docs: apply fleet-template (16-artifact scaffold)

Adds missing standard artifacts: - README.md (if missing) - AGENTS.md (AI agent contract) - PLAN.md (current sprint) - STATUS.md (where we are) - DEVELOPMENT.md (dev workflow) - DEPLOYMENT.md (deploy procedure) - TESTING.md (test strategy) - DECISIONS.md (ADR index + templates) - .github/CODEOWNERS - .github/workflows/ci.yml Preserves all existing artifacts. Refs: RugMunchMedia/fleet-template
2026-07-02 02:07:13 +07:00 · 2026-07-02 02:07:13 +07:00 · 47ba268131
commit 47ba268131
310 changed files with 38429 additions and 0 deletions
--- a/tests/test_scraper.py
+++ b/tests/test_scraper.py
@ -0,0 +1,60 @@
+import pytest
+
+from scraper import PryScraper
+
+
+@pytest.mark.asyncio
+async def test_scraper_invalid_url() -> None:
+    s = PryScraper()
+    result = await s._scrape_attempt("not-a-url", {}, 0)
+    assert result["status"] == "error"
+
+
+def test_scraper_quality_score_high() -> None:
+    s = PryScraper()
+    content = "This is a test article. " * 50
+    score = s._quality_score(content)
+    assert score >= 20
+
+
+def test_scraper_quality_score_empty() -> None:
+    s = PryScraper()
+    score = s._quality_score("")
+    assert score == 0
+
+
+def test_scraper_quality_score_low() -> None:
+    s = PryScraper()
+    score = s._quality_score("short")
+    assert score < 20
+
+
+def test_scraper_rotate_ua_changes() -> None:
+    s = PryScraper()
+    ua1 = s._rotate_ua()
+    ua2 = s._rotate_ua()
+    assert ua1 != ua2 or s._ua_index != 0
+
+
+def test_scraper_build_headers_shape() -> None:
+    s = PryScraper()
+    headers = s._build_headers("https://example.com")
+    assert "User-Agent" in headers
+    assert "Accept" in headers
+    assert "Accept-Language" in headers
+    assert headers["User-Agent"].startswith("Mozilla")
+
+
+def test_scraper_extract_title() -> None:
+    s = PryScraper()
+    html = "<html><head><title>Test Title</title></head><body><p>Hello</p></body></html>"
+    result = s._extract(html, "https://example.com", {})
+    assert result["title"] == "Test Title"
+
+
+def test_scraper_extract_content_via_markdownify() -> None:
+    s = PryScraper()
+    html = "<html><body><p>Simple paragraph text here.</p></body></html>"
+    result = s._extract(html, "https://example.com", {})
+    assert "content" in result
+    assert len(result["content"]) > 0