GroupDocs.Annotation .NET チュートリアル: PDF ページの抽出

Install-Package GroupDocs.Annotation -Version 25.4.0

dotnet add package GroupDocs.Annotation --version 25.4.0

using GroupDocs.Annotation;

// This is your starting point for everything
Annotator annotator = new Annotator("YOUR_DOCUMENT_DIRECTORY/sample.pdf");

// Direct answer – the core extraction logic
var annotator = new Annotator("input.pdf");
var options = new PdfSaveOptions { FirstPage = 2, LastPage = 4 };
annotator.Save("output.pdf", options);

string inputPath = Path.Combine("YOUR_DOCUMENT_DIRECTORY", "sample.pdf");
using (Annotator annotator = new Annotator(inputPath))
{
    // All the magic happens inside this using block
    // The 'using' statement ensures proper cleanup when we're done
}

var options = new PdfSaveOptions
{
    FirstPage = 10,   // start at page 10
    LastPage = 15     // end at page 15
};

var saveOptions = new Options.SaveOptions 
{
    FirstPage = 2,  // Start from page 2
    LastPage = 4    // End at page 4
};

annotator.Save(Path.Combine("YOUR_OUTPUT_DIRECTORY", "result.pdf"), saveOptions);

using GroupDocs.Annotation;
using System.IO;

string inputPath = Path.Combine("YOUR_DOCUMENT_DIRECTORY", "sample.pdf");
using (Annotator annotator = new Annotator(inputPath))
{
    var saveOptions = new Options.SaveOptions 
    {
        FirstPage = 2,  // Extract pages 2-4
        LastPage = 4
    };
    
    annotator.Save(Path.Combine("YOUR_OUTPUT_DIRECTORY", "extracted_pages.pdf"), saveOptions);
}

public static class PathHelper
{
    public const string InputFolder = @"C:\Docs\Input";
    public const string OutputFolder = @"C:\Docs\Output";

    public static string GetInputPath(string fileName) =>
        Path.Combine(InputFolder, fileName);

    public static string GetOutputPath(string fileName) =>
        Path.Combine(OutputFolder, fileName);
}

namespace PathManagement
{
    public static class Constants
    {
        private const string DocumentDirectory = "YOUR_DOCUMENT_DIRECTORY";
        private const string OutputDirectory = "YOUR_OUTPUT_DIRECTORY";

        // These methods make path management a breeze
        public static string GetDocumentFilePath(string fileName)
        {
            return Path.Combine(DocumentDirectory, fileName);
        }

        public static string GetOutputFilePath(string fileName)
        {
            return Path.Combine(OutputDirectory, fileName);
        }
    }
}

var source = PathHelper.GetInputPath("contract.pdf");
var target = PathHelper.GetOutputPath("contract_pages_10_15.pdf");
using var annotator = new Annotator(source);
var options = new PdfSaveOptions { FirstPage = 10, LastPage = 15 };
annotator.Save(target, options);

string inputPath = Constants.GetDocumentFilePath("sample.pdf");
string outputPath = Constants.GetOutputFilePath("extracted_pages.pdf");

using (Annotator annotator = new Annotator(inputPath))
{
    var saveOptions = new Options.SaveOptions 
    {
        FirstPage = 2,
        LastPage = 4
    };
    
    annotator.Save(outputPath, saveOptions);
}

string[] documentFiles = {"doc1.pdf", "doc2.pdf", "doc3.pdf"};

foreach (string docFile in documentFiles)
{
    string inputPath = Constants.GetDocumentFilePath(docFile);
    using (Annotator annotator = new Annotator(inputPath))
    {
        var saveOptions = new Options.SaveOptions 
        {
            FirstPage = 1,
            LastPage = 3  // Extract first 3 pages from each
        };
        
        string outputName = $"extracted_{docFile}";
        annotator.Save(Constants.GetOutputFilePath(outputName), saveOptions);
    }
}

try
{
    using (Annotator annotator = new Annotator(inputPath))
    {
        // Your extraction code here
    }
}
catch (Exception ex)
{
    // Log the error and handle gracefully
    Console.WriteLine($"Error processing document: {ex.Message}");
}

// Instead of extracting pages 1-100 at once, do it in smaller batches
for (int startPage = 1; startPage <= 100; startPage += 10)
{
    int endPage = Math.Min(startPage + 9, 100);
    
    var saveOptions = new Options.SaveOptions 
    {
        FirstPage = startPage,
        LastPage = endPage
    };
    
    // Process this batch
}

// Good - resources are automatically cleaned up
using (Annotator annotator = new Annotator(inputPath))
{
    // Your code here
}

// Bad - resources might not get cleaned up properly
Annotator annotator = new Annotator(inputPath);
// Do stuff...
// annotator.Dispose(); // You might forget this!

using System.Diagnostics;

Stopwatch stopwatch = Stopwatch.StartNew();

using (Annotator annotator = new Annotator(inputPath))
{
    var saveOptions = new Options.SaveOptions 
    {
        FirstPage = 1,
        LastPage = 10
    };
    
    annotator.Save(outputPath, saveOptions);
}

stopwatch.Stop();
Console.WriteLine($"Page extraction completed in {stopwatch.ElapsedMilliseconds} ms");

if (!File.Exists(sourcePath))
    throw new FileNotFoundException($"Input file not found: {sourcePath}");

string inputPath = Constants.GetDocumentFilePath("sample.pdf");

if (!File.Exists(inputPath))
{
    throw new FileNotFoundException($"Input file not found: {inputPath}");
}

int totalPages = annotator.DocumentInfo.PagesCount;
if (options.FirstPage < 1 || options.LastPage > totalPages)
    throw new ArgumentOutOfRangeException("Page range is outside the document bounds.");

// You'd need to implement GetPageCount() method or check the document properties
int totalPages = GetDocumentPageCount(inputPath);

if (saveOptions.LastPage > totalPages)
{
    throw new ArgumentException($"Last page ({saveOptions.LastPage}) exceeds document length ({totalPages})");
}

[ApiController]
[Route("api/[controller]")]
public class DocumentController : ControllerBase
{
    [HttpPost("extract-pages")]
    public IActionResult ExtractPages([FromBody] PageExtractionRequest request)
    {
        try
        {
            // Your GroupDocs extraction code here
            return Ok("Pages extracted successfully");
        }
        catch (Exception ex)
        {
            return BadRequest($"Error: {ex.Message}");
        }
    }
}

using (var context = new DocumentContext())
{
    var document = context.Documents.First(d => d.Id == documentId);
    
    // Extract pages
    using (Annotator annotator = new Annotator(document.FilePath))
    {
        // Extraction code...
    }
    
    // Update database
    document.LastProcessed = DateTime.Now;
    document.ExtractedPageCount = (saveOptions.LastPage - saveOptions.FirstPage) + 1;
    context.SaveChanges();
}