github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

patch to fix #2499, pelican import assert when downloading wordpress artifact with non utf-8 chars.

Browse source
This commit is contained in:
Roland Askew 2019-01-11 19:20:14 +13:00
commit ff7433f161
1 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
pelican/tools/pelican_import.py
View file

@ -12,7 +12,7 @@ from codecs import open
from collections import defaultdict
from six.moves.urllib.error import URLError
from six.moves.urllib.parse import urlparse
from six.moves.urllib.parse import urlparse, urlsplit, urlunsplit, quote
from six.moves.urllib.request import urlretrieve
# because logging.setLoggerClass has to be called before logging.getLogger
@ -729,6 +729,12 @@ def download_attachments(output_path, urls):
full_path = os.path.join(output_path, localpath)
if not os.path.exists(full_path):
os.makedirs(full_path)
# Generate percent-encoded URL
scheme, netloc, path, query, fragment = urlsplit(url)
path = quote(path)
url = urlunsplit((scheme, netloc, path, query, fragment))
print('downloading {}'.format(filename))
try:
urlretrieve(url, os.path.join(full_path, filename))