Please use the script to find all duplicate files from your computer on the specific folder or path
Note: Script will find duplicate files based on its hash string value (MD5), not only based on file’ name.
You can also change the path to find duplicates over there!
## find and remove duplicate files, by hash (by file' content)!
import os
import hashlib
def hashfile(path, blocksize = 65536):
try:
afile = open(path, 'rb')
hasher = hashlib.md5()
buf = afile.read(blocksize)
while len(buf) > 0:
hasher.update(buf)
buf = afile.read(blocksize)
afile.close()
return hasher.hexdigest()
except Exception as e:
print e
def findDup(parentFolder):
# Dups in format {hash:[names]}
dups = {}
for dirName, subdirs, fileList in os.walk(parentFolder):
print('Scanning %s...' % dirName)
for filename in fileList:
# Get the path to the file
path = os.path.join(dirName, filename)
# Calculate hash
file_hash = hashfile(path)
# Add or append the file path
if file_hash in dups:
dups[file_hash].append(path)
else:
dups[file_hash] = [path]
return dups
def printResults(dict1):
results = list(filter(lambda x: len(x) > 1, dict1.values()))
if len(results) > 0:
print('Duplicates Found:')
print('The following files are same. The name could differ, but the content is same')
print('__')
for result in results:
for subresult in result:
print('%s' % subresult)
print('__')
else:
print('No duplicate files found.')
def removeDuplicates(dict1):
results = list(filter(lambda x: len(x) > 1, dict1.values()))
if len(results) > 0:
print '
'
print 'Removed Files:'
print('__')
for result in results:
for ele in result[:-1]:
os.remove(ele)
print ele
print('__')
else:
pass
if __name__ == '__main__':
dict = findDup('C:\\Users\\Administrator\\Downloads') ## you change your path here...
printResults(dict)
removeDuplicates(dict)
Sample Output:
