import jieba
#stopwords = {}.fromkeys([ line.rstrip() for line in open(‘stopword.txt‘) ])
stopwords = {}.fromkeys([‘的‘, ‘附近‘])
segs = jieba.cut(‘北京附近的租房‘, cut_all=False)
final = ‘‘
for seg in segs:
seg = seg.encode(‘gbk‘)
if seg not in stopwords:
final += seg
print final
原文：http://www.cnblogs.com/xiaoli2018/p/4953170.html