kevinveenbirkenbach/duplicate-file-handler
1
0
Fork 0
mirror of https://github.com/kevinveenbirkenbach/duplicate-file-handler.git synced 2024-11-22 05:51:03 +01:00
Code Issues Packages Projects Releases Wiki Activity

implemented progress

Browse Source
This commit is contained in:
Kevin Veen-Birkenbach 2023-11-14 13:39:59 +01:00
parent 8fc0d37a09
commit 0c49ca0fcc
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
main.py
View File

@ -2,6 +2,7 @@ import os
import argparse import argparse
import hashlib import hashlib
from collections import defaultdict from collections import defaultdict
from tqdm import tqdm
def md5sum(filename): def md5sum(filename):
hash_md5 = hashlib.md5() hash_md5 = hashlib.md5()
@ -13,10 +14,10 @@ def md5sum(filename):
def find_duplicates(directories, file_type): def find_duplicates(directories, file_type):
hashes = defaultdict(list) hashes = defaultdict(list)
for directory in directories: for directory in directories:
for root, dirs, files in os.walk(directory, followlinks=False): for root, dirs, files in tqdm(os.walk(directory, followlinks=False), desc="Indexing files", unit="dir"):
for filename in files: for filename in files:
if file_type and not filename.endswith(file_type): if file_type and not filename.endswith(file_type):
continue continue
path = os.path.join(root, filename) path = os.path.join(root, filename)
if not os.path.islink(path): if not os.path.islink(path):
file_hash = md5sum(path) file_hash = md5sum(path)