Files
simbarag/blueprints/beli/logic.py
T
ryan ccc5126ae0 Sample least-recently-fetched friends instead of random
Replaces random.sample with a staleness-ordered pick: friends never
fetched sort first (epoch timestamp), then oldest fetched_at. Ensures
full following list coverage over successive nightly runs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-09-18 07:15:35 -04:00

253 lines
8.9 KiB
Python

import asyncio
import logging
import random
from datetime import datetime, timezone
from utils.beli_service import (
RANKING_CATEGORIES,
REQUEST_SPACING,
authenticate,
extract_business,
fetch_bookmarks,
fetch_following,
fetch_user_rankings,
is_token_expired,
refresh_access_token,
)
from tortoise.functions import Max
from .models import BeliProfile, BeliRestaurant, BeliStatus
logger = logging.getLogger(__name__)
MAX_PROFILES_PER_USER = 3
NIGHTLY_BATCH_SIZE = 3
NIGHTLY_WINDOW_SECONDS = 4 * 3600 # spread refreshes across a 4-hour window
FRIEND_SAMPLE_SIZE = 5 # friends to randomly refresh per profile per night
async def _get_access_token(profile: BeliProfile) -> str:
"""Return a live access token, refreshing or re-authenticating as needed."""
if profile.beli_refresh_token and not is_token_expired(profile.beli_refresh_token):
try:
token = await refresh_access_token(profile.beli_refresh_token)
return token
except Exception:
logger.warning(
"Refresh token failed for profile %s, falling back to password",
profile.id,
)
session = await authenticate(profile.beli_email, profile.beli_password)
profile.beli_user_id = session["user_id"]
profile.beli_refresh_token = session["refresh_token"]
await profile.save()
return session["access_token"]
async def _refresh_friend_sample(profile: BeliProfile, access_token: str) -> int:
"""Fetch rankings for a random sample of followed users and upsert them."""
try:
following = await fetch_following(access_token, profile.beli_user_id)
except Exception as e:
logger.debug("Beli following fetch skipped for profile %s: %s", profile.id, e)
return 0
if not following:
return 0
# Pick the FRIEND_SAMPLE_SIZE stalest friends — never-fetched first, then oldest
fetched_rows = (
await BeliRestaurant.filter(profile=profile)
.exclude(friend_beli_user_id="")
.group_by("friend_beli_user_id")
.annotate(last_fetched=Max("fetched_at"))
.values("friend_beli_user_id", "last_fetched")
)
last_fetched: dict[str, datetime] = {
r["friend_beli_user_id"]: r["last_fetched"] for r in fetched_rows
}
_epoch = datetime.fromtimestamp(0, tz=timezone.utc)
sample = sorted(
following,
key=lambda f: last_fetched.get(str(f.get("id") or ""), _epoch),
)[:FRIEND_SAMPLE_SIZE]
upserted = 0
for friend in sample:
friend_id = str(friend.get("id") or "")
friend_name = friend.get("full_name") or friend.get("username") or friend_id
if not friend_id:
continue
for category in RANKING_CATEGORIES:
await asyncio.sleep(REQUEST_SPACING)
try:
results = await fetch_user_rankings(access_token, friend_id, category)
except Exception as e:
# 405 = private profile; log quietly and skip
logger.debug(
"Beli friend ranking skipped (%s/%s): %s", friend_id, category, e
)
continue
for idx, item in enumerate(results):
biz = extract_business(item, rank_index=idx + 1)
if not biz:
continue
await BeliRestaurant.update_or_create(
profile=profile,
beli_business_id=biz["beli_business_id"],
status=BeliStatus.BEEN,
friend_beli_user_id=friend_id,
beli_category=category,
defaults={
"friend_name": friend_name,
"name": biz["name"],
"city": biz["city"],
"neighborhood": biz["neighborhood"],
"cuisine": biz["cuisine"],
"price_range": biz["price_range"],
"rank_index": biz["rank_index"],
"score": biz["score"],
"notes": None,
"tags": biz["tags"],
},
)
upserted += 1
if upserted:
logger.info(
"Beli profile %s: %d friend restaurants upserted from %d friends",
profile.id,
upserted,
len(sample),
)
return upserted
async def refresh_profile(profile_id: str) -> dict:
"""Fetch the latest rankings and bookmarks for a profile and upsert them."""
