protected void Page_Load(object sender, EventArgs e)
{
String inputFile = Server.MapPath(@".\bin\columns.pdf");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
// Get dimensions of the first document page
RectangleF rectangle = extractor.GetPageRectangle(0);
// Get text from the 1/3 of the page
rectangle.Width = rectangle.Width / 3f;
Response.Clear();
Response.ContentType = "text/html";
extractor.SetExtractionArea(rectangle);
Response.Write("<pre>");
// Save extracted text to output stream
extractor.SavePageTextToStream(0, Response.OutputStream);
Response.Write("</pre>");
Response.End();
}
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");
int pageCount = extractor.GetPageCount();
// Search each page for some keyword
for (int i = 0; i < pageCount; i++)
{
if (extractor.Find(i, "References", false))
{
// If page contains the keyword, extract a text from it.
// For demonstration we'll extract the text from top part of the page only
extractor.SetExtractionArea(0, 0, 600, 200);
string text = extractor.GetTextFromPage(i);
Console.WriteLine(text);
}
}
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
private void btnGetData_Click(object sender, EventArgs e)
{
StringBuilder result = new StringBuilder();
RectangleF[] selection = pdfViewerControl1.SelectionInPoints;
using (TextExtractor extractor = new TextExtractor())
{
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
extractor.LoadDocumentFromFile(pdfViewerControl1.InputFile);
extractor.OCRMode = OCRMode.Auto;
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
extractor.OCRResolution = 300;
for (int i = 0; i < selection.Length; i++)
{
extractor.SetExtractionArea(selection[i]);
result.AppendLine(_dataLabels[i]);
result.AppendLine(extractor.GetText(pdfViewerControl1.CurrentPageIndex, pdfViewerControl1.CurrentPageIndex));
result.AppendLine();
}
}
MessageBox.Show(result.ToString());
}
//public string ReadFromPositionSpire()
//{
// PdfPageBase page = Document.Pages[0];
// string text = page.ExtractText(new RectangleF(50, 50, 500, 100));
// StringBuilder sb = new StringBuilder();
// sb.AppendLine(text);
// return sb.ToString();
// return string.Empty;
//}
public string BytescoutPDFExtractor(string path)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
path = @"C:\Users\zulfiqar\Downloads\ExpenseClaimForm1_b2abe30fabca4b1ca322fafd74306ceb (1).pdf";
// load the document
extractor.LoadDocumentFromFile(path);
// get page count
//int pageCount = extractor.GetPageCount();
//int count = 0;
// iterate through pages
// define rectangle location to extract from
RectangleF location = new RectangleF(0, 0, 200, 200);
// set extraction area
extractor.SetExtractionArea(location);
// extract text bounded by the extraction area
string extractedString = extractor.GetTextFromPage(0);
return(extractedString);
}
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");
// read width of the very first page (zero index)
float pageWidth = extractor.GetPageRect_Width(0);
float pageHeight = extractor.GetPageRect_Height(0);
// now we are extracting content assuming we have 3 columns
// equally distributed on pages
// first calculate the width of the one column by dividing page width by number of columns (3)
float columnWidth = pageWidth / 3f;
// iterate through 3 columns
for (int i = 0; i < 3; i++)
{
// set the extraction area to the #i column
extractor.SetExtractionArea(i * columnWidth, 0, columnWidth, pageHeight);
string outFileName = "columns-column" + i + ".txt";
extractor.SavePageTextToFile(0, outFileName);
// Open output file in default associated application
System.Diagnostics.Process.Start(outFileName);
}
}
/// <summary>
/// Get text from particular region
/// </summary>
private static string GetTextFromRegion(TextExtractor textExtractor, RectangleF extractionRegion, int pageIndex = 0)
{
// Set Extraction Area
textExtractor.SetExtractionArea(extractionRegion);
// Get Text from that region
return(textExtractor.GetTextFromPage(pageIndex));
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor textExtractor = new TextExtractor();
textExtractor.RegistrationName = "demo";
textExtractor.RegistrationKey = "demo";
// Create Bytescout.PDFExtractor.TableDetector instance
TableDetector tableDetector = new TableDetector();
tableDetector.RegistrationKey = "demo";
tableDetector.RegistrationName = "demo";
// Set table detection mode to "bordered tables" - best for tables with closed solid borders.
tableDetector.ColumnDetectionMode = ColumnDetectionMode.BorderedTables;
// We should define what kind of tables we should detect.
