Inspect a list of images to see if any of them have really giant dimensions

how_big_them_shits_is.py

#!/usr/bin/env python3
"""
This script takes as input a list of image IDs from image table and
uses the Pillow python library to determine the height and width
of each image. Indicate if the image is larger than a configured pixel limit.
"""

from argparse import ArgumentParser
import os
import sys
import struct
import imghdr

__version__ = '0.1'
binstore_path = ""
library = ""


def parse_args():
    parser = ArgumentParser(
        usage='%(prog)s [options] [INFILE ...]',
        description=__doc__,
        prog=os.path.basename(sys.argv[0])
    )
    parser.add_argument('infile', metavar='INFILE',
                        help='File containing the list of images')
    parser.add_argument('-b', '--binstore-path', default="/mnt/binstore/",
                        help='Path to the directory containing the binstore')
    parser.add_argument('--library', choices=['native', 'pillow'],
                        default='pillow',
                        help='''Use PIL image processing if available, else
                        use native options to read the image headers''')
    parser.add_argument('--version', action='version', version=__version__)
    args = parser.parse_args()
    if not (args.infile):
        parser.error("An input file must be specified")
        sys.exit(0)
    global binstore_path
    global library
    binstore_path = args.binstore_path
    library = args.library
    return args


def is_too_big(image):
    """Determine if this image is larger than the application can handle"""
    height, width = image.size
    return is_too_many_pixels(height, width)


def is_too_many_pixels(height, width):
    """Determine if the height * width of this image results in exceeding the
    max pixel check"""
    return (height * width) >= 64000000


def get_image_size(fname):
    #  http://stackoverflow.com/questions/8032642/how-to-obtain-image-size-using-standard-python-class-without-using-external-lib
    with open(fname, 'rb') as fhandle:
        head = fhandle.read(24)
        if len(head) != 24:
            return
        if imghdr.what(fname) == 'png':
            check = struct.unpack('>i', head[4:8])[0]
            if check != 0xd0a1a0a:
                return
            width, height = struct.unpack('>ii', head[16:24])
        elif imghdr.what(fname) == 'gif':
            width, height = struct.unpack('<HH', head[6:10])
        elif imghdr.what(fname) == 'jpeg':
            try:
                fhandle.seek(0)  # Read 0xff next
                size = 2
                ftype = 0
                while not 0xc0 <= ftype <= 0xcf:
                    fhandle.seek(size, 1)
                    byte = fhandle.read(1)
                    while ord(byte) == 0xff:
                        byte = fhandle.read(1)
                        ftype = ord(byte)
                        size = struct.unpack('>H', fhandle.read(2))[0] - 2
                        #  We are at a SOFn block
                        fhandle.seek(1, 1)  # Skip 'precision' byte
                        height, width = struct.unpack('>HH', fhandle.read(4))
            except Exception:  # IGNORE:W0703
                return
        else:
            return
        return width, height


def handle_name(imagename):
    """Check a single image file"""
    try:
        from PIL import Image
    except ImportError:
        pass

    if Image and library == 'pillow':
        try:
            with Image.open(imagename) as im:
                print(imagename, im.format, "%dx%d" % im.size)
                if is_too_big(im):
                    print(imagename, " is too big at ", im.size)
        except IOError:
            print("error opening ", imagename)
            pass
    else:
        try:
            width, height = get_image_size(imagename)
            if is_too_big(width, height):
                print(imagename, " is too big at ", width, height, " pixels")
        except IOError:
            print("error opening ", imagename, " with native library")
            pass


def get_image_filename_from_imagename(imagename):
    newname = imagename.replace('-', '45')[::-1]
    first_three_chars = list(newname[:3])
    binstorepath = binstore_path + 'jsbs/%s.bin' % '/'.join(first_three_chars+[newname])
    print("binstore path for", imagename, " is ", binstorepath)
    return imagename


def main():
    """ This function handles the main logic of the script"""
    args = parse_args()
    infile = args.infile if args.infile else sys.exit(0)
    print(args.binstore_path)
    print(args.library)
    with open(infile) as fobj:
        for line in fobj:
            line = line.replace('\n', '')
            handle_name(get_image_filename_from_imagename(line))
            # print(line, " is ", get_image_size(line))


if __name__ == "__main__":
    main()