rates/backend/services/direct_profiles/eviivo.py

import re
from datetime import date, timedelta
from .base import BaseProfile

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
                  "(KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
}

# Matches any opening tag that contains data-room-type-id="..."
_TAG_RE = re.compile(r'<[^>]*data-room-type-id="[^"]*"[^>]*>', re.DOTALL)

# Individual data-* attribute extractor
_ATTR_RE = re.compile(r'data-([\w-]+)="([^"]*)"')


def _slugify(text: str) -> str:
    """Lowercase and replace whitespace runs with underscores."""
    return re.sub(r'\s+', '_', text.strip().lower())


def _extract_data_attrs(tag: str) -> dict:
    """Return all data-* attributes from an HTML opening tag as a flat dict."""
    return {m.group(1): m.group(2) for m in _ATTR_RE.finditer(tag)}


class EviivoProfile(BaseProfile):
    name = "eviivo"
    label = "Eviivo"
    required_params = [
        {
            "key": "property_slug",
            "label": "Property Slug",
            "help": "Path segment after via.eviivo.com/, e.g. StagLdgeGL54",
        },
    ]

    @classmethod
    def detect(cls, url: str) -> dict | None:
        # Matches: https://via.eviivo.com/StagLdgeGL54  (with optional path/query)
        m = re.search(r'via\.eviivo\.com/([A-Za-z0-9_-]+)', url)
        if m:
            return {"property_slug": m.group(1)}
        return None

    async def fetch_category_names(self, client, params: dict) -> tuple[dict, dict]:
        slug = params["property_slug"]
        try:
            r = await client.get(f"https://via.eviivo.com/{slug}", headers=HEADERS, timeout=20)
        except Exception:
            return {}, {}
        if r.status_code != 200:
            return {}, {}
        room_names: dict[str, str] = {}
        rate_names: dict[str, str] = {}
        for tag in _TAG_RE.finditer(r.text):
            attrs = _extract_data_attrs(tag.group(0))
            room_id = attrs.get("room-type-id", "").strip()
            if not room_id:
                continue
            room_name = attrs.get("item-name", "").strip()
            rate_plan = attrs.get("rate-plan-name", "").strip()
            rate_id = f"{room_id}_{_slugify(rate_plan) if rate_plan else 'standard'}"
            if room_name:
                room_names[room_id] = room_name
            if rate_plan:
                rate_names[rate_id] = rate_plan
        return room_names, rate_names

    async def fetch_arrival_dates(self, client, params: dict) -> list[str]:
        """Return the next 90 days as ISO date strings starting from tomorrow.

        Eviivo has no dedicated calendar endpoint; availability is determined
        by whether rooms appear in the fetch_night_rates response.
        """
        tomorrow = date.today() + timedelta(days=1)
        return [
            (tomorrow + timedelta(days=i)).isoformat()
            for i in range(90)
        ]

    async def fetch_night_rates(self, client, params: dict, arrival: str, nights: int = 1) -> list[dict]:
        """Scrape Eviivo room rates for a given arrival date and stay length."""
        slug = params["property_slug"]
        arrival_date = date.fromisoformat(arrival)
        departure_date = arrival_date + timedelta(days=nights)

        url = f"https://via.eviivo.com/{slug}"
        query = {
            "startdate": arrival,
            "enddate": departure_date.isoformat(),
            "adults1": 2,
            "children1": 0,
        }

        try:
            r = await client.get(url, params=query, headers=HEADERS, timeout=20)
        except Exception:
            return []

        if r.status_code != 200:
            return []

        html = r.text
        results = []

        for tag in _TAG_RE.finditer(html):
            attrs = _extract_data_attrs(tag.group(0))

            room_type_id = attrs.get("room-type-id", "").strip()
            if not room_type_id:
                continue

            rate_plan_name = attrs.get("rate-plan-name", "").strip()
            rate_slug = _slugify(rate_plan_name) if rate_plan_name else "standard"
            rate_id = f"{room_type_id}_{rate_slug}"

            price_str = attrs.get("price", "").strip()
            try:
                total_price = float(price_str)
            except (ValueError, TypeError):
                continue

            per_night = round(total_price / nights, 2) if nights > 0 else total_price
            currency = attrs.get("currency-code", "GBP").strip() or "GBP"

            prices = [
                {"amountBeforeTax": per_night, "amountAfterTax": per_night}
                for _ in range(nights)
            ]

            results.append({
                "roomId": room_type_id,
                "rateId": rate_id,
                "availability": 1,
                "prices": prices,
                "currencyCode": currency,
            })

        return results