"""
Fetches crypto news from NewsData.io free tier (200 requests/day).
Docs: https://newsdata.io/documentation
"""

import os
import logging
import requests
from datetime import datetime, timezone

logger = logging.getLogger(__name__)

NEWSDATA_BASE = "https://newsdata.io/api/1/news"

CRYPTO_QUERIES = [
    "bitcoin",
    "ethereum crypto",
    "crypto regulation",
    "DeFi blockchain",
    "crypto ETF",
]


class NewsDataCollector:
    def __init__(self):
        self.api_key = os.getenv("NEWSDATA_API_KEY", "")

    def _is_available(self) -> bool:
        return bool(self.api_key)

    def fetch_all(self) -> list[dict]:
        if not self._is_available():
            logger.info("[NewsData] No API key — skipping")
            return []

        articles: list[dict] = []
        seen_urls: set[str] = set()

        for query in CRYPTO_QUERIES:
            try:
                fetched = self._fetch(query)
                for a in fetched:
                    if a["url"] not in seen_urls:
                        seen_urls.add(a["url"])
                        articles.append(a)
                logger.debug(f"[NewsData] '{query}': {len(fetched)} articles")
            except Exception as exc:
                logger.warning(f"[NewsData] Failed for '{query}': {exc}")

        return articles

    def _fetch(self, query: str) -> list[dict]:
        params = {
            "apikey":   self.api_key,
            "q":        query,
            "language": "en",
            "category": "business,technology",
        }
        resp = requests.get(NEWSDATA_BASE, params=params, timeout=15)
        resp.raise_for_status()
        data = resp.json()

        results = []
        for item in data.get("results", []):
            pub_raw = item.get("pubDate", "")
            try:
                published = datetime.strptime(pub_raw, "%Y-%m-%d %H:%M:%S").replace(
                    tzinfo=timezone.utc
                ).isoformat()
            except Exception:
                published = datetime.now(timezone.utc).isoformat()

            title   = item.get("title") or ""
            content = item.get("content") or item.get("description") or ""
            results.append({
                "source":    f"NewsData/{item.get('source_id', 'unknown')}",
                "title":     title,
                "summary":   content[:500],
                "url":       item.get("link") or item.get("source_url", ""),
                "published": published,
                "type":      "news",
                "score":     0,
                "text":      f"{title}. {content}".strip(),
            })

        return results