Files
nuzlocke-tracker/backend/src/app/seeds/fetch_pokeapi.py
Julian Tabel f7f5417b6b Add all Gen 1-9 games with colors to seed data
- Add 37 games from Gen 1-9 (Red/Blue through Scarlet/Violet)
- Add color field to Game model matching box art/branding
- Add migration for games.color column
- Update fetch_pokeapi.py to fetch all games and output colors
- Update seed loader to upsert game colors
- Update frontend Game type to include color field

Games without PokeAPI encounter data (ORAS, Let's Go, Sword/Shield,
BDSP, Legends Arceus, Scarlet/Violet) have location structure but
empty encounter tables.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-06 11:46:10 +01:00

898 lines
29 KiB
Python

"""Fetch game data from local PokeAPI submodule and write static JSON seed files.
Reads from the PokeAPI/api-data git submodule at data/pokeapi/ — no network
access or container needed. Only uses Python stdlib.
Usage:
python -m app.seeds.fetch_pokeapi
Requires the submodule to be initialized:
git submodule update --init
"""
import json
import re
import sys
from pathlib import Path
REPO_ROOT = Path(__file__).parents[4] # backend/src/app/seeds -> repo root
POKEAPI_DIR = REPO_ROOT / "data" / "pokeapi" / "data" / "api" / "v2"
DATA_DIR = Path(__file__).parent / "data"
def load_resource(endpoint: str, resource_id: int) -> dict:
"""Load a PokeAPI resource from the local submodule data."""
path = POKEAPI_DIR / endpoint / str(resource_id) / "index.json"
with open(path) as f:
return json.load(f)
def extract_id(url: str) -> int:
"""Extract the numeric ID from a PokeAPI URL (absolute or relative)."""
return int(url.rstrip("/").split("/")[-1])
# Game definitions - Gen 1 through Gen 8
VERSION_GROUPS = {
# === Generation 1 ===
"red-blue": {
"versions": ["red", "blue"],
"generation": 1,
"region": "kanto",
"region_id": 1,
"games": {
"red": {
"name": "Pokemon Red",
"slug": "red",
"release_year": 1996,
"color": "#FF1111",
},
"blue": {
"name": "Pokemon Blue",
"slug": "blue",
"release_year": 1996,
"color": "#1111FF",
},
},
},
"yellow": {
"versions": ["yellow"],
"generation": 1,
"region": "kanto",
"region_id": 1,
"games": {
"yellow": {
"name": "Pokemon Yellow",
"slug": "yellow",
"release_year": 1998,
"color": "#FFD733",
},
},
},
# === Generation 2 ===
"gold-silver": {
"versions": ["gold", "silver"],
"generation": 2,
"region": "johto",
"region_id": 2,
"extra_regions": [1], # Kanto post-game
"games": {
"gold": {
"name": "Pokemon Gold",
"slug": "gold",
"release_year": 1999,
"color": "#DAA520",
},
"silver": {
"name": "Pokemon Silver",
"slug": "silver",
"release_year": 1999,
"color": "#C0C0C0",
},
},
},
"crystal": {
"versions": ["crystal"],
"generation": 2,
"region": "johto",
"region_id": 2,
"extra_regions": [1], # Kanto post-game
"games": {
"crystal": {
"name": "Pokemon Crystal",
"slug": "crystal",
"release_year": 2000,
"color": "#4FD9FF",
},
},
},
# === Generation 3 ===
"ruby-sapphire": {
"versions": ["ruby", "sapphire"],
"generation": 3,
"region": "hoenn",
"region_id": 3,
"games": {
"ruby": {
"name": "Pokemon Ruby",
"slug": "ruby",
"release_year": 2002,
"color": "#A00000",
},
"sapphire": {
"name": "Pokemon Sapphire",
"slug": "sapphire",
"release_year": 2002,
"color": "#0000A0",
},
},
},
"emerald": {
"versions": ["emerald"],
"generation": 3,
"region": "hoenn",
"region_id": 3,
"games": {
"emerald": {
"name": "Pokemon Emerald",
"slug": "emerald",
"release_year": 2005,
"color": "#00A000",
},
},
},
"firered-leafgreen": {
"versions": ["firered", "leafgreen"],
