# -*- coding: utf-8 -*-
# @Time    : 2022/5/31 8:52
# @Author  : ZhaoXiangPeng
# @File    : gz.py

import gzip
import json
import ujson


def data_parse(io):
    data = json.load(io)
    items = data['items']
    for item in items:
        doi = item.get('DOI')
        dtype = item.get('type')
        issn = item.get('ISSN')
        title = item.get('title') and item.get('title')[0]
        source = item.get('container-title') and item.get('container-title')[0]
        print('****************************************************\n'
              'TITLE:    %s\n'
              'DOI:      %s\n'
              'TYPE:     %s\n'
              'ISSN:     %s\n'
              'SOURCE:   %s\n' % (title, doi, dtype, issn, source))
        if not item.get('reference-count', 0):
            continue
        try:
            reference_list = []
            for reference in item.get('reference', []):
                ref_doi = reference.get('DOI')
                if ref_doi:
                    # do something
                    reference_list.append(ref_doi)
                    continue
                ref_at = reference.get('article-title')
                if ref_at:
                    print(ref_at)
                    reference_list.append(ref_at)
                    continue
                ref_jt = reference.get('journal-title')
        except KeyError:
            print(item.keys())


def un_gz(file_name):
    g_file = gzip.GzipFile(file_name)
    return g_file


if __name__ == '__main__':
    un_gz('H:/crossref_public_data_file_2021_01/1.json.gz')