private void btn_BrowserPDF_Click(object sender, EventArgs e)
{
if (string.IsNullOrEmpty(txt_BatchName.Text))
{
MessageBox.Show("Vui lòng điền tên batch", "Lỗi", MessageBoxButtons.OK, MessageBoxIcon.Warning);
return;
}
OpenFileDialog dlg = new OpenFileDialog();
dlg.Filter = "Types PDF|*.pdf";
dlg.Multiselect = false;
if (dlg.ShowDialog() == DialogResult.OK)
{
_lFileNames = dlg.FileNames;
txt_ImagePath.Text = Path.GetFullPath(dlg.FileName);
}
var f = new PdfFocus {
Serial = "1234567890"
};
string pdfFile = txt_ImagePath.Text;
f.OpenPdf(pdfFile);
TongSoTrang = f.PageCount;
lbl_Page.Text = TongSoTrang + " Pages";
}
public static bool FindTextInPdfFile(string fileFullPath, string text, ref CancellationTokenSource cts)
{
var pdfFocus = new PdfFocus();
try
{
pdfFocus.OpenPdf(fileFullPath);
if (pdfFocus.PageCount > 0)
{
for (var i = 1; i < pdfFocus.PageCount + 1; i++)
{
if (cts.IsCancellationRequested)
{
break;
}
if (pdfFocus.ToText(i, i).IndexOf(text, StringComparison.OrdinalIgnoreCase) >= 0)
{
pdfFocus.ClosePdf();
return(true);
}
}
}
}
catch (Exception)
{
return(false);
}
finally
{
pdfFocus.ClosePdf();
}
return(false);
}
/// <summary>
/// pdf生成xml
/// </summary>
/// <param name="pdfFile"></param>
/// <returns></returns>
public static bool PdfToXMLAsFiles(string pdfFile)
{
try
{
string pathToXml = Path.ChangeExtension(pdfFile, ".xml");
// Convert PDF file to XML file.
PdfFocus f = new PdfFocus();
// This property is necessary only for registered version.
// f.Serial = "XXXXXXXXXXX";
// Let's convert only tables to XML and skip all textual data.
f.XmlOptions.ConvertNonTabularDataToSpreadsheet = false;
f.OpenPdf(pdfFile);
if (f.PageCount > 0)
{
int result = f.ToXml(pathToXml);
if (result == 0)
{
//Show XML document in browser 选择直接打开
// Process.Start(new ProcessStartInfo(pathToXml) { UseShellExecute = true });
return(true);
}
}
}
catch (Exception e)
{
Console.WriteLine(e.ToString());
}
return(false);
}
/// <summary>
/// pdf生成excel
/// </summary>
/// <param name="pdfFile"></param>
/// <returns></returns>
public static void PdfToExcelAsFiles(string pdfFile)
{
try
{
string excelFile = Path.ChangeExtension(pdfFile, ".xls");
PdfFocus f = new PdfFocus();
// 'true' = Convert all data to spreadsheet (tabular and even textual).
// 'false' = Skip textual data and convert only tabular (tables) data.
f.ExcelOptions.ConvertNonTabularDataToSpreadsheet = false;
// 'true' = Preserve original page layout.
// 'false' = Place tables before text.
