如何有效地检查文件夹是否包含文件列表

Question

我想检查是否所有文件(B01:B12(都存在于某个文件夹中。如果是这种情况，它应该返回True。我知道文件名的末尾，但开头可能有所不同。

目前，我有以下代码。它是有效的，但我觉得它可以做得更有效率。有人知道如何改进吗？

def Check3(filename, root):
path = os.path.join(root, filename)
os.chdir(path)
for dirpath, dirnames, filenames in os.walk(path):
for filename in filenames:
if filename.endswith('_B01.jp2'):
B01 = True
elif filename.endswith('_B02.jp2'):
B02 = True
elif filename.endswith('_B03.jp2'):
B03 = True
elif filename.endswith('_B04.jp2'):
B04 = True
elif filename.endswith('_B05.jp2'):
B05 = True
elif filename.endswith('_B06.jp2'):
B06 = True
elif filename.endswith('_B07.jp2'):
B07 = True
elif filename.endswith('_B08.jp2'):
B08 = True
elif filename.endswith('_B8A.jp2'):
B8A = True
elif filename.endswith('_B09.jp2'):
B09 = True
elif filename.endswith('_B10.jp2'):
B10 = True
elif filename.endswith('_B11.jp2'):
B11 = True
elif filename.endswith('_B12.jp2'):
B12 = True
return B01 and B02 and B03 and B04 and B05 and B06 and B07
and B08 and B8A and B09 and B10 and B11 and B12

Answer 1

您可以使用pathlib获取所有文件，从文件名中提取最后8个字符，然后构建期望的后缀，最后进行比较。

from pathlib import Path
all_last8 = set()
for path in Path(r'your directory').rglob('*.jp2'):
# exract last 8 chars of file name
all_last8.add(path.name[-8:])
# construct all expected suffixes
# hardcode this way, it is same run time efficient
# more verbose though
expected = {'_B01.jp2', '_B02.jp2', '_B03.jp2', }  # ...
# if they are of same pattern
# expected = set([f'_B{str(i).zfill(2)}.jp2' for i in range(1, 13)])
valid = all_last8.issuperset(expected)
print(valid)

代码首先获取所有的文件名和后缀，在进行全局比较时可能会有更有效的方法。

Answer 2

您可以使用glob库，它会在要检查的文件夹下列出符合给定条件的文件。

from glob import glob
def Check3(root):
# list the files which match a specific condition
files = glob('{}/*/*.jp2'.format(root))

# create the list of files you want to check that exists
extensions_check_list = ['_B01.jp2', '_B02.jp2', '_B03.jp2', '_B04.jp2', '_B05.jp2', '_B06.jp2', '_B07.jp2', '_B08.jp2', '_B09.jp2', '_B10.jp2', '_B11.jp2', '_B12.jp2']

# if the number of found files is equal to the number of the expected returns True
return sum([file in extensions_check_list for file in files]) == len(extensions_check_list)

Answer 3

import wizzi_utils as wu  # pip install wizzi_utils

def check_if_sequential(dir_path: str, files_suffix: list) -> bool:
files_in_dir = wu.find_files_in_folder(dir_path=dir_path, file_suffix='')
print('files_in_dir:')
for idx, f in enumerate(files_in_dir):
print('t{}: {}'.format(idx + 1, f))
all_found = True
for suffix in files_suffix:
file_with_suffix_found = False
for file in files_in_dir:
if file.endswith(suffix):
file_with_suffix_found = True
break
if not file_with_suffix_found:
print('suffix {} not found'.format(suffix))
all_found = False
break
if all_found:
print('all files with suffix given found in folder')
else:
print('not all files found')
return all_found

def main() -> None:
files_suffix = [
'_B01.jp2', '_B02.jp2', '_B03.jp2', '_B04.jp2', '_B05.jp2', '_B06.jp2', '_B07.jp2',
'_B08.jp2', '_B8A.jp2', '_B09.jp2', '_B10.jp2', '_B11.jp2', '_B12.jp2',
]
_ = check_if_sequential(dir_path='./my_files', files_suffix=files_suffix)
return

if __name__ == '__main__':
main()

如果所有文件后缀都在文件夹中(还有一个我们不需要的额外文件(，输出将是：

files_in_dir:
1: D:/workspace/2021wizzi_utils/temp/my_files/bla_B01.jp2
2: D:/workspace/2021wizzi_utils/temp/my_files/bla_B02.jp2
3: D:/workspace/2021wizzi_utils/temp/my_files/bla_B03.jp2
4: D:/workspace/2021wizzi_utils/temp/my_files/bla_B04.jp2
5: D:/workspace/2021wizzi_utils/temp/my_files/bla_B06.jp2
6: D:/workspace/2021wizzi_utils/temp/my_files/bla_B07.jp2
7: D:/workspace/2021wizzi_utils/temp/my_files/bla_B08.jp2
8: D:/workspace/2021wizzi_utils/temp/my_files/bla_B09.jp2
9: D:/workspace/2021wizzi_utils/temp/my_files/bla_B10.jp2
10: D:/workspace/2021wizzi_utils/temp/my_files/bla_B11.jp2
11: D:/workspace/2021wizzi_utils/temp/my_files/bla_B12.jp2
12: D:/workspace/2021wizzi_utils/temp/my_files/bla_B8A.jp2
13: D:/workspace/2021wizzi_utils/temp/my_files/random_file.txt
14: D:/workspace/2021wizzi_utils/temp/my_files/x_B05.jp2
all files with suffix given found in folder

现在删除一个并重新运行。我删除了bla_B06.jp2，输出将是：

files_in_dir:
1: D:/workspace/2021wizzi_utils/temp/my_files/bla_B01.jp2
2: D:/workspace/2021wizzi_utils/temp/my_files/bla_B02.jp2
3: D:/workspace/2021wizzi_utils/temp/my_files/bla_B03.jp2
4: D:/workspace/2021wizzi_utils/temp/my_files/bla_B04.jp2
5: D:/workspace/2021wizzi_utils/temp/my_files/bla_B07.jp2
6: D:/workspace/2021wizzi_utils/temp/my_files/bla_B08.jp2
7: D:/workspace/2021wizzi_utils/temp/my_files/bla_B09.jp2
8: D:/workspace/2021wizzi_utils/temp/my_files/bla_B10.jp2
9: D:/workspace/2021wizzi_utils/temp/my_files/bla_B11.jp2
10: D:/workspace/2021wizzi_utils/temp/my_files/bla_B12.jp2
11: D:/workspace/2021wizzi_utils/temp/my_files/bla_B8A.jp2
12: D:/workspace/2021wizzi_utils/temp/my_files/random_file.txt
13: D:/workspace/2021wizzi_utils/temp/my_files/x_B05.jp2
suffix _B06.jp2 not found
not all files found