结巴分词python脚本

#-*-coding:utf-8-*- 2018-04-17 想要用绝佳的编程技术实现一些事情
import jieba
import os
def savefile(savepath,content):
    with open(savepath,'w',encoding="utf-8") as fp:
        fp.write(content)

def readfile(path):
    with open(path,'r',encoding="utf-8") as fp:
        c=fp.read()
    return c                      
before_path = "D:/fenglongyu_SoftWare/data/train/"
after_path = "D:/fenglongyu_SoftWare/data/textC/"
catelist = os.listdir(before_path)#获取before_path下所有子目录下 为每个目录下的所有文件
print(catelist)
for mydir in catelist:
    class_path = before_path+mydir+r"/"#拼出分类子目录的路径
    after_dir = after_path+mydir+r"/"
          #拼出分词后的料分类目录
        #不存在路径时创建
    if not os.path.exists(after_dir):
        os.makedirs(after_dir)
    file_list= os.listdir(class_path)
    for file_path in file_list:
        fullname = class_path+file_path #拼出文件名的全路径
        content = readfile(fullname).strip()
        #读取文件内容
        #删除换行和多余的空格
        content_seg = jieba.cut(content)
        savefile(after_dir+file_path," ".join(content_seg))
print("分词结束！！")