# ==============================================================================
# Author: Simon-Pierre Boucher <contact@spboucher.ai>
# File:   src/net.py
# Desc:   Fetch commun des acteurs KA — curl_cffi (empreinte TLS Chrome) +
#         proxy Apify (résidentiel par défaut), throttling poli, retries à
#         backoff EXPONENTIEL + jitter sur 403/407/408/425/429/500/502/503/504
#         avec rotation de session proxy (nouvelle IP) à chaque tentative.
#         GET et POST partagent le même moteur de retries.
# ==============================================================================
from __future__ import annotations

import asyncio
import random
import re

from apify import Actor
from curl_cffi import requests as cffi

UA = ("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 "
      "(KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36")

# statuts transitoires : mur anti-bot, proxy, rate-limit, erreurs serveur
RETRY_STATUSES = frozenset({403, 407, 408, 425, 429, 500, 502, 503, 504})


def _backoff(attempt: int) -> float:
    """Backoff exponentiel plafonné + jitter (anti-troupeau)."""
    return min(1.2 * (2 ** attempt), 12.0) + random.uniform(0.0, 0.8)


class Fetcher:
    """HTTP poli : proxy Apify + impersonation Chrome + retries robustes."""

    def __init__(self, proxy_configuration, delay: float = 1.0) -> None:
        self.proxy_configuration = proxy_configuration
        self.delay = delay
        self._lock = asyncio.Lock()
        self._last = 0.0

    async def _throttle(self) -> None:
        async with self._lock:
            now = asyncio.get_event_loop().time()
            wait = self.delay - (now - self._last)
            if wait > 0:
                await asyncio.sleep(wait)
            self._last = asyncio.get_event_loop().time()

    async def request(self, method: str, url: str,
                      headers: dict | None = None, data=None,
                      retries: int = 4, session_id: str | None = None,
                      impersonate: str | None = "chrome"):
        hdrs = {"User-Agent": UA,
                "Accept-Language": "fr-CA,fr;q=0.9,en;q=0.8"}
        if headers:
            hdrs.update(headers)
        last_exc: Exception | None = None
        for attempt in range(retries):
            await self._throttle()
            proxy = None
            if self.proxy_configuration:
                sid = session_id or f"s{random.randint(1, 999_999)}"
                sid = re.sub(r"[^\w._~]", "", sid)[:40] or "s"
                # nouvelle session proxy (nouvelle IP) à chaque tentative
                proxy = await self.proxy_configuration.new_url(
                    session_id=f"{sid}r{attempt}")
            try:
                resp = await asyncio.to_thread(
                    cffi.request, method, url, headers=hdrs, data=data,
                    impersonate=impersonate, timeout=60, allow_redirects=True,
                    proxies={"http": proxy, "https": proxy} if proxy else None)
                if resp.status_code in RETRY_STATUSES \
                        and attempt < retries - 1:
                    Actor.log.warning(
                        f"HTTP {resp.status_code} {url} — retry {attempt + 1}")
                    await asyncio.sleep(_backoff(attempt))
                    continue
                return resp
            except Exception as exc:  # réseau/proxy : on retente
                last_exc = exc
                await asyncio.sleep(_backoff(attempt))
        if last_exc:
            raise last_exc
        raise RuntimeError(f"échec après {retries} tentatives : {url}")

    async def get(self, url: str, headers: dict | None = None,
                  retries: int = 4, session_id: str | None = None,
                  impersonate: str | None = "chrome"):
        return await self.request("GET", url, headers=headers,
                                  retries=retries, session_id=session_id,
                                  impersonate=impersonate)

    async def post(self, url: str, data=None, headers: dict | None = None,
                   retries: int = 4, session_id: str | None = None,
                   impersonate: str | None = "chrome"):
        return await self.request("POST", url, data=data, headers=headers,
                                  retries=retries, session_id=session_id,
                                  impersonate=impersonate)