mecab sample

!/usr/bin/python
# -*- coding: utf-8 -*-</code>
 
#%m POS ID 36-47 is noun
#%s 0: known 1: unknown
 
#tasks
#1 create a set to avoid noun duplication
#2 set rules to avoid url tokenization
#3 sort noun set to prioritize type:1 nouns
 
import sys
import MeCab
 
class MeCabTagger:
 
def __init__(self, text = ""):
	self.m = MeCab.Tagger ('-F%m\s%h\s%s\s')
	self.nouns = []
	print "Creating MeCabTagger instance."
	self.parseText(text)
 
def parseText(self, text):
	self.posList = []
	taggedSpeach = self.m.parse (text)
	taggedSpeachList = taggedSpeach.split(" ")
	lenOfSpeach = (len(taggedSpeachList) - 1)/3
	for i in range(lenOfSpeach):
		self.posList.append(taggedSpeachList[3*i:3*(i+1)])
		#print " ".join(taggedSpeachList)
 
def showNouns(self):
	if len(self.posList) == 0:
		print "No text parsed."
		return
	self.nouns = []
	for pos in self.posList:
		if int(pos[1]) &gt;=36 and int(pos[1]) self.nouns.append(pos[0])
			print " ".join(self.nouns)
 
mecab = MeCabTagger("２０代も後半に入ったので、年相応の行動を心掛けよう、というのが最近の私らの口癖です。")
mecab.showNouns()