file_pattern = 'data/columns/rows/N193-022_0184-col-*'
images = glob.glob(file_pattern)
data = []
for image in images:
if 'header' not in image:
filename = image.split('/')[-1]
volume = re.search(r'(N193-\d+)_', filename).group(1)
page = re.search(r'N193-\d+_(\d+)-col', filename).group(1)
column = re.search(r'N193-\d+_\d+-col-(\d+)', filename).group(1)
row = re.search(r'N193-\d+_\d+-col-\d+-(\d+)', filename).group(1)
data.append({'image': filename, 'volume': volume, 'page': page, 'column': column, 'row': row})
df = pd.DataFrame(data)
df['row'] = pd.to_numeric(df['row'])
df = df.sort_values('row')
df.head()