The source website uses <span class='energy-text energy-text--type-fire'> to render inline energy icons. BeautifulSoup's get_text() was stripping these spans, losing the energy type information and causing merged text like 'Discard aEnergy' instead of 'Discard a Fire Energy'. Changes: - Add ENERGY_TEXT_TYPES mapping for inline energy references - Add replace_energy_text_spans() to convert spans to text before extraction - Add extract_effect_text() helper with proper text joining (separator=' ') - Update parse_attack(), parse_ability(), _parse_trainer_details() to use it - Fix JSON encoding in convert_cards.py to use UTF-8 (ensure_ascii=False) Before: 'Discard an Energy from this Pokémon' After: 'Discard a Fire Energy from this Pokémon' Re-scraped all 372 cards and regenerated 382 definitions.
38 lines
1011 B
JSON
38 lines
1011 B
JSON
{
|
||
"id": "a1-185-dragonite",
|
||
"name": "Dragonite",
|
||
"set_code": "a1",
|
||
"set_name": "Genetic Apex",
|
||
"card_number": 185,
|
||
"rarity": "Rare",
|
||
"card_type": "pokemon",
|
||
"image_url": "https://assets.pokemon-zone.com/game-assets/CardPreviews/cPK_10_001850_00_KAIRYU_R.webp",
|
||
"image_file": null,
|
||
"source_url": "https://www.pokemon-zone.com/cards/a1/185/dragonite/",
|
||
"hp": 160,
|
||
"pokemon_type": "dragon",
|
||
"stage": "stage_2",
|
||
"evolves_from": "Dragonair",
|
||
"is_ex": false,
|
||
"abilities": [],
|
||
"attacks": [
|
||
{
|
||
"name": "Draco Meteor",
|
||
"cost": [
|
||
"water",
|
||
"lightning",
|
||
"colorless",
|
||
"colorless"
|
||
],
|
||
"damage": null,
|
||
"damage_modifier": null,
|
||
"effect_text": "1 of your opponent’s Pokémon is chosen at random 4 times. For each time a Pokémon was chosen, do 50 damage to it.",
|
||
"effect_id": null
|
||
}
|
||
],
|
||
"weakness": null,
|
||
"resistance": null,
|
||
"retreat_cost": 3,
|
||
"flavor_text": null,
|
||
"illustrator": "Hiroyuki Yamamoto"
|
||
} |