从 PDF 文件中提取图像

使用页面资源

以下代码片段也适用于 Aspose.PDF.Drawing 库。

图像保存在每个页面的 Resources 集合的 Images 集合中。要提取特定页面，然后使用图像的特定索引从 Images 集合中获取图像。

图像的索引返回一个 XImage 对象。该对象提供一个 Save 方法用于保存提取的图像。以下代码片段展示了如何从 PDF 文件中提取图像。

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ExtractImageFromPDF()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "ExtractImages.pdf"))
    {
        // Extract a particular image
        var xImage = document.Pages[1].Resources.Images[1];
        using (var outputImage = new FileStream(dataDir + "ExtractedImage.jpg", FileMode.Create))
        {
            // Save PDF document image
            xImage.Save(outputImage, System.Drawing.Imaging.ImageFormat.Jpeg);
        }

        // Save PDF document
        document.Save(dataDir + "ExtractImages_out.pdf");
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ExtractImageFromPDF()
{
    // The path to the documents directory
    string dataDir = RunExamples.GetDataDir_AsposePdf_WorkingDocuments();

    // Open PDF document
    using var document = new Aspose.Pdf.Document(dataDir + "ExtractImages.pdf");

    // Get the first image from the first page
    var xImage = document.Pages[1].Resources.Images[1];

    using var outputImage = File.Create(dataDir + "ExtractedImage.jpg");

    // Save PDF document image
    xImage.Save(outputImage, System.Drawing.Imaging.ImageFormat.Jpeg);

    // Save PDF document
    document.Save(dataDir + "ExtractImages_out.pdf");
}

使用 ImagePlacementAbsorber

随着 Aspose.PDF for .NET 7.0.0 的发布，我们引入了名为 ImagePlacement、ImagePlacementAbsorber 和 ImagePlacementCollection 的类，这些类提供与上述类类似的功能，以获取 PDF 文档中图像的分辨率和位置。

• ImagePlacementAbsorber 执行图像使用搜索，作为 ImagePlacement 对象集合。
• ImagePlacement 提供成员 Resolution 和 Rectangle，返回实际的图像放置值。

下一个代码片段也适用于 Aspose.Drawing 库。

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ExtractAndScaleImagesFromPDF()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Images();

    int imageCount = 0;

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "ImagePlacement.pdf"))
    {
        var abs = new Aspose.Pdf.ImagePlacementAbsorber();

        // Load the contents of the first page
        document.Pages[1].Accept(abs);

        // Iterate through each image placement on the first page
        foreach (var imagePlacement in abs.ImagePlacements)
        {
            // Get image properties
            Console.Out.WriteLine("image width: " + imagePlacement.Rectangle.Width);
            Console.Out.WriteLine("image height: " + imagePlacement.Rectangle.Height);
            Console.Out.WriteLine("image LLX: " + imagePlacement.Rectangle.LLX);
            Console.Out.WriteLine("image LLY: " + imagePlacement.Rectangle.LLY);
            Console.Out.WriteLine("image horizontal resolution: " + imagePlacement.Resolution.X);
            Console.Out.WriteLine("image vertical resolution: " + imagePlacement.Resolution.Y);

            // Extract a particular image
            using (var outputImage = new FileStream(dataDir + "ExtractedImage_" + imageCount.ToString() + ".jpg", FileMode.Create))
            {
                // Save PDF document image
                imagePlacement.Save(outputImage, System.Drawing.Imaging.ImageFormat.Jpeg);
            }

            ++imageCount;
        }
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ExtractAndScaleImagesFromPDF()
{
    // The path to the documents directory
    string dataDir = RunExamples.GetDataDir_AsposePdf_Images();
    int imageCount = 0;

    // Open PDF document
    using var document = new Aspose.Pdf.Document(dataDir + "ImagePlacement.pdf");
    var absorber = new Aspose.Pdf.ImagePlacementAbsorber();

    // Load contents of the first page
    document.Pages[1].Accept(absorber);

    // Iterate through each image placement on the first page
    foreach (var imagePlacement in absorber.ImagePlacements)
    {
        Console.WriteLine($"Image {imageCount}:");
        Console.WriteLine($"  Width: {imagePlacement.Rectangle.Width}");
        Console.WriteLine($"  Height: {imagePlacement.Rectangle.Height}");
        Console.WriteLine($"  LLX: {imagePlacement.Rectangle.LLX}");
        Console.WriteLine($"  LLY: {imagePlacement.Rectangle.LLY}");
        Console.WriteLine($"  Horizontal Resolution: {imagePlacement.Resolution.X}");
        Console.WriteLine($"  Vertical Resolution: {imagePlacement.Resolution.Y}");

        using var outputImage = File.Create(dataDir + $"ExtractedImage_{imageCount}.jpg");
        // Save PDF document image
        imagePlacement.Save(outputImage, System.Drawing.Imaging.ImageFormat.Jpeg);

        ++imageCount;
    }
}