memo: Python | pathlib

Construct path

Make the filename an object instead of strings.

1
2
3
4
5
6
7


from pathlib import Path

# Instantiate an object:
datadir = Path("./datadir")

# Joining Paths
new_path = datadir / "sampled.npy"

Iterate dir

.iterdir() method iterates over all the files in the given directory

1
2
3
4
5


from pathlib import Path
from collections import Counter

# count number of files of different types
Counter(path.suffix for path in Path.cwd().iterdir())

Return: Counter({'.md': 2, '.txt': 4, '.pdf': 2, '.py': 1})

.glob("*.txt") returns all the files with a .txt suffix in the current directory.

1
2


>>> Counter(path.suffix for path in Path.cwd().glob("*.p*"))
Counter({'.pdf': 2, '.py': 1})

.rglob() recursively find all the files in both the directory and its subdirectories.

1
2
3
4
5
6


def tree(Path(directory)):
  print(f"+ {directory}")
  for path in sorted(directory.rglob("*")):
    depth = len(path.relative_to(directory).parts)
    spacer = "    " * depth
    print(f"{spacer}+ {path.name}")

glob two patterns

python - How to glob two patterns with pathlib? - Stack Overflow

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13


from pathlib import Path

exts = [".jl", ".jsonlines"]
mainpath = "/path/to/dir"

# Same directory
files = [p for p in Path(mainpath).iterdir() if p.suffix in exts]

# Recursive
files = [p for p in Path(mainpath).rglob('*') if p.suffix in exts]

# 'files' will be a generator of Path objects, to unpack into strings:
list(files)