job-research/tests/apec/test_normalize.py
2026-06-01 13:30:33 +02:00

35 lines
1.1 KiB
Python

from job_research.apec.normalize import normalize_apec_listing
def test_normalize_apec_listing_extracts_minimal_shape() -> None:
html = """
<html>
<body>
<h1><span>Data</span> <strong>Engineer</strong></h1>
<div class="company"><span>Example</span> <em>Corp</em></div>
<div class="location">Paris</div>
<div class="contract">CDI</div>
<div class="description">Build pipelines</div>
</body>
</html>
"""
listing = normalize_apec_listing(
url="https://example.test/job/123",
html=html,
fetched_at="2026-06-01T10:00:00Z",
source_job_id="job-123",
published_at="2026-05-31",
)
assert listing.source == "apec"
assert listing.source_job_id == "job-123"
assert listing.url == "https://example.test/job/123"
assert listing.title == "Data Engineer"
assert listing.company == "Example Corp"
assert listing.location == "Paris"
assert listing.contract_type == "CDI"
assert listing.description_text == "Build pipelines"
assert listing.published_at == "2026-05-31"
assert listing.fetched_at == "2026-06-01T10:00:00Z"