mirror of https://github.com/fxsjy/jieba.git
23 lines
459 B
Python
23 lines
459 B
Python
import urllib.request, urllib.error, urllib.parse
|
|
import sys,time
|
|
import sys
|
|
sys.path.append("../../")
|
|
import jieba
|
|
import jieba.posseg as pseg
|
|
jieba.enable_parallel(4)
|
|
|
|
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","wb")
|
|
for w in words:
|
|
print(w.encode("utf-8"), "/", end=' ', file=log_f)
|
|
|
|
print('speed' , len(content)/tm_cost, " bytes/second")
|
|
|