Created
May 28, 2020 17:55
-
-
Save ratozumbi/dc1fe7dcdacd41a5329c4dc1fdf32961 to your computer and use it in GitHub Desktop.
python script that hashes files recursively then compare each one to find duplicates
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 hashlib | |
import os | |
def getHashes(path, fileHashes): | |
print("executing in "+ path) | |
for filename in os.listdir(path): | |
fullpath = os.path.join(path,filename) | |
if os.path.isfile(fullpath): | |
hasher = hashlib.md5() | |
with open(fullpath, 'rb') as afile: | |
#swap lines to work with big files | |
buf = afile.read() | |
hasher.update(buf) | |
# BLOCKSIZE = 65536 | |
# buf = afile.read(BLOCKSIZE) | |
# while len(buf) > 0: | |
# hasher.update(buf) | |
# buf = afile.read(BLOCKSIZE) | |
fileHashes.write(hasher.hexdigest() + "##" + fullpath + "\n") | |
else: | |
getHashes(fullpath, fileHashes) | |
with open("./hashes.txt", "w+") as fileHashes: | |
getHashes('.', fileHashes) | |
dicHashPath = {} | |
with open("./hashes.txt", "r") as fileHashes: | |
with open("./result.txt", "w+") as searchResult: | |
hashLines = fileHashes.readlines() | |
for line in hashLines: | |
lineHashPath = line.split("##") | |
if lineHashPath[0] in dicHashPath: | |
print("===================\nCopia encontrada em " + lineHashPath[1] + "Original: " + dicHashPath[lineHashPath[0]] + "MD5: " +lineHashPath[0] ) | |
searchResult.write("===================\nCopia encontrada em " + lineHashPath[1] + "Original: " + dicHashPath[lineHashPath[0]]+ "MD5: " +lineHashPath[0]+ "\n") | |
else: | |
dicHashPath[lineHashPath[0]] =lineHashPath[1] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment