republisher/tests/test_file_feeds.py

from pathlib import Path

from scrapy.http import TextResponse
from scrapy.settings import Settings

from repub import entrypoint as entrypoint_module
from repub.spiders.rss_spider import RssFeedSpider
from repub.utils import FileType, local_audio_path, local_image_path


def test_entrypoint_supports_file_feed_urls(tmp_path: Path, monkeypatch) -> None:
    fixture_path = (
        Path(__file__).resolve().parents[1] / "demo" / "fixtures" / "local-feed.rss"
    ).resolve()
    config_path = tmp_path / "repub.toml"
    config_path.write_text(
        f"""
out_dir = "out"

[[feeds]]
name = "Local Demo"
slug = "local-file"
url = "{fixture_path.as_uri()}"

[scrapy.settings]
LOG_LEVEL = "ERROR"
DOWNLOAD_TIMEOUT = 5
""".strip()
        + "\n",
        encoding="utf-8",
    )

    monkeypatch.setattr(entrypoint_module, "check_runtime", lambda *_: True)

    exit_code = entrypoint_module.entrypoint(["--config", str(config_path)])

    output_path = tmp_path / "out" / "feeds" / "local-file" / "feed.rss"
    assert exit_code == 0
    assert output_path.exists()
    output = output_path.read_text(encoding="utf-8")
    assert "<title>Local Demo Feed</title>" in output
    assert "<title>Local Demo Entry</title>" in output


def test_rss_spider_rewrites_public_asset_urls_as_relative_paths() -> None:
    spider = RssFeedSpider(feed_name="demo", url="https://example.com/feed.rss")
    spider.settings = Settings(
        values={
            "REPUBLISHER_IMAGE_DIR": "images",
            "REPUBLISHER_FILE_DIR": "files",
            "REPUBLISHER_AUDIO_DIR": "audio",
            "REPUBLISHER_VIDEO_DIR": "video",
        }
    )

    assert (
        spider.rewrite_image_url("https://example.com/media/photo.jpg")
        == f"images/{local_image_path('https://example.com/media/photo.jpg')}"
    )
    assert (
        spider.rewrite_file_url(
            FileType.AUDIO,
            "https://example.com/media/podcast.mp3",
        )
        == f"audio/{local_audio_path('https://example.com/media/podcast.mp3')}"
    )


def test_rss_spider_keeps_items_with_empty_content_encoded() -> None:
    feed_text = """<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Empty Content Feed</title>
    <link>https://example.com</link>
    <description>Feed with empty HTML content blocks.</description>
    <item>
      <title>Entry With Empty Content</title>
      <link>https://example.com/entry</link>
      <description>Summary text still exists.</description>
      <guid isPermaLink="false">entry-1</guid>
      <pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate>
      <content:encoded></content:encoded>
    </item>
  </channel>
</rss>
"""
    spider = RssFeedSpider(feed_name="demo", url="https://example.com/feed.rss")
    spider.settings = Settings(
        values={
            "REPUBLISHER_IMAGE_DIR": "images",
            "REPUBLISHER_FILE_DIR": "files",
            "REPUBLISHER_AUDIO_DIR": "audio",
            "REPUBLISHER_VIDEO_DIR": "video",
        }
    )
    response = TextResponse(
        url="https://example.com/feed.rss",
        body=feed_text.encode("utf-8"),
        encoding="utf-8",
    )

    parse_result = spider._parse(response)

    assert parse_result is not None
    items = list(parse_result)

    assert len(items) == 2
    assert items[0].el.findtext("title") == "Empty Content Feed"
    assert items[1].el.findtext("title") == "Entry With Empty Content"