public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
string outputDocumentPath = "SaveAsBitonalTiff.tiff";
string outputPagePath = "SaveAsBitonalTiff_page0.tiff";
using (PdfDocument pdf = new PdfDocument(@"..\Sample Data\jfif3.pdf"))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.HorizontalResolution = 300;
options.VerticalResolution = 300;
// specify bitonal TIFF as the desired output compression
options.Compression = ImageCompressionOptions.CreateBitonalTiff();
// save one page
pdf.Pages[0].Save(outputPagePath, options);
// save the whole document as multipage TIFF
pdf.SaveAsTiff(outputDocumentPath, options);
}
Console.WriteLine($"The output is located in {Environment.CurrentDirectory}");
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
var documentText = new StringBuilder();
using (var pdf = new PdfDocument("Sample data/Freedman Scora.pdf"))
{
using (var engine = new TesseractEngine(@"tessdata", "eng", EngineMode.Default))
{
for (int i = 0; i < pdf.PageCount; ++i)
{
if (documentText.Length > 0)
{
documentText.Append("\r\n\r\n");
}
PdfPage page = pdf.Pages[i];
string searchableText = page.GetText();
// Simple check if the page contains searchable text.
// We do not need to do OCR in that case.
if (!string.IsNullOrEmpty(searchableText.Trim()))
{
documentText.Append(searchableText);
continue;
}
// Save PDF page as high-resolution image
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.HorizontalResolution = 600;
options.VerticalResolution = 600;
string pageImage = $"page_{i}.png";
page.Save(pageImage, options);
using (var img = Pix.LoadFromFile(pageImage))
{
using (var recognizedPage = engine.Process(img))
{
var recognizedText = recognizedPage.GetText();
Console.WriteLine($"Mean confidence for page #{i}: {recognizedPage.GetMeanConfidence()}");
documentText.Append(recognizedText);
}
}
}
}
const string Result = "result.txt";
using (var writer = new StreamWriter(Result))
writer.Write(documentText.ToString());
Process.Start(Result);
}
}
private static IEnumerable <RecognizedTextChunk> recognizeWords(PdfPage page, TesseractEngine engine,
int resolution, string tempFileName)
{
// Save PDF page as high-resolution image
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.HorizontalResolution = resolution;
options.VerticalResolution = resolution;
page.Save(tempFileName, options);
using (var img = Pix.LoadFromFile(tempFileName))
{
using (var recognizedPage = engine.Process(img))
{
using (ResultIterator iter = recognizedPage.GetIterator())
{
const PageIteratorLevel Level = PageIteratorLevel.Word;
iter.Begin();
do
{
if (iter.TryGetBoundingBox(Level, out Rect bounds))
{
string text = iter.GetText(Level);
float confidence = iter.GetConfidence(Level);
yield return(new RecognizedTextChunk(text, bounds, confidence));
}
} while (iter.Next(Level));
}
}
}
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
// In order to receive log messages from Docotic.Pdf into a log4net logger,
// you would need to configure log4net. Here is a simplest one-line
// way to configure it. You might use any other way described in the docs
// https://logging.apache.org/log4net/release/manual/configuration.html
log4net.Config.XmlConfigurator.Configure();
// The above line configures log4net using properties from app.config file.
// Take a look into the app.config file, it contains more comments.
// After log4net is configured, there is nothing else to do, the library
// will put its log messages into the configured loggers.
// The following code should produce log messages in console and in
// log-file.txt file next to application's exe file.
using (PdfDocument pdf = new PdfDocument(@"..\Sample Data\Attachments.pdf"))
{
using (MemoryStream ms = new MemoryStream())
pdf.Pages[0].Save(ms, PdfDrawOptions.Create());
}
}
/// <summary>
/// Распознать текст нечитаемого PDF-файла.
