Documentize 25.12.0

.NET API to Process & Manipulate PDF Files

Documentize is a powerful class library that can be used with C#, F#, VB.NET for a wide range of PDF processing tasks: merge, split, rotate, resize, optimize, extract text, extract images, encrypt, decrypt, sign, add tables, add TOC. Documentize offers a wide range of features to enhance productivity. You can convert PDF to the following formats: PDF/A, HTML, DOC, DOCX, XLS, XLSX, CSV, ODS, PNG, JPEG, JPG, TIFF. Contains AI integration.

Key Features

PDF Manager

• Merge and Split PDF documents.
• Rotate, Resize pages of PDF documents.
• Compress PDF files by optimizing images and removing unused objects.
• Optimize PDF files (also known as applying a Fast Web View. This process allows web browsers and PDF viewers to display the first page of the document almost immediately while the rest of the file downloads in the background, creating a much faster and better user experience for large online documents.).
• Add a Table to a PDF document.
• Add a Table of Contents to PDF document.

PDF Extractor

• Extract Text from PDF documents.
• Extract Images from PDF documents.
• Extract Form Data from PDF documents.

PDF Converter

• Convert PDF documents to various formats like Word (DOC,DOCX), Excel (XLSX,CSV,ODS), Images (PNG, JPEG, TIFF), and HTML.
• Convert HTML documents to PDF.
• Create and Validate PDF/A-compliant files for long-term archiving.

PDF Security

• Encrypt or Decrypt PDF documents.
• Digitally sign and validate signatures on PDF.
• Add Timestamp to PDF.

PDF Form

• Create, fill, flatten and remove interactive forms.
• Export form data to DSV (CSV) or JSON formats.

Examples

Merge PDF files

var options = new MergeOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file_1.pdf"));
options.AddInput(new FileDataSource("path_to_your_pdf_file_2.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfManager.Merge(options);

Split PDF

var options = new SplitOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file_1.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file_2.pdf"));

PdfManager.Split(options);

Optimize PDF

var options = new OptimizeOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfManager.Optimize(options);

Rotate PDF

var options = new RotateOptions();
options.Rotation = Rotation.On90;
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfManager.Rotate(options);

Resize PDF

var options = new ResizeOptions();
options.PageSize = PageSize.A3;
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfManager.Resize(options);

Compress PDF

var options = new CompressOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfManager.Compress(options);

Add Table of Contents to PDF

var options = new TocOptions();
options.Title = "My Table of Contents";
options.GenerateBookmarks = true;
options.Headings.Add(new TocHeading("Introduction", 2, false, 1));
options.Headings.Add(new TocHeading("Chapter I", 3, true, 1));
options.Headings.Add(new TocHeading("Chapter II", 4, true, 1));
options.Headings.Add(new TocHeading("Example A", 4, true, 2));
options.Headings.Add(new TocHeading("Example B", 4, true, 2));
options.Headings.Add(new TocHeading("Example C", 4, true, 2));
options.Headings.Add(new TocHeading("Example D", 4, true, 2));
options.Headings.Add(new TocHeading("Chapter III", 5, true, 1));

options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfManager.AddTableOfContents(options);

Extract Text from PDF

var options = new ExtractTextOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));

var results = PdfExtractor.Extract(options);
var textExtracted = results.ResultCollection[0].ToString();

Extract Images from PDF

var options = new ExtractImagesOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new DirectoryDataSource("path_to_results_directory"));

var results = PdfExtractor.Extract(options);

Export Form values to CSV file

var options = new ExtractFormDataToDsvOptions(',', true);
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_csv_file.csv"));

PdfExtractor.Extract(options);

Encrypt PDF

var options = new EncryptOptions("123456", "qwerty");
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfSecurity.Encrypt(options);

Decrypt PDF

var options = new DecryptOptions("123456");
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfSecurity.Decrypt(options);

Digitally Sign a PDF

var options = new SignOptions("path_to_your_pfx_file.pfx", "password_of_your_pfx_file");
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfSecurity.Sign(options);

Convert PDF to PDF/A (PDF/A-3b in this case)

var options = new PdfToPdfAOptions
{
    PdfAVersion = PdfAStandardVersion.PDF_A_3B
};

options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"))
options.AddOutput(new FileDataSource("path_to_the_converted_file.pdf"));

PdfConverter.Convert(options);

Convert PDF to Word (.doc)

var options = new PdfToDocOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_file.doc"));

PdfConverter.Convert(options);

Convert PDF to Excel (.xlsx)

var options = new PdfToXlsOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_xlsx_file.xlsx"));

PdfConverter.Convert(options);

Convert PDF to HTML (.html)

var options = new PdfToHtmlOptions(PdfToHtmlOptions.SaveDataType.FileWithEmbeddedResources);
options.AddInput(new FileDataSource("path_to_input.pdf"));
options.AddOutput(new FileDataSource("path_to_output.html"));

PdfConverter.Convert(options);

Convert PDF to Png (.png)

var options = new PdfToPngOptions();
options.AddInput(new FileDataSource("path_to_input.pdf"));
options.AddOutput(new DirectoryDataSource("path_to_output_directory"));

PdfConverter.Convert(options);

Convert PDF to JPEG (.jpeg)

var options = new PdfToJpegOptions();
options.AddInput(new FileDataSource("path_to_input.pdf"));
options.AddOutput(new DirectoryDataSource("path_to_output_directory"));

PdfConverter.Convert(options);

Convert PDF to TIFF (.tiff)

var options = new PdfToTiffOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new DirectoryDataSource("path_to_output_directory"));

PdfConverter.Convert(options);

Flatten fields in PDF file

var options = new FlattenFieldsOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfForm.Flatten(options);

Remove fields in PDF file

var options = new RemoveFieldsOptions();
options.AddInput(new FileDataSource("path_to_your_pdf_file.pdf"));
options.AddOutput(new FileDataSource("path_to_result_pdf_file.pdf"));

PdfForm.Remove(options);

For more examples, visit our GitHub Examples page.