feat(realestate-collector): 30-day window + district extraction + completed skip
- Add _extract_district() helper with DISTRICT_PATTERN regex (서울 only)
- collect_all() now passes RCRIT_PBLANC_DE_FROM param (30-day window) to all detail endpoints
- collect_all() skips announcements where compute_status() returns '완료'
- collect_all() stamps district on each parsed announcement before upsert
- upsert_announcement(): add district to INSERT/VALUES/ON CONFLICT UPDATE; data.setdefault('district', None)
- ANNOUNCEMENT_COLUMNS: add 'district' (closes deferred gap from Task 2 review)
- 9 new tests in realestate-lab/tests/test_collector.py (6 unit + 3 integration)
- Full suite: 22 passed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1,9 +1,11 @@
|
||||
import os
|
||||
import re
|
||||
import logging
|
||||
from datetime import date, timedelta
|
||||
import requests
|
||||
from typing import List, Dict, Any
|
||||
|
||||
from .db import upsert_announcement, upsert_model, save_collect_log
|
||||
from .db import upsert_announcement, upsert_model, save_collect_log, compute_status
|
||||
|
||||
logger = logging.getLogger("realestate-lab")
|
||||
|
||||
@@ -19,6 +21,19 @@ DETAIL_ENDPOINTS = [
|
||||
("getOPTLttotPblancDetail", "getOPTLttotPblancMdl"),
|
||||
]
|
||||
|
||||
DISTRICT_PATTERN = re.compile(r"(?:서울특별시|서울시|서울)\s+(\S+?(?:구|군))")
|
||||
|
||||
|
||||
def _extract_district(parsed: Dict[str, Any]) -> str | None:
|
||||
"""파싱된 공고에서 자치구를 추출. 서울 외 지역·실패 시 None."""
|
||||
for src in (parsed.get("address"), parsed.get("region_name")):
|
||||
if not src:
|
||||
continue
|
||||
m = DISTRICT_PATTERN.search(src)
|
||||
if m:
|
||||
return m.group(1)
|
||||
return None
|
||||
|
||||
|
||||
def _api_call(endpoint: str, params: Dict[str, Any] = None) -> List[Dict]:
|
||||
"""페이지네이션 처리하여 API 전체 데이터를 반환한다."""
|
||||
@@ -130,28 +145,49 @@ def _parse_model(raw: Dict[str, Any]) -> Dict[str, Any]:
|
||||
|
||||
|
||||
def collect_all() -> Dict[str, Any]:
|
||||
"""모든 엔드포인트를 순회하며 공고 + 모델 데이터를 수집·저장한다."""
|
||||
"""모든 엔드포인트를 순회하며 공고 + 모델 데이터를 수집·저장한다.
|
||||
모집공고일 30일 이전 데이터는 API 파라미터로 사전 좁힘.
|
||||
status='완료'로 판정되는 응답은 저장하지 않음.
|
||||
"""
|
||||
if not API_KEY:
|
||||
logger.warning("API 키 미설정 — 수집 중단")
|
||||
save_collect_log(0, 0, "API 키 미설정")
|
||||
return {"new_count": 0, "total_count": 0}
|
||||
|
||||
today = date.today()
|
||||
date_from = (today - timedelta(days=30)).strftime("%Y%m%d")
|
||||
|
||||
total_count = 0
|
||||
new_count = 0
|
||||
skipped_completed = 0
|
||||
|
||||
for detail_ep, model_ep in DETAIL_ENDPOINTS:
|
||||
# 공고 상세 수집
|
||||
detail_rows = _api_call(detail_ep)
|
||||
# 공고 상세 수집 — API에 모집공고일 윈도우 파라미터 전달
|
||||
# 일부 엔드포인트는 파라미터 미지원일 수 있어 무시되지만 응답에 영향 없음
|
||||
detail_rows = _api_call(detail_ep, params={"RCRIT_PBLANC_DE_FROM": date_from})
|
||||
for raw in detail_rows:
|
||||
try:
|
||||
parsed = _parse_apt_detail(raw)
|
||||
# 일정 정보가 하나도 없는 공고는 건너뜀
|
||||
parsed["district"] = _extract_district(parsed)
|
||||
|
||||
# 일정 정보가 하나도 없는 공고는 건너뜀 (기존)
|
||||
has_dates = any(parsed.get(f) for f in (
|
||||
"receipt_start", "receipt_end", "spsply_start",
|
||||
"gnrl_rank1_start", "winner_date", "contract_start",
|
||||
))
|
||||
if not has_dates:
|
||||
continue
|
||||
|
||||
# status='완료'면 저장하지 않음 (자원 절감)
|
||||
status = compute_status(