f.ExcelOptions.PreservePageLayout = true;
f.OpenPdf(pdfFile);
if (f.PageCount > 0)
{
f.ToExcel(excelFile);
}
}
catch (Exception e)
{
Console.WriteLine(e.ToString());
}
}
protected void Upload(object sender, EventArgs e)
{
lblMessage.Visible = true;
PdfFocus f = new PdfFocus();
f.OpenPdf(uplPDF.FileBytes);
Session["focus"] = f;
ShowPdf();
}
public static async Task ConvertPDFtoWord(TelegramBotClient bot, Message msg)
{
if (msg.Document.FileName.Contains(".pdf"))
{
string path = String.Format(@"TelegramBotIQ Users File\Convert\{0}.pdf", msg.Document.FileName);
string file_id = msg.Document.FileId;
try
{
using (var filestream = System.IO.File.OpenWrite(path))
{
var filedowload = await bot.GetInfoAndDownloadFileAsync(
fileId : file_id,
destination : filestream
);
}
}
catch (Exception ex)
{
Console.WriteLine($"Error: {ex}");
await bot.SendTextMessageAsync(msg.Chat.Id, "Возникла ошибка :(" + Environment.NewLine +
"Не беспокойтесь, разрабу дадим по шапке");
}
PdfFocus f = new PdfFocus();
string pathDocx = String.Format(@"TelegramBotIQ Users File\Convert\{0}.docx", msg.Document.FileName);
f.OpenPdf(path);
if (f.PageCount > 0)
{
await bot.SendTextMessageAsync(msg.Chat.Id, "Подождите, идет конвертирование!");
f.WordOptions.Format = PdfFocus.CWordOptions.eWordDocument.Docx;
f.ToWord(pathDocx);
}
FileStream fileStream = System.IO.File.OpenRead(pathDocx);
InputOnlineFile file = new InputOnlineFile(fileStream);
await bot.SendDocumentAsync(msg.Chat.Id, file, caption : "Конвертирование завершено!");
}
else
{
await bot.SendTextMessageAsync(msg.Chat.Id, "Файл имеет не верный формат");
return;
}
}
/// <summary>
/// Return pdf page as image
/// </summary>
/// <param name="filename">filename of pdf</param>
/// <param name="page">page of pdf</param>
/// <returns>Pdf page as a png image</returns>
public static Image GetPdfPageAsImage(string filename, int page)
{
var testDataDirectory = AppSettings.Get("TestDataDirectory");
var f = new PdfFocus();
f.OpenPdf($"{testDataDirectory}{filename}");
if (f.PageCount > page)
{
f.ImageOptions.Dpi = 300;
return(f.ToDrawingImage(page));
}
return(null);
}
public string ConvertPDFtoWord(string FilePath)
{
string SaveToFileLocation = Properties.Settings.Default.FolderPath + "PdfToWrod.docx";
PdfFocus pdfFocus = new PdfFocus();
PdfDocument pdfDoc = new PdfDocument();
pdfDoc.LoadFromFile(FilePath);
pdfDoc.SaveToFile(SaveToFileLocation, FileFormat.DOC);
//System.Diagnostics.Process.Start(SaveToFileLocation);
return(SaveToFileLocation);
}
protected bool IsPageInRange(int page)
{
if (Session["focus"] != null)
{
PdfFocus f = (PdfFocus)Session["focus"];
if (page > 0 && page <= f.PageCount)
{
return(true);
}
}
return(false);
}
public Stream getWordStream(Stream file)
{
PdfFocus f = new PdfFocus();
f.OpenPdf(file);
byte[] docx = null;
if (f.PageCount > 0)
{
docx = f.ToWord();
}
Stream stream = new MemoryStream(docx);
return(stream);
}
public PDFParser(string PDFLocation, int FromPage, int ToPage)
{
DirLocation = PDFLocation.Substring(0, PDFLocation.LastIndexOf("\\"));
if (File.Exists(Path.Combine(DirLocation, "final.bin")))
{
Console.WriteLine("Loading Existing Table");
LoadTable();
Console.WriteLine("Table Loaded");
return;
}
Console.WriteLine("Loading Parsers");
pdfFocus = new PdfFocus();
pdfFocus.OpenPdf(PDFLocation);
xlApp = new Application();
if (xlApp == null)
{
throw new Exception("Excel not installed!!");
}
// Creating Directories
string loc1 = Path.Combine(DirLocation, "Excel Files");
if (!Directory.Exists(loc1))
{
Directory.CreateDirectory(loc1);
}
// Initialize Pages
CompleteList = new Page[ToPage - FromPage + 1];
Page.PDFLocation = PDFLocation;
for (int i = FromPage; i <= ToPage; ++i)
{
CompleteList[i - FromPage] = new Page {
PageNumber = i
}
}
;
Console.WriteLine("Parsers Loaded");
}
/// <summary>
/// Save pdf pages as images
/// </summary>
/// <param name="filename">filename of pdf to save as images</param>
public static void SavePdfToImage(string filename)
{
var testDataDirectory = AppSettings.Get("TestDataDirectory");
var f = new PdfFocus();
f.OpenPdf($"{testDataDirectory}{filename}");
if (f.PageCount > 0)
{
f.ImageOptions.Dpi = 300;
for (var p = 1; p < f.PageCount + 1; p = p + 1)
{
var img = f.ToDrawingImage(p);
img.Save($"{testDataDirectory}{filename}.{p}.png");
}
}
}
/// <summary>
/// Converts multiple PDF files to HTML files.
