欢迎使用CSDN-markdown编辑器

import sys
reload(sys)
sys.setdefaultencoding('utf8')
try:
with open('Dataset_words.txt', 'r') as trainingSet:
data = trainingSet.read()
for each_line in data:
print unicode(each_line).encode('utf8')
# words = each_line.split()
# print words
except IOError as err:
print 'File error' + str(err)

# s = u'陈超'
# print s.encode('utf-8')