public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
/*
* PDF documents don't always store the desired reading order of the text.
* Even if it does, the text is not required to be stored in the reading
* order for that language. Some languages even have multiple acceptible
* reading orders. Thus, Xtractor cannot guarantee getting text back in the
* desired reading order for a given language.
*
* However, if you know what reading order you expect from your document,
* it is still quite easy to get the desired result using LINQ. The example
* below sorts the text for English, meaning top -> bottom first,
* and left -> right second.
*/
Console.WriteLine("Extracting document text by reading order ...");
Xtractor.CharAndBox[] englishText = xtractor.ExtractTextWithLocation(pageNumber: 1, origin: Xtractor.Xtractor.CoordinateOrigin.BottomLeft);
IEnumerable <Xtractor.CharAndBox> sortedText = englishText.OrderBy(cab => cab.Box.Y).ThenBy(cab => cab.Box.X);
StringBuilder stringBuilder = new StringBuilder();
foreach (Xtractor.CharAndBox character in sortedText)
{
stringBuilder.Append(character.Character);
}
Console.WriteLine($"Document Text: {stringBuilder.ToString()}");
}
}
public static void Example()
{
/*
* Assume that you have a page with text that looks like this:
*
* ---------------------------------
| |
| North |
| |
| West Center East |
| |
| South |
| |
| ---------------------------------
*/
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Text.Location.pdf"))
{
//These functions have options to control which page you extract from, how many characters you want to get,
//how far to the side of the original text in PDF units to search, and which instance on that page to use
//as the reference point.
string up = xtractor.ExtractTextAbove(pageNumber: 1, text: "Center", length: int.MaxValue, unitType: Xtractor.Xtractor.UnitType.Character);
Console.WriteLine($"Text above center: {up.Trim()}");
string below = xtractor.ExtractTextBelow(pageNumber: 1, text: "Center", length: int.MaxValue, unitType: Xtractor.Xtractor.UnitType.Character);
Console.WriteLine($"Text below center: {below.Trim()}");
string right = xtractor.ExtractTextRight(pageNumber: 1, text: "Center", length: int.MaxValue, unitType: Xtractor.Xtractor.UnitType.Character);
Console.WriteLine($"Text right of center: {right.Trim()}");
string left = xtractor.ExtractTextLeft(pageNumber: 1, text: "Center", length: int.MaxValue, unitType: Xtractor.Xtractor.UnitType.Character);
Console.WriteLine($"Text left of center: {left.Trim()}");
}
}
public static void Example()
{
Console.WriteLine($"Counting number of pages in input document ...");
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
Console.WriteLine($" Number of pages found: {xtractor.PageTotal}.");
}
}
public static void Example()
{
// You have a few options, depending on how much detail you want.
// Note that all of the "Xtractor.Xtractor.CoordinateOrigin" arguments are optional.
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(@"..\..\..\Input\Xtractor.Input.pdf"))
{
string searchPhrase = "ActivePDF";
// Gives back the bounding box of each occurrance of "ActivePDF" on page 1,
// and results are relative to the top-left corner of the page.
Console.WriteLine($"Retrieve the bounding box coordinates for all instances of {searchPhrase} on page one.");
RectangleF[] page1BoundingBoxes = xtractor.FindText(text: searchPhrase, pageNumber: 1, origin: Xtractor.Xtractor.CoordinateOrigin.TopLeft);
Console.WriteLine($"{page1BoundingBoxes.Length.ToString()} instance(s) of {searchPhrase} found on page 1.");
foreach (RectangleF boundingBox in page1BoundingBoxes)
{
Console.WriteLine($" Box: ({boundingBox.X}, {boundingBox.Y}), ({boundingBox.X + boundingBox.Width}, {boundingBox.Y + boundingBox.Height})");
}
Console.WriteLine();
// Gives back the bounding box of each occurrance of "ActivePDF" in the document.
// Results are relative to the top-left corner of the page.
// The first dimension of the array is sorted by page number,
// so wholeDocumentBoundingBoxes[0] contains the same data as page1BoundingBoxes.
