blog-deeppavlov-covid-1

blog-deeppavlov-covid-1.py

from os.path import basename
def get_text(s):
    return ' '.join([x['text'] for x in s])

os.makedirs('text',exist_ok=True)

for fn in glob.glob('noncomm_use_subset/pdf_json/*'):
    with open(fn) as f:
        x = json.load(f)
    nfn = os.path.join('text',basename(fn).replace('.json','.txt'))
    with open(nfn,'w') as f:
        f.write(get_text(x['abstract']))
        f.write(get_text(x['body_text']))