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.
43 lines
1.1 KiB
JSON
43 lines
1.1 KiB
JSON
{
|
||
"id": "a1a-056-druddigon",
|
||
"name": "Druddigon",
|
||
"set_code": "a1a",
|
||
"set_name": "Mythical Island",
|
||
"card_number": 56,
|
||
"rarity": "Uncommon",
|
||
"card_type": "pokemon",
|
||
"image_url": "https://assets.pokemon-zone.com/game-assets/CardPreviews/cPK_10_002690_00_CRIMGAN_U.webp",
|
||
"image_file": null,
|
||
"source_url": "https://www.pokemon-zone.com/cards/a1a/56/druddigon/",
|
||
"hp": 100,
|
||
"pokemon_type": "dragon",
|
||
"stage": "basic",
|
||
"evolves_from": null,
|
||
"is_ex": false,
|
||
"abilities": [
|
||
{
|
||
"name": "Rough Skin",
|
||
"effect_text": "If this Pokémon is in the Active Spot and is damaged by an attack from your opponent’s Pokémon, do 20 damage to the Attacking Pokémon.",
|
||
"effect_id": null
|
||
}
|
||
],
|
||
"attacks": [
|
||
{
|
||
"name": "Dragon Claw",
|
||
"cost": [
|
||
"fire",
|
||
"water",
|
||
"colorless"
|
||
],
|
||
"damage": 90,
|
||
"damage_modifier": null,
|
||
"effect_text": null,
|
||
"effect_id": null
|
||
}
|
||
],
|
||
"weakness": null,
|
||
"resistance": null,
|
||
"retreat_cost": 2,
|
||
"flavor_text": null,
|
||
"illustrator": "Ryota Murayama"
|
||
} |