"generation": 3,
"region": "kanto",
"region_id": 1,
"games": {
"firered": {
"name": "Pokemon FireRed",
"slug": "firered",
"release_year": 2004,
"color": "#FF7327",
},
"leafgreen": {
"name": "Pokemon LeafGreen",
"slug": "leafgreen",
"release_year": 2004,
"color": "#00DD00",
},
},
},
# === Generation 4 ===
"diamond-pearl": {
"versions": ["diamond", "pearl"],
"generation": 4,
"region": "sinnoh",
"region_id": 4,
"games": {
"diamond": {
"name": "Pokemon Diamond",
"slug": "diamond",
"release_year": 2006,
"color": "#AAAAFF",
},
"pearl": {
"name": "Pokemon Pearl",
"slug": "pearl",
"release_year": 2006,
"color": "#FFAAAA",
},
},
},
"platinum": {
"versions": ["platinum"],
"generation": 4,
"region": "sinnoh",
"region_id": 4,
"games": {
"platinum": {
"name": "Pokemon Platinum",
"slug": "platinum",
"release_year": 2008,
"color": "#999999",
},
},
},
"heartgold-soulsilver": {
"versions": ["heartgold", "soulsilver"],
"generation": 4,
"region": "johto",
"region_id": 2,
"extra_regions": [1], # Kanto post-game
"games": {
"heartgold": {
"name": "Pokemon HeartGold",
"slug": "heartgold",
"release_year": 2010,
"color": "#B69E00",
},
"soulsilver": {
"name": "Pokemon SoulSilver",
"slug": "soulsilver",
"release_year": 2010,
"color": "#C0C0E0",
},
},
},
# === Generation 5 ===
"black-white": {
"versions": ["black", "white"],
"generation": 5,
"region": "unova",
"region_id": 5,
"games": {
"black": {
"name": "Pokemon Black",
"slug": "black",
"release_year": 2010,
"color": "#444444",
},
"white": {
"name": "Pokemon White",
"slug": "white",
"release_year": 2010,
"color": "#E1E1E1",
},
},
},
"black-2-white-2": {
"versions": ["black-2", "white-2"],
"generation": 5,
"region": "unova",
"region_id": 5,
"games": {
"black-2": {
"name": "Pokemon Black 2",
"slug": "black-2",
"release_year": 2012,
"color": "#424B50",
},
"white-2": {
"name": "Pokemon White 2",
"slug": "white-2",
"release_year": 2012,
"color": "#E3CED0",
},
},
},
# === Generation 6 ===
"x-y": {
"versions": ["x", "y"],
"generation": 6,
"region": "kalos",
"region_id": 6,
"games": {
"x": {
"name": "Pokemon X",
"slug": "x",
"release_year": 2013,
"color": "#025DA6",
},
"y": {
"name": "Pokemon Y",
"slug": "y",
"release_year": 2013,
"color": "#EA1A3E",
},
},
},
"omega-ruby-alpha-sapphire": {
"versions": ["omega-ruby", "alpha-sapphire"],
"generation": 6,
"region": "hoenn",
"region_id": 3,
"games": {
"omega-ruby": {
"name": "Pokemon Omega Ruby",
"slug": "omega-ruby",
"release_year": 2014,
"color": "#CF3025",
},
"alpha-sapphire": {
"name": "Pokemon Alpha Sapphire",
"slug": "alpha-sapphire",
"release_year": 2014,
"color": "#26649C",
},
},
},
# === Generation 7 ===
"sun-moon": {
"versions": ["sun", "moon"],
"generation": 7,
"region": "alola",
"region_id": 7,
"games": {
"sun": {
"name": "Pokemon Sun",
"slug": "sun",
"release_year": 2016,
"color": "#F1912B",
},
"moon": {
"name": "Pokemon Moon",
"slug": "moon",
"release_year": 2016,
"color": "#5599CA",
},
},
},
"ultra-sun-ultra-moon": {
"versions": ["ultra-sun", "ultra-moon"],
"generation": 7,
"region": "alola",
"region_id": 7,
"games": {
"ultra-sun": {
"name": "Pokemon Ultra Sun",
"slug": "ultra-sun",
"release_year": 2017,
"color": "#E95B2B",
},
"ultra-moon": {
"name": "Pokemon Ultra Moon",
"slug": "ultra-moon",
"release_year": 2017,
"color": "#204E8C",
},
},
},
"lets-go": {
"versions": ["lets-go-pikachu", "lets-go-eevee"],
"generation": 7,
"region": "kanto",
"region_id": 1,
"games": {
"lets-go-pikachu": {
"name": "Pokemon Let's Go Pikachu",
"slug": "lets-go-pikachu",
