Public Access
feat: implement Lucky California scraper with Playwright + BeautifulSoup
- Add BaseScraper with rate limiting, retries, session management - Add LuckyCaliforniaScraper with Playwright for dynamic content - Add ScraperService to save scraped items to grocery_item table - Connect /api/admin/scrape to ScraperService - Update ORIENTATION.md phase table
This commit is contained in:
@@ -2,6 +2,7 @@ from fastapi import APIRouter, Depends, HTTPException
|
||||
from sqlalchemy.orm import Session
|
||||
from app.database import get_db
|
||||
from app.models import ScrapeLog, EmailLog, MealPlan
|
||||
from app.services.scraper_service import ScraperService
|
||||
from typing import List, Optional
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
@@ -10,22 +11,10 @@ router = APIRouter()
|
||||
|
||||
@router.post("/scrape")
|
||||
def trigger_scrape(source: str = "lucky_california", scrape_type: str = "weekly_ad", db: Session = Depends(get_db)):
|
||||
scrape_log = ScrapeLog(
|
||||
source=source,
|
||||
scrape_type=scrape_type,
|
||||
status="started",
|
||||
started_at=datetime.now()
|
||||
)
|
||||
db.add(scrape_log)
|
||||
db.commit()
|
||||
db.refresh(scrape_log)
|
||||
scraper_service = ScraperService(db)
|
||||
result = scraper_service.run_scrape(source=source, scrape_type=scrape_type)
|
||||
|
||||
return {
|
||||
"message": "Scrape initiated",
|
||||
"scrape_id": str(scrape_log.id),
|
||||
"source": source,
|
||||
"scrape_type": scrape_type
|
||||
}
|
||||
return result
|
||||
|
||||
|
||||
@router.get("/logs")
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
from .base import BaseScraper
|
||||
from .lucky_ca_scraper import LuckyCaliforniaScraper
|
||||
|
||||
__all__ = ["BaseScraper", "LuckyCaliforniaScraper"]
|
||||
@@ -0,0 +1,138 @@
|
||||
import time
|
||||
import logging
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Optional, List, Dict, Any
|
||||
from datetime import datetime
|
||||
from urllib.parse import urljoin
|
||||
import requests
|
||||
from requests.adapters import HTTPAdapter
|
||||
from urllib3.util.retry import Retry
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class BaseScraper(ABC):
|
||||
def __init__(
|
||||
self,
|
||||
base_url: str,
|
||||
rate_limit_seconds: float = 2.0,
|
||||
max_retries: int = 3,
|
||||
timeout: int = 30
|
||||
):
|
||||
self.base_url = base_url.rstrip("/")
|
||||
self.rate_limit_seconds = rate_limit_seconds
|
||||
self.max_retries = max_retries
|
||||
self.timeout = timeout
|
||||
self.last_request_time = 0.0
|
||||
self.session = self._create_session()
|
||||
|
||||
def _create_session(self) -> requests.Session:
|
||||
session = requests.Session()
|
||||
|
||||
retry_strategy = Retry(
|
||||
total=self.max_retries,
|
||||
backoff_factor=1.0,
|
||||
status_forcelist=[429, 500, 502, 503, 504],
|
||||
allowed_methods=["HEAD", "GET", "OPTIONS"]
|
||||
)
|
||||
|
||||
adapter = HTTPAdapter(max_retries=retry_strategy, pool_maxsize=10)
|
||||
session.mount("http://", adapter)
|
||||
session.mount("https://", adapter)
|
||||
|
||||
session.headers.update({
|
||||
"User-Agent": "Mozilla/5.0 (compatible; MealPlannerBot/1.0; +https://mealplanner.local)",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Accept-Language": "en-US,en;q=0.5",
|
||||
})
|
||||
|
||||
return session
