goon/app/connectors/freeomovie.py

"""freeomovie.to, movie source (WordPress "bestia" theme, NIE dooplay).

Dodany 2026-07-02 (ocena). Pełnometrażowe filmy, świeże (auto-poster, dziś), tytuły
DVD → title-trigram mirror-attach do canonical (paradisehill/TPDB movies), dokładając
playback_sources. Scope: TYLKO `/category/full-movie/` (homepage miesza scen-klipy,
które orphanowałyby jako filmy).

Struktura:
  - listing `<li class="thumi"><a href title>` → URL filmu + czysty tytuł
  - detail: `var TABS=[{label,url},...]` (hostery), `"articleSection"` (gatunki + obsada;
    gatunki PRZED "XXX Movies" → tagi), `"datePublished"` (data POSTA, NIE rok produkcji)

Świadomie NIE bierzemy:
  - release_year: datePublished to data uploadu (2026), nie rok filmu → fałszywy rok
    psułby year-scoring przy matchu do canonical (film z 2010 dostałby 2026). Lepiej None.
  - performerów/studia z articleSection: format miesza performer/alias/studio bez czystego
    delimitera → ryzyko junk-performera ("Deeveeous" studio jako performer). Mirror i tak
    doczepia się do canonical po tytule, a TPDB enrichment dokłada obsadę/studio autorytatywnie.

Playback: TABS hostery → MoviePlaybackSource per host (voe/luluvid/vidhide resolvują się
VPS-side; myvidplay = DoodStream clone, phone-side, wymaga myvidplay.com w DOOD_HOSTS).
Pomijamy streamtape (martwy malware) + mxdrop (flaky).
"""
from __future__ import annotations

import html
import json
import logging
import re
from collections.abc import Iterator
from datetime import datetime
from urllib.parse import urlparse

from app.connectors.base import (
    BaseMovieConnector,
    RawMovie,
    RawPlaybackSource,
    RawTag,
)
from app.extractors import browser_get
from app.models.source import SourceKind
from app.normalize.text import slugify

log = logging.getLogger(__name__)

_BASE = "https://www.freeomovie.to"
_LIST_ITEM_RE = re.compile(
    r'<li[^>]*class="thumi"[^>]*>\s*<a[^>]+href="(?P<url>https://www\.freeomovie\.to/[a-z0-9\-]+/)"[^>]*title="(?P<title>[^"]+)"',
    re.IGNORECASE,
)
_TABS_RE = re.compile(r"var\s+TABS\s*=\s*(\[.*?\])\s*;", re.DOTALL)
_ARTICLE_SECTION_RE = re.compile(r'"articleSection"\s*:\s*"([^"]+)"')
# Poster: <img class="... rmbd ..." src="..."> (fastpic.org itp.). Bez tego film-orphan
# (tytuł bez matchu do canonical) miał poster_url=None → pusty kafelek (report 8f8c10c0).
_POSTER_RE = re.compile(
    r'<img[^>]+class="[^"]*\brmbd\b[^"]*"[^>]+src="(https?://[^"]+)"',
    re.IGNORECASE,
)

# Hostery pomijane (martwe/flaky). player4me = JS-SPA bez znanego resolvera (28 martwych
# źródeł freeomovie:video, report 8f8c10c0).
_SKIP_HOSTS = ("streamtape", "mxdrop", "mixdrop", "streamsb", "player4me")


def _host_label(embed_url: str) -> str | None:
    host = (urlparse(embed_url).hostname or "").lower()
    if not host:
        return None
    parts = host.replace("www.", "").split(".")
    # Rejestrowalna domena (SLD), nie subdomena: video.player4me.xyz → 'player4me' (nie
    # 'video'), myvidplay.com → 'myvidplay'. Inaczej origin był śmieciowy (freeomovie:video).
    return parts[-2] if len(parts) >= 2 else parts[0]


class FreeoMovieConnector(BaseMovieConnector):
    kind = SourceKind.scraper
    name = "freeomovie"
    base_url = _BASE