"release_year": 2018,
"color": "#F5DA00",
},
"lets-go-eevee": {
"name": "Pokemon Let's Go Eevee",
"slug": "lets-go-eevee",
"release_year": 2018,
"color": "#D4924B",
},
},
},
# === Generation 8 ===
"sword-shield": {
"versions": ["sword", "shield"],
"generation": 8,
"region": "galar",
"region_id": 8,
"games": {
"sword": {
"name": "Pokemon Sword",
"slug": "sword",
"release_year": 2019,
"color": "#00D4E7",
},
"shield": {
"name": "Pokemon Shield",
"slug": "shield",
"release_year": 2019,
"color": "#EF3B6E",
},
},
},
"brilliant-diamond-shining-pearl": {
"versions": ["brilliant-diamond", "shining-pearl"],
"generation": 8,
"region": "sinnoh",
"region_id": 4,
"games": {
"brilliant-diamond": {
"name": "Pokemon Brilliant Diamond",
"slug": "brilliant-diamond",
"release_year": 2021,
"color": "#44BAE5",
},
"shining-pearl": {
"name": "Pokemon Shining Pearl",
"slug": "shining-pearl",
"release_year": 2021,
"color": "#E18AAA",
},
},
},
"legends-arceus": {
"versions": ["legends-arceus"],
"generation": 8,
"region": "hisui",
"region_id": 9,
"games": {
"legends-arceus": {
"name": "Pokemon Legends: Arceus",
"slug": "legends-arceus",
"release_year": 2022,
"color": "#36597B",
},
},
},
# === Generation 9 ===
"scarlet-violet": {
"versions": ["scarlet", "violet"],
"generation": 9,
"region": "paldea",
"region_id": 10,
"games": {
"scarlet": {
"name": "Pokemon Scarlet",
"slug": "scarlet",
"release_year": 2022,
"color": "#F93C3C",
},
"violet": {
"name": "Pokemon Violet",
"slug": "violet",
"release_year": 2022,
"color": "#A96EEC",
},
},
},
}
# Encounter methods to include (excludes gift, legendary-only, etc.)
INCLUDED_METHODS = {
"walk",
"surf",
"old-rod",
"good-rod",
"super-rod",
"rock-smash",
"headbutt",
}
# Collect all pokemon dex numbers across games
all_pokemon_dex: set[int] = set()
def clean_location_name(name: str) -> str:
"""Convert PokeAPI location slug to a clean display name.
e.g. 'kanto-route-1' -> 'Route 1'
'pallet-town' -> 'Pallet Town'
"""
for prefix in [
"kanto-", "johto-", "hoenn-", "sinnoh-",
"unova-", "kalos-", "alola-", "galar-",
]:
if name.startswith(prefix):
name = name[len(prefix):]
break
name = name.replace("-", " ").title()
name = re.sub(r"Route (\d+)", r"Route \1", name)
return name
def clean_area_name(area_name: str, location_name: str) -> str | None:
"""Extract meaningful area suffix, or None if it's the default area."""
if area_name.startswith(location_name):
suffix = area_name[len(location_name):].strip("-").strip()
if not suffix or suffix == "area":
return None
return suffix.replace("-", " ").title()
return area_name.replace("-", " ").title()
def get_encounters_for_area(area_id: int, version_name: str) -> list[dict]:
"""Get encounter data for a location area, filtered by version."""
area = load_resource("location-area", area_id)
encounters = []
for pe in area["pokemon_encounters"]:
pokemon_url = pe["pokemon"]["url"]
dex_num = extract_id(pokemon_url)
pokemon_name = pe["pokemon"]["name"]
for vd in pe["version_details"]:
if vd["version"]["name"] != version_name:
continue
for enc in vd["encounter_details"]:
method = enc["method"]["name"]
if method not in INCLUDED_METHODS:
continue
encounters.append({
"pokemon_name": pokemon_name,
"national_dex": dex_num,
"method": method,
"chance": enc["chance"],
"min_level": enc["min_level"],
"max_level": enc["max_level"],
})
return encounters
def aggregate_encounters(raw_encounters: list[dict]) -> list[dict]:
"""Aggregate encounter rates by pokemon + method (sum chances across level ranges)."""
