# Author: Simon-Pierre Boucher
# Contact: contact@spboucher.ai
"""Client REST Firecrawl : search, map, scrape.

Le respect du robots.txt et le débit sont gérés en amont (voir src/robots.py et
src/scraper.py). Ce client reste une couche transport minimale.
"""

from __future__ import annotations

import time
from typing import Any, Optional

import requests

from .util import RateLimiter


class FirecrawlClient:
    # ka4 : fail-fast pour ne pas bloquer le crawl concurrent
    def __init__(self, api_key: str, base_url: str = "https://api.firecrawl.dev", delay: float = 1.5,
                 timeout: int = 45, retries: int = 2):
        self.base = base_url.rstrip("/")
        self.session = requests.Session()
        self.session.headers.update(
            {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
        )
        self.limiter = RateLimiter(delay)
        self.timeout = timeout
        self.retries = retries

    def _post(self, path: str, payload: dict[str, Any], retries: Optional[int] = None) -> dict[str, Any]:
        url = f"{self.base}{path}"
        last_err: Optional[Exception] = None
        for attempt in range(retries or self.retries):
            self.limiter.wait()
            try:
                r = self.session.post(url, json=payload, timeout=self.timeout)
                if r.status_code == 429:
                    time.sleep(1.5 * (attempt + 1))
                    continue
                r.raise_for_status()
                return r.json()
            except Exception as e:  # noqa: BLE001
                last_err = e
                time.sleep(1.0 * (attempt + 1))
        raise RuntimeError(f"Firecrawl {path} a échoué: {last_err}")

    def search(self, query: str, limit: int = 10) -> list[dict[str, Any]]:
        data = self._post("/v1/search", {"query": query, "limit": limit})
        return data.get("data", []) or []

    def map(self, url: str, search: Optional[str] = None, limit: int = 200) -> list[str]:
        payload: dict[str, Any] = {"url": url, "limit": limit}
        if search:
            payload["search"] = search
        data = self._post("/v1/map", payload)
        links = data.get("links", []) or []
        return [l["url"] if isinstance(l, dict) else l for l in links]

    def scrape(self, url: str, formats: Optional[list[str]] = None) -> dict[str, Any]:
        # demande aussi les liens -> alimente la frontière agressive
        data = self._post("/v1/scrape", {"url": url, "formats": formats or ["markdown", "links"]})
        d = data.get("data", {}) or {}
        return {
            "markdown": d.get("markdown", "") or "",
            "metadata": d.get("metadata", {}) or {},
            "links": d.get("links", []) or [],
            "backend": "firecrawl",
        }