rename same file names in different directories

[elnk]

I have a directory which has 10 other dirs with many files:

- directory
- dir1
- dir2
- dir3
- ...

How can i rename duplicate files from all dirs?
For ex. we have 2 files with name "file1.txt" in "dir1" and "dir2" and we must rename one.

[AdamHensley]

import os; base_dir='path/to/your/directory'; seen_files={}; [os.rename(os.pa Replace 'path/to/your/directory' with the actual path. This will rename duplicates by adding a counter.

[menator01]

Here one way

import os

# Path for executing script
path = os.path.realpath(os.path.dirname(__file__))

# Get all folders in cyrrent folder
folders = [folder for folder in os.listdir(f'{path}') if os.path.isdir(f'{path}/{folder}')]

# Loop through folders
for folder in folders:

    # Get all files in each folder
    files = os.listdir(f'{path}/{folder}')

    # Loop through files and change file name by adding folder prefix
    for file in files:
        os.rename(f'{path}/{folder}/{file}', f'{path}/{folder}/{folder}_{file}')

[Larz60+]

see this post.

[Pedroski55]

The files are different, because they lie in different paths. Change 1, the others will not change.

I put a.txt and b.txt in the main folder and in 3 subfolders.

If you really want to do this, (I think it is unescessary), maybe like this:

from pathlib import Path

def myApp():
    mydir = Path('/home/pedro/temp/')
    file_name_list = [filename.name for filename in mydir.rglob("*") if filename.is_file()]
    len(file_name_list) # 95
    # can't do this with a generator can't use .count(f)
    duplicates = [f for f in file_name_list if file_name_list.count(f) > 1]
    # get tuples of name and number of duplicates
    duplicates = [(f, file_name_list.count(f)) for f in file_name_list if file_name_list.count(f) > 1]
    # get rid of the duplicates in duplicates
    duplicates_set = set(duplicates)
    # can't change sets so convert the set to a list
    dl = list(duplicates_set)
    # now change each tuple in dl to a list
    # because lists are mutable
    for i in range(len(dl)):
        dl[i] = list(dl[i])
    # a generator to get all file names
    file_name_gen = (filename for filename in mydir.rglob("*") if filename.is_file())
    # for each file name look if it is 1 of the lists in dl
    for f in file_name_gen:
        for d in dl:
            if d[0] == f.name:
                print(f.name)
                newname = f.rename(Path(f.parent, f"{f.stem}_{d[1]}_{f.suffix}"))
                print(newname)
                # reduce the duplicate count by 1
                d[1] = d[1] - 1

Now, the numbering starts from the highest number for each subset of different duplicate files and decreases.

Output:
myApp()
a.txt
/home/pedro/temp/a_4_.txt
b.txt
/home/pedro/temp/b_4_.txt
a.txt
/home/pedro/temp/arxiv.org/a_3_.txt
b.txt
/home/pedro/temp/arxiv.org/b_3_.txt
a.txt
/home/pedro/temp/asteriskmag.com/a_2_.txt
b.txt
/home/pedro/temp/asteriskmag.com/b_2_.txt
a.txt
/home/pedro/temp/20BE/a_1_.txt
b.txt
/home/pedro/temp/20BE/b_1_.txt

[snippsat]

Also when removing duplicates it can better to use file hash,then sure that file is a dublicate.
It's easy to use as hashlib and also pathlib is in standard library.
So rglob('*') is recursively and will iterate through all subdirectories.

from pathlib import Path
import hashlib
import os

def remove_duplicate(path: Path) -> Path:
    '''
    Choice <path> will recursively iterate through all subdirectories
    Remove comment <os.remove> and will delete duplicate
    '''
    unique = {}
    for file in Path(path).rglob('*'):
        if file.is_file():
            with open(file, 'rb') as f:
                filehash = hashlib.md5(f.read()).hexdigest()
                if filehash not in unique:
                    unique[filehash] = file
                else:
                    # Test print before removing
                    print(f'Removing --> {unique[filehash]}')
                    '''try:
                        os.remove(unique[filehash])
                    except OSError:
                        pass'''

if __name__ == '__main__':
    path = Path(r'G:\div_code\reader_env\my_folder')
    remove_duplicate(path)