# -*- coding: utf-8 -*-
"""
Created on Mon Sep 25 11:50:28 2017
@author: su
"""
import jieba.analyse
import jieba.posseg
content = u"中国,是以华夏文明为源泉、中华文化为基础,并以汉族为主体民族的多民族国家,通用汉语、汉字,汉族与少数民族被统称为“中华民族”,又称为炎黄子孙、龙的传人。"
keywords = jieba.analyse.extract_tags(content,topK=20,withWeight=True,allowPOS=("n","ns","ns"))
for item in keywords:
print(item[0],item[1])
keywords = jieba.analyse.textrank(content,topK=20,withWeight=True,allowPOS=("n","ns","ns"))
for item in keywords:
print(item[0],item[1])
words =jieba.posseg.cut(content)
print(type(words))
for word,flag in words:
print("%s,%s"%(word,flag))
"""
Created on Mon Sep 25 11:50:28 2017
@author: su
"""
import jieba.analyse
import jieba.posseg
content = u"中国,是以华夏文明为源泉、中华文化为基础,并以汉族为主体民族的多民族国家,通用汉语、汉字,汉族与少数民族被统称为“中华民族”,又称为炎黄子孙、龙的传人。"
keywords = jieba.analyse.extract_tags(content,topK=20,withWeight=True,allowPOS=("n","ns","ns"))
for item in keywords:
print(item[0],item[1])
keywords = jieba.analyse.textrank(content,topK=20,withWeight=True,allowPOS=("n","ns","ns"))
for item in keywords:
print(item[0],item[1])
words =jieba.posseg.cut(content)
print(type(words))
for word,flag in words:
print("%s,%s"%(word,flag))