/// </summary>
/// <param name="page">Нечитаемая PDF-страница.</param>
/// <returns>Распознанный текст со страницы.</returns>
private static string RecognizePageText(PdfPage page)
{
var options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.HorizontalResolution = 200;
options.VerticalResolution = 200;
using var memoryStream = new MemoryStream();
page.Save(memoryStream, options);
using var engine = new TesseractEngine(@"tessdata\fast", "rus+eng", EngineMode.LstmOnly);
using var img = Pix.LoadFromMemory(memoryStream.GetBuffer());
using var recognizedPage = engine.Process(img);
return(recognizedPage.GetText());
}
private void printDocument_PrintPage(object sender, PrintPageEventArgs e)
{
Graphics gr = e.Graphics;
using (var stream = new MemoryStream())
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.HorizontalResolution = gr.DPI;
options.VerticalResolution = gr.DPI;
PdfPage page = m_pdf.Pages[m_printDocument.PrintSettings.SelectedPageRange.Start - 1 + e.CurrentPage];
page.Save(stream, options);
stream.Position = 0;
using (var bitmap = new Bitmap(stream))
gr.DrawImage(bitmap, 0, 0);
}
}
public static void PDFToImage(string path, string savePath, string extension)
{
// replace string.Empty with your license key
LicenseManager.AddLicenseData(LicenceKey);
using (PdfDocument pdf = new PdfDocument(path))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.Compression = ImageCompressionOptions.CreateJpeg();
var index = 1;
foreach (var pdfPage in pdf.Pages)
{
var fileName = savePath + "-" + index++ + extension;
pdfPage.Save(fileName, options);
}
}
}
static void Process(string file)
{
using (var pdfDocumentStream = File.OpenRead(file))
{
var document = new PdfDocument(pdfDocumentStream);
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
var images = document.GetImages();
int index = 0;
foreach (var page in document.Pages)
{
index++;
string imagePath = $@"C:\Users\goddi\Desktop\文档暂存\pdfimages\{ Path.GetFileName(file)}-{index}.jpg";
page.Save(new FileStream(imagePath, FileMode.Create), options);
}
}
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
string outputPath = "SaveAsTiff.tiff";
using (var pdf = new PdfDocument(@"Sample Data\jfif3.pdf"))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
pdf.SaveAsTiff(outputPath, options);
}
Process.Start(outputPath);
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
string outputPath = "SaveAsTiff.tiff";
using (PdfDocument pdf = new PdfDocument(@"..\Sample Data\jfif3.pdf"))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
pdf.SaveAsTiff(outputPath, options);
}
Console.WriteLine($"The output is located in {Environment.CurrentDirectory}");
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
string pathToImage = "SavePageAsImage.jpg";
using (PdfDocument pdf = new PdfDocument(@"Sample Data\jfif3.pdf"))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.Compression = ImageCompressionOptions.CreateJpeg();
pdf.Pages[1].Save(pathToImage, options);
}
Process.Start(pathToImage);
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
string pathToImage = "SavePageCustomResolution.png";
using (PdfDocument pdf = new PdfDocument(@"Sample Data\gmail-cheat-sheet.pdf"))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.HorizontalResolution = 600;
options.VerticalResolution = 600;
pdf.Pages[0].Save(pathToImage, options);
}
Process.Start(pathToImage);
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
// In order to receive log messages from Docotic.Pdf into a NLog logger,
// you would need to configure NLog. It is a common practice to put NLog
// configuration into app.config file.
// Take a look into the app.config file, it contains more comments.
// After NLog is configured, there is nothing else to do, the library
// will put its log messages into the configured loggers.
// The following code should produce log messages in console and in
// log-file.txt file next to application's exe file.
using (PdfDocument pdf = new PdfDocument(@"..\Sample Data\Attachments.pdf"))
{
using (MemoryStream ms = new MemoryStream())
pdf.Pages[0].Save(ms, PdfDrawOptions.Create());
}
}
private async Task <Stream> Inner()
{
var filename = "我的简历.pdf";
using (var pdfDocumentStream = File.OpenRead(filename))
{
var document = new PdfDocument(pdfDocumentStream);
var page = document.Pages[0];
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.Compression = ImageCompressionOptions.CreateJpeg();
double resolutionRate = page.Resolution / 200;
options.HorizontalResolution = 200;
options.VerticalResolution = 200;
var memoryStream = new MemoryStream();
{
page.Save(memoryStream, options);
}
memoryStream.Seek(0, SeekOrigin.Begin);
return(await Task.FromResult(memoryStream));
}
}
public static async Task <List <Stream> > PDFToImage(string path)
{
// replace string.Empty with your license key
LicenseManager.AddLicenseData(LicenceKey);
return(await Task.Run(() =>
{
var streamList = new List <Stream>();
using (PdfDocument pdf = new PdfDocument(path))
{
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.Compression = ImageCompressionOptions.CreateJpeg();
foreach (var page in pdf.Pages)
{
var outputStream = new MemoryStream();
page.Save(outputStream, options);
streamList.Add(outputStream);
}
}
return streamList;
}));
}
public static void Main()
{
// NOTE:
// When used in trial mode, the library imposes some restrictions.
// Please visit http://bitmiracle.com/pdf-library/trial-restrictions.aspx
// for more information.
var documentText = new StringBuilder();
using (var pdf = new PdfDocument(@"..\Sample data\Freedman Scora.pdf"))
{
var location = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location);
var tessData = Path.Combine(location, @"tessdata");
using (var engine = new TesseractEngine(tessData, "eng", EngineMode.LstmOnly))
{
for (int i = 0; i < pdf.PageCount; ++i)
{
if (documentText.Length > 0)
{
documentText.Append("\r\n\r\n");
}
PdfPage page = pdf.Pages[i];
string searchableText = page.GetText();
// Simple check if the page contains searchable text.
// We do not need to perform OCR in that case.
if (!string.IsNullOrEmpty(searchableText.Trim()))
{
documentText.Append(searchableText);
continue;
}
// This page is not searchable.
// Save PDF page as a high-resolution image.
PdfDrawOptions options = PdfDrawOptions.Create();
options.BackgroundColor = new PdfRgbColor(255, 255, 255);
options.HorizontalResolution = 200;
options.VerticalResolution = 200;
string pageImage = $"page_{i}.png";
page.Save(pageImage, options);
// Perform OCR
using (Pix img = Pix.LoadFromFile(pageImage))
{
using (Page recognizedPage = engine.Process(img))
{
Console.WriteLine($"Mean confidence for page #{i}: {recognizedPage.GetMeanConfidence()}");
string recognizedText = recognizedPage.GetText();
documentText.Append(recognizedText);
}
}
File.Delete(pageImage);
}
}
}
const string Result = "result.txt";
using (var writer = new StreamWriter(Result))
writer.Write(documentText.ToString());
Console.WriteLine($"The output is located in {Environment.CurrentDirectory}");
}