"""porntrex.com — KVS engine direct stream extractor.

2026-05-22: VPS Hetzner IP znów dociera do porntrex (HTTP 200) — wcześniej blokada
trzymała `porntrexcom` na `_vps_blocked_fallback`. Patrz [[goon_porntrex_vps_unblocked]].

KVS player: detail page ma `flashvars` z `video_url` / `video_alt_url` / `video_alt_url2`
(480p / 720p / 1080p), każdy to `get_file/<srv>/<token>/<path>.mp4/` URL.

`get_file` 302 → `cdn.pcdn.cloudswitches.com/...mp4?expires=<ts>&md5=<sig>` — to
**time-bound signed URL** (nie IP-bound). Mobile ExoPlayer może pobrać get_file
(follow 302) i grać direct z CDN — zero VPS bandwidth. Stąd `mobile_direct_ok=True`.

Token w `get_file` URL bywa single-use (410 po reuse), więc NIE resolvujemy 302 na
backendzie — oddajemy get_file URL, mobile zużywa token sam przy pierwszym fetchu.
"""
from __future__ import annotations

import logging
import re

from app.extractors._fetch import fetch_tube_html
from app.extractors._models import StreamSource

log = logging.getLogger(__name__)

_BASE = "https://www.porntrex.com"

# flashvars: `video_url: 'https://.../get_file/...mp4/'` + `video_url_text: '480p'`.
# Warianty: video_url, video_alt_url, video_alt_url2, video_alt_url3...
_URL_RE = re.compile(
    r"(video(?:_alt)?_url\d*)\s*:\s*'(https?://[^']+/get_file/[^']+)'",
    re.IGNORECASE,
)
_TEXT_RE = re.compile(
    r"(video(?:_alt)?_url\d*)_text\s*:\s*'([^']*)'",
    re.IGNORECASE,
)


def _quality_rank(label: str | None) -> int:
    """`1080p` → 1080, `720p HD` → 720. Do sortowania malejąco."""
    if not label:
        return -1
    m = re.search(r"(\d{3,4})\s*p", label, re.IGNORECASE)
    return int(m.group(1)) if m else -1


def extract(page_url: str, *, timeout: float = 60.0) -> list[StreamSource] | None:
    html = fetch_tube_html(page_url, timeout=timeout)

    # Mapa <var_name> → quality label (np. video_alt_url → "720p HD").
    quality_by_var: dict[str, str] = {}
    for m in _TEXT_RE.finditer(html):
        quality_by_var[m.group(1).lower()] = m.group(2).strip()

    seen: set[str] = set()
    result: list[StreamSource] = []
    for m in _URL_RE.finditer(html):
        var_name = m.group(1).lower()
        url = m.group(2)
        if url in seen:
            continue
        seen.add(url)
        quality = quality_by_var.get(var_name)
        result.append(
            StreamSource(
                link=url,
                type="mp4",
                quality=quality or None,
                referer=_BASE + "/",
                # CDN po 302 jest time-bound (expires+md5), nie IP-bound —
                # mobile gra direct z get_file, zero VPS proxy bandwidth.
                raw={"mobile_direct_ok": True},
            )
        )

    if not result:
        log.info("porntrex: no KVS video_url in flashvars on %s", page_url)
        return None

    result.sort(key=lambda s: _quality_rank(s.quality), reverse=True)
    return result