-
-
Save voyeg3r/4373177 to your computer and use it in GitHub Desktop.
I my research on file duplicated solutions this is cool piece of code :)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import os | |
import hashlib | |
# source: http://stackoverflow.com/questions/748675/finding-duplicate-files-and-removing-them | |
# This version uses the file size and a hash of the contents to find duplicates. You can pass | |
# it multiple paths, it will scan all paths recursively and report all duplicates found. | |
def chunk_reader(fobj, chunk_size=1024): | |
"""Generator that reads a file in chunks of bytes""" | |
while True: | |
chunk = fobj.read(chunk_size) | |
if not chunk: | |
return | |
yield chunk | |
def check_for_duplicates(paths, hash=hashlib.sha1): | |
hashes = {} | |
for path in paths: | |
for dirpath, dirnames, filenames in os.walk(path): | |
for filename in filenames: | |
full_path = os.path.join(dirpath, filename) | |
hashobj = hash() | |
for chunk in chunk_reader(open(full_path, 'rb')): | |
hashobj.update(chunk) | |
file_id = (hashobj.digest(), os.path.getsize(full_path)) | |
duplicate = hashes.get(file_id, None) | |
if duplicate: | |
print "Duplicate found: %s and %s" % (full_path, duplicate) | |
else: | |
hashes[file_id] = full_path | |
if sys.argv[1:]: | |
check_for_duplicates(sys.argv[1:]) | |
else: | |
print "Please pass the paths to check as parameters to the script" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment