def _sort_locations(locations, expand_dir=False):
"""
Sort locations into "files" (archives) and "urls", and return
a pair of lists (files,urls)
"""
files = []
urls = []
# puts the url for the given file path into the appropriate list
def sort_path(path):
url = path_to_url(path)
if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
urls.append(url)
else:
files.append(url)
for url in locations:
is_local_path = os.path.exists(url)
is_file_url = url.startswith('file:')
if is_local_path or is_file_url:
if is_local_path:
path = url
else:
path = url_to_path(url)
if os.path.isdir(path):
if expand_dir:
path = os.path.realpath(path)
for item in os.listdir(path):
sort_path(os.path.join(path, item))
elif is_file_url:
urls.append(url)
elif os.path.isfile(path):
sort_path(path)
else:
logger.warning(
"Url '%s' is ignored: it is neither a file "
"nor a directory.", url)
elif is_url(url):
# Only add url with clear scheme
urls.append(url)
else:
logger.warning(
"Url '%s' is ignored. It is either a non-existing "
"path or lacks a specific scheme.", url)
return files, urls
评论列表
文章目录
