如何从 PDF 文档中提取图像

/// <summary>

/// Extracting Images from Pdf File With .Net C# and PDF Library

/// </summary>

private int _writedImageIndex = 0;

public void ExtractAllImages()

{

    //Initialize the SDK library

    //You have to call this function before you can call any PDF processing functions.

    PdfCommon.Initialize();

    //Open and load a PDF document from a file.

    using (var doc = PdfDocument.Load(@”c:\test001.pdf”)) // C# Read PDF File

    {

        //Enumerate all pages sequentially in a given document

        foreach (var page in doc.Pages)

        {

            //Extract and save images

            ExtractImagesFromPage(page);

            //dipose page object to unload it from memory

            page.Dispose();

        }

    }

}

private void ExtractImagesFromPage(PdfPage page)

{

    //Enumerate all objects on a page

    foreach (var obj in page.PageObjects)

    {

        var imageObject = obj as PdfImageObject;

        if (imageObject == null)

            continue; //if not an image object then nothing do

        //Save image to disk

        var path = string.Format(@”c:\\Images\\image_{0}.png”, ++_writedImageIndex);

        imageObject.Bitmap.Image.Save(path, ImageFormat.Png);

    }

}

END

公司名称：北京哲想软件有限公司

北京哲想软件官方网站：cogitosoft.com

北京哲想软件微信公众平台账号：cogitosoftware

北京哲想软件微博：哲想软件

北京哲想软件邮箱：sales@cogitosoft.com

销售（俞先生）联系方式：+86（010）68421378

微信：18610247936     QQ：368531638