// So we set min required number of columns to 3 ...
tableDetector.DetectionMinNumberOfColumns = 3;
// ... and we set min required number of rows to 3
tableDetector.DetectionMinNumberOfRows = 3;
// Load sample PDF document
textExtractor.LoadDocumentFromFile(@".\sample3.pdf");
tableDetector.LoadDocumentFromFile(@".\sample3.pdf");
// Get page count
int pageCount = tableDetector.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
int t = 1;
// Find first table and continue if found
if (tableDetector.FindTable(i))
{
do
{
// Set extraction area for CSV extractor to rectangle received from the table detector
textExtractor.SetExtractionArea(tableDetector.FoundTableLocation);
// Export the table to TEXT file
textExtractor.SavePageTextToFile(i, "page-" + i + "-table-" + t + ".txt");
t++;
}while (tableDetector.FindNextTable()); // search next table
}
}
// Cleanup
textExtractor.Dispose();
tableDetector.Dispose();
// Open first output file in default associated application (for demo purposes)
ProcessStartInfo processStartInfo = new ProcessStartInfo("page-0-table-1.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
private void btnRunOCR_Click(object sender, EventArgs e)
{
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(pdfViewerControl1.InputFile);
// 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\net4.00\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;
// Set the extraction area to the viewer's selection rectangle
RectangleF[] selection = pdfViewerControl1.SelectionInPoints;
if (selection.Length > 0)
{
extractor.SetExtractionArea(selection[0]);
}
// Show wait cursor
Cursor = Cursors.WaitCursor;
try
{
// Perform OCR and save result to file
extractor.SavePageTextToFile(pdfViewerControl1.CurrentPageIndex, "result.txt");
}
finally
{
// Revert cursor to default
Cursor = Cursors.Default;
}
// Cleanup
extractor.Dispose();
// Open output file in default associated application
System.Diagnostics.Process.Start("result.txt");
}
protected void Page_Load(object sender, EventArgs e)
{
// This test file will be copied to the project directory on the pre-build event (see the project properties).
String inputFile = Server.MapPath("columns.pdf");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
// read width of the very first page (zero index)
float pageWidth = extractor.GetPageRect_Width(0);
float pageHeight = extractor.GetPageRect_Height(0);
// now we are extracting content assuming we have 3 columns
// equally distributed on pages
// first calculate the width of the one column by dividing page width by number of columns (3)
float columnWidth = pageWidth / 3f;
Response.Clear();
Response.ContentType = "text/html";
// iterate through 3 columns
for (int i = 0; i < 3; i++)
{
// set the extraction area to the #i column
extractor.SetExtractionArea(i * columnWidth, 0, columnWidth, pageHeight);
// Save extracted text to output stream
extractor.SavePageTextToStream(0, Response.OutputStream);
}
Response.End();
}
static void Main(string[] args)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
// Load document
extractor.LoadDocumentFromFile(@".\sample2.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
// Iterate through pages
for (int i = 0; i < pageCount; i++)
{
// Define rectangle location to extract from
RectangleF location = new RectangleF(0, 0, 200, 200);
// Set extraction area
extractor.SetExtractionArea(location);
// Extract text from the extraction area
string text = extractor.GetTextFromPage(i);
Console.WriteLine("Extracted from page #" + i + ":");
Console.WriteLine();
Console.WriteLine(text);
// Reset the extraction area
extractor.ResetExtractionArea();
Console.WriteLine();
}
// Cleanup
extractor.Dispose();
