feat(v2): add BCL snapshot extractor and command

This commit is contained in:
Alfredo Di Stasio
2026-03-13 14:32:21 +01:00
parent 97913c4a79
commit 5df973467d
9 changed files with 357 additions and 1 deletions

View File

@ -1,3 +1,4 @@
from .bcl import BCLSnapshotExtractor
from .base import (
BaseSnapshotExtractor,
ExtractionResult,
@ -12,6 +13,7 @@ from .registry import available_extractors, create_extractor
__all__ = [
"BaseSnapshotExtractor",
"BCLSnapshotExtractor",
"LBASnapshotExtractor",
"ExtractionResult",
"ExtractorError",

View File

@ -0,0 +1,137 @@
from __future__ import annotations
from typing import Any
from django.conf import settings
from .base import BaseSnapshotExtractor, ExtractorConfigError, ExtractorNormalizationError, ExtractorParseError
from .http import ResponsibleHttpClient
def _first_non_empty(record: dict[str, Any], *keys: str) -> Any:
for key in keys:
value = record.get(key)
if value not in (None, ""):
return value
return None
class BCLSnapshotExtractor(BaseSnapshotExtractor):
"""
Basketball Champions League MVP extractor.
Scope is intentionally conservative:
- one configured public stats endpoint
- one configured season label
- normalized player-season rows only
"""
extractor_name = "bcl"
source_name = "bcl"
def __init__(self, *, http_client: ResponsibleHttpClient | None = None):
self.url = settings.EXTRACTOR_BCL_STATS_URL.strip()
self.season_label = settings.EXTRACTOR_BCL_SEASON_LABEL.strip()
self.competition_external_id = settings.EXTRACTOR_BCL_COMPETITION_EXTERNAL_ID.strip()
self.competition_name = settings.EXTRACTOR_BCL_COMPETITION_NAME.strip()
self.include_raw_payload = settings.EXTRACTOR_INCLUDE_RAW_PAYLOAD
self.http_client = http_client or ResponsibleHttpClient(
user_agent=settings.EXTRACTOR_USER_AGENT,
timeout_seconds=settings.EXTRACTOR_HTTP_TIMEOUT_SECONDS,
retries=settings.EXTRACTOR_HTTP_RETRIES,
retry_sleep_seconds=settings.EXTRACTOR_RETRY_SLEEP_SECONDS,
request_delay_seconds=settings.EXTRACTOR_REQUEST_DELAY_SECONDS,
)
if not self.url:
raise ExtractorConfigError("EXTRACTOR_BCL_STATS_URL is required for bcl extractor.")
if not self.season_label:
raise ExtractorConfigError("EXTRACTOR_BCL_SEASON_LABEL is required for bcl extractor.")
if not self.competition_external_id:
raise ExtractorConfigError("EXTRACTOR_BCL_COMPETITION_EXTERNAL_ID is required.")
if not self.competition_name:
raise ExtractorConfigError("EXTRACTOR_BCL_COMPETITION_NAME is required.")
def fetch(self) -> Any:
return self.http_client.get_json(self.url)
def parse(self, payload: Any) -> list[dict[str, Any]]:
if isinstance(payload, list):
return payload
if not isinstance(payload, dict):
raise ExtractorParseError("BCL payload must be a JSON object or array.")
for key in ("records", "data", "players", "items"):
rows = payload.get(key)
if isinstance(rows, list):
return rows
raise ExtractorParseError("BCL payload must contain one of: records, data, players, items.")
def normalize_record(self, source_record: dict[str, Any]) -> dict[str, Any]:
player_obj = source_record.get("player") if isinstance(source_record.get("player"), dict) else {}
team_obj = source_record.get("team") if isinstance(source_record.get("team"), dict) else {}
full_name = _first_non_empty(
source_record,
"full_name",
"player_name",
"name",
) or _first_non_empty(player_obj, "full_name", "name")
first_name = _first_non_empty(source_record, "first_name") or _first_non_empty(player_obj, "first_name")
last_name = _first_non_empty(source_record, "last_name") or _first_non_empty(player_obj, "last_name")
player_external_id = _first_non_empty(
source_record, "player_external_id", "player_id", "athlete_id"
) or _first_non_empty(player_obj, "id", "player_id")
team_external_id = _first_non_empty(source_record, "team_external_id", "team_id") or _first_non_empty(
team_obj, "id", "team_id"
)
team_name = _first_non_empty(source_record, "team_name", "team") or _first_non_empty(team_obj, "name")
normalized = {
"competition_external_id": self.competition_external_id,
"competition_name": self.competition_name,
"season": self.season_label,
"team_external_id": team_external_id,
"team_name": team_name,
"player_external_id": player_external_id,
"full_name": full_name,
"first_name": first_name,
"last_name": last_name,
"birth_date": _first_non_empty(source_record, "birth_date") or _first_non_empty(
player_obj, "birth_date", "dob"
),
"nationality": _first_non_empty(source_record, "nationality")
or _first_non_empty(player_obj, "nationality", "country"),
"height_cm": _first_non_empty(source_record, "height_cm") or _first_non_empty(player_obj, "height_cm"),
"weight_kg": _first_non_empty(source_record, "weight_kg") or _first_non_empty(player_obj, "weight_kg"),
"position": _first_non_empty(source_record, "position") or _first_non_empty(player_obj, "position"),
"role": _first_non_empty(source_record, "role"),
"games_played": _first_non_empty(source_record, "games_played", "gp"),
"minutes_per_game": _first_non_empty(source_record, "minutes_per_game", "mpg"),
"points_per_game": _first_non_empty(source_record, "points_per_game", "ppg"),
"rebounds_per_game": _first_non_empty(source_record, "rebounds_per_game", "rpg"),
"assists_per_game": _first_non_empty(source_record, "assists_per_game", "apg"),
"steals_per_game": _first_non_empty(source_record, "steals_per_game", "spg"),
"blocks_per_game": _first_non_empty(source_record, "blocks_per_game", "bpg"),
"turnovers_per_game": _first_non_empty(source_record, "turnovers_per_game", "tov"),
"fg_pct": _first_non_empty(source_record, "fg_pct", "fg_percentage"),
"three_pt_pct": _first_non_empty(
source_record, "three_pt_pct", "three_point_pct", "3p_pct", "three_pct"
),
"ft_pct": _first_non_empty(source_record, "ft_pct", "ft_percentage"),
}
missing = [key for key, value in normalized.items() if key != "role" and value in (None, "")]
if missing:
raise ExtractorNormalizationError(f"bcl row missing required fields: {', '.join(sorted(missing))}")
normalized["team_external_id"] = str(normalized["team_external_id"]).strip()
normalized["player_external_id"] = str(normalized["player_external_id"]).strip()
normalized["competition_external_id"] = str(normalized["competition_external_id"]).strip()
normalized["season"] = str(normalized["season"]).strip()
if self.include_raw_payload:
normalized["raw_payload"] = source_record
return normalized

