mediSync/utils/download_samples.py

import logging
import urllib.request
from pathlib import Path

# Set up logging
logging.basicConfig(
    level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
logger = logging.getLogger(__name__)

# Sample X-ray image URLs (from public sources)
SAMPLE_IMAGES = [
    # Normal chest X-ray
    {
        "url": "https://prod-images-static.radiopaedia.org/images/53448173/322830a37f0fa0852773ca2db3e8d8_big_gallery.jpeg",
        "filename": "normal_chest_xray.jpg",
        "description": "Normal chest X-ray",
    },
    # X-ray with pneumonia
    {
        "url": "https://prod-images-static.radiopaedia.org/images/52465460/e4d8791bd7502ab72af8d9e5c322db_big_gallery.jpg",
        "filename": "pneumonia_xray.jpg",
        "description": "X-ray with pneumonia",
    },
    # X-ray with cardiomegaly
    {
        "url": "https://prod-images-static.radiopaedia.org/images/556520/cf17c05750adb04b2a6e23afb47c7d_big_gallery.jpg",
        "filename": "cardiomegaly_xray.jpg",
        "description": "X-ray with cardiomegaly",
    },
    # X-ray with lung nodule
    {
        "url": "https://prod-images-static.radiopaedia.org/images/19972291/41eed1a2cdad06d26c3f415a6ed65a_big_gallery.jpeg",
        "filename": "nodule_xray.jpg",
        "description": "X-ray with lung nodule",
    },
]


def download_sample_images(output_dir="data/sample"):
    """
    Download sample X-ray images for testing.

    Args:
        output_dir (str): Directory to save images

    Returns:
        list: Paths to downloaded images
    """
    # Get the directory of the script
    script_dir = Path(__file__).resolve().parent.parent

    # Create output directory if it doesn't exist
    output_path = script_dir / output_dir
    output_path.mkdir(parents=True, exist_ok=True)

    downloaded_paths = []

    for image in SAMPLE_IMAGES:
        try:
            filename = image["filename"]
            url = image["url"]
            output_file = output_path / filename

            # Skip if file already exists
            if output_file.exists():
                logger.info(f"File already exists: {output_file}")
                downloaded_paths.append(str(output_file))
                continue

            # Download the image
            logger.info(f"Downloading {url} to {output_file}")

            # Set a user agent to avoid blocking
            opener = urllib.request.build_opener()
            opener.addheaders = [("User-Agent", "Mozilla/5.0")]
            urllib.request.install_opener(opener)

            # Download the file
            urllib.request.urlretrieve(url, output_file)

            logger.info(f"Successfully downloaded {filename}")
            downloaded_paths.append(str(output_file))

        except Exception as e:
            logger.error(f"Error downloading {image['url']}: {e}")

    logger.info(
        f"Downloaded {len(downloaded_paths)} out of {len(SAMPLE_IMAGES)} images"
    )
    return downloaded_paths


def create_sample_info_file(output_dir="data/sample"):
    """
    Create a text file with information about the sample images.

    Args:
        output_dir (str): Directory with sample images
    """
    # Get the directory of the script
    script_dir = Path(__file__).resolve().parent.parent

    # Output path
    output_path = script_dir / output_dir
    info_file = output_path / "sample_info.txt"

    with open(info_file, "w") as f:
        f.write("# Sample X-ray Images\n\n")

        for image in SAMPLE_IMAGES:
            f.write(f"## {image['filename']}\n")
            f.write(f"Description: {image['description']}\n")
            f.write(f"Source: {image['url']}\n\n")

        f.write(
            "\nThese images are used for testing and demonstration purposes only.\n"
        )
        f.write(
            "Please note that these images are from public medical education sources.\n"
        )
        f.write("Do not use for clinical decision making.\n")

    logger.info(f"Created sample info file: {info_file}")


if __name__ == "__main__":
    # Download sample images
    downloaded_paths = download_sample_images()

    # Create info file
    create_sample_info_file()

    print(f"Downloaded {len(downloaded_paths)} sample images.")
    print("Run the application with: python app.py")