/// </summary>
static void ConvertMultiplePdfToHtmls()
{
// Directory with *.pdf files.
string pdfDirectory = Path.GetFullPath(@"..\..\..\..\..\");
string[] pdfFiles = Directory.GetFiles(pdfDirectory, "*.pdf");
PdfFocus f = new PdfFocus();
// After purchasing the license, please insert your serial number here to activate the component:
//f.Serial = "123456789";
int success = 0;
int total = 0;
foreach (string pdfFile in pdfFiles)
{
Console.WriteLine("Converting {0} ...", Path.GetFileName(pdfFile));
f.OpenPdf(pdfFile);
total++;
if (f.PageCount > 0)
{
// Path (must exist) to a directory to store images after converting. Notice also to the property "ImageSubFolder".
f.HtmlOptions.ImageFolder = Path.GetDirectoryName(pdfFile);
// A folder (will be created by the component) without any drive letters, only the folder as "myfolder".
f.HtmlOptions.ImageSubFolder = String.Format("{0}_images", Path.GetFileNameWithoutExtension(pdfFile));
// We recommend to use PNG type for storing images.
f.HtmlOptions.ImageType = PdfFocus.CHtmlOptions.eHtmlImageType.Png;
// How to store images: Inside HTML document as base64 images or as linked separate image files.
f.HtmlOptions.IncludeImageInHtml = false;
string resultFile = Path.ChangeExtension(pdfFile, ".html");
if (f.ToHtml(resultFile) == 0)
{
success++;
}
}
}
// Show results:
Console.WriteLine("{0} of {1} files converted successfully!", success, total);
Console.WriteLine("Press any key ...");
Console.ReadLine();
// Open folder with HTML files after converting.
System.Diagnostics.Process.Start(pdfDirectory);
}
private string OpenPDF(string path) //метод конвертирования PDF
{
//Создания экземпляра класса для конвертации pdf в jpg
string txtFile = DirectoryTemporary + "textOCR.txt";
PdfFocus f = new PdfFocus();
f.OpenPdf(path);
Console.WriteLine($"Колличество страниц: {f.PageCount}");
if (f.PageCount > 0)
{
f.ImageOptions.ImageFormat = System.Drawing.Imaging.ImageFormat.Jpeg;
f.ImageOptions.Dpi = 300;
//Деление каждой страницы pdf на изображения
f.ToImage(DirectoryTemporary, "page");
}
using (FileStream fileStream = File.Open(txtFile, FileMode.Create))
{
using (StreamWriter strWrite = new StreamWriter(fileStream))
{
for (int i = 1; i < f.PageCount + 1; i++)
{
string pathPage = DirectoryTemporary + $"page{i}.jpg";
try
{
using (TesseractEngine engine = new TesseractEngine(@"tessdata", "rus", EngineMode.Default))
{
using (var img = Pix.LoadFromFile(pathPage))
{
using (var page = engine.Process(img))
{
Console.WriteLine("Качество скана: {0}", page.GetMeanConfidence());
var text = page.GetText();
strWrite.WriteLine($"{text}");
}
}
}
}
catch (Exception ex)
{
Console.WriteLine("Error: {0}", ex.Message);
}
}
}
}
return(txtFile);
}
/// <summary>
/// Load a scanned PDF document with help of Tesseract OCR (free OCR library) and save the result as DOCX document.
/// </summary>
static void LoadScannedPdf()
{
// Here we'll load a scanned PDF document (perform OCR) containing a text on English, Russian and Vietnamese.
// Next save the OCR result as a new DOCX document.
// First steps:
// 1. Download data files for English, Russian and Vietnamese languages.
// Please download the files: eng.traineddata, rus.traineddata and vie.traineddata.
// From here (good and fast): https://github.com/tesseract-ocr/tessdata_fast
// or (best and slow): https://github.com/tesseract-ocr/tessdata_best
// 2. Copy the files: eng.traineddata, rus.traineddata and vie.traineddata to
// the folder "tessdata" in the Project root.
// 3. Be sure that the folder "tessdata" also contains "pdf.ttf" file.