|
||||
|
||||
def _rate_limit(self) -> None:
|
||||
elapsed = time.time() - self.last_request_time
|
||||
if elapsed < self.rate_limit_seconds:
|
||||
sleep_time = self.rate_limit_seconds - elapsed
|
||||
logger.debug(f"Rate limiting: sleeping {sleep_time:.2f}s")
|
||||
time.sleep(sleep_time)
|
||||
self.last_request_time = time.time()
|
||||
|
||||
def _get(self, url: str, **kwargs) -> Optional[requests.Response]:
|
||||
self._rate_limit()
|
||||
|
||||
full_url = url if url.startswith("http") else urljoin(self.base_url, url)
|
||||
|
||||
for attempt in range(self.max_retries + 1):
|
||||
try:
|
||||
logger.debug(f"GET {full_url} (attempt {attempt + 1})")
|
||||
response = self.session.get(full_url, timeout=self.timeout, **kwargs)
|
||||
response.raise_for_status()
|
||||
return response
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger.warning(f"Request failed (attempt {attempt + 1}): {e}")
|
||||
if attempt >= self.max_retries:
|
||||
logger.error(f"Max retries reached for {full_url}")
|
||||
return None
|
||||
time.sleep(2 ** attempt)
|
||||
|
||||
return None
|
||||
|
||||
def _post(self, url: str, data: Dict[str, Any] = None, **kwargs) -> Optional[requests.Response]:
|
||||
self._rate_limit()
|
||||
|
||||
full_url = url if url.startswith("http") else urljoin(self.base_url, url)
|
||||
|
||||
for attempt in range(self.max_retries + 1):
|
||||
try:
|
||||
logger.debug(f"POST {full_url} (attempt {attempt + 1})")
|
||||
response = self.session.post(full_url, data=data, timeout=self.timeout, **kwargs)
|
||||
response.raise_for_status()
|
||||
return response
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger.warning(f"POST request failed (attempt {attempt + 1}): {e}")
|
||||
if attempt >= self.max_retries:
|
||||
logger.error(f"Max retries reached for {full_url}")
|
||||
return None
|
||||
time.sleep(2 ** attempt)
|
||||
|
||||
return None
|
||||
|
||||
@abstractmethod
|
||||
def scrape(self) -> Dict[str, Any]:
|
||||
pass
|
||||
|
||||
def log_scrape(self, status: str, items_scraped: int = 0, error_message: str = None) -> None:
|
||||
logger.info(f"Scrape {status}: {items_scraped} items, error: {error_message}")
|
||||
|
||||
|
||||
class SeleniumScraper(BaseScraper):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self._playwright = None
|
||||
|
||||
def _init_playwright(self):
|
||||
if self._playwright is None:
|
||||
from playwright.sync_api import sync_playwright
|
||||
self._playwright = sync_playwright().start()
|
||||
self._browser = self._playwright.chromium.launch(headless=True)
|
||||
self._context = self._browser.new_context(
|
||||
user_agent="Mozilla/5.0 (compatible; MealPlannerBot/1.0)"
|
||||
)
|
||||
|
||||
def _get_playwright(self):
|
||||
self._init_playwright()
|
||||
return self._playwright
|
||||
|
||||
def get_browser_page(self, url: str):
|
||||
self._get_playwright()
|
||||
page = self._context.new_page()
|
||||
page.goto(url, wait_until="networkidle", timeout=30000)
|
||||
return page
|
||||
|
||||
def cleanup(self):
|
||||
if self._browser:
|
||||
self._browser.close()
|
||||
if self._playwright:
|
||||
self._playwright.stop()
|
||||
self._playwright = None
|
||||
@@ -0,0 +1,180 @@
|
||||
import logging
|
||||
import re
|
||||
from typing import Dict, Any, List, Optional
|
||||
from datetime import datetime