Console.WriteLine($"Retrieve the bounding box coordinates for all instances of {searchPhrase} in the document.");
RectangleF[][] wholeDocumentBoundingBoxes = xtractor.FindText(text: searchPhrase, origin: Xtractor.Xtractor.CoordinateOrigin.TopLeft);
for (int i = 0; i < wholeDocumentBoundingBoxes.Length; ++i)
{
Console.WriteLine($"{wholeDocumentBoundingBoxes[i].Length.ToString()} instance(s) of {searchPhrase} found on page {i + 1}.");
for (int j = 0; j < wholeDocumentBoundingBoxes[i].Length; ++j)
{
RectangleF boundingBox = wholeDocumentBoundingBoxes[i][j];
Console.WriteLine($" Box: ({boundingBox.X}, {boundingBox.Y}), ({boundingBox.X + boundingBox.Width}, {boundingBox.Y + boundingBox.Height})");
}
}
// Uses the regex @"\w+" to find all words on page 1. Gets back each word and location found.
// Returned coordinates are given relative to the bottom left corner, in PDF units.
Tuple <string, RectangleF>[] allWordsPage1 = xtractor.FindText(new Regex(@"\w+"), 1, Xtractor.Xtractor.CoordinateOrigin.BottomLeft);
// Uses the regex @"\w+" to find all words in the document. Gets back each word and location found.
// Returned coordinates are given relative to the bottom left corner, in PDF units.
// allWordsWholeDocument[0] contains the same data as allWordsPage1.
Tuple <string, RectangleF>[][] allWordsWholeDocument = xtractor.FindText(re: new Regex(@"\w+"), origin: Xtractor.Xtractor.CoordinateOrigin.BottomLeft);
// Extracts the location of each individual character on page 1. Coordinates are relative to the top left corner.
// The order of characters is in the PDF's order, which may or may not be in natural reading order.
Xtractor.CharAndBox[] eachCharacterPage1 = xtractor.ExtractTextWithLocation(pageNumber: 1, origin: Xtractor.Xtractor.CoordinateOrigin.TopLeft);
// Extracts the location of each individual character in the whole document. Coordinates are relative to the bottom left corner.
// eachCharacterWholeDocument[0] contains the same characters in the same order as eachCharacterPage1, but the
// coordinates returned will differ because they used different coordinate spaces when they were called.
// Coordinates will match if they used the same coordinate space.
// The order of characters is in the PDF's order, which may or may not be in natural reading order.
Xtractor.CharAndBox[][] eachCharacterWholeDocument = xtractor.ExtractTextWithLocation(origin: Xtractor.Xtractor.CoordinateOrigin.BottomLeft);
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
Xtractor.DocumentInfo xtractorDocInfo = xtractor.GetDocumentInfo();
WriteMetadata(XtractorDocInfo: xtractorDocInfo);
Console.WriteLine();
WritePermissions(XtractorDocInfo: xtractorDocInfo);
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
string searchTerm = "ActivePDF";
Console.WriteLine($"Counting search term, {searchTerm}, instances ...");
// Count instances on just the first page.
int searchResults = xtractor.CountInstances(text: searchTerm, pageNumber: 1);
Console.WriteLine($" Instances of {searchTerm} found on the first page: {searchResults}");
// Count instances in the entire document.
searchResults = xtractor.CountInstances(text: searchTerm);
Console.WriteLine($" Instances of {searchTerm} found in the document: {searchResults}");
}
}
public static void Example()
{
// You have two options for extracting the page size.
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
Console.WriteLine("Extracting document page dimensions ...");
// Extract the page size as two floats from page one.
float width, height;
xtractor.GetPageSize(pageNumber: 1, width: out width, height: out height);
Console.WriteLine($" Page one Width: {width} Height: {height}");
// Extract the page size from page two as a rectangle.
RectangleF pageSize = xtractor.GetPageSize(pageNumber: 2);
Console.WriteLine($" Page two Width: {pageSize.Width} Height: {pageSize.Height}");
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
// This method extracts the text from pages, one page at a time.
Console.WriteLine("Extract text from each page individually.");
for (int pageNum = 1; pageNum <= xtractor.PageTotal; ++pageNum)
{
string pageText = xtractor.ExtractText(pageNumber: pageNum);
Console.WriteLine($" Page {Convert.ToString(pageNum)} Text: {xtractor.ExtractText(pageNum)}");
}
// This method extracts the text from the whole document at once.