// Let's start:
string inpFile = @"..\..\scan.pdf";
string outFile = "Result.docx";
PdfFocus f = new PdfFocus();
f.OCROptions.Mode = PdfFocus.COCROptions.eOCRMode.AllImages;
f.OCROptions.Method += PerformOCRTesseract;
f.OpenPdf(inpFile);
bool result = false;
if (f.PageCount > 0)
{
result = f.ToWord(outFile) == 0;
}
// Open the result for demonstration purposes.
if (result)
{
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
else
{
Console.WriteLine("Conversion failed!");
}
}
private void UploadAndConvert()
{
openWordDoc.Title = "Open PDF file to convert";
openWordDoc.Filter = "PDF Files|*.pdf";
if (openWordDoc.ShowDialog() == DialogResult.OK)
{
PdfFocus pdfFocus = new PdfFocus();
pdfFocus.OpenPdf(openWordDoc.FileName);
saveWordDoc.Title = "Save Doc file";
saveWordDoc.Filter = "Word Files|*.docx";
if (saveWordDoc.ShowDialog() == DialogResult.OK)
{
pdfFocus.ToWord(saveWordDoc.FileName);
MessageBox.Show("Converted Successfully", "Info", MessageBoxButtons.OK, MessageBoxIcon.Information);
}
}
}
private void ConvertToTextPdfFocusButton_Click(object sender, EventArgs e)
{
var pdf = new PdfFocus();
var stopwatch = new Stopwatch();
stopwatch.Start();
pdf.OpenPdf(new MemoryStream(_binaryPdfFile));
stopwatch.Stop();
PdfFocusStatsDetails.Text = $"Load Pdf Binary: {stopwatch.Elapsed.Seconds} seconds\r\n\r\n";
stopwatch.Reset();
stopwatch.Start();
var text = pdf.ToText();
stopwatch.Stop();
PdfFocusStatsDetails.Text += $"Convert to Text: {stopwatch.Elapsed.Seconds} seconds";
ExtractedTextTextBox.Text = text;
File.WriteAllText(@"C:\Base64\PdfFocus.txt", text);
}
private void ShowPdf()
{
if (Session["focus"] != null)
{
PdfFocus f = (PdfFocus)Session["focus"];
if (f.PageCount > 0)
{
f.HtmlOptions.IncludeImageInHtml = true;
f.EmbeddedImagesFormat = PdfFocus.eImageFormat.Png;
int page = (int)Session["page"];
string html = f.ToHtml(page, page);
htmlLiteral.Text = html;
txtPage.Text = String.Format("Page {0} of {1}", page, f.PageCount);
}
}
}
/// <summary>
/// 将PDF文档转换为图片的方法
/// </summary>
/// <param name="pdfInputPath">PDF文件路径</param>
/// <param name="imageOutputPath">图片输出路径</param>
/// <param name="imageName">生成图片的名字</param>
/// <param name="startPageNum">从PDF文档的第几页开始转换</param>
/// <param name="endPageNum">从PDF文档的第几页开始停止转换</param>
/// <param name="imageFormat">设置所需图片格式</param>
/// <param name="definition">设置图片的清晰度，数字越大越清晰</param>
public static void ConvertPDF2Image(string pdfInputPath, string imageOutputPath,
string imageName, int startPageNum, int endPageNum, ImageFormat imageFormat, Definition definition)
{
PdfFocus pdfFocus = new PdfFocus();
pdfFocus.OpenPdf(pdfInputPath);
if (!Directory.Exists(imageOutputPath))
{
Directory.CreateDirectory(imageOutputPath);
}
// validate pageNum
if (startPageNum <= 0)
{
startPageNum = 1;
}
if (endPageNum > pdfFocus.PageCount)
{
endPageNum = pdfFocus.PageCount;
}
if (startPageNum > endPageNum)
{
int tempPageNum = startPageNum;
startPageNum = endPageNum;
endPageNum = startPageNum;
}
// start to convert each page
for (int i = startPageNum; i <= endPageNum; i++)
{
byte[] img = pdfFocus.ToImage(i);
using (FileStream fs1 = File.Create(imageOutputPath + imageName + i.ToString() + "." + imageFormat.ToString()))
{
fs1.Write(img, 0, img.Length);
}
}
pdfFocus.ClosePdf();
}
public static bool PdfToHtml(this FileInfo file, DirectoryInfo writeToDirectory, ILog logger, out FileInfo resultFile)
{
resultFile = null;
try
{
PdfFocus pdf = new PdfFocus();
pdf.OpenPdf(file.FullName);
string fileName = $"{Path.GetFileNameWithoutExtension(file.FullName)}.html";
resultFile = new FileInfo(Path.Combine(writeToDirectory.FullName, fileName));
if (resultFile.Exists)
{
resultFile = new FileInfo(resultFile.FullName.GetNextFileName());
}
pdf.ToHtml(resultFile.FullName);
return(true);
