adelgado/find_duplicate_files
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add scanning

Browse source
This commit is contained in:
Antonio J. Delgado 2023-01-25 14:30:40 +02:00
parent aa503a4234
commit 4f294524ca
1 changed files with 19 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
find_duplicate_files/find_duplicate_files.py
View file

@ -27,24 +27,27 @@ class find_duplicate_files:
self.first_directory = first_directory self.first_directory = first_directory
self.second_directory = second_directory self.second_directory = second_directory
first_files = self._find_files(self.first_directory) first_files = self.recursive_scandir(self.first_directory)
second_files = self._find_files(self.second_directory) second_files = self.recursive_scandir(self.second_directory)
def _find_files(self, directory, hidden=False): def recursive_scandir(self, path, ignore_hidden_files=True):
if os.path.exists(directory): ''' Recursively scan a directory for files'''
files = list() files = []
with os.scandir(directory) as it: try:
for entry in it: for file in os.scandir(path):
if not entry.name.startswith('.') and entry.is_file(): if not file.name.startswith('.'):
file = { if file.is_file():
'file': entry.name
}
files.append(file) files.append(file)
self._log.debug(f"Found {len(files)} in '{directory}'") elif file.is_dir(follow_symlinks=False):
return files more_files = self.recursive_scandir(
else: file.path,
self._log.error(f"Given path '{directory}' doesn't exist.") ignore_hidden_files=ignore_hidden_files
sys.exit(1) )
if more_files:
files = files + more_files
except PermissionError as error:
self._log.warning(f"Permission denied accessing folder '{path}'")
return files
def _init_log(self): def _init_log(self):
''' Initialize log object ''' ''' Initialize log object '''