find_p279.py

import sys
import json
import os
import bz2
import gzip
def read_dump(path):
    mode = 'r'
    file_ = os.path.split(path)[-1]
    if file_.endswith('.gz'):
        f = gzip.open(path, mode)
    elif file_.endswith('.bz2'):
        f = bz2.BZ2File(path, mode)
    elif file_.endswith('.json'):
        f = open(path, mode)
    else:
        raise NotImplementedError(f'Reading file {file_} is not supported')
    try:
        for line in f:
            if isinstance(line, bytes):
                line = line.decode('utf-8')
            try:
                yield json.loads(line.strip().strip(','))
            except json.JSONDecodeError:
                continue
    finally:
        f.close()

with open('P279.txt', 'w') as f:
    f.write('')


for item in read_dump(sys.argv[1]):
    id_ = item['id']
    p31s = []
    p279s = []
    if 'P279' not in item.get('claims', {}):
        continue
    if 'P31' not in item.get('claims', {}):
        continue
    for claim in item.get('claims', {}).get('P31', []):
        try:
            p31 = claim['mainsnak']['datavalue']['value']['id']
        except:
            continue
        p31s.append(p31)
    for claim in item.get('claims', {}).get('P279', []):
        try:
            p279 = claim['mainsnak']['datavalue']['value']['id']
        except:
            continue
        p279s.append(p279)
     with open('P279.txt', 'a') as f:
        for p31 in p31s:
            f.write(id_[1:] + ' ' + p31[1:] + '\n')
        for p279 in p279s:
            f.write(id_[1:] + ' ' + p279[1:] + '\n')