}
catch (Exception ex)
{
logger.Error("An exception occurred: {0}\r\n{1}", ex.Message, ex.StackTrace);
return(false);
}
}
private static Dictionary <string, string> GetFileContentsThroughSautin(string[] files)
{
Dictionary <string, string> contents = new Dictionary <string, string>();
foreach (var file in files)
{
string content = string.Empty;
PdfFocus f = new PdfFocus();
f.XmlOptions.ConvertNonTabularDataToSpreadsheet = true;
f.OpenPdf(file);
if (f.PageCount > 0)
{
content = f.ToXml();
}
contents.Add(file, content);
}
return(contents);
}
public static void ConvertToImg(string path, ref ProgressBar progressBar, ref double time, ref Label label)
{
//Stopwatch sw = new Stopwatch();
// sw.Start();
SautinSoft.PdfFocus f = new PdfFocus();
f.OpenPdf(path);
int pageCount = f.PageCount;
string prefixFilePath = "PDF\\";
f.ImageOptions.Dpi = 320;
Stopwatch sw = new Stopwatch();
Cutter.setMaximumAndStep(progressBar, f.PageCount * 2);
for (int i = 1; i <= f.PageCount; i++)
{
sw.Start();
f.ToImage(prefixFilePath + i.ToString() + ".jpeg", i);
sw.Stop();
time -= sw.ElapsedMilliseconds;
TimeCalc.MinuteSeconds(time, label);
sw.Reset();
}
f.ClosePdf();
for (int i = 1; i <= pageCount; i++)
{
sw.Start();
Cutter.Cut(prefixFilePath + i.ToString() + ".jpeg", i, progressBar);
sw.Stop();
time -= sw.ElapsedMilliseconds;
TimeCalc.MinuteSeconds(time, label);
sw.Reset();
}
}
private static long TimeCutPage(string fileName)
{
SautinSoft.PdfFocus f = new PdfFocus();
long timeFor1 = 0;
long timeFor2 = 0;
f.OpenPdf(fileName);
f.ImageOptions.Dpi = 320;
pages = f.PageCount;
sw.Start();
f.ToImage(prefixFilePath, 1);
sw.Stop();
timeFor1 = sw.ElapsedMilliseconds;
sw.Start();
f.ToImage(prefixFilePath, 2);
sw.Stop();
timeFor2 = sw.ElapsedMilliseconds;
long allTime = timeFor1 + ((timeFor2 - timeFor1) * (f.PageCount - 1));
f.ClosePdf();
timeForJpeg = allTime;
sw.Reset();
return(timeForJpeg);
}
public void ConvertPdfToExcel(string _PdfPath)
{
string _pathToExcel = System.IO.Path.ChangeExtension(_PdfPath, "xls");
SautinSoft.PdfFocus fs = new PdfFocus();
// 'true' = Convert all data to spreadsheet (tabular and even textual).
// 'false' = Skip textual data and convert only tabular (tables) data.
fs.ExcelOptions.ConvertNonTabularDataToSpreadsheet = true;
fs.ExcelOptions.PreservePageLayout = true;
fs.OpenPdf(_PdfPath);
if (fs.PageCount > 0)
{
int result = fs.ToExcel(_pathToExcel);
//Open a produced Excel workbook
if (result == 0)
{
System.Diagnostics.Process.Start(_pathToExcel);
}
}
}
/// <summary>
/// Converts multiple PDF files into a single HTML document.
/// </summary>
static void ConvertMultiplePdfToSingleHtml()
{
// Directory with *.pdf files.
string pdfDirectory = Path.GetFullPath(@"..\..\..\..\..\");
string htmlFile = Path.GetFullPath("Result.html");
string[] pdfFiles = Directory.GetFiles(pdfDirectory, "*.pdf");
// Here we'll keep our Html document.
StringBuilder singleHtml = new StringBuilder();
singleHtml.Append("<html><body>");
PdfFocus f = new PdfFocus();
//f.Serial = "123456789";
int success = 0;
int total = 0;
foreach (string pdfFile in pdfFiles)
{
Console.WriteLine("Converting {0} ...", Path.GetFileName(pdfFile));
f.OpenPdf(pdfFile);
total++;
if (f.PageCount > 0)
{
// Path (must exist) to a directory to store images after converting. Notice also to the property "ImageSubFolder".
f.HtmlOptions.ImageFolder = Path.GetDirectoryName(htmlFile);
// A folder (will be created by the component) without any drive letters, only the folder as "myfolder".
f.HtmlOptions.ImageSubFolder = "images";
// We recommend to use PNG type for storing images.
f.HtmlOptions.ImageType = PdfFocus.CHtmlOptions.eHtmlImageType.Png;
// How to store images: Inside HTML document as base64 images or as linked separate image files.