// The string[] is sorted by page number, where index 'n' is page 'n + 1'.
string[] allTextArray = xtractor.ExtractText();
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
//Simple regex to search for all words.
Regex re = new Regex(pattern: "\\w+");
Console.WriteLine($"Counting regular expression, {re.ToString()}, instances ...");
//Count instances on just the first page.
int searchResults = xtractor.CountInstances(re: re, pageNumber: 1);
Console.WriteLine($" Instances of {re.ToString()} found on the first page: {searchResults}");
//Count instances in the entire document.
searchResults = xtractor.CountInstances(re: re);
Console.WriteLine($" Instances of {re.ToString()} found in the document: {searchResults}");
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
//This saves the text from just page 1 to a file.
xtractor.ExtractTextToFile(filename: @"..\..\..\Output\PageOneText.txt", pageNumber: 1);
Process.Start(@"PageOneText.txt");
//This saves the text from the whole document to a file.
xtractor.ExtractTextToFile(filename: @"WholeDocumentText.txt");
Process.Start(@"WholeDocumentText.txt");
//This overload contains an optional parameter for a string to insert
//between the result of each page. It defaults to "\n". Each page may
//contain newlines as well, so modify this if you need to be able to
//tell pages apart.
xtractor.ExtractTextToFile(filename: @"WholeDocumentTextPageBreak.txt", pageSeparationStr: "This is a page break.");
Process.Start(@"WholeDocumentTextPageBreak.txt");
}
}
public static void Example()
{
// Xtractor supports many image file formats, including jpg, png, tiff, and more.
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
PointF location = new PointF(x: 50f, y: 50f);
// On page 1, finds the image 50 units from the left edge,
// and 50 units from the top, and saves to a jpg file.
xtractor.ExtractImageToFile(filename: @"..\..\..\Output\ExtractImagesByLocation.jpg", pageNumber: 1, location: location, origin: Xtractor.Xtractor.CoordinateOrigin.TopLeft);
// On page 1, finds the image 50 units from the left edge,
// and 700 units from the bottom, and saves to a png file.
xtractor.ExtractImageToFile(filename: @"..\..\..\Output\ExtractImagesByLocation.png", pageNumber: 1, location: new PointF(x: 50f, y: 700f), origin: Xtractor.Xtractor.CoordinateOrigin.BottomLeft);
// Extracts the image 50 units from the left edge and 50 from the top of page 1, and returns it in memory.
Bitmap imageAtLocation = xtractor.ExtractImage(pageNumber: 1, location: location, origin: Xtractor.Xtractor.CoordinateOrigin.TopLeft);
imageAtLocation.Dispose();
}
}
public static void Example()
{
using (Xtractor.Xtractor xt = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
// Saves all images on page 1 to bmp files.
// The function will replace #PAGE# with the page number (1) and #NUM# with
// the order it appeared on the page, starting at 1 and counting up.
// The literal file names, after the #PAGE# AND #NUM# substitutions were made, are returned.
// Using both #PAGE# and #NUM# are optional.
string[] bmpFileNames = xt.ExtractImagesToFile(filenameOrMask: @"..\..\..\Output\#PAGE#_#NUM#.bmp", pageNumber: 1);
foreach (string bmpFileName in bmpFileNames)
{
Process.Start(fileName: bmpFileName);
}
Console.WriteLine("First page BMP image processing complete, press any key to continue.");
// Saves all images in the entire document to JPG files.
string[] jpgFileNames = xt.ExtractImagesToFile(filenameOrMask: @"..\..\..\Output\#PAGE#_#NUM#.jpg");
foreach (string jpgFileName in jpgFileNames)
{
Process.Start(fileName: jpgFileName);
}
Console.WriteLine("JPG image processing complete, press any key to continue.");
// Extracts all images on page 1, and returns them in memory.
Bitmap[] allImagesPage1 = xt.ExtractImages(pageNumber: 1);
// Process the images
DisposeBitmaps(allImagesPage1);
// Extracts all images in the whole document, and returns them in memory.
