static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.Remover2 instance
Remover2 remover = new Remover2("demo", "demo");
// Mask removed text, which ultimately black out region
remover.MaskRemovedText = true;
// Load sample PDF document
remover.LoadDocumentFromFile(@"samplePDF_EmailSSN.pdf");
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(@"samplePDF_EmailSSN.pdf");
// Enable RegexSearch
textExtractor.RegexSearch = true;
// Set word matching options
textExtractor.WordMatchingMode = WordMatchingMode.None;
// Search SSN in format 202-55-0130
string regexPatternSSN = "[0-9]{3}-[0-9]{2}-[0-9]{4}";
// Search email Addresses
string regexPatternEmail = @"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,6}\b";
// Search results for SSN
ISearchResult[] searchResultsSSN = textExtractor.FindAll(0, regexPatternSSN, caseSensitive: false);
// Search results for Email
ISearchResult[] searchResultEmail = textExtractor.FindAll(0, regexPatternEmail, caseSensitive: false);
// Remove SSN result text objects find by SearchResults.
remover.AddTextToRemove(searchResultsSSN);
// Remove Email result text objects find by SearchResults.
remover.AddTextToRemove(searchResultEmail);
// Perform removal of specified objects
remover.PerformRemoval(@"result1.pdf");
}
// Open output file in default application
ProcessStartInfo processStartInfo = new ProcessStartInfo("result1.pdf");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
// Clean up.
remover.Dispose();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.Remover instance
Remover remover = new Remover("demo", "demo");
// Load sample PDF document
remover.LoadDocumentFromFile(@"sample1.pdf");
// Search Keyword
string SearchKeyword = "Martian dichotomy";
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(@"sample1.pdf");
// Set word matching options
textExtractor.WordMatchingMode = WordMatchingMode.None;
ISearchResult[] searchResults = textExtractor.FindAll(0, SearchKeyword, caseSensitive: false);
// Remove text objects find by SearchResults.
// NOTE: The removed text might be larger than the specified rectangle. Currently the Remover is unable
// to split PDF text objects.
remover.RemoveText(searchResults, @"result1.pdf");
}
// Open output file in default application
System.Diagnostics.Process.Start("result1.pdf");
// Clean up.
remover.Dispose();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.Remover2 instance
Remover2 remover = new Remover2("demo", "demo");
// Mask removed text, which ultimately black out region
remover.MaskRemovedText = true;
// Load sample PDF document
remover.LoadDocumentFromFile(@"samplePDF_SSNNo.pdf");
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(@"samplePDF_SSNNo.pdf");
// Search SSN in format 202-55-0130
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
string regexPattern = "[0-9]{3}-[0-9]{2}-[0-9]{4}";
// Enable RegexSearch
textExtractor.RegexSearch = true;
// Set word matching options
textExtractor.WordMatchingMode = WordMatchingMode.None;
// Search results
ISearchResult[] searchResults = textExtractor.FindAll(0, regexPattern, caseSensitive: false);
// Remove text objects find by SearchResults.
remover.AddTextToRemove(searchResults);
// Perform removal of specified objects
remover.PerformRemoval(@"result1.pdf");
}
// Open output file in default application
ProcessStartInfo processStartInfo = new ProcessStartInfo("result1.pdf");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
// Clean up.
remover.Dispose();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.Remover instance
Remover remover = new Remover("demo", "demo");
// Load sample PDF document
remover.LoadDocumentFromFile(@"samplePDF_SSNNo.pdf");
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(@"samplePDF_SSNNo.pdf");
// Search SSN in format 202-55-0130
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
string regexPattern = "[0-9]{3}-[0-9]{2}-[0-9]{4}";
// Enable RegexSearch
textExtractor.RegexSearch = true;
// Set word matching options
textExtractor.WordMatchingMode = WordMatchingMode.None;
ISearchResult[] searchResults = textExtractor.FindAll(0, regexPattern, caseSensitive: false);
// Remove text objects find by SearchResults.
// NOTE: The removed text might be larger than the specified rectangle. Currently the Remover is unable
// to split PDF text objects.
remover.RemoveText(searchResults, @"result1.pdf");
}
// Open output file in default application
ProcessStartInfo processStartInfo = new ProcessStartInfo("result1.pdf");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
// Clean up.
remover.Dispose();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.Remover instance
Remover remover = new Remover("demo", "demo");
// Load sample PDF document
remover.LoadDocumentFromFile(@"samplePDF_EmailAddress.pdf");
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(@"samplePDF_EmailAddress.pdf");
// Search email Addresses
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
string regexPattern = @"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,6}\b";
// Enable RegexSearch
textExtractor.RegexSearch = true;
// Set word matching options
textExtractor.WordMatchingMode = WordMatchingMode.None;
ISearchResult[] searchResults = textExtractor.FindAll(0, regexPattern, caseSensitive: false);
// Remove text objects find by SearchResults.
