Count unique EXIF tags

count-exif-tags.py

    def grouper(iterable, n, fillvalue=None):
        args = [iter(iterable)] * n
        return izip_longest(*args, fillvalue=fillvalue)

    # read exif data and build a list of unique keys

    media_files = []
    for root, sub_folders, files in walk(app.config['MEDIA_ROOT']):
        for f in files:
            media_files.append(path.join(root, f))

    chunksize=512
    lm = len(media_files)
    ng = lm / chunksize

    exif_keys = {}
    with ExifTool() as et:
        print "Examining {} files ({} groups)".format(lm, ng)
        for i, group in enumerate(grouper(media_files, chunksize)):
            group = filter(None, group)
            print "group #{}/{} group sz: {}".format(i, ng, len(group))
            metadata = et.get_metadata_batch(group)
            for entry in metadata:
                for k,v in entry.items():
                    if k in exif_keys:  exif_keys[k] += 1
                    else:               exif_keys[k] = 1

    print "Found {} keys".format(len(exif_keys))