json_parser.py

import json
import glob
import os
import re,datetime
import dateutil.parser

SRCDIR = 'src'
OUTDIR = 'out'

def get_dispinfo(dat):
    keys_base = ['title', 'url']
    keys_user = ['id']
    out_list = []
    [out_list.append('{0}: {1}'.format(k, dat[k])) for k in keys_base]
    [out_list.append('{0}: {1}'.format(k, dat['user'][k])) for k in keys_user]
    return out_list

def normalize_datestr(s):
    l = s.split("+")
    return l[0]

def str_to_datetime(s):
    return dateutil.parser.parse(s)
    # return datetime.datetime.strptime(s, '%Y-%m-%dT%H:%M:%S')

def datetime_to_str(dt):
    return dt.strftime("%Y%m%d_%H%M%S")

def format_doc(doc_info, doc_body):
    doc_info.insert(0,'```')
    doc_info.append('```\n')
    doc_info.append(doc_body)
    return '\n'.join(doc_info)

def get_src_filenames():
    globpat = os.path.join(SRCDIR, '*.json')
    files = glob.glob(globpat)
    return files

def generate_out_filename(json_dict, src_filename):
    # src: ORIGFILENAME.json
    # out: OUTDIR/username/YYYYMMDD_hhmmss_ORIGFILENAME.md
    username = json_dict['user']['id']
    created_at = str_to_datetime(normalize_datestr(json_dict['created_at']))
    datestr = datetime_to_str(created_at)
    src_base = (os.path.splitext(os.path.basename(src_filename)))[0] # path,ext を除去
    out_basename = '{0}_{1}.md'.format(datestr, src_base)
    # outdir: OUTDIR/username
    dir_by_user = os.path.join(OUTDIR, username)
    if not os.path.isdir(dir_by_user): os.makedirs(dir_by_user)
    # 
    out_file = os.path.join(dir_by_user, out_basename)
    return out_file


def main():
    src_files = get_src_filenames()
    for src_file in src_files:
        with open(src_file,'r') as sf:
            json_dict = json.load(sf)
            doc_info = get_dispinfo(json_dict)
            doc_body = json_dict['body']

            out_content = format_doc(doc_info, doc_body)

            out_file = generate_out_filename(json_dict, src_file)
            with open(out_file, 'w') as of:
                of.write(out_content)



if __name__ == "__main__":
    main()

"""
qiitaの出力ファイルのデータ構造例

  "rendered_body": 本文html
  "body": 本文ソース
  "coediting": false,
  "comments_count": 0,
  "created_at": "2016-11-07T16:25:08+09:00",
  "group": null,
  "id": "0e28e1ca3a17da7e666a",
  "likes_count": 0,
  "private": false,
  "reactions_count": 0,
# ....
  "title": "WP プラグイン 利用例（パンくず・ナビ）",
  "updated_at": "2016-11-07T16:32:49+09:00",
  "url": "https://srk-sd.qiita.com/inakagawa/items/0e28e1ca3a17da7e666a",
  "user": {
    "id": "inakagawa",
    "permanent_id": 17730,
    "profile_image_url": "https://qiita-image-store.s3.amazonaws.com/0/17730/profile-images/1473682242"
  },



"""