This commit is contained in:
2023-01-13 14:24:11 +08:00
parent 11885055f8
commit c1cecd4d1d
2 changed files with 20 additions and 17 deletions

View File

@@ -13,23 +13,26 @@ def main():
print(repeated_file)
# import guan
# repeated_file = guan.find_repeated_file_with_same_filename(directory='./', missed_directory_with_words=[], missed_file_with_words=[], num=1000)
# repeated_file = guan.find_repeated_file_with_same_filename(directory='./', ignored_directory_with_words=[], ignored_file_with_words=[], num=1000)
# print(repeated_file)
def find_repeated_file_with_same_filename(directory='./', missed_directory_with_words=[], missed_file_with_words=[], num=1000):
def find_repeated_file_with_same_filename(directory='./', ignored_directory_with_words=[], ignored_file_with_words=[], num=1000):
import os
from collections import Counter
file_list = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
file_list.append(files[i0])
for word in missed_file_with_words:
if word in files[i0]:
file_list.remove(files[i0])
for word in missed_directory_with_words:
for word in ignored_directory_with_words:
if word in root:
file_list.remove(files[i0])
file_list.remove(files[i0])
for word in ignored_file_with_words:
if word in files[i0]:
try:
file_list.remove(files[i0])
except:
pass
count_file = Counter(file_list).most_common(num)
repeated_file = []
for item in count_file: