EiSiMo
eb66284172
apply service
- POST /internal/fetch-listing: headless Playwright fetch of a listing URL,
returns {html, image_urls[], final_url}. Uses the same browser
fingerprint/profile as the apply run so bot guards don't kick in
web service
- New enrichment pipeline (web/enrichment.py):
/internal/flats → upsert → kick() enrichment in a background thread
1. POST /internal/fetch-listing on apply
2. llm.extract_flat_details(html, url) — Haiku tool-use call returns
structured JSON (address, rooms, rent, description, pros/cons, etc.)
3. Download each image directly to /data/flats/<slug>/NN.<ext>
4. Persist enrichment_json + image_count + enrichment_status on the flat
- llm.py: minimal Anthropic /v1/messages wrapper, no SDK
- DB migration v5 adds enrichment_json/_status/_updated_at + image_count
- Admin "Altbestand anreichern" button (POST /actions/enrich-all) queues
backfill for all pending/failed rows; runs in a detached task
- GET /partials/wohnung/<id> renders _wohnung_detail.html
- GET /flat-images/<slug>/<n> serves the downloaded image
UI
- Chevron on each list row toggles an inline detail pane (HTMX fetch on
first open, hx-preserve keeps it open across the 3–30 s polls)
- CSS .flat-gallery normalises image tiles to a 4/3 aspect with object-fit:
cover so different source sizes align cleanly
- "analysiert…" / "?" chips on the list reflect enrichment_status
Config
- ANTHROPIC_API_KEY + ANTHROPIC_MODEL wired into docker-compose's web
service (default model: claude-haiku-4-5-20251001)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
69 lines
3.1 KiB
Python
69 lines
3.1 KiB
Python
import secrets
|
|
import sys
|
|
from os import getenv
|
|
from pathlib import Path
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
|
|
def _required(key: str) -> str:
|
|
val = getenv(key)
|
|
if not val:
|
|
print(f"missing required env var: {key}", file=sys.stderr)
|
|
sys.exit(1)
|
|
return val
|
|
|
|
|
|
# --- Admin bootstrap ----------------------------------------------------------
|
|
# On first boot the web service seeds this user as an admin in the database.
|
|
# Afterwards the user record in SQLite is authoritative: changing the hash in
|
|
# env does NOT rotate the DB password — use the /einstellungen UI.
|
|
AUTH_USERNAME: str = _required("AUTH_USERNAME")
|
|
AUTH_PASSWORD_HASH: str = _required("AUTH_PASSWORD_HASH")
|
|
|
|
# --- Session cookie -----------------------------------------------------------
|
|
SESSION_SECRET: str = getenv("SESSION_SECRET") or secrets.token_urlsafe(48)
|
|
SESSION_COOKIE_NAME: str = "lazyflat_session"
|
|
SESSION_MAX_AGE_SECONDS: int = int(getenv("SESSION_MAX_AGE_SECONDS", str(60 * 60 * 24 * 7)))
|
|
COOKIE_SECURE: bool = getenv("COOKIE_SECURE", "true").lower() in ("true", "1", "yes", "on")
|
|
|
|
# --- Internal service auth ----------------------------------------------------
|
|
INTERNAL_API_KEY: str = _required("INTERNAL_API_KEY")
|
|
|
|
# --- Apply service ------------------------------------------------------------
|
|
APPLY_URL: str = getenv("APPLY_URL", "http://apply:8000")
|
|
APPLY_TIMEOUT: int = int(getenv("APPLY_TIMEOUT", "600"))
|
|
APPLY_FAILURE_THRESHOLD: int = int(getenv("APPLY_FAILURE_THRESHOLD", "3"))
|
|
|
|
# --- Alert service knob (mirrored so web can predict the next scrape) ---------
|
|
ALERT_SCRAPE_INTERVAL_SECONDS: int = int(getenv("ALERT_SCRAPE_INTERVAL_SECONDS", getenv("SLEEP_INTERVALL", "60")))
|
|
|
|
# --- Storage ------------------------------------------------------------------
|
|
DATA_DIR: Path = Path(getenv("DATA_DIR", "/data"))
|
|
DATA_DIR.mkdir(parents=True, exist_ok=True)
|
|
DB_PATH: Path = DATA_DIR / "lazyflat.sqlite"
|
|
|
|
# Retention (errors / audit / application forensics). Default 14 days.
|
|
RETENTION_DAYS: int = int(getenv("RETENTION_DAYS", "14"))
|
|
RETENTION_RUN_INTERVAL_SECONDS: int = int(getenv("RETENTION_RUN_INTERVAL_SECONDS", str(60 * 60)))
|
|
|
|
# --- Rate limiting ------------------------------------------------------------
|
|
LOGIN_RATE_LIMIT: int = int(getenv("LOGIN_RATE_LIMIT", "5"))
|
|
LOGIN_RATE_WINDOW_SECONDS: int = int(getenv("LOGIN_RATE_WINDOW_SECONDS", "900"))
|
|
|
|
# --- Email (system-wide SMTP for notifications) -------------------------------
|
|
SMTP_HOST: str = getenv("SMTP_HOST", "")
|
|
SMTP_PORT: int = int(getenv("SMTP_PORT", "587"))
|
|
SMTP_USERNAME: str = getenv("SMTP_USERNAME", "")
|
|
SMTP_PASSWORD: str = getenv("SMTP_PASSWORD", "")
|
|
SMTP_FROM: str = getenv("SMTP_FROM", "lazyflat@localhost")
|
|
SMTP_STARTTLS: bool = getenv("SMTP_STARTTLS", "true").lower() in ("true", "1", "yes", "on")
|
|
|
|
# --- App URL (used to build links in notifications) ---------------------------
|
|
PUBLIC_URL: str = getenv("PUBLIC_URL", "https://flat.lab.moritz.run")
|
|
|
|
# --- LLM enrichment (Anthropic Haiku) -----------------------------------------
|
|
ANTHROPIC_API_KEY: str = getenv("ANTHROPIC_API_KEY", "")
|
|
ANTHROPIC_MODEL: str = getenv("ANTHROPIC_MODEL", "claude-haiku-4-5-20251001")
|