Console.WriteLine("Press any key to exit...");
Console.ReadKey();
}
static void Main(string[] args)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
// load the document
extractor.LoadDocumentFromFile("../../sample2.pdf");
// get page count
int pageCount = extractor.GetPageCount();
int count = 0;
// iterate through pages
for (int i = 0; i < pageCount; i++)
{
// define rectangle location to extract from
RectangleF location = new RectangleF(0, 0, 200, 200);
// set extraction area
extractor.SetExtractionArea(location);
// extract text bounded by the extraction area
string extractedString = extractor.GetTextFromPage(i);
Console.WriteLine("Extracted from page #" + i + ":\r\n" + extractedString);
// reset extraction area to full page (by default)
extractor.ResetExtractionArea();
Console.WriteLine("\r\n");
}
Console.WriteLine("Press any key to exit...");
Console.ReadKey();
}
static void Main(string[] args)
{
// Create TextExtractor instance
TextExtractor textExtractor = new TextExtractor("demo", "demo");
textExtractor.WordMatchingMode = WordMatchingMode.ExactMatch; // Set exact search (default is SmartSearch that works like in Adobe Reader)
// Create XMLExtractor instance
XMLExtractor xmlExtractor = new XMLExtractor("demo", "demo");
// Load document
textExtractor.LoadDocumentFromFile("Invoice.pdf");
xmlExtractor.LoadDocumentFromFile("Invoice.pdf");
// Results
string invoiceNo = string.Empty;
string invoiceDate = string.Empty;
string total = string.Empty;
string tableData = string.Empty;
// Iterate pages
for (int i = 0; i < textExtractor.GetPageCount(); i++)
{
RectangleF pageRectangle = textExtractor.GetPageRectangle(i);
RectangleF tableRect = new RectangleF(0, 0, pageRectangle.Width, 0);
// Search for "Invoice No."
if (textExtractor.Find(i, "Invoice No.", false))
{
// Get the found text rectangle
RectangleF textRect = textExtractor.FoundText.Bounds;
// Assume the text at right is the invoice number.
// Shift the rectangle to the right:
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
// Set the extraction region and extract the text
textExtractor.SetExtractionArea(textRect);
invoiceNo = textExtractor.GetTextFromPage(i).Trim();
}
// Search for "Invoice Date" and extract text at right
if (textExtractor.Find(i, "Invoice Date", false))
{
RectangleF textRect = textExtractor.FoundText.Bounds;
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
textExtractor.SetExtractionArea(textRect);
invoiceDate = textExtractor.GetTextFromPage(i).Trim();
}
// Search for "Quantity" keyword to detect the top of the tabular data rectangle
if (textExtractor.Find(i, "Quantity", false))
{
// Keep the top table coordinate
tableRect.Y = textExtractor.FoundText.Bounds.Top; // use textRect.Bottom if you want to skip column headers
}
// Search for "TOTAL" (it will be also the bottom of tabular data rectangle)
if (textExtractor.Find(i, "TOTAL", true /* case sensitive! */))
{
RectangleF textRect = textExtractor.FoundText.Bounds;
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
textExtractor.SetExtractionArea(textRect);
total = textExtractor.GetTextFromPage(i).Trim();
// Calculate the table height
tableRect.Height = textRect.Top - tableRect.Top;
}
// Extract tabular data using XMLExtractor
if (tableRect.Height > 0)
{
xmlExtractor.SetExtractionArea(tableRect);
tableData = xmlExtractor.GetXMLFromPage(i);
}
}
// Display extracted data
Console.WriteLine("Invoice No.: " + invoiceNo);
Console.WriteLine("Invoice Date: " + invoiceDate);
Console.WriteLine("TOTAL: " + total);
Console.WriteLine("Table Data: ");
Console.WriteLine(tableData);
Console.WriteLine("Press any key...");
Console.ReadKey();
}
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);
}
}
}
