"""News spider/pipeline: skip audio, use pubDate, don't log dupes as errors."""

from __future__ import annotations

import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
_SCRAPER = ROOT / "news/scraper"
if str(_SCRAPER) not in sys.path:
    sys.path.insert(0, str(_SCRAPER))


def test_is_audio_enclosure():
    from newsScraper.feed_util import is_audio_url

    assert is_audio_url("https://cdn.example/podcast.mp3") is True
    assert is_audio_url("https://cdn.example/show.m4a?x=1") is True
    assert is_audio_url("https://www.example.com/world/story") is False


def test_article_timestamp_prefers_pubdate():
    from newsScraper.feed_util import article_timestamp

    ts = article_timestamp("Tue, 01 Apr 2025 12:00:00 GMT")
    assert ts.tzinfo is not None
    assert ts.year == 2025
    assert ts.month == 4
    assert ts.day == 1


def test_pipeline_does_not_wrap_dropitem_as_error():
    src = (ROOT / "news/scraper/newsScraper/pipelines.py").read_text()
    assert "except DropItem" in src
    assert "seen_urls.add" in src or "self.seen_urls.add" in src


def test_spider_skips_audio_before_request():
    src = (ROOT / "news/scraper/newsScraper/spiders/news_spider.py").read_text()
    assert "is_audio_url" in src
    assert "article_timestamp" in src
    assert "datetime.datetime.now()" not in src