代码拉取完成,页面将自动刷新
import os
from config import Config
from process_pipelines.chatterbot import chatterbot_process_pipeline
from process_pipelines.douban import douban_process_pipeline
from process_pipelines.ptt import ptt_process_pipeline
from process_pipelines.qingyun import qingyun_process_pipeline
from process_pipelines.subtitle import subtitle_process_pipeline
from process_pipelines.tieba import tieba_process_pipeline
from process_pipelines.weibo import weibo_process_pipeline
from process_pipelines.xiaohuangji import xiaohuangji_process_pipeline
def process_all_corpus():
if not os.path.exists(Config.clean_chat_corpus_root):
os.mkdir(Config.clean_chat_corpus_root)
douban_process_pipeline()
chatterbot_process_pipeline()
ptt_process_pipeline()
qingyun_process_pipeline()
subtitle_process_pipeline()
tieba_process_pipeline()
weibo_process_pipeline()
xiaohuangji_process_pipeline()
if __name__ == '__main__':
process_all_corpus()
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。