root/software/similar images/find_duplicates_simple.py @ 29083756
| e28ae23a | dsorber | #!/opt/local/bin/python2.7
|
|
from collections import defaultdict
|
|||
import imghdr
|
|||
import os
|
|||
import sys
|
|||
import pHash
|
|||
# Find Duplicates Simple
|
|||
# Attempt to find images by looking for exact hash collisions.
|
|||
# This method is not very sophisticated and does not work all
|
|||
# that well.
|
|||
def main():
|
|||
img_map = defaultdict(list)
|
|||
# Make sure at least one command line argument was provided
|
|||
if len(sys.argv) < 2:
|
|||
print 'Usage: find_duplicate_simple <path>'
|
|||
return -1;
|
|||
# Print out the path we're walking
|
|||
path = sys.argv[1]
|
|||
print 'Step 1: Walk path: {:s}\n'.format(path)
|
|||
# Walk the root path
|
|||
for root, dirs, files in os.walk(path):
|
|||
for file in files:
|
|||
img_path = os.path.join(root, file)
|
|||
# Check the make sure the file is an actual image
|
|||
if not imghdr.what(img_path):
|
|||
continue
|
|||
img_hash = pHash.imagehash(img_path)
|
|||
print '{:s} -> {:016X}'.format(img_path, img_hash)
|
|||
img_map[img_hash].append(img_path)
|
|||
print '\n\nStep 2: find duplicates\n'
|
|||
# Now look through the image hash dictionary for matches
|
|||
for img_hash, files in img_map.items():
|
|||
if len(files) > 2:
|
|||
print '{:016X}'.format(img_hash)
|
|||
for file_path in files:
|
|||
print '\t{:s}'.format(file_path)
|
|||
if __name__ == '__main__':
|
|||
sys.exit(main())
|