Created
September 14, 2021 16:02
-
-
Save rldotai/cc1e4169e9ec6941a9b332f52217c6df to your computer and use it in GitHub Desktop.
Bulk renaming files with Python to make them more consistent/easier to type. Not especially difficult, but it comes up surprisingly often.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Renaming files to make them more consistent/easier to type. | |
""" | |
import unicodedata | |
import re | |
from pathlib import Path | |
# You can use whatever function you prefer, but Django's slugify is pretty slick | |
def slugify(value, allow_unicode=False): | |
""" | |
Taken from https://github.com/django/django/blob/master/django/utils/text.py | |
Convert to ASCII if 'allow_unicode' is False. Convert spaces or repeated | |
dashes to single dashes. Remove characters that aren't alphanumerics, | |
underscores, or hyphens. Convert to lowercase. Also strip leading and | |
trailing whitespace, dashes, and underscores. | |
""" | |
value = str(value) | |
if allow_unicode: | |
value = unicodedata.normalize("NFKC", value) | |
else: | |
value = ( | |
unicodedata.normalize("NFKD", value) | |
.encode("ascii", "ignore") | |
.decode("ascii") | |
) | |
value = re.sub(r"[^\w\s-]", "", value.lower()) | |
return re.sub(r"[-\s]+", "_", value).strip("-_") | |
# Get all files contained within a directory and its subdirectories | |
to_rename = (x for x in SOME_DIRECTORY.rglob("**/*") if x.is_file()) | |
# Rename all paths accordingly | |
for path in to_rename: | |
new_path = path.with_stem(slugify(path.stem)) | |
print(path) | |
print(new_path) | |
path.rename(new_path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment