munch-ease-backend/products/__init__.py

import json
from typing import List, Optional, Tuple

from products import coles, woolworths
from products.models import Product
from products.repository import (
    add_tag,
    find_product_by_id as find_product_by_id,
    find_product_by_key,
    find_product_by_tag as find_product_by_tag,
    get_tags,
    insert_product,
)

SCRAPERS = {"woolworths": woolworths, "coles": coles}


def _get_shop_key(link: str) -> Tuple[Optional[str], Optional[str]]:  # (shop_code, product_id)
    for shop_code, shop_scraper in SCRAPERS.items():
        product_id = shop_scraper.get_product_id(link)
        if product_id:
            return shop_code, product_id
    return None, None


async def add_missing_tags(conn, product: Product, tags: List[str]):
    existing_tags = {tag async for tag in get_tags(conn, product)}
    remaining_tags = set(tags) - existing_tags
    if not remaining_tags:
        return False

    for tag in remaining_tags:
        await add_tag(conn, product, tag)

    return product


async def get_or_create(conn, url: str, tags: List[str]) -> Optional[Product]:
    shop_code, product_id = _get_shop_key(url)
    if not shop_code or not product_id:
        return None

    existing = await find_product_by_key(conn, shop_code, product_id)
    if existing:
        await add_missing_tags(conn, existing, tags)
        return existing

    scraper = SCRAPERS[shop_code]
    product_data, raw_response = await scraper.scrape(product_id)
    product = Product(id=-1, shop_code=shop_code, product_id=product_id, link=url, **product_data)

    await insert_product(conn, product, raw_response)
    await add_missing_tags(conn, product, tags)

    return product


def _dump_json_data_to_log(data: dict, product_id: str) -> str:
    import os
    import re

    dir = "./data/dump"
    if not os.path.exists(dir):
        os.makedirs(dir)

    prefix = f"product_{product_id}"
    suffix = ".json"
    file_ids = [
        int(re.findall(r"\d+", f)[0])
        for f in os.listdir(dir)
        if re.match(prefix + r"\d+" + suffix, f)
    ]
    id = max(file_ids) + 1 if file_ids else 0
    filename = f"{prefix}{id}{suffix}"
    full_path = os.path.join(dir, filename)
    with open(full_path, "w") as f:
        json.dump(data, f, indent=4)
    return full_path