def _splitByControlCharacters(self, val):
# extract non-control characters
output = []
s = ''
for c in unicode(val):
if unicodedata.category(c)[0] == 'C':
if len(s) > 0:
# start a new string if we found a control character
output.append(str(s))
s = ''
else:
s += c
# clean up any left over string
if len(s) > 0:
output.append(str(s))
# return extracts strings
return output
评论列表
文章目录