mirror of https://github.com/fxsjy/jieba.git
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
22 lines
403 B
Python
22 lines
403 B
Python
from __future__ import print_function
|
|
import sys
|
|
import time
|
|
sys.path.append("../")
|
|
import jieba
|
|
jieba.initialize()
|
|
import jieba.posseg as pseg
|
|
|
|
url = sys.argv[1]
|
|
content = open(url,"rb").read()
|
|
t1 = time.time()
|
|
words = list(pseg.cut(content))
|
|
|
|
t2 = time.time()
|
|
tm_cost = t2-t1
|
|
|
|
log_f = open("1.log","w")
|
|
log_f.write(' / '.join(map(str, words)))
|
|
|
|
print('speed' , len(content)/tm_cost, " bytes/second")
|
|
|