static void Main(string[] args)
{
string inputFile = @".\sample2.pdf";
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
int pageCount = extractor.GetPageCount();
// Search each page for a keyword
for (int i = 0; i < pageCount; i++)
{
if (extractor.Find(i, "bombardment", false))
{
// Extract page
using (DocumentSplitter splitter = new DocumentSplitter("demo", "demo"))
{
splitter.OptimizeSplittedDocuments = true;
int pageNumber = i + 1; // (!) page number in ExtractPage() is 1-based
string outputFile = @".\page" + pageNumber + ".pdf";
splitter.ExtractPage(inputFile, outputFile, pageNumber);
Console.WriteLine("Extracted page " + pageNumber + " to file \"" + outputFile + "\"");
}
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputFile = @".\sample.pdf";
using (DocumentSplitter splitter = new DocumentSplitter("demo", "demo"))
{
splitter.OptimizeSplittedDocuments = true;
// Extracting specific page:
// =========================
splitter.ExtractPage(inputFile, "page3.pdf", 3); // (!) Note: page number is 1-based.
Console.WriteLine(@"Extracted page 3 to file ""page3.pdf""");
Console.WriteLine();
// Split in two parts:
// ===================
splitter.Split(inputFile, "part1.pdf", "part2.pdf", 3); // (!) Note: page number is 1-based.
Console.WriteLine(@"Splitted at page 3 to files ""part1.pdf"" and ""part2.pdf""");
Console.WriteLine();
// Split by ranges:
// ================
string[] files = splitter.Split(inputFile, "1-3,4-6,7,8-"); // (!) Note: page numbers are 1-based; ending "-" means "to the end".
Console.WriteLine(@"Splitted by ranges: ");
foreach (string file in files)
{
Console.WriteLine(" " + Path.GetFileName(file));
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}