|
||||
from urllib.parse import urljoin
|
||||
from bs4 import BeautifulSoup
|
||||
from .base import SeleniumScraper
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class LuckyCaliforniaScraper(SeleniumScraper):
|
||||
def __init__(self, base_url: str = "https://luckysupermarkets.com"):
|
||||
super().__init__(base_url=base_url, rate_limit_seconds=3.0)
|
||||
self.ingredients_cache = {}
|
||||
|
||||
def scrape(self) -> Dict[str, Any]:
|
||||
logger.info("Starting Lucky California scrape")
|
||||
result = {
|
||||
"source": "lucky_california",
|
||||
"scrape_type": "weekly_ad",
|
||||
"started_at": datetime.now().isoformat(),
|
||||
"items_scraped": 0,
|
||||
"items": []
|
||||
}
|
||||
|
||||
try:
|
||||
featured_items = self.scrape_featured_coupons()
|
||||
result["items"].extend(featured_items)
|
||||
result["items_scraped"] = len(featured_items)
|
||||
|
||||
result["completed_at"] = datetime.now().isoformat()
|
||||
result["status"] = "success"
|
||||
logger.info(f"Lucky California scrape complete: {result['items_scraped']} items")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Lucky California scrape failed: {e}")
|
||||
result["status"] = "failed"
|
||||
result["error_message"] = str(e)
|
||||
result["completed_at"] = datetime.now().isoformat()
|
||||
|
||||
return result
|
||||
|
||||
def scrape_featured_coupons(self) -> List[Dict[str, Any]]:
|
||||
url = f"{self.base_url}/coupons/Coupon%2Flu-featured-in-ad"
|
||||
logger.info(f"Scraping featured coupons from {url}")
|
||||
|
||||
page = self.get_browser_page(url)
|
||||
content = page.content()
|
||||
page.close()
|
||||
|
||||
soup = BeautifulSoup(content, "html.parser")
|
||||
items = []
|
||||
|
||||
coupon_items = soup.find_all("div", class_=re.compile(r"coupon|item|product", re.I))
|
||||
if not coupon_items:
|
||||
headline = soup.find("h1")
|
||||
if headline:
|
||||
logger.info(f"Page loaded, headline: {headline.get_text().strip()}")
|
||||
|
||||
titles = soup.find_all(["h2", "h3", "a"], string=re.compile(r"\$[\d\.]+"))
|
||||
for title_elem in titles[:20]:
|
||||
try:
|
||||
item = self._parse_coupon_item(title_elem)
|
||||
if item:
|
||||
items.append(item)
|
||||
except Exception as e:
|
||||
logger.debug(f"Failed to parse item: {e}")
|
||||
continue
|
||||
|
||||
logger.info(f"Found {len(items)} coupon items")
|
||||
return items
|
||||
|
||||
def _parse_coupon_item(self, element) -> Optional[Dict[str, Any]]:
|
||||
text = element.get_text().strip()
|
||||
|
||||
price_match = re.search(r'\$[\d,]+\.?\d*', text)
|
||||
if not price_match:
|
||||
return None
|
||||
|
||||
price_str = price_match.group().replace("$", "").replace(",", "")
|
||||
try:
|
||||
price = float(price_str)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
name_elem = element.find_parent("a") or element.find_parent("div")
|
||||
name = text.split("$")[0].strip() if "$" in text else text
|
||||
name = re.sub(r'\s+', " ", name).strip()[:200]
|
||||
|
||||
if not name or len(name) < 3:
|
||||
return None
|
||||
|
||||
image_url = None
|
||||
img_elem = element.find_parent().find("img") if element.find_parent() else None
|
||||
if img_elem and img_elem.get("src"):
|
||||
image_url = img_elem["src"]
|
||||
|
||||
product_url = None
|
||||
link_elem = element.find_parent("a") if element.find_parent() else element.find("a")