    _MAX_PAGES_DELTA = 3
    _MAX_PAGES_FULL = 40

    def __init__(self, *, timeout: float = 30.0) -> None:
        self._timeout = timeout

    def close(self) -> None:
        pass

    def _fetch(self, url: str) -> str:
        if not url.startswith("http"):
            url = _BASE + url
        r = browser_get(
            url,
            headers={
                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/125.0",
                "Accept": "text/html,application/xhtml+xml",
                "Referer": _BASE + "/",
            },
            timeout=self._timeout,
            follow_redirects=True,
        )
        if r.status_code >= 400:
            raise RuntimeError(f"{r.status_code} for {url}")
        return r.text

    def fetch_movies(
        self, *, since: datetime | None = None, limit: int | None = None
    ) -> Iterator[RawMovie]:
        seen = 0
        seen_urls: set[str] = set()
        max_pages = self._MAX_PAGES_DELTA if since is not None else self._MAX_PAGES_FULL
        for page in range(1, max_pages + 1):
            path = "/category/full-movie/" if page == 1 else f"/category/full-movie/page/{page}/"
            try:
                listing = self._fetch(path)
            except Exception as e:
                log.warning("freeomovie listing page=%d failed: %s", page, e)
                return
            items = [(m.group("url"), html.unescape(m.group("title")).strip())
                     for m in _LIST_ITEM_RE.finditer(listing)]
            if not items:
                log.info("freeomovie: empty page=%d, stop", page)
                return
            for url, title in items:
                if url in seen_urls:
                    continue
                seen_urls.add(url)
                try:
                    movie = self._parse_detail(url, title)
                except Exception as e:
                    log.warning("freeomovie detail %s failed: %s", url, e)
                    continue
                if movie is None:
                    continue
                yield movie
                seen += 1
                if limit is not None and seen >= limit:
                    return

    def _parse_detail(self, url: str, title: str) -> RawMovie | None:
        detail = self._fetch(url)
        if not title:
            return None

        # Tagi: gatunki z articleSection PRZED "XXX Movies" (reszta = obsada/studio, skip).
        tags: list[RawTag] = []
        seen_tag: set[str] = set()
        sm = _ARTICLE_SECTION_RE.search(detail)
        if sm:
            for part in sm.group(1).split(","):
                name = part.strip()
                if not name or name.lower() == "xxx movies":
                    if name.lower() == "xxx movies":
                        break  # dalej idzie obsada/studio, nie tagi
                    continue
                sl = slugify(name)
                if not sl or sl in seen_tag:
                    continue
                seen_tag.add(sl)
                tags.append(RawTag(external_id=f"{self.name}:tag:{sl}", name=name, slug=sl))

        # Playback: TABS array hosterów.
        playback: list[RawPlaybackSource] = []
        seen_host: set[str] = set()
        tm = _TABS_RE.search(detail)
        if tm:
            try:
                arr = json.loads(tm.group(1))
            except (json.JSONDecodeError, ValueError):
                arr = []
            for entry in arr:
                embed = (entry.get("url") or "").strip() if isinstance(entry, dict) else ""
                if not embed.startswith("http"):
                    continue
                host = _host_label(embed)
                if not host or host in _SKIP_HOSTS or host in seen_host:
                    continue
                seen_host.add(host)
                playback.append(
                    RawPlaybackSource(
                        origin=f"{self.name}:{host}",
                        page_url=embed,
                        embed_url=embed,
                    )
                )
        if not playback:
            return None  # bez playbacku film jest bezużyteczny (nie tworzymy orphana)

        pm = _POSTER_RE.search(detail)
        poster_url = html.unescape(pm.group(1)) if pm else None

        slug = urlparse(url).path.strip("/").split("/")[-1]
        return RawMovie(
            external_id=slug,
            title=title,
            url=url,
            poster_url=poster_url,
            tags=tags,
            playback_sources=playback,
            raw={"source": "freeomovie", "url": url},
        )