agg: dict[tuple[int, str], dict] = {}
for enc in raw_encounters:
key = (enc["national_dex"], enc["method"])
if key not in agg:
agg[key] = {
"national_dex": enc["national_dex"],
"pokemon_name": enc["pokemon_name"],
"method": enc["method"],
"encounter_rate": 0,
"min_level": enc["min_level"],
"max_level": enc["max_level"],
}
agg[key]["encounter_rate"] += enc["chance"]
agg[key]["min_level"] = min(agg[key]["min_level"], enc["min_level"])
agg[key]["max_level"] = max(agg[key]["max_level"], enc["max_level"])
result = list(agg.values())
for r in result:
r["encounter_rate"] = min(r["encounter_rate"], 100)
return sorted(result, key=lambda x: (-x["encounter_rate"], x["pokemon_name"]))
def process_version(version_name: str, vg_info: dict) -> list[dict]:
"""Process all locations for a specific game version.
Creates hierarchical route structure where locations with multiple areas
become parent routes with child routes for each area.
"""
print(f"\n--- Processing {version_name} ---")
region = load_resource("region", vg_info["region_id"])
location_refs = list(region["locations"])
# Include extra regions (e.g., Kanto for Johto games)
for extra_region_id in vg_info.get("extra_regions", []):
extra_region = load_resource("region", extra_region_id)
location_refs = location_refs + list(extra_region["locations"])
print(f" Found {len(location_refs)} locations")
routes = []
order = 1
for loc_ref in location_refs:
loc_name = loc_ref["name"]
loc_id = extract_id(loc_ref["url"])
display_name = clean_location_name(loc_name)
location = load_resource("location", loc_id)
areas = location["areas"]
if not areas:
continue
all_encounters: list[dict] = []
area_specific: dict[str, list[dict]] = {}
for area_ref in areas:
area_id = extract_id(area_ref["url"])
area_slug = area_ref["name"]
area_suffix = clean_area_name(area_slug, loc_name)
encounters = get_encounters_for_area(area_id, version_name)
if not encounters:
continue
if area_suffix and len(areas) > 1:
area_specific[area_suffix] = encounters
else:
all_encounters.extend(encounters)
# If we have multiple area-specific encounters, create a parent route
# with child routes for each area (hierarchical grouping)
if area_specific and len(area_specific) > 1:
# Create parent route (no encounters - just a logical grouping)
parent_order = order
order += 1
child_routes = []
for area_suffix, area_encs in area_specific.items():
aggregated = aggregate_encounters(area_encs)
if aggregated:
route_name = f"{display_name} ({area_suffix})"
for enc in aggregated:
all_pokemon_dex.add(enc["national_dex"])
child_routes.append({
"name": route_name,
"order": order,
"encounters": aggregated,
})
order += 1
# Only add parent if we have child routes
if child_routes:
routes.append({
"name": display_name,
"order": parent_order,
"encounters": [], # Parent routes have no encounters
"children": child_routes,
})
elif area_specific:
# Only one area-specific route - don't create parent/child, just use suffix
for area_suffix, area_encs in area_specific.items():
aggregated = aggregate_encounters(area_encs)
if aggregated:
route_name = f"{display_name} ({area_suffix})"
for enc in aggregated:
all_pokemon_dex.add(enc["national_dex"])
routes.append({
"name": route_name,
"order": order,
"encounters": aggregated,
})
order += 1
# Non-area-specific encounters (or single area without suffix)
if all_encounters:
aggregated = aggregate_encounters(all_encounters)
if aggregated:
for enc in aggregated:
all_pokemon_dex.add(enc["national_dex"])
routes.append({
"name": display_name,
"order": order,
"encounters": aggregated,
})
order += 1
# Count routes including children
total_routes = sum(1 + len(r.get("children", [])) for r in routes)
print(f" Routes with encounters: {total_routes}")
total_enc = sum(
len(r["encounters"]) + sum(len(c["encounters"]) for c in r.get("children", []))
for r in routes
)
print(f" Total encounter entries: {total_enc}")
return routes
def fetch_all_pokemon() -> list[dict]:
"""Fetch all Pokemon species from the local PokeAPI data."""
