tests/unit/test_cli.py

@@ -1,24 +1,41 @@
-import pytest
+import pytest
-
+
-from scrape_movies.presentation import cli, soup_steps
+from scrape_movies.presentation import cli, hacker_news_steps, soup_steps
-
+
-
+
-def test_main_when_soup_step_is_given_prints_output(
+def test_main_when_soup_step_is_given_prints_output(
-    capsys: pytest.CaptureFixture[str],
+    capsys: pytest.CaptureFixture[str],
-) -> None:
+) -> None:
-    for step in soup_steps.STEPS:
+    for step in soup_steps.STEPS:
-        assert cli.main(["soup", step]) == 0
+        assert cli.main(["soup", step]) == 0
-        assert capsys.readouterr().out.strip(), step
+        assert capsys.readouterr().out.strip(), step
-
+
-
+
-def test_main_when_no_command_prints_help(
+def test_main_when_no_command_prints_help(
-    capsys: pytest.CaptureFixture[str],
+    capsys: pytest.CaptureFixture[str],
-) -> None:
+) -> None:
-    assert cli.main([]) == 0
+    assert cli.main([]) == 0
-    assert "usage:" in capsys.readouterr().out
+    assert "usage:" in capsys.readouterr().out
-
+
-
+
-def test_render_step_when_title_returns_page_title() -> None:
+def test_render_step_when_title_returns_page_title() -> None:
-    assert soup_steps.render_step("title") == (
+    assert soup_steps.render_step("title") == (
-        "soup.title.string -> Angela's Personal Site"
+        "soup.title.string -> Angela's Personal Site"
-    )
+    )
+
+
+def test_main_when_hacker_news_top_from_fixture_prints_top_story(
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    assert cli.main(["hacker-news", "top", "--source", "fixture"]) == 0
+    out = capsys.readouterr().out
+    assert "Mozilla lays off 250 employees" in out
+    assert "1312 points" in out
+
+
+def test_main_when_every_hacker_news_step_runs_from_fixture_prints_output(
+    capsys: pytest.CaptureFixture[str],
+) -> None:
+    for step in hacker_news_steps.STEPS:
+        assert cli.main(["hacker-news", step, "--source", "fixture"]) == 0
+        assert capsys.readouterr().out.strip(), step

tests/unit/test_hacker_news.py

@@ -0,0 +1,59 @@
+from scrape_movies.constants import HACKER_NEWS_FIXTURE_PATH
+from scrape_movies.domain.story import Story
+from scrape_movies.infrastructure import hacker_news
+from scrape_movies.infrastructure.soup_basics import load_html
+
+PAGE = """
+<table><tr class="athing" id="1"><td><span class="titleline">
+<a href="https://example.com/one">One</a></span></td></tr>
+<tr><td><span class="score">12 points</span></td></tr>
+<tr class="athing" id="2"><td><span class="titleline">
+<a href="https://example.com/job">A job ad</a></span></td></tr>
+<tr><td>no score here</td></tr></table>
+"""
+
+
+def _fixture() -> str:
+    return load_html(HACKER_NEWS_FIXTURE_PATH)
+
+
+def test_parse_stories_when_page_has_score_reads_integer() -> None:
+    assert hacker_news.parse_stories(PAGE)[0] == Story(
+        "One", "https://example.com/one", 12
+    )
+
+
+def test_parse_stories_when_story_has_no_score_uses_zero() -> None:
+    assert hacker_news.parse_stories(PAGE)[1].upvotes == 0
+
+
+def test_parse_stories_when_page_has_no_stories_returns_empty() -> None:
+    assert hacker_news.parse_stories("<p>nothing</p>") == []
+
+
+def test_parse_stories_when_fixture_returns_thirty_stories() -> None:
+    assert len(hacker_news.parse_stories(_fixture())) == 30
+
+
+def test_get_titles_when_fixture_starts_with_first_headline() -> None:
+    assert hacker_news.get_titles(_fixture())[0] == "Joan Feynman 1927-2020"
+
+
+def test_get_links_when_fixture_returns_one_address_per_story() -> None:
+    links = hacker_news.get_links(_fixture())
+    assert len(links) == 30
+    assert links[0].startswith("https://www.aps.org/")
+
+
+def test_get_upvotes_when_fixture_returns_integers() -> None:
+    upvotes = hacker_news.get_upvotes(_fixture())
+    assert upvotes[:2] == [38, 205]
+    assert all(isinstance(points, int) for points in upvotes)
+
+
+def test_first_story_markup_when_page_has_story_shows_title_row() -> None:
+    assert 'class="titleline"' in hacker_news.first_story_markup(PAGE)
+
+
+def test_first_story_markup_when_page_has_no_story_returns_empty() -> None:
+    assert hacker_news.first_story_markup("<p>x</p>") == ""

