = new byte[filestream.Length];
            filestream.Read(arr, 0, (int)filestream.Length);
            string baser64 = Convert.ToBase64String(arr);
            filestream.Close();
            return baser64;
        }

        public static string UrlEncode(string str)
        {
            StringBuilder sb = new StringBuilder();
            byte[] byStr = System.Text.Encoding.UTF8.GetBytes(str); //默认System.Text.Encoding.Default.GetBytes(str)
            for (int i = 0; i < byStr.Length; i++)
            {
                sb.Append(@"%" + Convert.ToString(byStr[i], 16));
            }
            return (sb.ToString());
        }

三、这里的部分是把pdf格式的发票，自动转换为png格式，提供出百度云api需要的文件格式。

private ImageList GetImage(string[] files)
        {
            ImageList list = new ImageList();
            for (int i = 0; i < files.Length; i++)
            {
                list.Images.Add(files[i], Image.FromFile(files[i]));
                list.ImageSize = new Size(80, 60);
            }
            return list;
        }

        private string[] GetImages()
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Multiselect = true;//设置选择多个文件
            ofd.InitialDirectory = @"C:\images\";//设置初始目录 TODO:改为系统默认我的文档中的图片文件夹
            ofd.Multiselect = true;
            //ofd.Filter = "JPG(*.jpg)|*.jpg|JPEG(*.jpeg)|*.jpeg|PNG(*.png)|*.png|GIF(*.gif)|*.gif|所有文件(*.*)|*.*";
            ofd.Title = "请选择要识别的发票的图片";
            ofd.Filter = "图片文件(*.jpg *.jpeg *.bmp *.png)|*.jpg;*.jpeg;*.bmp;*.png;*.pdf";
            if (ofd.ShowDialog() == DialogResult.OK && ofd.FileNames != null)
            {
                string[] files = ofd.FileNames;
                //pdf文件转换为png图片文件
                string imageName = "";
                for (int i = 0; i < files.Length; i++)
                {
                    if (Path.GetExtension(files[i]).ToUpper().Contains(".PDF"))
                    {
                        imageName = Path.GetFileNameWithoutExtension(files[i]);
                        files[i] = Common.ConvertPDF2Image(files[i], imageName, 0, 1, ImageFormat.Png);
                        errMsg.AppendText(DateTime.Now.ToLongTimeString().ToString() + " 已将" + imageName + ".pdf自动转换为png图片格式\r\n");
                    }
                }
                return files;
            }
            else
            {
                return null;
            }
        }

        //格式化日期格式
        public string fmartDate(string date)
        {
            date = date.Replace("年", "-");
            date = date.Replace("月", "-");
            date = date.Replace("日", "");
            return date;
        }

四、获取api返回的数据，输出到dataGridView中。

private void 识别发票ToolStripMenuItem_Click(object sender, EventArgs e)
        {
            if (this.listView1.Items.Count == 0)
            {
                MessageBox.Show("请先选择要识别的发票！", "消息提示", MessageBoxButtons.OKCancel, MessageBoxIcon.Exclamation);
                return;
            }