f.HtmlOptions.IncludeImageInHtml = false;
// Let's make our CSS inline to be able merge HTML documents without any problems.
f.HtmlOptions.InlineCSS = true;
// We need only contents of <body>...</body>.
f.HtmlOptions.ProduceOnlyHtmlBody = true;
string tempHtml = f.ToHtml();
if (!String.IsNullOrEmpty(tempHtml))
{
success++;
// Add tempHtml into a single HTML.
singleHtml.Append(tempHtml);
}
}
}
singleHtml.Append("</body></html>");
// Show results:
File.WriteAllText(htmlFile, singleHtml.ToString());
Console.WriteLine("{0} of {1} files converted and merged into {2}!", success, total, Path.GetFileName(htmlFile));
Console.WriteLine("Press any key ...");
Console.ReadLine();
// Open our single HTML document.
System.Diagnostics.Process.Start(htmlFile);
}
/// <summary>
/// How to convert all files to a single XLS file.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/from-customers-convert-pdf-docx-rtf-to-single-xls-workbook-net-csharp-vb.php
/// </remarks>
public static void ConvertToSingleXls()
{
// In this example we'll use not only Document .Net component, but also
// another SautinSoft 'component - PDF Focus .Net (to perform conversion from PDF to single xls workbook).
// First of all, please perform "Rebuild Solution" to restore PDF Focus .Net package from NuGet.
// Our steps:
// 1. Convert all RTF, DOCX, PDF files into a single PDF document. (by Document .Net).
// 2. Convert the single PDF into a single XLS workbook. (by PDF Focus .Net).
byte[] singlePdfBytes = null;
// This file we need only to show intermediate result.
string singlePdfFile = "Single.pdf";
string workingDir = @"..\..\";
string singleXlsFile = "Single.xls";
List <string> supportedFiles = new List <string>();
foreach (string file in Directory.GetFiles(workingDir, "*.*"))
{
string ext = Path.GetExtension(file).ToLower();
if (ext == ".pdf" || ext == ".docx" || ext == ".rtf")
{
supportedFiles.Add(file);
}
}
// Create single pdf.
DocumentCore singlePDF = new DocumentCore();
foreach (string file in supportedFiles)
{
DocumentCore dc = DocumentCore.Load(file);
Console.WriteLine("Adding: {0}...", Path.GetFileName(file));
// Create import session.
ImportSession session = new ImportSession(dc, singlePDF, StyleImportingMode.KeepSourceFormatting);
// Loop through all sections in the source document.
foreach (Section sourceSection in dc.Sections)
{
// Because we are copying a section from one document to another,
// it is required to import the Section into the destination document.
// This adjusts any document-specific references to styles, bookmarks, etc.
//
// Importing a element creates a copy of the original element, but the copy
// is ready to be inserted into the destination document.
Section importedSection = singlePDF.Import <Section>(sourceSection, true, session);
// First section start from new page.
if (dc.Sections.IndexOf(sourceSection) == 0)
{
importedSection.PageSetup.SectionStart = SectionStart.NewPage;
}
// Now the new section can be appended to the destination document.
singlePDF.Sections.Add(importedSection);
}
}
// Save our single document into PDF format in memory.
// Let's save our document to a MemoryStream.
using (MemoryStream Pdf = new MemoryStream())
{
singlePDF.Save(Pdf, new PdfSaveOptions()
{
Compliance = PdfCompliance.PDF_A1a
});
singlePdfBytes = Pdf.ToArray();
}
// Open the result for demonstration purposes.