// NOTE: The removed text might be larger than the specified rectangle. Currently the Remover is unable
// to split PDF text objects.
remover.RemoveText(searchResults, @"result1.pdf");
}
// Open output file in default application
System.Diagnostics.Process.Start("result1.pdf");
// Clean up.
remover.Dispose();
}
private void BtnFindAll_Click(object sender, EventArgs e)
{
if (tbSearchExpression.Text.Length > 1)
{
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(pdfViewerControl1.InputFile);
// Set options from UI
textExtractor.RegexSearch = cbRegex.Checked;
textExtractor.WordMatchingMode = WordMatchingMode.None;
// Search for text in all pages and store rectangles of found pieces
for (int pageIndex = 0; pageIndex < textExtractor.GetPageCount(); pageIndex++)
{
ISearchResult[] searchResults = textExtractor.FindAll(pageIndex, tbSearchExpression.Text, caseSensitive: true);
if (searchResults.Length > 0)
{
_foundTextRectangles[pageIndex] = searchResults.Select(searchResult => searchResult.Bounds).ToArray();
}
}
}
// Select fount rectangles in PDF Viewer
if (_foundTextRectangles.ContainsKey(pdfViewerControl1.CurrentPageIndex))
{
pdfViewerControl1.SelectionInPoints = _foundTextRectangles[pdfViewerControl1.CurrentPageIndex];
}
}
else
{
MessageBox.Show(@"Try larger search string");
}
}
static void Main(string[] args)
{
MemoryStream searchablePDFStream = new MemoryStream();
// STEP-1: Make Searchable PDF
// STEP-2: Get search text result from that searchable PDF
// STEP-3: Remove sensitive data
// Create Bytescout.PDFExtractor.SearchablePDFMaker instance
using (var searchablePDFMaker = new SearchablePDFMaker("demo", "demo"))
{
// Load sample PDF document
searchablePDFMaker.LoadDocumentFromFile("sampleScannedPDF_EmailAddress.pdf");
// Set the location of language data files
searchablePDFMaker.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// Set OCR language
searchablePDFMaker.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Set PDF document rendering resolution
searchablePDFMaker.OCRResolution = 300;
// Save extracted text to file
searchablePDFMaker.MakePDFSearchable(searchablePDFStream);
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load stream into TextExtractor
textExtractor.LoadDocumentFromStream(searchablePDFStream);
// Search email Addresses
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
string regexPattern = @"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,6}\b";
// Enable RegexSearch
textExtractor.RegexSearch = true;
// Set word matching options
textExtractor.WordMatchingMode = WordMatchingMode.None;
ISearchResult[] searchResults = textExtractor.FindAll(0, regexPattern, caseSensitive: false);
// Create Bytescout.PDFExtractor.Remover instance
using (var remover = new Remover2("demo", "demo"))
{
// Load sample PDF document
remover.LoadDocumentFromStream(searchablePDFStream);
// Mask removed text
remover.MaskRemovedText = true;
// Make output file unsearchable
remover.MakePDFUnsearchable = true;
// Provide text to remove
remover.AddTextToRemove(searchResults);
// Remove text objects find by SearchResults.
remover.PerformRemoval("result1.pdf");
}
}
}
// Open output file in default application
ProcessStartInfo processStartInfo = new ProcessStartInfo("result1.pdf");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
string inputDocument = @".\samplePDF_SSNNo.pdf";
string outputDocument = @".\samplePDF_SSNNo_edited.pdf";
try
{
// Create Bytescout.PDFExtractor.TextExtractor instance
using (TextExtractor extractor = new TextExtractor("demo", "demo"))
{
// Create Bytescout.PDFExtractor.Remover2 instance
using (Remover2 remover = new Remover2("demo", "demo"))
{
// Load sample PDF document
extractor.LoadDocumentFromFile("samplePDF_SSNNo.pdf");
remover.LoadDocumentFromFile(inputDocument);
extractor.RegexSearch = true; // Enable the regular expressions
int pageCount = extractor.GetPageCount();
// Search through pages
for (int pageIndex = 0; pageIndex < pageCount; pageIndex++)
{
// Search SSN in format 202-55-0130 using regular expression.
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
string regexPattern = "[0-9]{3}-[0-9]{2}-[0-9]{4}";
// Search each page for the pattern
ISearchResult[] searchResults = extractor.FindAll(pageIndex, regexPattern, caseSensitive: false);
foreach (var element in searchResults)
{
Console.WriteLine("Found SSN No: " + element.Text);
// Add rectangle of the found SSN to Remover
remover.AddTextToRemove(pageIndex, element.Bounds);
}
}
// Mask replaced text with black rectangle
remover.MaskRemovedText = true;
// Change the color of the mask rectangle, if necessary
//remover.MaskColor = Color.Red;
remover.PerformRemoval(outputDocument);
Console.WriteLine("Found SSNs removed, result saved to file \"" + outputDocument + "\"");
}
}
// Open result file in default associated application (for the demonstration purpose)
var processStartInfo = new ProcessStartInfo(outputDocument)
{
UseShellExecute = true
};
Process.Start(processStartInfo);
}
catch (Exception ex)
{
Console.WriteLine("Error: " + ex.Message);
}
Console.WriteLine();
Console.WriteLine("Press enter key to continue...");
Console.ReadLine();
}
