new_vk_parser/src/vk_parser_app/source_adapters.py

from __future__ import annotations

import json
from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Any

import aiohttp

from .constants import PLATFORM_SITE, PLATFORM_VK


def json_object(value: Any) -> dict[str, Any]:
    if isinstance(value, dict):
        return dict(value)
    if isinstance(value, str):
        try:
            parsed = json.loads(value)
        except json.JSONDecodeError:
            return {}
        return parsed if isinstance(parsed, dict) else {}
    return {}


@dataclass
class SourceMedia:
    url: str
    media_type: str = "photo"


@dataclass
class SourceItem:
    external_id: str
    url: str
    text: str
    posted_at: datetime
    media: list[SourceMedia] = field(default_factory=list)
    raw: dict[str, Any] = field(default_factory=dict)

    @property
    def body_text(self) -> str:
        return str(self.raw.get("text") or "").strip()


def validate_source_config(platform: str, config: dict[str, Any]) -> None:
    if platform == PLATFORM_VK:
        return
    if platform != PLATFORM_SITE:
        raise ValueError("Неподдерживаемая площадка")
    if not config:
        raise ValueError("Для сайта нужен конфиг JSON")
    if config.get("format") != "rss":
        raise ValueError('Сейчас поддерживается только "format": "rss"')
    if str(config.get("access") or "auto") not in {"auto", "http", "cloudflare"}:
        raise ValueError('access должен быть "auto", "http" или "cloudflare"')
    try:
        max_items = int(config.get("max_items", 20))
    except (TypeError, ValueError) as exc:
        raise ValueError("max_items должен быть целым числом") from exc
    if not 1 <= max_items <= 100:
        raise ValueError("max_items должен быть от 1 до 100")
    follow_links = config.get("follow_links", False)
    if not isinstance(follow_links, bool):
        raise ValueError("follow_links должен быть true или false")
    if follow_links and not str(config.get("content_selector") or "").strip():
        raise ValueError("При follow_links=true нужен content_selector")
    try:
        min_text_length = int(config.get("min_text_length", 0))
    except (TypeError, ValueError) as exc:
        raise ValueError("min_text_length должен быть целым числом") from exc
    if not 0 <= min_text_length <= 100_000:
        raise ValueError("min_text_length должен быть от 0 до 100000")


def _posted_at(value: Any) -> datetime:
    try:
        parsed = datetime.fromisoformat(str(value).replace("Z", "+00:00"))
    except (TypeError, ValueError):
        return datetime.now(timezone.utc)
    if parsed.tzinfo is None:
        parsed = parsed.replace(tzinfo=timezone.utc)
    return parsed.astimezone(timezone.utc)


class SiteParserClient:
    def __init__(
        self,
        session: aiohttp.ClientSession,
        base_url: str,
        token: str,
        rucaptcha_token: str,
        timeout_sec: int,
    ) -> None:
        self.session = session
        self.base_url = base_url.rstrip("/")
        self.token = token
        self.rucaptcha_token = rucaptcha_token
        self.timeout = aiohttp.ClientTimeout(total=max(10, timeout_sec))

    async def fetch(self, source: dict) -> tuple[list[SourceItem], dict[str, Any] | None]:
        if not self.base_url or not self.token:
            raise RuntimeError("Site Parser URL или токен не настроены")
        config = json_object(source.get("settings_json"))
        validate_source_config(PLATFORM_SITE, config)
        runtime_state = json_object(source.get("runtime_state_json"))
        payload = {
            "url": source["url"],
            "config": config,
            "rucaptcha_token": self.rucaptcha_token or None,
            "browser_state": runtime_state.get("browser_state"),
            "browser_user_agent": runtime_state.get("browser_user_agent"),
        }
        try:
            async with self.session.post(
                f"{self.base_url}/v1/parse",
                json=payload,
                headers={"X-Worker-Token": self.token},
                timeout=self.timeout,
            ) as response:
                data = await response.json(content_type=None)
                if response.status >= 400:
                    raise RuntimeError(f"Site Parser HTTP {response.status}: {data.get('detail', data)}")
        except TimeoutError as exc:
            raise RuntimeError(f"Site Parser превысил таймаут {int(self.timeout.total)} сек") from exc
        except aiohttp.ClientError as exc:
            raise RuntimeError(f"Site Parser недоступен: {exc}") from exc

        items = []
        for raw in data.get("items") or []:
            title = str(raw.get("title") or "").strip()
            body = str(raw.get("text") or "").strip()
            body_starts_with_title = title and (
                body.casefold() == title.casefold()
                or body.casefold().startswith(f"{title}\n".casefold())
            )
            text = body if body_starts_with_title else "\n\n".join(part for part in (title, body) if part)
            url = str(raw.get("url") or source["url"]).strip()
            external_id = str(raw.get("external_id") or url).strip()
            if not external_id:
                continue
            media = [
                SourceMedia(str(item["url"]), str(item.get("type") or "photo"))
                for item in raw.get("media") or []
                if isinstance(item, dict) and item.get("url")
            ]
            items.append(SourceItem(external_id, url, text, _posted_at(raw.get("published_at")), media, raw))
        state = data.get("browser_state")
        return items, (
            {
                "browser_state": state,
                "browser_user_agent": str(data.get("browser_user_agent") or "") or None,
            }
            if isinstance(state, dict)
            else None
        )