static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XMLExtractor instance
XMLExtractor xmlExtractor = new XMLExtractor();
xmlExtractor.RegistrationName = "demo";
xmlExtractor.RegistrationKey = "demo";
// Create Bytescout.PDFExtractor.TableDetector instance
TableDetector tableDetector = new TableDetector();
tableDetector.RegistrationKey = "demo";
tableDetector.RegistrationName = "demo";
// 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 columns to 3
tableDetector.DetectionMinNumberOfRows = 3;
// Load sample PDF document
xmlExtractor.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 XML extractor to rectangle received from the table detector
xmlExtractor.SetExtractionArea(tableDetector.FoundTableLocation);
// Export the table to XML file
xmlExtractor.SavePageXMLToFile(i, "page-" + i + "-table-" + t + ".xml");
t++;
}while (tableDetector.FindNextTable()); // search next table
}
}
xmlExtractor.Dispose();
tableDetector.Dispose();
// Open first output file in default associated application (for demo purposes)
System.Diagnostics.Process.Start("page-0-table-1.xml");
}
static void Main()
{
// Create XMLExtractor instance
XMLExtractor extractor = new XMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("interactiveform.pdf");
// Get PDF document text as XML
string xmlText = extractor.GetXML();
// Load XML
XmlDocument xmlDocument = new XmlDocument();
xmlDocument.LoadXml(xmlText);
// Select all "control" nodes
XmlNodeList formControls = xmlDocument.SelectNodes("//control");
if (formControls != null)
{
foreach (XmlNode formControl in formControls)
{
XmlAttribute typeAttribute = formControl.Attributes["type"];
// Trace filled textboxes
if (typeAttribute.Value == "editbox")
{
if (!String.IsNullOrEmpty(formControl.InnerText))
{
Trace.WriteLine("EDITBOX " + formControl.Attributes["id"].Value + ": " + formControl.InnerText);
}
}
// Trace checked checkboxes
else if (typeAttribute.Value == "checkbox")
{
if (formControl.Attributes["state"].Value == "1")
{
Trace.WriteLine("CHECKBOX " + formControl.Attributes["id"].Value + ": " + formControl.Attributes["state"].Value);
}
}
}
}
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XMLExtractor instance
XMLExtractor extractor = new XMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
extractor.SaveXMLToFile("output.XML");
Console.WriteLine();
Console.WriteLine("Data has been extracted to 'output.XML' file.");
Console.WriteLine();
Console.WriteLine("Press any key to continue and open XML in default XML viewer...");
Console.ReadKey();
Process.Start("output.XML");
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XMLExtractor instance
XMLExtractor extractor = new XMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
extractor.SaveXMLToFile("output.XML");
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Data has been extracted to 'output.XML' file.");
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XMLExtractor instance
XMLExtractor extractor = new XMLExtractor();
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.SaveXMLToFile("output.xml");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.xml");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
private void PdfExtract(string fileToOpen)
{
// Create Bytescout.PDFExtractor.XMLExtractor instance
XMLExtractor extractor = new XMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(fileToOpen);
extractor.SaveXMLToFile("output.XML");
RoutesBoxList.Items.Add("Data has been extracted to 'output.XML' file.");
RoutesBoxList.Items.Add("Press any key to continue and open XML in default XML viewer)...");
Process.Start("output.XML");
}
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()
{
// Create XMLExtractor instance
XMLExtractor extractor = new XMLExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\filled_form.pdf");
// Get PDF document text as XML
string xmlText = extractor.GetXML();
// Load XML
XmlDocument xmlDocument = new XmlDocument();
xmlDocument.LoadXml(xmlText);
// Select all "control" nodes
XmlNodeList formControls = xmlDocument.SelectNodes("//control");
if (formControls != null)
{
foreach (XmlNode controlNode in formControls)
{
XmlAttribute typeAttribute = controlNode.Attributes["type"];
// Show textboxes
if (typeAttribute.Value == "editbox")
{
Console.WriteLine("EDITBOX:");
Console.WriteLine(" id = " + controlNode.Attributes["id"].Value);
Console.WriteLine(" text = " + controlNode.InnerText);
}
// Show checkboxes
else if (typeAttribute.Value == "checkbox")
{
Console.WriteLine("CHECKBOX:");
Console.WriteLine(" id = " + controlNode.Attributes["id"].Value);
Console.WriteLine(" state = " + controlNode.Attributes["state"].Value);
}
// Show radio-buttons
else if (typeAttribute.Value == "radiobutton")
{
Console.WriteLine("RADIOBUTTON:");
Console.WriteLine(" group = " + controlNode.Attributes["id"].Value);
Console.WriteLine(" state = " + controlNode.Attributes["state"].Value);
Console.WriteLine(" value = " + controlNode.InnerText);
}
// Show comboboxes
else if (typeAttribute.Value == "combobox")
{
Console.WriteLine("COMBOBOX:");
Console.WriteLine(" id = " + controlNode.Attributes["id"].Value);
// list items:
foreach (XmlNode valueNode in controlNode.SelectNodes("values/value"))
{
if (valueNode.Attributes["selected"]?.Value == "true")
{
Console.WriteLine(" value (selected) = " + valueNode.InnerText);
}
else
{
Console.WriteLine(" value = " + valueNode.InnerText);
}
}
}
// Show listboxes
else if (typeAttribute.Value == "listbox")
{
Console.WriteLine("LISTBOX:");
Console.WriteLine(" id = " + controlNode.Attributes["id"].Value);
// list items:
foreach (XmlNode valueNode in controlNode.SelectNodes("values/value"))
{
if (valueNode.Attributes["selected"]?.Value == "true")
{
Console.WriteLine(" value (selected) = " + valueNode.InnerText);
}
else
{
Console.WriteLine(" value = " + valueNode.InnerText);
}
}
}
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