|
||||
parsed.get("receipt_start", "") or "",
|
||||
parsed.get("receipt_end", "") or "",
|
||||
parsed.get("winner_date", "") or "",
|
||||
)
|
||||
if status == "완료":
|
||||
skipped_completed += 1
|
||||
continue
|
||||
|
||||
_, is_new = upsert_announcement(parsed)
|
||||
total_count += 1
|
||||
if is_new:
|
||||
@@ -168,5 +204,5 @@ def collect_all() -> Dict[str, Any]:
|
||||
except Exception as e:
|
||||
logger.error("모델 upsert 실패 [%s]: %s", model_ep, e)
|
||||
save_collect_log(new_count, total_count)
|
||||
logger.info("수집 완료: new=%d, total=%d", new_count, total_count)
|
||||
logger.info("수집 완료: new=%d, total=%d, skipped_completed=%d", new_count, total_count, skipped_completed)
|
||||
return {"new_count": new_count, "total_count": total_count}
|
||||
|
||||
@@ -194,6 +194,7 @@ def _ann_row_to_dict(r) -> Dict[str, Any]:
|
||||
|
||||
def upsert_announcement(data: Dict[str, Any]) -> tuple:
|
||||
"""공고 upsert — house_manage_no + pblanc_no 기준. Returns (dict, is_new: bool)."""
|
||||
data.setdefault("district", None) # 수동 등록 등에서 누락 시 안전 처리
|
||||
status = compute_status(
|
||||
data.get("receipt_start", ""),
|
||||
data.get("receipt_end", ""),
|
||||
@@ -208,7 +209,7 @@ def upsert_announcement(data: Dict[str, Any]) -> tuple:
|
||||
conn.execute("""
|
||||
INSERT INTO announcements (
|
||||
house_manage_no, pblanc_no, house_nm, house_secd, house_dtl_secd,
|
||||
rent_secd, region_code, region_name, address, total_units,
|
||||
rent_secd, region_code, region_name, district, address, total_units,
|
||||
rcrit_date, receipt_start, receipt_end, spsply_start, spsply_end,
|
||||
gnrl_rank1_start, gnrl_rank1_end, winner_date, contract_start,
|
||||
contract_end, homepage_url, pblanc_url, constructor, developer,
|
||||
@@ -216,7 +217,7 @@ def upsert_announcement(data: Dict[str, Any]) -> tuple:
|
||||
status, source
|
||||
) VALUES (
|
||||
:house_manage_no, :pblanc_no, :house_nm, :house_secd, :house_dtl_secd,
|
||||
:rent_secd, :region_code, :region_name, :address, :total_units,
|
||||
:rent_secd, :region_code, :region_name, :district, :address, :total_units,
|
||||
:rcrit_date, :receipt_start, :receipt_end, :spsply_start, :spsply_end,
|
||||
:gnrl_rank1_start, :gnrl_rank1_end, :winner_date, :contract_start,
|
||||
:contract_end, :homepage_url, :pblanc_url, :constructor, :developer,
|
||||
@@ -230,6 +231,7 @@ def upsert_announcement(data: Dict[str, Any]) -> tuple:
|
||||
rent_secd=excluded.rent_secd,
|
||||
region_code=excluded.region_code,
|
||||
region_name=excluded.region_name,
|
||||
district=excluded.district,
|
||||
address=excluded.address,
|
||||
total_units=excluded.total_units,
|
||||
rcrit_date=excluded.rcrit_date,
|
||||
@@ -368,7 +370,7 @@ def create_announcement(data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
|
||||
ANNOUNCEMENT_COLUMNS = {
|
||||
"house_nm", "house_secd", "house_dtl_secd", "rent_secd",
|
||||
"region_code", "region_name", "address", "total_units",
|
||||
"region_code", "region_name", "district", "address", "total_units",
|
||||
"rcrit_date", "receipt_start", "receipt_end", "spsply_start", "spsply_end",
|
||||
"gnrl_rank1_start", "gnrl_rank1_end", "winner_date",
|
||||
"contract_start", "contract_end", "homepage_url", "pblanc_url",
|
||||
|
||||
Reference in New Issue
Block a user