// The first dimension in the array is sorted by page number in ascending order.
// allImagesWholeDocument
Bitmap[][] allImagesWholeDocument = xt.ExtractImages();
// Process the images
DisposeBitmaps(allImagesWholeDocument);
}
}
public static void Example()
{
// When it comes to extracting bookmarks, you have two options.
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
// Extract bookmarks as a JSON string.
Console.WriteLine($"Extracting bookmarks as a JSON string.");
string bookmarksJson = xtractor.GetBookmarksAsJson();
string bookmarksJonFile = "bookmarks.json";
using (FileStream outputStream = new FileStream(path: bookmarksJonFile, mode: FileMode.OpenOrCreate, access: FileAccess.ReadWrite))
{
byte[] bookmarksBytes = Encoding.UTF8.GetBytes(s: bookmarksJson);
outputStream.Write(array: bookmarksBytes, offset: 0, count: bookmarksBytes.Length);
}
Console.WriteLine($"Bookmark JSON data saved to: ${System.IO.Directory.GetCurrentDirectory()}\\{bookmarksJonFile}");
Console.WriteLine();
// Extract bookmarks as a tree structure.
Console.WriteLine($"Extracting bookmarks as a tree structure.");
Xtractor.DocumentOutline bookmarks = xtractor.GetBookmarksAsTree();
PrintBookmarks(bookmarks: bookmarks);
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
// If you know where on the page you want to look, you can
// restrict extractions to just that area. In this example,
// we'll just a square 100 units on each side and pull from a
// corner.
const float boxWidth = 100, boxHeight = 810;
for (int pageNum = 1; pageNum <= xtractor.PageTotal; ++pageNum)
{
// PDF allows each page to be a different size, so we should get the
// page size for each page rather than once for the whole document.
float pageWidth, pageHeight;
xtractor.GetPageSize(pageNumber: pageNum, width: out pageWidth, height: out pageHeight);
// We use Image Coordinates as the text origin [top left is (0, 0)]
RectangleF topBox = new RectangleF(x: pageWidth - boxWidth,
y: 0,
width: boxWidth,
height: boxHeight);
string textTopRight = xtractor.ExtractTextWithin(pageNumber: pageNum, rect: topBox, origin: Xtractor.Xtractor.CoordinateOrigin.TopLeft);
Console.WriteLine($"Top Right Text Page {pageNum}: {textTopRight}");
Console.WriteLine();
// or we can use PDF coordinates [bottom left is (0, 0)]
RectangleF bottomBox = new RectangleF(x: pageWidth - boxWidth,
y: boxHeight,
width: boxWidth,
height: boxHeight);
string textBottomLeft = xtractor.ExtractTextWithin(pageNumber: pageNum, rect: bottomBox, origin: Xtractor.Xtractor.CoordinateOrigin.BottomLeft);
Console.WriteLine($"Bottom Right Text Page {pageNum}: {textBottomLeft}");
Console.WriteLine();
}
}
}
public static void Example()
{
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(@"..\..\..\Input\Xtractor.Input.pdf"))
{
// Simple Regex to search for numbers.
Regex re = new Regex(pattern: "\\d+");
// Finds all the numbers on page 1.
Console.WriteLine("Searching first page ...");
string[] page1Matches = xtractor.FindAllByRegex(re: re, pageNumber: 1);
Console.WriteLine($"{page1Matches.Length} results found on page one.");
Console.WriteLine();
// Finds all numbers in the whole document. The first dimension
// of the array is sorted by page number.
Console.WriteLine("Searching entire document ...");
string[][] wholeDocumentMatches = xtractor.FindAllByRegex(re: re);
for (int i = 0; i < wholeDocumentMatches.Length; ++i)
{
Console.WriteLine($"{wholeDocumentMatches[i].Length} results found on page {i + 1}.");
}
}
}
// This example contains different ways of opening an Xtractor input
// file and how to handle passwords.
public static void Example()
{
// Open a file from disk.
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.pdf"))
{
// Perform your extractions here.
Console.WriteLine("Successfully opened Xtractor.Input.pdf with Xtractor.");
}
//Open a file from memory.
byte[] examplePDF = File.ReadAllBytes(@"..\..\..\Input\Xtractor.Input.pdf");
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(file: examplePDF))
{
// Perform your extractions here.
