Deduplicate photo directories based on the basename + size

deduplicate_photos.py

# pip install exifread

import os
import shutil
import exifread

def get_date(filename):
    try:
        with open(filename, 'rb') as fh:
            tags = exifread.process_file(fh, stop_tag="Image DateTime")
            dateTaken = tags["Image DateTime"]
            dateTaken = dateTaken.values[:10].replace(':', '')
            return dateTaken
    except KeyError:
        return 'unknown'

existing_size = {}
for dirpath, dirnames, filenames in os.walk("."):
    for filename in [f for f in filenames if f[0] != '.' and
                    f[-4:].upper() in ['.JPG', '.GIF', '.PNG', '.MOV', '.AVI', 'RAW']]:
        full_name = os.path.join(dirpath, filename)
        print(full_name)
        size = os.path.getsize(full_name)
        datestamp = get_date(full_name)
        try:
            basename = filename.split(' ')[0].split('.')[0] + '_' + datestamp + '_' + str(size)
        except UnicodeDecodeError:
            continue
        if basename not in existing_size:
            existing_size[basename] = []
        existing_size[basename].append(full_name)

existing_size =  {k: v for k, v in existing_size.items() if len(v) > 1}
        
remove = False
for file_list in existing_size.values():
    rem_list = file_list[:-1]
    print(rem_list, file_list[-1])
    if remove:
        for filename in rem_list:
            os.remove(filename)

        
# now for real: