Saving highlighted content automatically as images

Message Topic Search Topic Options Post Reply Create New Topic Printable Version Translate Topic

private void ExtractAnnots_Click(object sender, EventArgs e)
    {
        int dpi = 300;
        Rectangle r;
        List<Rectangle> annotList = new List<Rectangle>();

        QP.LoadFromFile("samplefile.pdf", "");

        for (int p = 1; p <= QP.PageCount(); p++)
        {
            QP.SelectPage(p);  // Select the current page.
            QP.SetOrigin(1);   // Set origin to top left.

            annotList.Clear();

            for (int i = 1; i <= QP.AnnotationCount(); i++)
            {
                if (QP.GetAnnotStrProperty(i, 101) == "Highlight")
                {
                    r = new Rectangle((int)(QP.GetAnnotDblProperty(i, 105) * dpi / 72.0),  // x
                                      (int)(QP.GetAnnotDblProperty(i, 106) * dpi / 72.0),  // y
                                      (int)(QP.GetAnnotDblProperty(i, 107) * dpi / 72.0),  // w
                                      (int)(QP.GetAnnotDblProperty(i, 108) * dpi / 72.0)); // h

                    annotList.Add(r); // Add the bounding box to the annotation list for this page.

                    string s = String.Format("page={0}: x={1} y={2} w={3} h={4}\n", p, r.X, r.Y, r.Width, r.Height);
                    OutputTxt.AppendText(s);
                }
            }

            // Now we have a list of annotations for the current page.
            // Delete the annotations from the PDF in memory so we don't render them.

            for (int i = QP.AnnotationCount(); i >= 0;  i--)   
                QP.DeleteAnnotation(i);

            QP.RenderPageToFile(dpi, p, 0, "page.bmp");   // 300 dpi, 0=bmp
            Bitmap bmp = Image.FromFile("page.bmp") as Bitmap; 

            for (int i=0;i<annotList.Count;i++)
            {
                Bitmap cropped = bmp.Clone(annotList, bmp.PixelFormat);

                string filename = String.Format("annot_p{0}_{1}.bmp", p, i+1);
                cropped.Save(filename);
            }

            bmp.Dispose();
        }

        QP.RemoveDocument(QP.SelectedDocument());
    }

Author	Message Topic Search Topic Options Post Reply Create New Topic Printable Version Translate Topic
vg2786 Members Profile Find Members Posts Beginner Joined: 21 Jan 12 Status: Offline Points: 1	Post Options Post Reply Quote vg2786 Report Post Thanks(0) Quote Reply Topic: Saving highlighted content automatically as images Posted: 21 Jan 12 at 11:53AM
	Hello Everyone, I have a pdf file in which some text and images are highlighted using highlight text(U) tool. Is there a way to automatically extract all the highlighted content as separate images and save it to a folder? I dont want readable text. I just want all the highlighted content as images. Thanks I want to upload the sample file. But here there is no option to upload the sample file. http://www.sendspace.com/file/hejhkp

Ingo Members Profile Find Members Posts Moderator Group Joined: 29 Oct 05 Status: Offline Points: 3529	Post Options Post Reply Quote Ingo Report Post Thanks(0) Quote Reply Posted: 21 Jan 12 at 9:57PM
	Hi! No. It's not possible with a QuickPDF-function and i fear you won't find any pdf-library on the world offering this functionality. You can try to do it yourself WITH QuickPDF. It will be the hardest stuff you ever done developing ;-) Sorry... Cheers and welcome here, Ingo Edited by Ingo - 21 Jan 12 at 9:58PM

edvoigt Members Profile Find Members Posts Senior Member Joined: 26 Mar 11 Location: Berlin, Germany Status: Offline Points: 111	Post Options Post Reply Quote edvoigt Report Post Thanks(0) Quote Reply Posted: 23 Jan 12 at 4:58PM
	Hi, i think you are on a wrong way. Instead of using a tool to highlight areas of interest use easy a screenshot-programm and you get images. I use for this http://screenpresso.com. A powerfull easy to use solution. To extract the highlighted areas directly from PDF is a hard nut. Cheers, Werner

AndrewC Members Profile Find Members Posts Moderator Group Joined: 08 Dec 10 Location: Geelong, Aust Status: Offline Points: 841	Post Options Post Reply Quote AndrewC Report Post Thanks(0) Quote Reply Posted: 23 Jan 12 at 11:53PM
	Here is some C# code that does the job. private void ExtractAnnots_Click(object sender, EventArgs e) { int dpi = 300; Rectangle r; List<Rectangle> annotList = new List<Rectangle>(); QP.LoadFromFile("samplefile.pdf", ""); for (int p = 1; p <= QP.PageCount(); p++) { QP.SelectPage(p); // Select the current page. QP.SetOrigin(1); // Set origin to top left. annotList.Clear(); for (int i = 1; i <= QP.AnnotationCount(); i++) { if (QP.GetAnnotStrProperty(i, 101) == "Highlight") { r = new Rectangle((int)(QP.GetAnnotDblProperty(i, 105) * dpi / 72.0), // x (int)(QP.GetAnnotDblProperty(i, 106) * dpi / 72.0), // y (int)(QP.GetAnnotDblProperty(i, 107) * dpi / 72.0), // w (int)(QP.GetAnnotDblProperty(i, 108) * dpi / 72.0)); // h annotList.Add(r); // Add the bounding box to the annotation list for this page. string s = String.Format("page={0}: x={1} y={2} w={3} h={4}\n", p, r.X, r.Y, r.Width, r.Height); OutputTxt.AppendText(s); } } // Now we have a list of annotations for the current page. // Delete the annotations from the PDF in memory so we don't render them. for (int i = QP.AnnotationCount(); i >= 0; i--) QP.DeleteAnnotation(i); QP.RenderPageToFile(dpi, p, 0, "page.bmp"); // 300 dpi, 0=bmp Bitmap bmp = Image.FromFile("page.bmp") as Bitmap; for (int i=0;i<annotList.Count;i++) { Bitmap cropped = bmp.Clone(annotList, bmp.PixelFormat); string filename = String.Format("annot_p{0}_{1}.bmp", p, i+1); cropped.Save(filename); } bmp.Dispose(); } QP.RemoveDocument(QP.SelectedDocument()); }