Console.WriteLine("Successfully opened Xtractor.Input.pdf with Xtractor as a byte array.");
}
// Open a file with a password from disk.
using (SecureString password = new SecureString())
{
// We recommend never storing secure data like a password in a
// 'string', however we will here for simplicity.
string insecurePassword = "******";
foreach (char c in insecurePassword)
{
password.AppendChar(c);
}
password.MakeReadOnly();
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.Secure.pdf", password: password))
{
// Perform your extractions here.
Console.WriteLine("Successfully opened Xtractor.Input.Secure.pdf with Xtractor and input password.");
}
}
// Open a file with a password from memory.
examplePDF = File.ReadAllBytes(@"..\..\..\Input\Xtractor.Input.Secure.pdf");
using (SecureString password = new SecureString())
{
string insecurePassword = "******";
foreach (char c in insecurePassword)
{
password.AppendChar(c);
}
password.MakeReadOnly();
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(file: examplePDF, password: password))
{
// Perform your extractions here.
Console.WriteLine("Successfully opened Xtractor.Input.Secure.pdf with Xtractor as a byte array using a password.");
}
}
// Handle an invalid password.
// We aren't using a 'using' block here, like most other examples.
// Since the runtime expands 'using' into a try/finally pattern anyway, we'll
// manually expand it so we can add in a 'catch' as well.
{
Xtractor.Xtractor xtractor = null;
try
{
string password = "******";
SecureString securePassword = new SecureString();
foreach (char c in password)
{
securePassword.AppendChar(c);
}
securePassword.MakeReadOnly();
xtractor = new Xtractor.Xtractor(filename: @"..\..\..\Input\Xtractor.Input.Secure.pdf", password: securePassword);
// Perform your extractions here.
Console.WriteLine("Successfully opened Xtractor.Input.pdf with Xtractor.");
}
catch (Xtractor.InvalidPasswordException)
{
// Handle the error here.
Console.WriteLine("InvalidPasswordException caught opening Xtractor.Input.Secure.pdf");
}
finally
{
xtractor?.Dispose();
}
}
}
static void Main(string[] args)
{
string appPath = System.AppDomain.CurrentDomain.BaseDirectory;
string newPDF = "GeneratedPDF.pdf";
int result = -1;
// Use Toolkit to create a new PDF
using (APToolkitNET.Toolkit toolkit = new APToolkitNET.Toolkit())
{
toolkit.OutputPageHeight = 792.0f;
toolkit.OutputPageWidth = 612.0f;
Console.WriteLine($"Toolkit: Generating new PDF using NewPage");
// Open the output file in memory
result = toolkit.OpenOutputFile("MEMORY");
if (result != 0)
{
WriteResult($"Toolkit: Failed to open output file in-memory, error code {result}");
return;
}
// Each time a new page is required call NewPage
toolkit.NewPage();
// Text can be added onto the new page with
// SetFont, PrintText and PrintMultilineText functions
toolkit.SetFont("Helvetica", 24);
toolkit.PrintText(36.0f, 720.0f, $"Toolkit Version: {toolkit.ToolkitVersion}");
// Images can be added onto the new page with
// PrintImage, PrintJPEG and PrintTIFF
toolkit.PrintJPEG($"{appPath}IMG.jpg", 36.0f, 36.0f, 540.0f, 684.0f, true);
// Close the new file to complete PDF creation
toolkit.CloseOutputFile();
// Save the new PDF to the application path
result = toolkit.SaveMemoryToDisk($"{appPath}{newPDF}");
if (result != 0)
{
WriteResult($"Toolkit: SaveMemoryToDisk failed, error code {result}");
return;
}
Console.WriteLine($"Toolkit: New pdf created {appPath}{newPDF}");
// Use Toolkit Compressor to compress images
Console.WriteLine("Toolkit.Compressor: Compressing generated PDF");
toolkit.OpenOutputFile("MEMORY");
if (result != 0)
{
WriteResult($"Toolkit Compressor: Failed to open output file in-memory, error code {result}");
return;
}
// Retrieves the entire PDF as a string variable after you call
// CloseOutputFile and set the output file name to MEMORY.
