# Author: Simon-Pierre Boucher
# Contact: contact@spboucher.ai
"""Client REST Scrapfly (https://scrapfly.io) — backend de scrape alternatif.

Atouts : rendu JavaScript, contournement anti-bot (ASP), proxies. Utile quand
Firecrawl échoue ou renvoie une page vide (SPA, protection anti-scraping).
"""

from __future__ import annotations

import time
from typing import Any, Optional

import requests

from .util import RateLimiter


class ScrapflyClient:
    def __init__(self, api_key: str, base_url: str = "https://api.scrapfly.io", delay: float = 1.5,
                 render_js: bool = False):
        self.api_key = api_key
        self.base = base_url.rstrip("/")
        self.render_js = render_js
        self.session = requests.Session()
        self.limiter = RateLimiter(delay)

    def scrape(self, url: str, render_js: Optional[bool] = None, retries: int = 2) -> dict[str, Any]:
        params = {
            "key": self.api_key,
            "url": url,
            "format": "markdown",
            "asp": "true",  # Anti Scraping Protection bypass
            "render_js": "true" if (self.render_js if render_js is None else render_js) else "false",
        }
        last_err: Optional[Exception] = None
        for attempt in range(retries):
            self.limiter.wait()
            try:
                r = self.session.get(f"{self.base}/scrape", params=params, timeout=70)
                if r.status_code == 429:
                    time.sleep(1.5 * (attempt + 1))
                    continue
                r.raise_for_status()
                result = (r.json() or {}).get("result", {}) or {}
                content = result.get("content", "") or ""
                meta = {
                    "title": (result.get("metadata") or {}).get("title", "")
                    if isinstance(result.get("metadata"), dict)
                    else "",
                    "status_code": result.get("status_code"),
                    "url": result.get("url", url),
                }
                return {"markdown": content, "metadata": meta, "links": [], "backend": "scrapfly"}
            except Exception as e:  # noqa: BLE001
                last_err = e
                time.sleep(1.5 * (attempt + 1))
        raise RuntimeError(f"Scrapfly scrape a échoué: {last_err}")