Files
check_duplicate_files/app.py
T

52 lines
1.6 KiB
Python

from _in_package import *
import config
import common
import runing_data
def traverse_dir(root_dir):
for path, dirs, files in os.walk(root_dir):
path = common.formatting_path(path)
for filename in files:
runing_data.file_path_list.append(path + filename)
def hash_files_from_glist(algorithm: function):
for f_path in runing_data.file_path_list:
with open(f_path, "rb") as f:
f_hash = hashlib.file_digest(f, algorithm)
runing_data.file_hash_results.append(runing_data.FileHashResult(f_path, f_hash.hexdigest(), algorithm.__name__))
runing_data.hash_to_files[(f_hash.hexdigest(), algorithm.__name__)].append(f_path)
def print_info():
for t in runing_data.hash_to_files:
if len(runing_data.hash_to_files[t]) > 1:
st_size = os.stat(runing_data.hash_to_files[t][0]).st_size
if st_size <= 10240:
continue
print(t, f"size: {st_size} Byte")
for fp in runing_data.hash_to_files[t]:
print("\t", fp)
print()
def reg_opts():
parser = argparse.ArgumentParser()
parser.add_argument("-P", "--path", default=None, required=False)
parser.add_argument("--fsize", default=None, required=False, help="只打印文件大小大于fsize Byte的重复文件")
args = parser.parse_args()
if args.path != None:
config.work_dir = args.path
elif args.fsize != None:
config.flag_size = args.fsize
reg_opts()
if not os.path.exists(config.work_dir):
exit(-1)
traverse_dir(config.work_dir)
hash_files_from_glist(hashlib.sha256)
print_info()