|
||||
if link_elem and link_elem.get("href"):
|
||||
product_url = urljoin(self.base_url, link_elem["href"])
|
||||
|
||||
item = {
|
||||
"name": name,
|
||||
"current_price": price,
|
||||
"image_url": image_url,
|
||||
"product_url": product_url,
|
||||
"is_on_sale": True,
|
||||
"scraped_at": datetime.now().isoformat(),
|
||||
"scraped_url": self.base_url
|
||||
}
|
||||
|
||||
return item
|
||||
|
||||
def scrape_produce(self) -> List[Dict[str, Any]]:
|
||||
url = f"{self.base_url}/coupons/Coupon%2Flu-produce"
|
||||
logger.info(f"Scraping produce from {url}")
|
||||
|
||||
page = self.get_browser_page(url)
|
||||
content = page.content()
|
||||
page.close()
|
||||
|
||||
soup = BeautifulSoup(content, "html.parser")
|
||||
items = []
|
||||
|
||||
for item_elem in soup.find_all("div", class_=re.compile(r"product|item|coupon")):
|
||||
try:
|
||||
item = self._parse_coupon_item(item_elem)
|
||||
if item:
|
||||
item["aisle"] = "Produce"
|
||||
items.append(item)
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
return items
|
||||
|
||||
def scrape_meat_seafood(self) -> List[Dict[str, Any]]:
|
||||
url = f"{self.base_url}/coupons/Coupon%2Flu-meat-seafood"
|
||||
logger.info(f"Scraping meat & seafood from {url}")
|
||||
|
||||
page = self.get_browser_page(url)
|
||||
content = page.content()
|
||||
page.close()
|
||||
|
||||
soup = BeautifulSoup(content, "html.parser")
|
||||
items = []
|
||||
|
||||
for item_elem in soup.find_all("div", class_=re.compile(r"product|item|coupon")):
|
||||
try:
|
||||
item = self._parse_coupon_item(item_elem)
|
||||
if item:
|
||||
item["aisle"] = "Meat"
|
||||
items.append(item)
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
return items
|
||||
|
||||
def scrape_dairy_eggs(self) -> List[Dict[str, Any]]:
|
||||
url = f"{self.base_url}/coupons/Coupon%2Flu-dairy-eggs"
|
||||
logger.info(f"Scraping dairy & eggs from {url}")
|
||||
|
||||
page = self.get_browser_page(url)
|
||||
content = page.content()
|
||||
page.close()
|
||||
|
||||
soup = BeautifulSoup(content, "html.parser")
|
||||
items = []
|
||||
|
||||
for item_elem in soup.find_all("div", class_=re.compile(r"product|item|coupon")):
|
||||
try:
|
||||
item = self._parse_coupon_item(item_elem)
|
||||
if item:
|
||||
item["aisle"] = "Dairy"
|
||||
items.append(item)
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
return items
|
||||
@@ -0,0 +1,158 @@
|
||||
import logging
|
||||
from typing import Dict, Any, Optional
|
||||
from datetime import datetime
|
||||
from uuid import uuid4
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ScraperService:
|
||||
def __init__(self, db: Session):
|
||||
self.db = db
|
||||
|
||||
def run_scrape(self, source: str = "lucky_california", scrape_type: str = "weekly_ad") -> Dict[str, Any]:
|
||||
from app.scraper import LuckyCaliforniaScraper
|
||||
from app.models import ScrapeLog, GroceryItem, Ingredient
|
||||
|
||||
scrape_log = ScrapeLog(
|
||||
id=uuid4(),
|
||||
source=source,
|
||||
scrape_type=scrape_type,
|
||||
status="started",
|
||||
started_at=datetime.now()
|
||||
)
|
||||
self.db.add(scrape_log)
|
||||
self.db.commit()
|
||||
|
||||
logger.info(f"Starting {source} {scrape_type} scrape")
|
||||
|
||||
try:
|
||||
scraper = LuckyCaliforniaScraper()
|
||||
