oliver/rss-news
1
0
Fork 0
Code Issues 3 Pull requests Projects Releases 12 Packages Wiki Activity Actions

feat(rewrite): add batch rewrite run, AI tags for WP, and agentur contact detection

Browse source
This commit is contained in:
Oliver 2026-02-21 14:39:47 +01:00
parent da269d08f1
commit b0f995d5c9
No known key found for this signature in database
10 changed files with 374 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

27
backend/tests/test_source_extraction.py
View file

@ -26,6 +26,25 @@ SAMPLE_HTML = """
</html>
"""
SAMPLE_HTML_AGENTUR = """
<!doctype html>
<html lang="de">
<head>
<meta charset="utf-8" />
<meta property="og:title" content="Demo Meldung Agentur" />
</head>
<body>
<article>
<p>Inhalt der Meldung.</p>
<h3>Agentur</h3>
<p>Agenturname GmbH</p>
<p>presse@agentur.example</p>
<p>Original-Content von Beispiel</p>
</article>
</body>
</html>
"""
class _FakeHeaders:
@staticmethod
@ -64,6 +83,14 @@ class TestSourceExtraction(unittest.TestCase):
self.assertIn("Pressekontakt", extracted.press_contact or "")
self.assertIsNone(extracted.extraction_error)
@patch("backend.app.source_extraction.urlopen")
def test_extract_article_detects_agentur_block_as_press_contact(self, mock_urlopen) -> None:
mock_urlopen.return_value = _FakeResponse(SAMPLE_HTML_AGENTUR)
extracted = extract_article("https://www.presseportal.de/pm/155103/6210401")
self.assertIn("Agentur", extracted.press_contact or "")
self.assertIn("Agenturname", extracted.press_contact or "")
self.assertIn("presse@agentur.example", extracted.press_contact or "")
if __name__ == "__main__":
unittest.main()