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;
}
}
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);
}
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);
}
}
}
/// <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!");
}
}