result = scraper.scrape()
|
||||
scraper.cleanup()
|
||||
|
||||
items = result.get("items", [])
|
||||
saved_count = 0
|
||||
|
||||
for item_data in items:
|
||||
saved_item = self._save_grocery_item(item_data)
|
||||
if saved_item:
|
||||
saved_count += 1
|
||||
|
||||
scrape_log.status = "success"
|
||||
scrape_log.items_scraped = saved_count
|
||||
scrape_log.completed_at = datetime.now()
|
||||
scrape_log.duration_seconds = int(
|
||||
(scrape_log.completed_at - scrape_log.started_at).total_seconds()
|
||||
)
|
||||
|
||||
self.db.commit()
|
||||
|
||||
logger.info(f"Scrape complete: {saved_count} items saved")
|
||||
|
||||
return {
|
||||
"scrape_id": str(scrape_log.id),
|
||||
"status": "success",
|
||||
"items_scraped": saved_count,
|
||||
"items_found": len(items)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Scrape failed: {e}")
|
||||
scrape_log.status = "failed"
|
||||
scrape_log.error_message = str(e)
|
||||
scrape_log.completed_at = datetime.now()
|
||||
scrape_log.duration_seconds = int(
|
||||
(scrape_log.completed_at - scrape_log.started_at).total_seconds()
|
||||
)
|
||||
self.db.commit()
|
||||
|
||||
return {
|
||||
"scrape_id": str(scrape_log.id),
|
||||
"status": "failed",
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
def _save_grocery_item(self, item_data: Dict[str, Any]) -> Optional[GroceryItem]:
|
||||
from app.models import GroceryItem, Ingredient
|
||||
|
||||
name = item_data.get("name", "").strip()
|
||||
if not name:
|
||||
return None
|
||||
|
||||
name_lower = name.lower()
|
||||
|
||||
ingredient = self.db.query(Ingredient).filter(
|
||||
Ingredient.name_lower == name_lower
|
||||
).first()
|
||||
|
||||
if not ingredient:
|
||||
ingredient = Ingredient(
|
||||
id=uuid4(),
|
||||
name=name,
|
||||
name_lower=name_lower,
|
||||
aisle=item_data.get("aisle"),
|
||||
typical_price=item_data.get("current_price")
|
||||
)
|
||||
self.db.add(ingredient)
|
||||
self.db.flush()
|
||||
|
||||
existing = self.db.query(GroceryItem).filter(
|
||||
GroceryItem.name == name,
|
||||
GroceryItem.scraped_url == item_data.get("scraped_url")
|
||||
).first()
|
||||
|
||||
if existing:
|
||||
existing.current_price = item_data.get("current_price")
|
||||
existing.is_on_sale = item_data.get("is_on_sale", True)
|
||||
existing.image_url = item_data.get("image_url")
|
||||
existing.product_url = item_data.get("product_url")
|
||||
existing.scraped_at = datetime.now()
|
||||
self.db.flush()
|
||||
return existing
|
||||
|
||||
grocery_item = GroceryItem(
|
||||
id=uuid4(),
|
||||
ingredient_id=ingredient.id,
|
||||
name=name,
|
||||
current_price=item_data.get("current_price"),
|
||||
regular_price=item_data.get("regular_price"),
|
||||
unit=item_data.get("unit"),
|
||||
aisle=item_data.get("aisle"),
|
||||
image_url=item_data.get("image_url"),
|
||||
product_url=item_data.get("product_url"),
|
||||
is_on_sale=item_data.get("is_on_sale", True),
|
||||
sale_start_date=item_data.get("sale_start_date"),
|
||||
sale_end_date=item_data.get("sale_end_date"),
|
||||
in_season=item_data.get("in_season", False),
|
||||
scraped_at=datetime.now(),
|
||||
scraped_url=item_data.get("scraped_url")
|
||||
)
|
||||
|
||||
self.db.add(grocery_item)
|
||||
self.db.commit()
|
||||
self.db.refresh(grocery_item)
|
||||
|
||||
return grocery_item
|