profile = await BeliProfile.get_or_none(id=profile_id)
if not profile or not profile.enabled:
return {"skipped": True}
try:
access_token = await _get_access_token(profile)
upserted = 0
# Fetch all ranking categories (restaurants the user has been to and ranked)
for category in RANKING_CATEGORIES:
await asyncio.sleep(REQUEST_SPACING)
results = await fetch_user_rankings(
access_token, profile.beli_user_id, category
)
for idx, item in enumerate(results):
biz = extract_business(item, rank_index=idx + 1)
if not biz:
continue
await BeliRestaurant.update_or_create(
profile=profile,
beli_business_id=biz["beli_business_id"],
status=BeliStatus.BEEN,
friend_beli_user_id="",
beli_category=category,
defaults={
"name": biz["name"],
"city": biz["city"],
"neighborhood": biz["neighborhood"],
"cuisine": biz["cuisine"],
"price_range": biz["price_range"],
"rank_index": biz["rank_index"],
"score": biz["score"],
"notes": biz["notes"],
"tags": biz["tags"],
},
)
upserted += 1
# Fetch bookmarks (want-to-try list) — non-fatal if unavailable
await asyncio.sleep(REQUEST_SPACING)
try:
bookmarks = await fetch_bookmarks(access_token)
except Exception as e:
logger.warning(
"Beli bookmarks fetch failed for profile %s: %s", profile_id, e
)
bookmarks = []
for item in bookmarks:
biz = extract_business(item)
if not biz:
continue
await BeliRestaurant.update_or_create(
profile=profile,
beli_business_id=biz["beli_business_id"],
status=BeliStatus.WANT_TO_TRY,
friend_beli_user_id="",
beli_category="",
defaults={
"name": biz["name"],
"city": biz["city"],
"neighborhood": biz["neighborhood"],
"cuisine": biz["cuisine"],
"price_range": biz["price_range"],
"rank_index": None,
"score": None,
"notes": biz["notes"],
"tags": biz["tags"],
},
)
upserted += 1
profile.last_refreshed_at = datetime.now(timezone.utc)
profile.last_error = None
await profile.save()
logger.info(
"Beli profile %s refreshed: %d restaurants upserted", profile_id, upserted
)
return {"ok": True, "upserted": upserted}
except Exception as e:
profile.last_error = str(e)
await profile.save()
logger.error("Failed to refresh Beli profile %s: %s", profile_id, e)
return {"error": str(e)}
async def _refresh_after_delay(profile_id: str, delay: float) -> None:
await asyncio.sleep(delay)
profile = await BeliProfile.get_or_none(id=profile_id)
if not profile:
return
await refresh_profile(profile_id)
# Friend sampling only runs during nightly scheduled refreshes, not manual ones
try:
access_token = await _get_access_token(profile)
await _refresh_friend_sample(profile, access_token)
except Exception as e:
logger.warning("Friend sample failed for profile %s: %s", profile_id, e)
async def schedule_nightly_refresh() -> dict:
"""Pick the NIGHTLY_BATCH_SIZE stalest profiles and schedule them with random delays."""
profiles = (
await BeliProfile.filter(enabled=True)
.order_by("last_refreshed_at")
.limit(NIGHTLY_BATCH_SIZE)
.all()
)
if not profiles:
logger.info("No enabled Beli profiles to refresh")
return {"scheduled": 0}
for profile in profiles:
delay = random.uniform(0, NIGHTLY_WINDOW_SECONDS)
asyncio.create_task(_refresh_after_delay(str(profile.id), delay))
logger.info("Scheduled Beli refresh for profile %s in %.0fs", profile.id, delay)
return {"scheduled": len(profiles)}