            Common.ShowProcessing("", this, (obj) =>
            {
                //这里采用委托的方式解决线程卡死问题
                this.Invoke(new Action(delegate
                {
                    foreach (ListViewItem item in this.listView1.Items)
                    {
                        try
                        {
                            var invoiceInfo = JsonConvert.DeserializeObject<dynamic>(vatInvoice(item.SubItems[0].Name));
                            var items = invoiceInfo.words_result;
                            if (items != null)
                            {
                                //写入数据表格
                                int index = this.dataGridView1.Rows.Add();
                                this.dataGridView1.Rows[index].Cells[0].Value = items.InvoiceType;
                                this.dataGridView1.Rows[index].Cells[1].Value = items.InvoiceCode;
                                this.dataGridView1.Rows[index].Cells[2].Value = items.InvoiceNum;
                                this.dataGridView1.Rows[index].Cells[3].Value = fmartDate((string)items.InvoiceDate);
                                this.dataGridView1.Rows[index].Cells[4].Value = items.SellerName;
                                this.dataGridView1.Rows[index].Cells[5].Value = items.SellerRegisterNum;
                                this.dataGridView1.Rows[index].Cells[6].Value = items.SellerAddress;
                                this.dataGridView1.Rows[index].Cells[7].Value = items.SellerBank;
                                this.dataGridView1.Rows[index].Cells[8].Value = Common.NumberToZero((string)items.TotalAmount);
                                this.dataGridView1.Rows[index].Cells[9].Value = "0";
                                if (Common.IsPropertyExist(items, "CommodityTaxRate"))
                                {
                                    if (!Common.IsNullOrEmpty(items.CommodityTaxRate[0].word))
                                    {
                                        this.dataGridView1.Rows[index].Cells[9].Value = Common.NumberToZero((string)items.CommodityTaxRate[0].word.ToString().Replace("%", ""));
                                    }
                                }
                                this.dataGridView1.Rows[index].Cells[10].Value = Common.NumberToZero((string)items.TotalTax);
                                this.dataGridView1.Rows[index].Cells[11].Value = items.AmountInFiguers;
                                this.dataGridView1.Rows[index].Cells[12].Value = items.InvoiceType.ToString().Contains("电子") ? "是" : "否";
                                this.dataGridView1.Rows[index].Cells[13].Value = items.PurchaserName;
                                this.dataGridView1.Rows[index].Cells[14].Value = "一般计税";
                                Application.DoEvents();
                                addMessage(item.SubItems[0].Text + " 识别完成！");
                            }
                            else
                            {
                                if (invoiceInfo.error_code != null)
                                {
                                    addMessage(item.SubItems[0].Text + " -->" + apiErrorMessage((string)invoiceInfo.error_code));
                                }
                            }
                        }
                        catch (Exception err)
                        {
                            addMessage(item.SubItems[0].Text + err.Message + " 识别出错，已跳过！");
                        }
                    }
                }));
                //这里写处理耗时的代码，代码处理完成则自动关闭该窗口
            }, null);

        }

五、导出发票明细到EXECL表格中。

private void 导出发票信息ToolStripMenuItem_Click(object sender, EventArgs e)
        {
            if (this.dataGridView1.Rows.Count == 0)
            {
                MessageBox.Show("发票列表信息为空，不能执行导出！", "消息提示", MessageBoxButtons.OKCancel, MessageBoxIcon.Exclamation);
                return;
            }

            string fileName = "";
            SaveFileDialog sfd = new SaveFileDialog();
            sfd.Filter = "导出发票Excel(*.xls)|*.xls";
            sfd.FileName = "发票明细 - " + DateTime.Now.ToString("yyyyMMddHHmmss");
            if (sfd.ShowDialog() == DialogResult.OK)
            {
                Common.ShowProcessing("正在导出，请稍候...", this, (obj) =>
                {
                    fileName = sfd.FileName;
                    HSSFWorkbook wb = new HSSFWorkbook();
                    ISheet sheet = wb.CreateSheet("sheet1");
                    int columnCount = dataGridView1.ColumnCount; //列数
                    int rowCount = dataGridView1.Rows.Count;      //行数
                    for (int i = 0; i < columnCount; i++)
                    {
                        sheet.SetColumnWidth(i, 15 * 256);
                    }
                    //报表标题
                    IRow row = sheet.CreateRow(0);
                    row.HeightInPoints = 25;
                    ICell cell = row.CreateCell(0);
                    cell.SetCellValue("发票信息台账");

                    ICellStyle style = wb.CreateCellStyle();

                    style.Alignment = NPOI.SS.UserModel.HorizontalAlignment.Center;
                    style.VerticalAlignment = NPOI.SS.UserModel.VerticalAlignment.Center;

                    style.BorderTop = NPOI.SS.UserModel.BorderStyle.Thin;
                    style.BorderRight = NPOI.SS.UserModel.BorderStyle.Thin;
                    style.BorderBottom = NPOI.SS.UserModel.BorderStyle.Thin;
                    style.BorderLeft = NPOI.SS.UserModel.BorderStyle.Thin;
                    style.FillBackgroundColor = HSSFColor.Black.Index;
                    style.FillForegroundColor = HSSFColor.White.Index;

