static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\net2.00\tessdata";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Apply predefined profiles
extractor.Profiles = "scanned, no-layout";
// Extract text to file
extractor.SaveTextToFile("result1.txt");
extractor.Reset();
// Load another document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Load and apply custom profiles
extractor.LoadProfiles("profiles.json");
extractor.Profiles = "keep-formatting, ocr-forced-200dpi";
// Extract text to file
extractor.SaveTextToFile("result2.txt");
extractor.Dispose();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample_english_arabic.pdf");
// Enable Arabic (and other RTL languages) text detection
extractor.RTLTextAutoDetectionEnabled = true;
// Save extracted text to file
extractor.SaveTextToFile(@".\result.txt");
// Cleanup
extractor.Dispose();
// Open result file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\result.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main()
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Get PDF files
string[] pdfFiles = Directory.GetFiles(".", "*.pdf");
foreach (string file in pdfFiles)
{
// Load document
extractor.LoadDocumentFromFile(file);
// Save extracted text to .txt file
extractor.SaveTextToFile(Path.ChangeExtension(file, ".txt"));
// Reset the extractor before load another file
extractor.Reset();
}
// Cleanup
extractor.Dispose();
}
static void Main(string[] args)
{
// When processing huge PDF documents you may run into OutOfMemoryException.
// This example demonstrates a way to spare the memory by disabling page data caching.
// Create Bytescout.PDFExtractor.TextExtractor instance
using (TextExtractor extractor = new TextExtractor("demo", "demo"))
{
try
{
// Load sample PDF document
extractor.LoadDocumentFromFile("sample2.pdf");
// Disable page data caching, so processed pages wiil be disposed automatically
extractor.PageDataCaching = PageDataCaching.None;
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
}
catch (PDFExtractorException exception)
{
Console.Write(exception.ToString());
}
}
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
private static void ConvertPdfToTxt(object state)
{
// Get filename and event from params
string file = (string)((object[])state)[0];
ManualResetEvent doneEvent = (ManualResetEvent)((object[])state)[1];
string resultFileName = Path.GetFileName(file) + ".txt";
try
{
Console.WriteLine("Converting " + file);
using (TextExtractor extractor = new TextExtractor("demo", "demo"))
{
extractor.LoadDocumentFromFile(file);
extractor.SaveTextToFile(resultFileName);
}
Console.WriteLine("Finished " + resultFileName);
}
finally
{
// Signal the thread is finished
doneEvent.Set();
// Release semaphore
ThreadLimiter.Release();
}
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\DocumentWithWatermark.pdf");
// Filter text using text filter
extractor.AddFilter(@"^COPY$", caseSensitive: true, useRegex: true);
// Filter text using appearance filter
// extractor.AddFilter("Arial", fontSize: 203, exclude: true);
// Save extracted text to file
extractor.SaveTextToFile(@".\result.txt");
// Cleanup
extractor.Dispose();
// Open result file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\result.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\columns.pdf");
// Extract text by columns (useful if PDF document is designed in column layout like a newspaper)
extractor.ExtractColumnByColumn = true;
// Save extracted text to file
extractor.SaveTextToFile(@".\result.txt");
// Cleanup
extractor.Dispose();
// Open result file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\result.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Input file Url
var inputUrl = @"https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf";
// Get Input Stream
var inpStream = GetStreamFromUrl(inputUrl);
// Load sample PDF document
extractor.LoadDocumentFromStream(inpStream);
// Save extracted text to file
extractor.SaveTextToFile(@".\result.txt");
// Cleanup
extractor.Dispose();
// Open result file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\result.txt");
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
try
{
//Files
string fileName = "hindiText.pdf";
string destFileName = "extractedText.txt";
//Read all text from pdf file
using (TextExtractor extractor = new TextExtractor())
{
// Load PDF document
extractor.LoadDocumentFromFile(fileName);
//Option 1: Extract all text and write to destination file
extractor.SaveTextToFile(destFileName, encoding: Encoding.Unicode);
Console.WriteLine("All extracted text (hindi) written successfully to destination text file.");
//Option 2: Read all text to string variable
//string allText = extractor.GetText();
}
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of "tessdata" folder containing language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\Redistributable\net2.00\tessdata\";
// Set OCR language
extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in /tessdata
// Find more language files at https://github.com/tesseract-ocr/tessdata/tree/3.04.00
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// You can also apply various preprocessing filters
// to improve the recognition on low-quality scans.
// Automatically deskew skewed scans
//extractor.OCRImagePreprocessingFilters.AddDeskew();
// Repair broken letters
//extractor.OCRImagePreprocessingFilters.AddDilate();
// Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentations errors)
//extractor.OCRImagePreprocessingFilters.AddVerticalLinesRemover();
//extractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover();
// Remove noise
//extractor.OCRImagePreprocessingFilters.AddMedian();
// Apply Gamma Correction
//extractor.OCRImagePreprocessingFilters.AddGammaCorrection();
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
extractor.Dispose();
// Open output file in default associated application
System.Diagnostics.Process.Start("output.txt");
}
private static void ThreadProc(object stateInfo)
{
int threadIndex = (int)((object[])stateInfo)[0];
ManualResetEvent allFinishedEvent = (ManualResetEvent)((object[])stateInfo)[1];
string inputFile = (string)((object[])stateInfo)[2];
string outputFile = (string)((object[])stateInfo)[3];
int startPage = (int)((object[])stateInfo)[4];
int endPage = (int)((object[])stateInfo)[5];
try
{
Console.WriteLine("Thread #{0} started with the page range from {1} to {2}.", threadIndex, startPage, endPage);
Stopwatch stopwatch = Stopwatch.StartNew();
// Process the piece
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Set page separator. Default is '\f' (Form Feed)
textExtractor.PageSeparator = Environment.NewLine;
// Since we are only extracting text, disable the caching to reduce memory usage
textExtractor.PageDataCaching = PageDataCaching.None;
textExtractor.OCRMode = OCRMode.Auto;
textExtractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\net4.00\tessdata\";
textExtractor.OCRLanguage = "eng";
// 300 DPI resolution is recommended.
