استخراج الصور من مستندات PDF باستخدام C#

var uploadRequest = new UploadFileRequest(remotePdfPath, File.ReadAllBytes(localPdfPath));
storageApi.UploadFile(uploadRequest);

var imagesRequest = new GetDocumentImagesRequest(remotePdfPath);
ImagesResult imagesResult = parserApi.GetDocumentImages(imagesRequest);

foreach (ImageInfo imgInfo in imagesResult.Images)
{
    byte[] imageBytes = Convert.FromBase64String(imgInfo.Base64Data);
    string extension = imgInfo.FileExtension?.TrimStart('.').ToLower() ?? "bin";
    string fileName = $"extracted_page{imgInfo.PageNumber}_img{imgInfo.ImageIndex}_{imageCounter}.{extension}";
    File.WriteAllBytes(fileName, imageBytes);
}

var deleteRequest = new DeleteFileRequest(remotePdfPath);
storageApi.DeleteFile(deleteRequest);

using System;
using System.IO;
using System.Collections.Generic;
using GroupDocs.Parser.Cloud.Sdk.Api;
using GroupDocs.Parser.Cloud.Sdk.Client;
using GroupDocs.Parser.Cloud.Sdk.Model;
using GroupDocs.Parser.Cloud.Sdk.Model.Requests;

namespace ExtractImagesFromPdf
{
    class Program
    {
        static void Main(string[] args)
        {
            // Configuration – replace with your actual credentials
            var config = new Configuration
            {
                ClientId = "YOUR_CLIENT_ID",
                ClientSecret = "YOUR_CLIENT_SECRET"
            };

// APIs
            var storageApi = new StorageApi(config);
            var parserApi = new ParserApi(config);

// Input PDF path (local) and remote name in storage
            const string localPdfPath = "input.pdf";
            const string remotePdfPath = "input.pdf";

try
            {
                // -------------------------------------------------
                // 1. Upload PDF to GroupDocs Cloud storage (if not already there)
                // -------------------------------------------------
                if (!File.Exists(localPdfPath))
                    throw new FileNotFoundException($"Local file not found: {localPdfPath}");

var uploadRequest = new UploadFileRequest(remotePdfPath, File.ReadAllBytes(localPdfPath));
                storageApi.UploadFile(uploadRequest);

// -------------------------------------------------
                // 2. Retrieve document images (all pages)
                // -------------------------------------------------
                var imagesRequest = new GetDocumentImagesRequest(remotePdfPath);
                ImagesResult imagesResult = parserApi.GetDocumentImages(imagesRequest);

// -------------------------------------------------
                // 3. Save each extracted image to disk
                // -------------------------------------------------
                int imageCounter = 0;
                foreach (ImageInfo imgInfo in imagesResult.Images)
                {
                    // Image data is returned as Base64 string
                    byte[] imageBytes = Convert.FromBase64String(imgInfo.Base64Data);

// Build a descriptive file name
                    string extension = imgInfo.FileExtension?.TrimStart('.').ToLower() ?? "bin";
                    string fileName = $"extracted_page{imgInfo.PageNumber}_img{imgInfo.ImageIndex}_{imageCounter}.{extension}";
                    File.WriteAllBytes(fileName, imageBytes);

Console.WriteLine($"Saved: {fileName} ({imgInfo.Width}x{imgInfo.Height} px, {imgInfo.Resolution} DPI)");
                    imageCounter++;
                }

Console.WriteLine($"Total images extracted: {imageCounter}");
            }
            catch (ApiException apiEx)
            {
                Console.Error.WriteLine($"GroupDocs API error: {apiEx.ErrorCode} - {apiEx.Message}");
            }
            catch (Exception ex)
            {
                Console.Error.WriteLine($"Unexpected error: {ex.Message}");
            }
            finally
            {
                // -------------------------------------------------
                // 4. Optional cleanup – delete the uploaded PDF from storage
                // -------------------------------------------------
                try
                {
                    var deleteRequest = new DeleteFileRequest(remotePdfPath);
                    storageApi.DeleteFile(deleteRequest);
                }
                catch
                {
                    // Ignored – cleanup is optional
                }
            }
        }
    }
}

curl -X POST "https://api.groupdocs.cloud/v2.0/oauth2/token" \
     -H "Content-Type: application/x-www-form-urlencoded" \
     -d "grant_type=client_credentials&client_id=YOUR_CLIENT_ID&client_secret=YOUR_CLIENT_SECRET"

curl -X PUT "https://api.groupdocs.cloud/v2.0/storage/file/input.pdf" \
     -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
     -H "Content-Type: application/pdf" \
     --data-binary "@input.pdf"

curl -X GET "https://api.groupdocs.cloud/v2.0/parser/input.pdf/images" \
     -H "Authorization: Bearer YOUR_ACCESS_TOKEN"

curl -X GET "https://api.groupdocs.cloud/v2.0/parser/input.pdf/images" \
     -H "Authorization: Bearer YOUR_ACCESS_TOKEN" | \
     jq -r '.images[] | "\(.pageNumber)_\(.imageIndex).\(.fileExtension) \(.base64Data)"' | \
     while read filename b64; do
         echo "$b64" | base64 -d > "$filename"
     done

dotnet add package GroupDocs.Parser-Cloud