extract_inout_from_projectnextnlp-chat-dialogue-corpus.py

# -*- coding:utf-8 -*-

import codecs
import json
import os
import sys


if __name__ == '__main__':
    def walk_json(path):
        for root, _, files in os.walk(path):
            for f in files:
                if f.endswith('.json'):
                    yield os.path.join(root, f)

    for json_name in walk_json(sys.argv[1]):
        speeches = []
        with codecs.open(json_name, 'r', 'utf8') as json_file:
            dialog_data = json.load(json_file)
            turns = dialog_data['turns']
            for turn in turns:
                speeches.append(turn['utterance'].encode('utf8'))
        if speeches:
            for i in range(len(speeches) - 1):
                sys.stdout.write("{:s}\n".format(speeches[i]))
                sys.stderr.write("{:s}\n".format(speeches[i+1]))