// Using of higher values will slow down the processing but does not guarantee the higher quality.
textExtractor.OCRResolution = 300;
textExtractor.LoadDocumentFromFile(inputFile);
textExtractor.SaveTextToFile(startPage, endPage, outputFile);
}
Console.WriteLine("Thread #{0} finished in {1}.", threadIndex, stopwatch.Elapsed);
}
finally
{
// If it was the last thread, signal the main thread about the finish.
if (Interlocked.Decrement(ref _runningThreadsCounter) == 0)
{
allFinishedEvent.Set();
}
// Release semaphore
_threadLimiter.Release();
}
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample2.pdf");
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
// Open output file in default associated application
System.Diagnostics.Process.Start("output.txt");
}
public MainWindow()
{
InitializeComponent();
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@"C:\Users\toky\Documents\Autogids_Autogids_20180131_008.pdf");
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
// Open output file in default associated application
System.Diagnostics.Process.Start("output.txt");
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample scanned document
extractor.LoadDocumentFromFile("InvoiceWithNoise.png");
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// Set OCR language
extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Find more language files at https://github.com/bytescout/ocrdata
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// Add profiles to fix issues with date.
// To deal with wrong V in dates you can use a regular expression. The following will replace only V characters which are located between numbers:
extractor.LoadProfiles("profiles.json");
extractor.Profiles = "ocr-dateIssue";
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// Set OCR language
extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Find more language files at https://github.com/bytescout/ocrdata
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// Enables max use of CPU and max use of multiple threads during OCR
extractor.OCRMaximizeCPUUtilization = true;
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample2.pdf");
// Save extracted text to file
extractor.SaveTextToFile(@".\result.txt");
// Cleanup
extractor.Dispose();
// Open result file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\result.txt");
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata\";
// Set OCR language
extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Find more language files at https://github.com/bytescout/ocrdata
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// You can also apply various preprocessing filters
// to improve the recognition on low-quality scans.
// Automatically deskew skewed scans
//extractor.OCRImagePreprocessingFilters.AddDeskew();
// Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentation errors)
//extractor.OCRImagePreprocessingFilters.AddVerticalLinesRemover();
//extractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover();
// Repair broken letters
//extractor.OCRImagePreprocessingFilters.AddDilate();
// Remove noise
//extractor.OCRImagePreprocessingFilters.AddMedian();
// Apply Gamma Correction
//extractor.OCRImagePreprocessingFilters.AddGammaCorrection();
// Add Contrast
//extractor.OCRImagePreprocessingFilters.AddContrast(20);
// (!) You can use new OCRAnalyser class to find an optimal set of image preprocessing
// filters for your specific document.
// See "OCR Analyser" example.
// Save extracted text to file
extractor.SaveTextToFile("output.txt");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Input document
string inputDocument = @".\sample_ocr.pdf";
// Document page index
int pageIndex = 0;
// Area of the document page to perform the analysis (optional).
// RectangleF.Empty means the full page.
RectangleF rectangle = RectangleF.Empty; // new RectangleF(100, 50, 350, 250);
// Location of language data files
string ocrLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata\";
// OCR language
string ocrLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Find more language files at https://github.com/bytescout/ocrdata
// Create OCRAnalyzer instance and activate it with your registration information
using (OCRAnalyzer ocrAnalyzer = new OCRAnalyzer("demo", "demo"))
{
// Display analysis progress
ocrAnalyzer.ProgressChanged += (object sender, string message, double progress, ref bool cancel) =>
{
Console.WriteLine(message);
};
// Load document to OCRAnalyzer
ocrAnalyzer.LoadDocumentFromFile(inputDocument);
// Setup OCRAnalyzer
ocrAnalyzer.OCRLanguage = ocrLanguage;
ocrAnalyzer.OCRLanguageDataFolder = ocrLanguageDataFolder;
// Set page area for analysis (optional)
ocrAnalyzer.SetExtractionArea(rectangle);
// Perform analysis and get results
OCRAnalysisResults analysisResults = ocrAnalyzer.AnalyzeByOCRConfidence(pageIndex);
// Now extract the text using detected OCR parameters
string outputDocument = @".\result.txt";
// Create TextExtractor instance
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document to TextExtractor
textExtractor.LoadDocumentFromFile(inputDocument);
// Setup TextExtractor
textExtractor.OCRMode = OCRMode.Auto;
textExtractor.OCRLanguageDataFolder = ocrLanguageDataFolder;
textExtractor.OCRLanguage = ocrLanguage;
// Apply analysis results to TextExtractor instance
ocrAnalyzer.ApplyResults(analysisResults, textExtractor);
// Set extraction area (optional)
textExtractor.SetExtractionArea(rectangle);
// Save extracted text to file
textExtractor.SaveTextToFile(outputDocument);
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo(outputDocument);
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
}
}
