def test_encode_html(self):
"""utils encode_html (FAILS - DISABLED)"""
# why this does not encode < ?
from flexget.utils.tools import encode_html
print(encode_html('<3'))
assert encode_html('<3') == '<3'
def test_encode_html(self):
"""utils encode_html (FAILS - DISABLED)"""
# why this does not encode < ?
from flexget.utils.tools import encode_html
print(encode_html('<3'))
assert encode_html('<3') == '<3'
def filename_from_headers(self, entry, response):
"""Checks entry filename if it's found from content-disposition"""
data = str(response.info())
# try to decode/encode, afaik this is against the specs but some servers do it anyway
try:
data = data.decode('utf-8')
log.debug('response info UTF-8 decoded')
except UnicodeError:
try:
data = unicode(data)
log.debug('response info unicoded')
except UnicodeError:
pass
# now we should have unicode string, let's convert into proper format where non-ascii
# chars are entities
data = encode_html(data)
try:
filename = email.message_from_string(data).get_filename(failobj=False)
except (AttributeError, SystemExit, KeyboardInterrupt):
raise # at least rethrow the most common stuff before catch-all
except:
log.error('Failed to decode filename from response: %r' % data)
return
if filename:
filename = decode_html(filename)
log.debug('Found filename from headers: %s' % filename)
if 'filename' in entry:
log.debug('Overriding filename %s with %s from content-disposition' % (entry['filename'], filename))
entry['filename'] = filename