View File

@ -1,10 +1,12 @@
from __future__ import annotations
from .bcl import BCLSnapshotExtractor
from .base import BaseSnapshotExtractor, ExtractorConfigError
from .lba import LBASnapshotExtractor
from .public_json import PublicJsonSnapshotExtractor
EXTRACTOR_REGISTRY: dict[str, type[BaseSnapshotExtractor]] = {
BCLSnapshotExtractor.extractor_name: BCLSnapshotExtractor,
LBASnapshotExtractor.extractor_name: LBASnapshotExtractor,
PublicJsonSnapshotExtractor.extractor_name: PublicJsonSnapshotExtractor,
}

View File

@ -0,0 +1,61 @@
from __future__ import annotations
from django.core.management.base import BaseCommand, CommandError
from django.utils.dateparse import parse_date
from apps.ingestion.extractors import ExtractorError, create_extractor
class Command(BaseCommand):
help = "Run only the BCL extractor and emit an import-ready snapshot JSON."
def add_arguments(self, parser):
parser.add_argument(
"--output-path",
dest="output_path",
default=None,
help="Directory or .json path to write output (default incoming dir).",
)
parser.add_argument(
"--snapshot-date",
dest="snapshot_date",
default=None,
help="Override snapshot date in YYYY-MM-DD format.",
)
parser.add_argument(
"--dry-run",
action="store_true",
help="Validate without writing output.",
)
parser.add_argument(
"--indent",
type=int,
default=2,
help="JSON indent level for emitted file.",
)
def handle(self, *args, **options):
snapshot_date = None
if options["snapshot_date"]:
snapshot_date = parse_date(options["snapshot_date"])
if snapshot_date is None:
raise CommandError("--snapshot-date must be YYYY-MM-DD.")
try:
extractor = create_extractor("bcl")
result = extractor.run(
output_path=options["output_path"],
snapshot_date=snapshot_date,
write_output=not options["dry_run"],
indent=options["indent"],
)
except ExtractorError as exc:
raise CommandError(str(exc)) from exc
output = str(result.output_path) if result.output_path else "<dry-run>"
self.stdout.write(
self.style.SUCCESS(
f"BCL extractor completed: source={result.source_name} "
f"date={result.snapshot_date} records={result.records_count} output={output}"
)
)