python jieba分词，高级篇

1，切分词语的步骤

import jieba

jieba.load_userdict(config.userdict) # 加载自定义关键词

corpara_sen = [] # 关键词语料库
for line in sentences:
    seg_cut = jieba.cut(line.strip()) # 切分单词
    words = " ".join(seg_cut) # 空格分隔
    seg_split = words.split() # 去掉空格
    seg = [word for word in seg_split if word not in stopwords] # 去掉停用词，根据停用词字典
    corpora_sen.append(seg)

2，字典不能分的词