Created
August 28, 2015 05:31
-
-
Save genzj/10f0d0f04e8e90c9387b to your computer and use it in GitHub Desktop.
Clean / unquote url encode sequences in downloaded files.
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
#!/usr/bin/env python | |
from __future__ import generators | |
from functools import partial | |
import os, os.path | |
try: | |
from urllib import unquote | |
except ImportError: | |
from urllib.parse import unquote | |
def legalize_win_file_name(filename, substituent='.'): | |
invalid_chars = r'\/:*?"<>|' | |
return ''.join(substituent if c in invalid_chars else c for c in filename) | |
def clean_name(filename, windows_name=True): | |
clean_name = unquote(filename) | |
return legalize_win_file_name(clean_name) if windows_name else clean_name | |
def rename_file(dirname, filename): | |
original, target = os.path.join(dirname, filename), os.path.join(dirname, clean_name(filename)) | |
if original == target: | |
# print("no change: %s"%(original, )) | |
return | |
print("rename %s to %s" % (original, target)) | |
os.rename(original, target) | |
def walk_folder(topdir): | |
for dirpath, dirnames, filenames in os.walk(topdir): | |
list(map(partial(rename_file,dirpath), filenames)) | |
if __name__ == "__main__": | |
walk_folder('.') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment