func extractPDFPagesAsImages(pdfPath string, outputDir string) error {
// Open the PDF file
f, err := os.Open(pdfPath)
if err != nil {
    return err
}
defer f.Close()

// Read the PDF document
doc, err := model.NewPdfReader(f)
if err != nil {
    return err
}

// Iterate over each page
numPages, err := doc.GetNumPages()
if err != nil {
    return err
}
for i := 0; i < numPages; i++ {
    _, err := doc.GetPage(i + 1)
    if err != nil {
        return err
    }

    // Render the page to an image
    img, err := renderPDFPageToImage(doc, i+1)
    if err != nil {
        return err
    }

    // Save the image as PNG
    outputFilePath := fmt.Sprintf("%s/page_%d.png", outputDir, i+1)
    outFile, err := os.Create(outputFilePath)
    if err != nil {
        return err
    }
    defer outFile.Close()

    err = png.Encode(outFile, img)
    if err != nil {
        return err
    }
}

return nil

}

This is my function that uses unipdf to convert a pdf file to all of its pages. Now it works the only issue is that the image outputted is really low res. How do I increase its quality so that the texts appear crisp

I have looked up multiple documentations even tried using ChatGPT but nothing gives me the right answer

func extractPDFPagesAsImages(pdfPath string, outputDir string) error {
// Open the PDF file
f, err := os.Open(pdfPath)
if err != nil {
    return err
}
defer f.Close()

// Read the PDF document
doc, err := model.NewPdfReader(f)
if err != nil {
    return err
}

// Iterate over each page
numPages, err := doc.GetNumPages()
if err != nil {
    return err
}
for i := 0; i < numPages; i++ {
    _, err := doc.GetPage(i + 1)
    if err != nil {
        return err
    }

    // Render the page to an image
    img, err := renderPDFPageToImage(doc, i+1)
    if err != nil {
        return err
    }

    // Save the image as PNG
    outputFilePath := fmt.Sprintf("%s/page_%d.png", outputDir, i+1)
    outFile, err := os.Create(outputFilePath)
    if err != nil {
        return err
    }
    defer outFile.Close()

    err = png.Encode(outFile, img)
    if err != nil {
        return err
    }
}

return nil

}

This is my function that uses unipdf to convert a pdf file to all of its pages. Now it works the only issue is that the image outputted is really low res. How do I increase its quality so that the texts appear crisp

I have looked up multiple documentations even tried using ChatGPT but nothing gives me the right answer

• go

1 Answer 1

You need to modify the rendering DPI (dots per inch) and use the appropriate image extraction settings.

func renderPDFPageToImage(doc *model.PdfReader, pageNum int) (image.Image, error) {
    page, err := doc.GetPage(pageNum)
    if err != nil {
        return nil, err
    }

    // Create device with high DPI (e.g., 300 DPI)
    device := render.NewImageDevice(render.ImageDeviceOptions{
        DPI:                     300,
        BackgroundColor:         color.White,
        EnableImageCompression:  false,
        CompressedImageQuality:  100,
        ImageQuality:            100,
        Scale:                   2.0,         // Optional
        ColorSpace:              "DeviceRGB", // Optional
    })

    if err := device.RenderPage(page); err != nil {
        return nil, err
    }

    return device.Image(), nil
}

func extractPDFPagesAsImages(pdfPath string, outputDir string) error {
    f, err := os.Open(pdfPath)
    if err != nil {
        return err
    }
    defer f.Close()

    doc, err := model.NewPdfReader(f)
    if err != nil {
        return err
    }

    numPages, err := doc.GetNumPages()
    if err != nil {
        return err
    }

    for i := 0; i < numPages; i++ {
        img, err := renderPDFPageToImage(doc, i+1)
        if err != nil {
            return err
        }

        outputFilePath := fmt.Sprintf("%s/page_%d.png", outputDir, i+1)
        outFile, err := os.Create(outputFilePath)
        if err != nil {
            return err
        }

        encoder := png.Encoder{
            CompressionLevel: png.NoCompression,
        }
        
        err = encoder.Encode(outFile, img)
        outFile.Close()
        if err != nil {
            return err
        }
    }

    return nil
}