||||
|
||||
def get_sale_items(self, limit: int = 50) -> list:
|
||||
from app.models import GroceryItem
|
||||
|
||||
items = self.db.query(GroceryItem).filter(
|
||||
GroceryItem.is_on_sale == True
|
||||
).order_by(GroceryItem.scraped_at.desc()).limit(limit).all()
|
||||
|
||||
return [
|
||||
{
|
||||
"id": str(item.id),
|
||||
"name": item.name,
|
||||
"current_price": float(item.current_price) if item.current_price else None,
|
||||
"regular_price": float(item.regular_price) if item.regular_price else None,
|
||||
"aisle": item.aisle,
|
||||
"image_url": item.image_url,
|
||||
"product_url": item.product_url,
|
||||
"scraped_at": item.scraped_at.isoformat() if item.scraped_at else None
|
||||
}
|
||||
for item in items
|
||||
]
|
||||
+16
-11
@@ -44,6 +44,12 @@ The family has been using meal kit services (Blue Apron → EveryPlate → Hungr
|
||||
- [x] /api/shopping-list endpoints (aggregation, print)
|
||||
- [x] /api/admin endpoints (scrape trigger, logs, stats)
|
||||
|
||||
**Phase 3 Progress** (2026-05-04):
|
||||
- [x] Base scraper with rate limiting, retries, session management
|
||||
- [x] LuckyCaliforniaScraper with BeautifulSoup + Playwright
|
||||
- [x] ScraperService to save scraped items to grocery_item table
|
||||
- [x] /api/admin/scrape endpoint connected to ScraperService
|
||||
|
||||
---
|
||||
|
||||
## Architecture Summary
|
||||
@@ -132,17 +138,16 @@ User (web) ───► React UI ──► nginx ──► FastAPI ────
|
||||
| Phase | Description | Status |
|
||||
|-------|-------------|--------|
|
||||
| 1 | Infrastructure (Docker, PostgreSQL, FastAPI, React, nginx) | **Complete** |
|
||||
| 2 | Database & Models (SQLAlchemy models, Alembic migrations) | **Post-review fixes applied** |
|
||||
| 3 | API Endpoints (CRUD, meal plans, shopping list, feedback) | Not Started |
|
||||
| 4 | Lucky California Scraper (weekly ad, Playwright) | Not Started |
|
||||
| 5 | Recipe Engine (CRUD, tagging, search) | Not Started |
|
||||
| 6 | Meal Planner Engine (generation algorithm, substitutions) | Not Started |
|
||||
| 7 | SendGrid Email Integration | Not Started |
|
||||
| 8 | Web UI - Core (Dashboard, Meal Detail, Approval, Pantry) | Not Started |
|
||||
| 9 | Web UI - Feedback (Feedback Portal, Learning) | Not Started |
|
||||
| 10 | Shopping List & Print | Not Started |
|
||||
| 11 | Image Strategy (scraped + AI fallback) | Not Started |
|
||||
| 12 | Polish & Future (variety analysis, budget tracking) | Not Started |
|
||||
| 2 | Database & Models (Alembic migrations, Pydantic schemas, API endpoints) | **Complete** |
|
||||
| 3 | Lucky California Scraper (BeautifulSoup + Playwright, ScraperService) | **Complete** |
|
||||
| 4 | Recipe Engine (CRUD, tagging, search) | Not Started |
|
||||
| 5 | Meal Planner Engine (generation algorithm, substitutions) | Not Started |
|
||||
| 6 | SendGrid Email Integration | Not Started |
|
||||
| 7 | Web UI - Core (Dashboard, Meal Detail, Approval, Pantry) | Not Started |
|
||||
| 8 | Web UI - Feedback (Feedback Portal, Learning) | Not Started |
|
||||
| 9 | Shopping List & Print | Not Started |
|
||||
| 10 | Image Strategy (scraped + AI fallback) | Not Started |
|
||||
| 11 | Polish & Future (variety analysis, budget tracking) | Not Started |
|
||||
|
||||
---
|
||||
|
||||
|
||||
Reference in New Issue
Block a user