文章提取关键词_jieba(IF-IDF/TextRank)

来源：互联网发布：笨方法学python ex26 编辑：程序博客网时间：2024/05/24 05:06

1、基于TextRank的提取文章关键词:extract_keyword_textrank.py:

#!usr/bin/env python#-*- coding:utf-8-*-import jiebaimport jieba.analyseimport codecsfile_path='./data/000000_0'result_file_path="./data/000000_0_result_textrank"f=open(file_path,'r')f_result=codecs.open(result_file_path,'w+','utf-8')f_result.write('[\n')texts=f.readlines()num_text=0for text in texts:text_id=texts.split('\t')[0]text_content=texts.split('\t')[3]f_result.write('{\"text_id\": %s\n'% text_id)keywords=jieba.analyse.textrank(text_content,topK=20,withWeight=True,allowPOS=('ns', 'n', 'vn', 'v'),withFlag=True)f_result.write('\"keyword\":{')num_text+=1for keyword in keywords:(word,flag)=keyword[0]weight=keyword[1]f_result.write('\"word\":%s,\"weight\":%s,\"nature\": %s\n'% (word,weight,flag))f_result.write('}\n')if num_text%100=0:print "已经处理%s篇文章" % num_textf_result.write(']\n')print "总共处理%s篇文章" num_textf_result.close()f.close()

2.基于IF-IDF的提取文章关键词extract_keywod_ifidf.py：

#!usr/bin/env python#-*- coding:utf-8-*-import jiebaimport jieba.analyseimport codecsfile_path='./data/000000_0'result_file_path="./data/000000_0_result_ifidf"f=open(file_path,'r')f_result=codecs.open(result_file_path,'w+','utf-8')f_result.write('[')texts=f.readlines()num_text=0for text in texts:text_id=texts.split('\t')[0]text_content=texts.split('\t')[3]f_result.write('{\"text_id\": %s\n'% text_id)keywords=jieba.analyse.extract_tags(text_content,topK=20,withWeight=True,allowPOS=('ns', 'n', 'vn', 'v'),withFlag=True)f_result.write('\"keyword\":{')num_text+=1for keyword in keywords:(word,flag)=keyword[0]weight=keyword[1]f_result.write('\"word\":%s,\"weight\":%s,\"nature\": %s\n'% (word,weight,flag))f_result.write('}')if num_text%100=0:print "已经处理%s篇文章" % num_textf_result.write(']')print "总共处理%s篇文章" %num_textf_result.close()f.close()

0 0