import json
import re

nikkei_scraps = []

with open('nikkei_scrap.json') as json_data:
    page_data = json.load(json_data)
    nikkei_scraps = [page['title']
                     for page in page_data['relatedPages']['links1hop']]

with open('takker-memex.json') as json_data:
    page_data = json.load(json_data)
    newspaper_data = {'pages': [page for page in page_data['pages']
                                if (page['title'] in nikkei_scraps) and re.search('日本経済新聞|NIKKEI|日経', page['title'])]}
    print(f'Got {len(newspaper_data["pages"])} pages')
    with open('output.json', 'w') as output:
        json.dump(newspaper_data, output, indent=4, ensure_ascii=False)