pokemon_dir = POKEAPI_DIR / "pokemon-species"
# Get all species IDs (directories with numeric names, excluding forms 10000+)
all_species = []
for entry in pokemon_dir.iterdir():
if entry.is_dir() and entry.name.isdigit():
dex = int(entry.name)
if dex < 10000: # Exclude alternate forms
all_species.append(dex)
all_species.sort()
print(f"\n--- Fetching {len(all_species)} Pokemon species ---")
pokemon_list = []
for i, dex in enumerate(all_species, 1):
poke = load_resource("pokemon", dex)
types = [t["type"]["name"] for t in poke["types"]]
pokemon_list.append({
"national_dex": dex,
"name": poke["name"].title().replace("-", " "),
"types": types,
"sprite_url": f"https://raw.githubusercontent.com/PokeAPI/sprites/master/sprites/pokemon/{dex}.png",
})
if i % 100 == 0 or i == len(all_species):
print(f" Fetched {i}/{len(all_species)}")
return sorted(pokemon_list, key=lambda x: x["national_dex"])
def flatten_evolution_chain(chain: dict, seeded_dex: set[int]) -> list[dict]:
"""Recursively flatten a PokeAPI evolution chain into (from, to) pairs."""
pairs = []
from_dex = int(chain["species"]["url"].rstrip("/").split("/")[-1])
for evo in chain.get("evolves_to", []):
to_dex = int(evo["species"]["url"].rstrip("/").split("/")[-1])
for detail in evo["evolution_details"]:
trigger = detail["trigger"]["name"]
min_level = detail.get("min_level")
item = detail.get("item")
if item:
item = item["name"]
held_item = detail.get("held_item")
if held_item:
held_item = held_item["name"]
# Collect other conditions as a string
conditions = []
if detail.get("min_happiness"):
conditions.append(f"happiness >= {detail['min_happiness']}")
if detail.get("min_affection"):
conditions.append(f"affection >= {detail['min_affection']}")
if detail.get("min_beauty"):
conditions.append(f"beauty >= {detail['min_beauty']}")
if detail.get("time_of_day"):
conditions.append(detail["time_of_day"])
if detail.get("known_move"):
conditions.append(f"knows {detail['known_move']['name']}")
if detail.get("known_move_type"):
conditions.append(f"knows {detail['known_move_type']['name']}-type move")
if detail.get("location"):
conditions.append(f"at {detail['location']['name']}")
if detail.get("party_species"):
conditions.append(f"with {detail['party_species']['name']} in party")
if detail.get("party_type"):
conditions.append(f"with {detail['party_type']['name']}-type in party")
if detail.get("gender") is not None:
conditions.append("female" if detail["gender"] == 1 else "male")
if detail.get("needs_overworld_rain"):
conditions.append("raining")
if detail.get("turn_upside_down"):
conditions.append("turn upside down")
if detail.get("trade_species"):
conditions.append(f"trade for {detail['trade_species']['name']}")
if detail.get("relative_physical_stats") is not None:
stat_map = {1: "atk > def", -1: "atk < def", 0: "atk = def"}
conditions.append(stat_map.get(detail["relative_physical_stats"], ""))
condition = ", ".join(conditions) if conditions else None
if from_dex in seeded_dex and to_dex in seeded_dex:
pairs.append({
"from_national_dex": from_dex,
"to_national_dex": to_dex,
"trigger": trigger,
"min_level": min_level,
"item": item,
"held_item": held_item,
"condition": condition,
})
# Recurse into further evolutions
pairs.extend(flatten_evolution_chain(evo, seeded_dex))
return pairs
def fetch_evolution_data(seeded_dex: set[int]) -> list[dict]:
"""Fetch evolution chains from local PokeAPI data for all seeded pokemon."""
