adb55dec12
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.
37 lines
865 B
JSON
37 lines
865 B
JSON
{
|
|
"id": "a1-184-dragonair",
|
|
"name": "Dragonair",
|
|
"set_code": "a1",
|
|
"set_name": "Genetic Apex",
|
|
"card_number": 184,
|
|
"rarity": "Uncommon",
|
|
"card_type": "pokemon",
|
|
"image_url": "https://assets.pokemon-zone.com/game-assets/CardPreviews/cPK_10_001840_00_HAKURYU_U.webp",
|
|
"image_file": null,
|
|
"source_url": "https://www.pokemon-zone.com/cards/a1/184/dragonair/",
|
|
"hp": 100,
|
|
"pokemon_type": "dragon",
|
|
"stage": "stage_1",
|
|
"evolves_from": "Dratini",
|
|
"is_ex": false,
|
|
"abilities": [],
|
|
"attacks": [
|
|
{
|
|
"name": "Tail Smack",
|
|
"cost": [
|
|
"water",
|
|
"lightning",
|
|
"colorless"
|
|
],
|
|
"damage": 80,
|
|
"damage_modifier": null,
|
|
"effect_text": null,
|
|
"effect_id": null
|
|
}
|
|
],
|
|
"weakness": null,
|
|
"resistance": null,
|
|
"retreat_cost": 1,
|
|
"flavor_text": null,
|
|
"illustrator": "kirisAki"
|
|
} |