jieba分词工具的实战例子（对一个文本分析）

一个小小的结巴分词使用的实例（涉及了大部分关于结巴的操作）

import jieba
import jieba.analyse as ana#关键词
import jieba.posseg as pos#词性
#打开或创建文件

#class jieba_cut_word():
#    test=''
#    open_test=open('test.txt','r')
#    write_result=open('result.txt','ab')
#    def create_txt(tes,res):
#        open(tes,'r')
#        open(res,'ab')
#    def cut_words():
#        with open()

#if _name_ == ' _main_ ':
#    cut_word=jieba_cut_word()
def get_content(path):
    with open(path,'r',  errors='ignore') as f:
        content=' '
        for l in f:
            #print(l)
            l=l.strip()
            content+=l
        #print(content)
    return content
def cut_word(content,result):
    with open(result,'a',encoding='gbk' ,errors='ignore') as g:
        jieba1=jieba.cut(content)
        g.write('\n')
        g.write('/'.join(jieba1))
        g.write('\n')
    g.close()

def get_main_word(content,result):
    with open(result,'a', encoding='gbk', errors='ignore') as g:
        jieba2=ana.extract_tags(content, topK=20)
        g.write('\n')
        print(' '.join(jieba2))
        g.write(' '.join(jieba2))
        #for l in jieba2:
        #    g.write(l)
#去除停用词

def stop_word(content,stop_words):#去除停用词，得到一个字符串
    #stopword={}.fromkeys(['等','怎样','如何','不论','包括','的']) 创建字典
    #with open(result,'a',encoding='gbk' ,errors='ignore') as g:
    jieba1=jieba.cut(content)
    content2=' '
    for seg in jieba1:
        #seg=seg.decode('utf-8')      
        if seg not in stop_words:
            content2+=seg
    return content2
def jiazai_stopword():
    stop_words=[line.strip() for line in open('stop_word.txt','r', errors='ignore').readlines()]
    return stop_words

#if  _name_ == '_main_':
test='test.txt'
result='result.txt'
content=get_content(test)
stop_words=jiazai_stopword()#加载停用词
content2=stop_word(content,stop_words)#去除停用词
jieba.load_userdict('dict1.txt')#加载自定义词典
cut_word(content2,result)
get_main_word(content2,result)
#之后做添加自定义词，去除停用词，提取关键词

存到手里好久了，今天把它发出来，，哈哈哈