From 9b7031b28e19b4d5b5780838d2ee8ab9eb6c8f27 Mon Sep 17 00:00:00 2001 From: Peter Lu Date: Thu, 26 Jan 2017 20:47:16 +0800 Subject: [PATCH] preserve non-ASCII characters when removing special characters in file name --- edx_dl/edx_dl.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/edx_dl/edx_dl.py b/edx_dl/edx_dl.py index cbf40b6c..218a74ac 100644 --- a/edx_dl/edx_dl.py +++ b/edx_dl/edx_dl.py @@ -781,8 +781,9 @@ def _build_filename_from_url(url, target_dir, filename_prefix, is_video=False, original_filename = 'video_%05d.mp4' % video_counter[0] else: original_filename = url.rsplit('/', 1)[1] - # escape characters like ':' that may cause problems under Windows - original_filename = quote(original_filename) + # remove special characters that may cause problems under Windows + original_filename = ''.join(list(filter( + lambda c: c not in ';/?:@&=+$,', original_filename))) filename = os.path.join(target_dir, filename_prefix + '-' + original_filename)