def run(cls):
print("### スクレイピング開始 ###")
pokemon_df = cls.__init_pokemon_df(Settings.COLUMNS)
detail_page_html_paths = sorted(
glob(
os.path.join(os.path.dirname(os.path.dirname(cls.FILE_PATH)),
"html/detail_page/*.html")))
for detail_page_html_path in detail_page_html_paths:
pokemon = Pokemon()
html_str = Utils.read_html(detail_page_html_path)
detail_page_bs = BeautifulSoup(html_str, "html.parser")
pokemon.no, pokemon.name = re.match(
r".*/([0-9]+)_(.+).html", detail_page_html_path).groups()
pokemon.types = cls.__get_types(detail_page_bs)
pokemon.abilities = cls.__get_abilities(detail_page_bs)
pokemon.status = cls.__get_status(detail_page_bs)
pokemon.is_final = cls.__get_is_final(detail_page_bs)
pokemon.region = cls.__get_region(pokemon.no, pokemon.name)
pokemon.is_mega_evolution = cls.__get_is_mega_evolution(
pokemon.name)
print(pokemon)
pokemon_srs = pd.Series(data=pokemon.reshape_to_list(),
index=Settings.COLUMNS)
pokemon_df = pokemon_df.append(pokemon_srs, ignore_index=True)
stat_columns = ["HP", "こうげき", "ぼうぎょ", "とくこう", "とくぼう", "すばやさ"]
stat_db = pokemon_df.loc[:, stat_columns].values.tolist()
pokemon_df["同一種族値"] = [
Utils.is_same_status(i, stat, stat_db)
for i, stat in enumerate(stat_db)
]
csv_path = Utils.make_dir(
os.path.dirname(os.path.dirname(cls.FILE_PATH)), "output")
pokemon_df.to_csv(os.path.join(csv_path, "pokemon_db.csv"),
index=False,
encoding="utf-8")
print("FILE: {} を出力しました。".format(
os.path.join(csv_path, "pokemon_db.csv")))
print("### スクレイピング終了 ###")
