import re
lines = open(r'123.txt', encoding='utf8').read()
x = ''.join(re.findall(u'[\u4e00-\u9fa5]+', lines)) #正则表达式，汉字的编码范围进行匹配
print(x)
print(len(x))
dict_list = {}
for i in range(len(x)):
if dict_list.get(x[i]):
dict_list[x[i]] = dict_list[x[i]] + 1
else:
dict_list[x[i]] = 1
print(dict_list)
print(len(dict_list))
for key,value in dict_list.items():
print(key,"--",value)
# fp = open('1234_key_value_3.txt', mode='w+')
# for key,value in dict_list.items():
# strs = str(key) + " " + str(value) +"\n"
# fp.write(strs)
# fp.close()
print("------------")
f_lines = open('1234_key_value_3.txt').readlines()
for line in f_lines:
strss = line.strip().split(" ")
print(strss[0],"-----",strss[1])