File.WriteAllBytes(singlePdfFile, singlePdfBytes);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(singlePdfFile)
{
UseShellExecute = true
});
SautinSoft.PdfFocus f = new PdfFocus();
f.OpenPdf(singlePdfBytes);
if (f.PageCount > 0)
{
f.ToExcel(singleXlsFile);
}
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(singleXlsFile)
{
UseShellExecute = true
});
}
public ActionResult <bool> EvaluateStudents([FromBody] List <Evaluation> evaluations)
{
var dao = new EvaluationsDao();
Directory.CreateDirectory(STUDENT_ANS_SHEET_UPLOAD_PATH);
foreach (var e in evaluations)
{
Console.WriteLine("-------------------------------------------------------");
Console.WriteLine($"Student Id {e.Student.Id}");
Console.WriteLine($"DateTime {e.DateTime?.ToString("yyyy-MM-dd")}");
var date = e.DateTime?.ToString("yyyy_MM_dd");
var fileName = $"AnswerKey_Student_{e.Student.Id}_{e.Examination.Course.CourseCode}_{date}.pdf";
var filePath = Path.Combine(STUDENT_ANS_SHEET_UPLOAD_PATH, fileName);
var bytes = Convert.FromBase64String(e.AnswerSheet);
System.IO.File.WriteAllBytes(filePath, bytes);
Console.WriteLine("File Written");
var refSheetName =
e.Examination.ReferenceAnswerSheet.Substring(
e.Examination.ReferenceAnswerSheet.LastIndexOf("/") + 1);
var refSheetPath = Path.Combine(REFERENCE_ANS_SHEET_UPLOAD_PATH, refSheetName);
Console.WriteLine($"Ref Sheet Path = {refSheetPath}");
var studentPdf = new PdfFocus();
Console.WriteLine($"Opening Student Pdf...");
studentPdf.OpenPdf(filePath);
var studentAnsText = studentPdf.ToText();
Console.WriteLine("Student pdf read successfully!");
studentPdf.ClosePdf();
Console.WriteLine("Closing student pdf");
var refPdf = new PdfFocus();
Console.WriteLine("Opening reference pdf");
refPdf.OpenPdf(refSheetPath);
var refAnsText = refPdf.ToText();
Console.WriteLine("Reference pdf read successfully!");
refPdf.ClosePdf();
Console.WriteLine("Closing reference pdf");
paralleldots pd = new paralleldots("AliC73YnPPScR8dJJEMD8qxinhFTTUjFPmJGs5yknY0");
Console.WriteLine("Calculating score");
var similarity = pd.similarity(studentAnsText, refAnsText);
var json = JsonValue.Parse(similarity);
var score = double.Parse(json["normalized_score"].ToString());
Console.WriteLine($"Score = {score}");
var percent = score / 5.0;
Console.WriteLine($"Percentage = {percent}");
e.MarksObtained = (int?)(e.Examination.TotalMarks * percent);
e.AnswerSheet = $"/api/examinations/student-ans-sheet/get/{fileName}";
Console.WriteLine("Writing result to database");
dao.CreateEvaluation(e);
Console.WriteLine("Written Successfully!");
}
return(true);
}
/// <summary>
/// Converts multiple PDF files into a single HTML document.
/// </summary>
static void ConvertMultiplePdfToSingleHtml()
{
// Directory with *.pdf files.
string pdfDirectory = Path.GetFullPath(@"..\..\");
string htmlFile = "Result.html";
string[] pdfFiles = Directory.GetFiles(pdfDirectory, "*.pdf");
// Here we'll keep our Html document.
StringBuilder singleHtml = new StringBuilder();
singleHtml.Append("<html>\r\n<head>\r\n");
singleHtml.Append(@"<meta http-equiv = ""Content-Type"" content=""text/html; charset=utf-8"" />");
singleHtml.Append("\r\n</head>\r\n<body>");
PdfFocus f = new PdfFocus();
//f.Serial = "XXXXXXXXXXX";
int success = 0;
int total = 0;
foreach (string pdfFile in pdfFiles)
{
Console.WriteLine("Converting {0} ...", Path.GetFileName(pdfFile));
f.OpenPdf(pdfFile);
total++;
if (f.PageCount > 0)
{
// How to store images: Inside HTML document as base64 images or as linked separate image files.
f.HtmlOptions.IncludeImageInHtml = false;
// Create own subfolder for each converted file to store images separately and don't mix up them.
f.HtmlOptions.ImageSubFolder = String.Format("{0}_images", Path.GetFileNameWithoutExtension(pdfFile));
// A template name for images
f.HtmlOptions.ImageFileName = "picture";
// Auto - the same image format as in the source PDF;
// 'Jpeg' to make the document size less;
// 'PNG' to keep the highest quality, but the highest size too.
f.EmbeddedImagesFormat = PdfFocus.eImageFormat.Auto;
// Let's make our CSS inline to be able merge HTML documents without any problems.
f.HtmlOptions.InlineCSS = true;
// We need only contents of <body>...</body>.
f.HtmlOptions.ProduceOnlyHtmlBody = true;
string tempHtml = f.ToHtml();
if (!String.IsNullOrEmpty(tempHtml))
{
success++;
// Add tempHtml into a single HTML.
singleHtml.Append(tempHtml);
}
}
}
singleHtml.Append("</body></html>");
// Show results:
File.WriteAllText(htmlFile, singleHtml.ToString());
Console.WriteLine("{0} of {1} files converted and merged into {2}!", success, total, Path.GetFileName(htmlFile));
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(htmlFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Converts multiple PDF files to HTML files.