toolkit.InputByteStream = toolkit.OutputByteStream;
// Open the input file
toolkit.OpenInputFile("MEMORY");
if (result != 0)
{
WriteResult($"Toolkit Compressor: Failed to open input file in-memory, error code {result}");
return;
}
// Instantiate the compressor object
APToolkitNET.Compressor compressor = toolkit.GetCompressor();
// Compresses images in the output PDF with the default settings.
compressor.CompressImages = true;
result = toolkit.CopyForm(0, 0);
if (result != 1)
{
WriteResult($"Toolkit Compressor: CopyForm failed, error code {result}");
return;
}
toolkit.CloseOutputFile();
// Save the compressed PDF to disk
result = toolkit.SaveMemoryToDisk($"{appPath}Toolkit.Compressed.pdf");
if (result != 0)
{
WriteResult($"Toolkit Compressor: SaveMemoryToDisk failed, error code {result}");
return;
}
Console.WriteLine($"Toolkit Compressor: Compressed pdf created {appPath}Toolkit.Compressed.pdf");
}
// Use Rasterizer to convert generated PDF to an image
Console.WriteLine("\nRasterizer: Converting generated PDF to image format");
using (APRasterizerNET.Rasterizer rasterizer =
new APRasterizerNET.Rasterizer())
{
// Open PDF
rasterizer.OpenFile($"{appPath}{newPDF}");
// Get page count of open file
int pageCount = rasterizer.NumPages();
for (int currentPage = 1; currentPage <= pageCount; currentPage++)
{
// Image Format
rasterizer.ImageFormat = APRasterizerNET.ImageType.ImgJPEG;
// Output Type
rasterizer.OutputFormat =
APRasterizerNET.OutputFormatType.OutFile;
// Other settings
rasterizer.OutputFileName =
$"{appPath}Rasterizer.ConvertPDFToJPEG.Page.{currentPage}.jpg";
// Render the current page
rasterizer.RenderPage(currentPage);
// Check for errors
if (rasterizer.LastError != 0)
{
WriteResult($"Error rendering page {currentPage}: {rasterizer.LastErrorMessage}");
}
Console.WriteLine($"Rasterizer: JPG image created at {appPath}Rasterizer.ConvertPDFToJPEG.Page.{currentPage}.jpg");
}
}
// Use Xtractor to extract text and images
Console.WriteLine("\nXtractor: Extracting images and text from the generated PDF");
using (Xtractor.Xtractor xtractor = new Xtractor.Xtractor(filename: $"{appPath}{newPDF}"))
{
// Saves all images in the entire document to JPG files.
string[] jpgFileNames = xtractor.ExtractImagesToFile(filenameOrMask: $"{appPath}Xtractor.#PAGE#_#NUM#.jpg");
Console.WriteLine($"Xtractor: Files extracted from \"{newPDF}\"");
foreach (string file in jpgFileNames)
{
Console.WriteLine($"\tExtracted File: {file}");
}
// This method extracts the text from the whole document at once.
// The string[] is sorted by page number, where index 'n' is page 'n + 1'.
string[] allTextArray = xtractor.ExtractText();
Console.WriteLine($"Xtractor: Text extracted from {newPDF}");
foreach (string text in allTextArray)
{
Console.WriteLine($"\tExtracted Text: {text}");
}
}
// Use Redactor to redact images and text from generated PDF
Console.WriteLine("\nRedactor: Redacting images and text from the generated PDF");
using (APRedactor.Redactor redactor = new APRedactor.Redactor(
filename: $"{appPath}{newPDF}"))
{
redactor.PageLiteralText = new string[]
{
"Version"
};
redactor.TextMode =
APRedactor.Redactor.TextRedactionMode.LiteralText;
redactor.ImageMode =
APRedactor.Redactor.ImageRedactionMode.Unconditional;
int redactionsPerformed = redactor.Redact();
redactor.Save($"{appPath}RedactImagesAndText.pdf");
Console.WriteLine($"Redactor: Redacted PDF created {appPath}RedactedImagesAndText.pdf");
}
WriteResult("\nSuccess!");
}