                    IFont font = wb.CreateFont();
                    font.FontName = "微软雅黑";
                    font.FontHeightInPoints = 12;
                    font.Boldweight = 700;
                    style.SetFont(font);//将新的样式赋给单元格
                    cell.CellStyle = style;
                    sheet.AddMergedRegion(new CellRangeAddress(0, 0, 0, columnCount - 1));

                    //表头
                    IRow row1 = sheet.CreateRow(1);
                    row1.HeightInPoints = 20;

                    ICellStyle styleHead = wb.CreateCellStyle();
                    styleHead.Alignment = NPOI.SS.UserModel.HorizontalAlignment.Center;
                    styleHead.VerticalAlignment = NPOI.SS.UserModel.VerticalAlignment.Center;
                    styleHead.BorderTop = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleHead.BorderRight = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleHead.BorderBottom = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleHead.BorderLeft = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleHead.FillBackgroundColor = HSSFColor.Black.Index;
                    styleHead.FillForegroundColor = HSSFColor.White.Index;

                    IFont font2 = wb.CreateFont();
                    font2.FontName = "微软雅黑";
                    font2.FontHeightInPoints = 10;
                    font2.Boldweight = 500;
                    styleHead.SetFont(font2);//将新的样式赋给单元格

                    for (int i = 0; i < columnCount; i++)
                    {
                        ICell row1cell = row1.CreateCell(i);
                        row1cell.SetCellValue(dataGridView1.Columns[i].HeaderText.ToString());
                        row1cell.CellStyle = styleHead;
                    }

                    //明细行，从第三列开始
                    int rowindex = 2;
                    ICellStyle styleBody = wb.CreateCellStyle();
                    styleBody.Alignment = NPOI.SS.UserModel.HorizontalAlignment.Left;
                    styleBody.VerticalAlignment = NPOI.SS.UserModel.VerticalAlignment.Center;
                    styleBody.BorderTop = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleBody.BorderRight = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleBody.BorderBottom = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleBody.BorderLeft = NPOI.SS.UserModel.BorderStyle.Thin;
                    styleBody.FillBackgroundColor = HSSFColor.Black.Index;
                    styleBody.FillForegroundColor = HSSFColor.White.Index;

                    IFont font3 = wb.CreateFont();
                    font3.FontName = "微软雅黑";
                    font3.FontHeightInPoints = 9;
                    font3.Boldweight = 500;
                    styleBody.SetFont(font3);//将新的样式赋给单元格
                    for (int i = 0; i < rowCount; i++)
                    {
                        IRow datarow = sheet.CreateRow(rowindex);
                        datarow.Height = 300;
                        for (int j = 0; j < columnCount; j++)
                        {
                            ICell datacell_0 = datarow.CreateCell(j);
                            datacell_0.SetCellValue(this.dataGridView1.Rows[i].Cells[j].Value.ToString());
                            datacell_0.CellStyle = styleBody;
                        }
                        rowindex += 1;
                    }
                    // 转为字节数组
                    MemoryStream stream = new MemoryStream();
                    wb.Write(stream);
                    var buf = stream.ToArray();

                    //保存为Excel文件
                    using (FileStream fs = new FileStream(fileName, FileMode.Create, FileAccess.Write))
                    {
                        fs.Write(buf, 0, buf.Length);
                        fs.Flush();
                        MessageBox.Show("导出 EXECL 成功！", "消息提示");
                        addMessage("导出发票信息到Execl表完成！");
                    }
                }, null);
            }
        }

操作说明如下：

版权说明：
本网站凡注明“广州京杭原创”的皆为本站原创文章，如需转载请注明出处！
本网转载皆注明出处，遵循行业规范，如发现作品内容版权或其它问题的，请与我们联系处理！
欢迎扫描右侧微信二维码与我们联系。

·上一条：如何在C#的Winform开发时将txt文件导入RichTextBox中 | ·下一条：nginx?一个域名配置多个入口(端口)？