print(f"\n--- Fetching evolution chains ---")
# First, get the evolution chain URL for each pokemon species
chain_ids: set[int] = set()
dex_sorted = sorted(seeded_dex)
for i, dex in enumerate(dex_sorted, 1):
species = load_resource("pokemon-species", dex)
chain_url = species["evolution_chain"]["url"]
chain_id = extract_id(chain_url)
chain_ids.add(chain_id)
if i % 50 == 0 or i == len(dex_sorted):
print(f" Species fetched: {i}/{len(dex_sorted)}")
print(f" Found {len(chain_ids)} unique evolution chains")
# Fetch each chain and flatten
all_pairs: list[dict] = []
seen: set[tuple[int, int, str]] = set()
for chain_id in sorted(chain_ids):
chain = load_resource("evolution-chain", chain_id)
pairs = flatten_evolution_chain(chain["chain"], seeded_dex)
for p in pairs:
key = (p["from_national_dex"], p["to_national_dex"], p["trigger"])
if key not in seen:
seen.add(key)
all_pairs.append(p)
print(f" Total evolution pairs: {len(all_pairs)}")
return sorted(all_pairs, key=lambda x: (x["from_national_dex"], x["to_national_dex"]))
def apply_evolution_overrides(evolutions: list[dict]) -> None:
"""Apply overrides from evolution_overrides.json if it exists."""
overrides_path = DATA_DIR / "evolution_overrides.json"
if not overrides_path.exists():
return
with open(overrides_path) as f:
overrides = json.load(f)
# Remove entries
for removal in overrides.get("remove", []):
evolutions[:] = [
e for e in evolutions
if not (e["from_national_dex"] == removal["from_dex"]
and e["to_national_dex"] == removal["to_dex"])
]
# Add entries
for addition in overrides.get("add", []):
evolutions.append({
"from_national_dex": addition["from_dex"],
"to_national_dex": addition["to_dex"],
"trigger": addition.get("trigger", "level-up"),
"min_level": addition.get("min_level"),
"item": addition.get("item"),
"held_item": addition.get("held_item"),
"condition": addition.get("condition"),
})
# Modify entries
for mod in overrides.get("modify", []):
for e in evolutions:
if (e["from_national_dex"] == mod["from_dex"]
and e["to_national_dex"] == mod["to_dex"]):
for key, value in mod.get("set", {}).items():
e[key] = value
# Re-sort
evolutions.sort(key=lambda x: (x["from_national_dex"], x["to_national_dex"]))
print(f" Applied overrides: {len(evolutions)} pairs after overrides")
def write_json(filename: str, data):
path = DATA_DIR / filename
with open(path, "w") as f:
json.dump(data, f, indent=2)
print(f" -> {path}")
def main():
if not POKEAPI_DIR.is_dir():
print(
f"Error: PokeAPI data not found at {POKEAPI_DIR}\n"
"Initialize the submodule with: git submodule update --init",
file=sys.stderr,
)
sys.exit(1)
DATA_DIR.mkdir(parents=True, exist_ok=True)
# Build games.json
games = []
for vg_info in VERSION_GROUPS.values():
for game_info in vg_info["games"].values():
games.append({
"name": game_info["name"],
"slug": game_info["slug"],
"generation": vg_info["generation"],
"region": vg_info["region"],
"release_year": game_info["release_year"],
"color": game_info.get("color"),
})
write_json("games.json", games)
print(f"Wrote {len(games)} games to games.json")
# Process each version
for vg_info in VERSION_GROUPS.values():
for ver_name in vg_info["versions"]:
routes = process_version(ver_name, vg_info)
write_json(f"{ver_name}.json", routes)
# Fetch all Pokemon species
pokemon = fetch_all_pokemon()
write_json("pokemon.json", pokemon)
print(f"\nWrote {len(pokemon)} Pokemon to pokemon.json")
# Build set of all seeded dex numbers for evolution filtering
all_seeded_dex = {p["national_dex"] for p in pokemon}
# Fetch evolution chains for all seeded Pokemon
evolutions = fetch_evolution_data(all_seeded_dex)
apply_evolution_overrides(evolutions)
write_json("evolutions.json", evolutions)
print(f"\nWrote {len(evolutions)} evolution pairs to evolutions.json")
print("\nDone! JSON files written to seeds/data/")
print("Review route ordering and curate as needed.")
if __name__ == "__main__":
main()