How to Search in PDF Using C#

search-in-pdf-using-csharp.md

Learn How to Search in PDF Using C#

search-in-pdf-using-csharp_case.cs

// Load the PDF file
Document pdfDocument = new Document("sample.pdf");

// Create a text absorber with a case-insensitive regular expression
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("(?i)INVOICE");

// Set text search options to enable regular expression usage
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textFragmentAbsorber.TextSearchOptions = textSearchOptions;

// Apply the absorber to all pages
pdfDocument.Pages.Accept(textFragmentAbsorber);

// Retrieve the matched text fragments
TextFragmentCollection textFragments = textFragmentAbsorber.TextFragments;

// Output the number of matches found
Console.WriteLine($"Found {textFragments.Count} instance(s) of the keyword.");

// Loop through and display each found text fragment
foreach (TextFragment fragment in textFragments)
{
    Console.WriteLine($"Text: {fragment.Text} | Page: {fragment.Page.Number}");
}

search-in-pdf-using-csharp_get.cs

// Load PDF and search for text
Document pdfDocument = new Document("sample.pdf");
TextFragmentAbsorber absorber = new TextFragmentAbsorber("invoice");
pdfDocument.Pages.Accept(absorber);

// Get matched fragments
TextFragmentCollection fragments = absorber.TextFragments;

// Print position and text for each match
foreach (TextFragment fragment in fragments)
{
    Console.WriteLine($"Text: {fragment.Text}");
    Console.WriteLine($"Page: {fragment.Page.Number}");
    Console.WriteLine($"Position - X: {fragment.Position.XIndent}, Y: {fragment.Position.YIndent}");
    Console.WriteLine($"Font: {fragment.TextState.Font.FontName}, Size: {fragment.TextState.FontSize}");
    Console.WriteLine("------------");
}

search-in-pdf-using-csharp_re.cs

// Load PDF and search for text
Document pdfDocument = new Document("sample.pdf");

// Enable regex in search options
TextSearchOptions searchOptions = new TextSearchOptions(true)
{
    IsRegularExpressionUsed = true
};

// Create absorber with date pattern
TextFragmentAbsorber absorber = new TextFragmentAbsorber(@"\d{2}/\d{2}/\d{4}", searchOptions);

// Apply absorber to pages
pdfDocument.Pages.Accept(absorber);

// Loop and print found patterns
foreach (TextFragment fragment in absorber.TextFragments)
{
    Console.WriteLine($"Found date: {fragment.Text} on Page {fragment.Page.Number}");
}

search-in-pdf-using-csharp_redact.cs

// Load PDF and search for text
Document pdfDocument = new Document("sample.pdf");

// Search for the name "John Doe"
TextFragmentAbsorber absorber = new TextFragmentAbsorber("John Doe");
pdfDocument.Pages.Accept(absorber);

// Loop through found fragments and redact
foreach (TextFragment fragment in absorber.TextFragments)
{
    // Get position and dimensions
    Aspose.Pdf.Rectangle rect = new Aspose.Pdf.Rectangle(
        fragment.Position.XIndent,
        fragment.Position.YIndent,
        fragment.Position.XIndent + fragment.Rectangle.Width,
        fragment.Position.YIndent + fragment.Rectangle.Height
    );

    // Create a redaction annotation
    RedactionAnnotation redaction = new RedactionAnnotation(fragment.Page, rect)
    {
        FillColor = Color.Black,
        Color = Color.Black
    };

    // Add and apply redaction
    fragment.Page.Annotations.Add(redaction);
    redaction.Redact();
}
// Save the modified document
pdfDocument.Save("SearchAndRedact.pdf");

search-in-pdf-using-csharp_text.cs

// Load the PDF file
Document pdfDocument = new Document("sample.pdf");

// Create a text absorber with the search keyword
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("invoice");

// Apply the absorber to all pages
pdfDocument.Pages.Accept(textFragmentAbsorber);

// Get the matched text fragments
TextFragmentCollection textFragments = textFragmentAbsorber.TextFragments;

// Print how many times the keyword was found
Console.WriteLine($"Found {textFragments.Count} instance(s) of the keyword.");

// Loop through and print each found text
foreach (TextFragment fragment in textFragments)
{
    Console.WriteLine($"Text: {fragment.Text} | Page: {fragment.Page.Number}");
}

search-in-pdf-using-csharp_word.cs

// Load the PDF file
Document pdfDocument = new Document("sample.pdf");

// Create a text absorber with a regular expression pattern for whole word match
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(@"\bcar\b");

// Set text search options to enable regular expression usage
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textFragmentAbsorber.TextSearchOptions = textSearchOptions;

// Apply the absorber to all pages
pdfDocument.Pages.Accept(textFragmentAbsorber);

// Retrieve the matched text fragments
TextFragmentCollection textFragments = textFragmentAbsorber.TextFragments;

// Output the number of matches found
Console.WriteLine($"Found {textFragments.Count} instance(s) of the keyword.");

// Loop through and display each found text fragment
foreach (TextFragment fragment in textFragments)
{
    Console.WriteLine($"Text: {fragment.Text} | Page: {fragment.Page.Number}");
}