使用 C# 从 PDF 文件中提取矢量数据

从 PDF 文档访问矢量数据

自 24.2 版本以来，Aspose.PDF for .NET 库允许从 PDF 文件中提取矢量数据。 下一个代码片段使用一些输入数据创建一个新的 Document 对象，初始化一个 ‘GraphicsAbsorber’（GraphicsAbsorber 返回矢量数据）来处理图形元素，然后访问文档的第二页以提取和分析这些元素。 它检索第二个图形元素的各种属性，例如其相关操作符、矩形和位置。

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

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "input.pdf"))
    {
        // Instantiate a new GraphicsAbsorber object to process graphic elements
        using (var grAbsorber = new Aspose.Pdf.Vector.GraphicsAbsorber())
        {
            // Visit the second page of the document to extract graphic elements
            grAbsorber.Visit(document.Pages[1]);

            // Retrieve the list of graphic elements from the GraphicsAbsorber
            var elements = grAbsorber.Elements;

            // Access the operators associated with the second graphic element
            var operations = elements[1].Operators;

            // Retrieve the rectangle associated with the second graphic element
            var rectangle = elements[1].Rectangle;

            // Get the position of the second graphic element
            var position = elements[1].Position;
        }
    }
}

从 PDF 文档提取矢量数据

要从 PDF 中提取矢量数据，我们可以使用 SVG 提取器：

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

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "VectorGraphics.pdf"))
    {
        // Save vector graphics from the first page to an SVG file
        document.Pages[1].TrySaveVectorGraphics(dataDir + "VectorGraphics_out.svg");
    }
}

将所有子路径单独提取为图像

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

    // Path to the directory where SVGs will be saved
    var svgDirPath = dataDir + "SvgOutput/";

    // Create extraction options
    var options = new Aspose.Pdf.Vector.SvgExtractionOptions
    {
        ExtractEverySubPathToSvg = true
    };

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "VectorGraphics.pdf"))
    {
        // Get the first page of the document
        var page = document.Pages[1];

        // Create SVG extractor
        var extractor = new Aspose.Pdf.Vector.SvgExtractor(options);
        // Extract SVGs from the page
        extractor.Extract(page, svgDirPath);
    }
}

将元素列表提取为单个图像

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

    // Initialize the list of graphic elements
    var elements = new List<Aspose.Pdf.Vector.GraphicElement>();

    // Example: Fill elements list with needed graphic elements (implement your logic here)

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "VectorGraphics.pdf"))
    {
        // Get the first page of the document
        var page = document.Pages[1];

        // Use SvgExtractor to extract SVGs
        var svgExtractor = new Aspose.Pdf.Vector.SvgExtractor();

        // Extract SVGs from graphic elements on the page
        svgExtractor.Extract(elements, page, Path.Combine(dataDir, "SvgOutput", "VectorGraphics_out.svg"));
    }
}

提取单个元素

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


    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "VectorGraphics.pdf"))
    {
        // Create a GraphicsAbsorber object to extract graphic elements
        var graphicsAbsorber = new Aspose.Pdf.Vector.GraphicsAbsorber();

        // Get the first page of the document
        var page = document.Pages[1];

        // Process the page to extract graphic elements
        graphicsAbsorber.Visit(page);

        // Extract the graphic element (XFormPlacement) and save it as SVG
        var xFormPlacement = graphicsAbsorber.Elements[1] as Aspose.Pdf.Vector.XFormPlacement;
        xFormPlacement.Elements[2].SaveToSvg(Path.Combine(dataDir, "SvgOutput", "VectorGraphics_out.svg"));
    }
}