using iTextSharp.text; using iTextSharp.text.pdf; using iTextSharp.text.pdf.parser; using iWare_SCADA_BusinessLogical.Properties; using Newtonsoft.Json.Linq; using Spire.Additions.Xps.Schema; using Spire.Pdf; using System; using System.Collections.Generic; using System.Drawing; using System.IO; using System.Linq; using System.Runtime; using System.Text; using Resources = iWare_SCADA_BusinessLogical.Properties.Resources; namespace iWare_SCADA_BusinessLogical.Utils { /// /// 文件帮助 /// public class FileHelper { private static char[] base64CodeArray = new char[] { 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '+', '/', '=' }; /// /// 判断一个文件是否是图片 /// /// /// public static bool IsImage(string name) { var extension = System.IO.Path.GetExtension(name).ToLower(); var imageExtensions = new List { ".jpg", ".png", ".ico", ".tif", ".bmp", ".gif" }; return imageExtensions.Contains(extension); } /// /// 判断一个文件是否为pdf文件 /// /// /// public static bool IsPdf(string name) { var extension = System.IO.Path.GetExtension(name).ToLower(); var pdfExtensions = new List { ".pdf" }; return pdfExtensions.Contains(extension); } /// /// 将指定路径下的文件转为byte数组 /// /// 指定路径 /// public static byte[] GetBytesByFile(string path) { try { if (!File.Exists(path)) { return new byte[0]; } var fileInfo = new FileInfo(path); byte[] buff = new byte[fileInfo.Length]; var fileStream = fileInfo.OpenRead(); fileStream.Read(buff, 0, int.Parse(fileStream.Length.ToString())); fileStream.Close(); return buff; } catch (Exception ex) { LogTextHelper.WriteLog(Resources.LogDir, "FileHelper", "GetBytesByFile", ex.Message); return new byte[0]; } } /// /// 将指定路径下的图片转成base64字符串 /// /// /// public static string GetBase64Str(string path) { try { using (MemoryStream ms1 = new MemoryStream()) { var bmp1 = new Bitmap(path); bmp1.Save(ms1, System.Drawing.Imaging.ImageFormat.Jpeg); byte[] arr1 = new byte[ms1.Length]; ms1.Position = 0; ms1.Read(arr1, 0, (int)ms1.Length); ms1.Close(); bmp1.Dispose(); return Convert.ToBase64String(arr1); } } catch (Exception ex) { LogTextHelper.WriteLog(Resources.LogDir, "FileHelper", "GetBytesByFile", ex.Message); return null; } } public static string GetBase64Str(Bitmap bitMap) { try { using (MemoryStream ms1 = new MemoryStream()) { bitMap.Save(ms1, System.Drawing.Imaging.ImageFormat.Jpeg); byte[] arr1 = new byte[ms1.Length]; ms1.Position = 0; ms1.Read(arr1, 0, (int)ms1.Length); ms1.Close(); return Convert.ToBase64String(arr1); } } catch (Exception ex) { LogTextHelper.WriteLog(Resources.LogDir, "FileHelper", "GetBytesByFile", ex.Message); return null; } } /// /// 是否base64字符串 /// /// 要判断的字符串 /// 字符串转换成的字节数组 /// public static bool IsBase64(string base64Str, out byte[] bytes) { //string strRegex = "^([A-Za-z0-9+/]{4})*([A-Za-z0-9+/]{4}|[A-Za-z0-9+/]{3}=|[A-Za-z0-9+/]{2}==)$"; bytes = null; if (string.IsNullOrEmpty(base64Str)) return false; else { if (base64Str.Contains(",")) base64Str = base64Str.Split(',')[1]; if (base64Str.Length % 4 != 0) return false; if (base64Str.Any(c => !base64CodeArray.Contains(c))) return false; } try { bytes = Convert.FromBase64String(base64Str); return true; } catch (FormatException) { return false; } } /// /// 把base64字符串转换成Bitmap /// /// 要转换的base64字符串 /// public static Bitmap Base64ToBitmap(string base64Str) { Bitmap bitmap = null; byte[] bytes = null; try { if (IsBase64(base64Str, out bytes)) { using (MemoryStream stream = new MemoryStream(bytes)) { stream.Seek(0, SeekOrigin.Begin);//为了避免有时候流指针定位错误,显式定义一下指针位置 bitmap = new Bitmap(stream); } } } catch (Exception) { bitmap = null; } return bitmap; } /// /// 删除文件夹strDir中nDays天以前的文件 /// /// /// public static void DeleteOldFiles(string dir, int days) { try { if (!Directory.Exists(dir) || days < 1) return; var now = DateTime.Now; foreach (var f in Directory.GetFileSystemEntries(dir).Where(f => File.Exists(f))) { var t = File.GetCreationTime(f); var elapsedTicks = now.Ticks - t.Ticks; var elapsedSpan = new TimeSpan(elapsedTicks); if (elapsedSpan.TotalDays > days) File.Delete(f); } } catch (Exception) { // ignored } } /// /// serch new file /// /// public static System.Collections.IEnumerable DetectNewFilesCSV(string