feat(extract): weekly tenant snapshots via ISO week partition

Tenants extractor now partitions by ISO week (e.g. 2026/W09) instead of
month (2026/02), so each weekly run writes a fresh file rather than
skipping for the rest of the month.

_load_tenant_ids() in playtomic_availability already globs */*/tenants.jsonl.gz
and sorts reverse — 'W09' > '02' alphabetically so weekly files take priority
over old monthly ones automatically.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Deeman
2026-02-28 17:19:19 +01:00
parent adf22924f6
commit 9116625884

View File

@@ -25,6 +25,7 @@ import json
import sqlite3
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import UTC, datetime
from pathlib import Path
import niquests
@@ -69,17 +70,23 @@ def _fetch_pages_parallel(pages: list[int], next_proxy) -> list[tuple[int, list[
def extract(
landing_dir: Path,
year_month: str,
year_month: str, # noqa: ARG001 — unused; tenants uses ISO week partition instead
conn: sqlite3.Connection,
session: niquests.Session,
) -> dict:
"""Fetch all Playtomic venues via global pagination. Returns run metrics."""
year, month = year_month.split("/")
dest_dir = landing_path(landing_dir, "playtomic", year, month)
"""Fetch all Playtomic venues via global pagination. Returns run metrics.
Partitioned by ISO week (e.g. 2026/W09) so each weekly run produces a
fresh file. _load_tenant_ids() in playtomic_availability globs across all
partitions and picks the most recent one.
"""
today = datetime.now(UTC)
year = today.strftime("%G") # ISO year (matches ISO week, differs from calendar year on week boundaries)
week = today.strftime("W%V") # ISO week: W01 … W53
dest_dir = landing_path(landing_dir, "playtomic", year, week)
dest = dest_dir / "tenants.jsonl.gz"
old_blob = dest_dir / "tenants.json.gz"
if dest.exists() or old_blob.exists():
logger.info("Already have tenants for %s/%s — skipping", year, month)
if dest.exists():
logger.info("Already have tenants for %s/%s — skipping", year, week)
return {"files_written": 0, "files_skipped": 1, "bytes_written": 0}
tiers = load_proxy_tiers()
@@ -155,7 +162,7 @@ def extract(
"files_written": 1,
"files_skipped": 0,
"bytes_written": bytes_written,
"cursor_value": year_month,
"cursor_value": f"{year}/{week}",
}