Dies ist der vollstaendige Inhalt des Artikels.
Weitere relevante Informationen fuer die Meldung.
Pressekontakt
Musterfirma GmbH, Kontakt: presse@example.org
"""
class _FakeHeaders:
@staticmethod
def get_content_charset():
return "utf-8"
class _FakeResponse:
headers = _FakeHeaders()
def __init__(self, body: str):
self._body = body.encode("utf-8")
def read(self):
return self._body
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
return False
class TestSourceExtraction(unittest.TestCase):
@patch("backend.app.source_extraction.urlopen")
def test_extract_article_parses_author_images_and_press_contact(self, mock_urlopen) -> None:
mock_urlopen.return_value = _FakeResponse(SAMPLE_HTML)
extracted = extract_article("https://www.presseportal.de/pm/118273/6158137")
self.assertEqual(extracted.title, "Demo Meldung von Presseportal")
self.assertEqual(extracted.author, "Max Mustermann")
self.assertEqual(extracted.canonical_url, "https://www.presseportal.de/pm/118273/6158137")
self.assertIn("vollstaendige Inhalt", extracted.content_text or "")
self.assertIn("Kurzbeschreibung", extracted.summary or "")
self.assertIn("https://www.presseportal.de/images/demo.jpg", extracted.images)
self.assertIn("Pressekontakt", extracted.press_contact or "")
self.assertIsNone(extracted.extraction_error)
if __name__ == "__main__":
unittest.main()