/// </summary>
static void ConvertMultiplePdfToHtmls()
{
// Directory with *.pdf files.
string pdfDirectory = Path.GetFullPath(@"..\..\");
string[] pdfFiles = Directory.GetFiles(pdfDirectory, "*.pdf");
DirectoryInfo htmlDirectory = new DirectoryInfo(@"htmls");
if (!htmlDirectory.Exists)
{
htmlDirectory.Create();
}
PdfFocus f = new PdfFocus();
// After purchasing the license, please insert your serial number here to activate the component:
//f.Serial = "XXXXXXXXXXX";
int success = 0;
int total = 0;
foreach (string pdfFile in pdfFiles)
{
Console.WriteLine("Converting {0} ...", Path.GetFileName(pdfFile));
f.OpenPdf(pdfFile);
total++;
if (f.PageCount > 0)
{
// Path (must exist) to a directory to store images after converting. Notice also to the property "ImageSubFolder".
f.HtmlOptions.ImageFolder = htmlDirectory.FullName;
// A folder (will be created by the component) without any drive letters, only the folder as "myfolder".
f.HtmlOptions.ImageSubFolder = String.Format("{0}_images", Path.GetFileNameWithoutExtension(pdfFile));
// A template name for images
f.HtmlOptions.ImageFileName = "picture";
// Auto - the same image format as in the source PDF;
// 'Jpeg' to make the document size less;
// 'PNG' to keep the highest quality, but the highest size too.
f.EmbeddedImagesFormat = PdfFocus.eImageFormat.Auto;
// How to store images: Inside HTML document as base64 images or as linked separate image files.
f.HtmlOptions.IncludeImageInHtml = false;
string htmlFile = Path.GetFileNameWithoutExtension(pdfFile) + ".html";
string htmlFilePath = Path.Combine(htmlDirectory.FullName, htmlFile);
if (f.ToHtml(htmlFilePath) == 0)
{
success++;
}
}
}
// Show results:
Console.WriteLine("{0} of {1} files converted successfully!", success, total);
// Open folder with HTML files after converting.
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(htmlDirectory.FullName)
{
UseShellExecute = true
});
}
private void ExtractImage()
{
int h = 1;
string[] ImageName = new string[TongSoTrang + 1];
foreach (DataGridViewRow dr in dataGridView1.Rows)
{
string temp = "";
string[] temp1 = null;
if (h < dataGridView1.RowCount)
{
temp = dr.Cells[2].Value != null ? dr.Cells[2].Value.ToString() : "";
if (temp.IndexOf(";", StringComparison.Ordinal) > 0)
{
temp1 = temp.Split(';');
for (int i = 0; i < temp1.Length; i++)
{
if (temp1[i].IndexOf("-", StringComparison.Ordinal) > 0)
{
string[] temp2 = temp1[i].Split('-');
for (int j = int.Parse(temp2[0]); j <= int.Parse(temp2[1]); j++)
{
ImageName[j] = dr.Cells[1].Value.ToString();
}
}
else
{
ImageName[int.Parse(temp1[i])] = dr.Cells[1].Value.ToString();
}
}
}
else
{
if (temp.IndexOf("-", StringComparison.Ordinal) > 0)
{
string[] temp2 = temp.Split('-');
for (int j = int.Parse(temp2[0]); j <= int.Parse(temp2[1]); j++)
{
ImageName[j] = dr.Cells[1].Value.ToString();
}
}
else
{
ImageName[int.Parse(temp)] = dr.Cells[1].Value.ToString();
}
}
}
h++;
}
var f = new PdfFocus {
Serial = "1234567890"
};
string pdfFile = txt_ImagePath.Text;
string imageDir = Path.GetDirectoryName(pdfFile);
List <PdfFocus.PdfImage> pdfImages = null;
f.OpenPdf(pdfFile);
if (f.PageCount > 0)
{
pdfImages = f.ExtractImages(1, f.PageCount);
// Show all extracted images.
if (pdfImages != null && pdfImages.Count > 0)
{
for (int i = 0; i < pdfImages.Count; i++)
{
string imageFile = Path.Combine(txt_FolderSaveImage.Text + "\\", ImageName[i + 1] + "_Page" + (i + 1) + ".jpg");
pdfImages[i].Picture.Save(imageFile);
}
}
}
}