MonitorDicPath,int seconds,DateTime startTime,DateTime endTime) { FindFiles findFiles; string localpath = MonitorDicPath; findFiles = new FindFiles(); findFiles.SearchPath = localpath; findFiles.ReturnStringType = false; // findFiles.SearchPattern = "*.XML-1"; findFiles.SearchPattern = "*.csv"; findFiles.SearchForDirectory = false; findFiles.SearchForFile = true; //findFiles.SearchCreationTime = LastTime;//不等于时间 //findFiles.SearchCreationEndTime = DateTime.Now.AddMinutes(-5); //findFiles.SearchModifyTime = DateTimeHelper.GetDateTime().AddSeconds(-seconds);//不等于时间 findFiles.SearchModifyTime = startTime.AddSeconds(-seconds);//不等于时间 findFiles.SearchModifyEndTime = endTime; return findFiles; } /// /// serch new file /// /// /// /// *.csv /// /// /// public static System.Collections.IEnumerable DetectNewFiles(string MonitorDicPath, string SearchPattern, int seconds, DateTime startTime, DateTime endTime) { FindFiles findFiles; string localpath = MonitorDicPath; findFiles = new FindFiles(); findFiles.SearchPath = localpath; findFiles.ReturnStringType = false; // findFiles.SearchPattern = "*.XML-1"; findFiles.SearchPattern =string.IsNullOrEmpty(SearchPattern)?"*.csv": SearchPattern; findFiles.SearchForDirectory = false; findFiles.SearchForFile = true; //findFiles.SearchCreationTime = LastTime;//不等于时间 //findFiles.SearchCreationEndTime = DateTime.Now.AddMinutes(-5); //findFiles.SearchModifyTime = DateTimeHelper.GetDateTime().AddSeconds(-seconds);//不等于时间 findFiles.SearchModifyTime = startTime.AddSeconds(-seconds);//不等于时间 findFiles.SearchModifyEndTime = endTime; return findFiles; } //public static string[] ReadPdf(string path) //{ // PdfReader pdfreader = new PdfReader(path); // string text = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfreader, 1); // string[] words = text.Split('\n'); // pdfreader.Close(); // return words; //} public static string ReadPdfFileForSpire(string fileName, string getPdfValue) { try { //FreeSpire读取PDF PdfReader reader = new PdfReader(fileName); int iPageNum = reader.NumberOfPages; //if (iPageNum <= 10)//Spire超过10页的会出问题 //{ //实例化pdfdocment对象 Spire.Pdf.PdfDocument doc = new Spire.Pdf.PdfDocument(); //加载pdf文件 doc.LoadFromFile(fileName); //实例化一个StringBuilder 对象 StringBuilder content = new StringBuilder(); //提取PDF所有页面的文本 foreach (PdfPageBase page in doc.Pages) { content.Append(page.ExtractText()); } var text = content.ToString(); string[] words = text.Split('\n'); if (getPdfValue.Equals("Result")) { var list = words[0].Split(' '); //取第一行最后一个值就是质量结果 var Result = list[list.Length - 1].Replace("\r", ""); return Result; } //} foreach (var item in words) { if (item.Contains(getPdfValue)) { string[] splitValue = item.Split(':'); if (splitValue.Count() > 1) { var spectlist= splitValue[1].Trim().Split(' '); return spectlist[0].Trim(); } } } } catch(Exception ex) { } return ""; } public static string ReadPdfConntent(string filePath, string getPdfValue) { List lst = new List(); try { string pdffilename = filePath; PdfReader pdfreader = new PdfReader(pdffilename); PdfReader.unethicalreading = true; int numberOfPages = pdfreader.NumberOfPages; //for (int i = 1; i <= numberOfPages; ++i) //{ // lst.Add(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfreader,i)); // text.AppendLine(); //} var pdfReader = new PdfReader(pdffilename); StreamWriter output = new StreamWriter(new FileStream("处理结果.txt", FileMode.Create)); int pageCount = pdfReader.NumberOfPages; for (int pg = 1; pg <= pageCount; pg++) { ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy(); var value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy); value = value.Replace(" ", ""); Console.WriteLine(value); output.Write(value); } output.Flush(); output.Close(); string text = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfreader, 1); string[] words = text.Split('\n'); foreach (var item in words) { string value = Encoding.UTF8.GetString(Encoding.UTF8.GetBytes(item)); if (value.Contains(getPdfValue)) { string[] splitValue = value.Split(':'); lst.Add(splitValue[1].Trim()); } } pdfreader.Close(); return lst.First(); } catch (Exception ex) { throw ex; } } } }