tests/unit/test_http_client.py

@@ -0,0 +1,59 @@
+from typing import Any
+
+import pytest
+import requests
+
+from scrape_movies.constants import REQUEST_TIMEOUT_SECONDS, USER_AGENT
+from scrape_movies.domain.errors import FetchError
+from scrape_movies.infrastructure import http_client
+
+
+class _Response:
+    def __init__(self, text: str, error: Exception | None = None) -> None:
+        self.text = text
+        self._error = error
+
+    def raise_for_status(self) -> None:
+        if self._error is not None:
+            raise self._error
+
+
+def test_fetch_html_when_request_succeeds_sends_user_agent_and_timeout(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    calls: list[dict[str, Any]] = []
+
+    def fake_get(url: str, **kwargs: Any) -> _Response:
+        calls.append({"url": url, **kwargs})
+        return _Response("<html></html>")
+
+    monkeypatch.setattr(requests, "get", fake_get)
+    assert http_client.fetch_html("http://example.test") == "<html></html>"
+    assert calls == [
+        {
+            "url": "http://example.test",
+            "headers": {"User-Agent": USER_AGENT},
+            "timeout": REQUEST_TIMEOUT_SECONDS,
+        }
+    ]
+
+
+def test_fetch_html_when_server_errors_raises_fetch_error(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    error = requests.HTTPError("500")
+    monkeypatch.setattr(requests, "get", lambda *a, **k: _Response("", error))
+    with pytest.raises(FetchError) as caught:
+        http_client.fetch_html("http://example.test")
+    assert caught.value.__cause__ is error
+
+
+def test_fetch_html_when_connection_fails_raises_fetch_error(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    def fail(*args: Any, **kwargs: Any) -> _Response:
+        raise requests.ConnectionError("down")
+
+    monkeypatch.setattr(requests, "get", fail)
+    with pytest.raises(FetchError):
+        http_client.fetch_html("http://example.test")

tests/unit/test_story.py

@@ -0,0 +1,15 @@
+from scrape_movies.domain.story import Story, top_story
+
+
+def test_top_story_when_scores_differ_returns_highest() -> None:
+    stories = [Story("a", "/a", 5), Story("b", "/b", 50), Story("c", "/c", 7)]
+    assert top_story(stories) == Story("b", "/b", 50)
+
+
+def test_top_story_when_scores_tie_returns_first() -> None:
+    stories = [Story("a", "/a", 9), Story("b", "/b", 9)]
+    assert top_story(stories) == Story("a", "/a", 9)
+
+
+def test_top_story_when_no_stories_returns_none() -> None:
+    assert top_story([]) is None

tests/unit/test_use_cases.py

@@ -0,0 +1,24 @@
+from scrape_movies.application import use_cases
+from scrape_movies.domain.story import Story
+
+
+def _fetch(url: str) -> str:
+    return f"html of {url}"
+
+
+def _parse(html: str) -> list[Story]:
+    return [Story(html, "/x", 3), Story("best", "/y", 99)]
+
+
+def test_list_stories_when_called_passes_page_through_parser() -> None:
+    stories = use_cases.list_stories(_fetch, _parse, "http://x")
+    assert stories[0].title == "html of http://x"
+
+
+def test_find_top_story_when_stories_exist_returns_highest() -> None:
+    top = use_cases.find_top_story(_fetch, _parse, "http://x")
+    assert top == Story("best", "/y", 99)
+
+
+def test_find_top_story_when_page_is_empty_returns_none() -> None:
+    assert use_cases.find_top_story(_fetch, lambda html: [], "http://x") is None