言語処理100本ノック(2020): 21

"""
21. カテゴリ名を含む行を抽出
記事中でカテゴリ名を宣言している行を抽出せよ．
"""

import json


def get_uk_text(path):
    with open(path) as f:
        for line in f:
            line_data = json.loads(line)
            if line_data["title"] == "イギリス":
                data = line_data
                break
    return data["text"]


uk_text = get_uk_text("jawiki-country.json")
uk_text_list = uk_text.split("\n")
ans = [x for x in uk_text_list if "Category:" in x[:11]]

for a in ans:
    print(a)

# [[Category:イギリス|*]]
# [[Category:イギリス連邦加盟国]]
# [[Category:英連邦王国|*]]
# [[Category:G8加盟国]]
# [[Category:欧州連合加盟国|元]]
# [[Category:海洋国家]]
# [[Category:現存する君主国]]
# [[Category:島国]]
# [[Category:1801年に成立した国家・領域]]