{ "sha": "228aef5a95a2c480cda8ce067071be537e398c30", "message": "加入 Aerospace Global News 資料來源\n\n新增主動抓取來源、原站新聞解析器與回歸測試。", "author": { "login": "nnneeeooo-nnneeeooo", "name": "", "email": "" }, "committer": { "login": "web-flow", "name": "", "email": "" }, "created_at": "2026-07-29T16:46:25Z", "files": [ { "filename": "pipeline/common.py", "previous_filename": "", "status": "modified", "additions": 12, "deletions": 0, "changes": 12 }, { "filename": "pipeline/fetch.py", "previous_filename": "", "status": "modified", "additions": 54, "deletions": 0, "changes": 54 }, { "filename": "tests/test_aerospace_global_news.py", "previous_filename": "", "status": "added", "additions": 96, "deletions": 0, "changes": 96 } ], "diff": "@@ -243,6 +243,18 @@ def group_has_material(group: dict) -> bool:\\n \"en\": \"Global incident tracking\",\\n },\\n },\\n+ \"aerospaceglobalnews\": {\\n+ \"name\": \"Aerospace Global News\",\\n+ \"kind\": \"media\",\\n+ \"fmt\": \"HTML\",\\n+ \"url\": \"https://aerospaceglobalnews.com/\",\\n+ \"endpoint\": \"https://aerospaceglobalnews.com/latest-news/\",\\n+ \"type\": \"html\",\\n+ \"cover\": {\\n+ \"zh\": \"全球航太、民航、國防、太空與技術新聞\",\\n+ \"en\": \"Global aerospace, air transport, defence, space & technology news\",\\n+ },\\n+ },\\n \"flightaware\": {\\n \"name\": \"FlightAware\",\\n \"kind\": \"data\",\\n@@ -386,6 +386,59 @@ def _parse_eurocontrol(soup: BeautifulSoup, base: str) -> list[dict]:\\n return items\\n \\n \\n+def _agn_date_after(anchor, base: str) -> datetime | None:\\n+ \"\"\"Find the date following an AGN listing link without crossing cards.\"\"\"\\n+ current_url = urljoin(base, str(anchor.get(\"href\") or \"\"))\\n+ for index, node in enumerate(anchor.next_elements):\\n+ if index >= 60:\\n+ break\\n+ if getattr(node, \"name\", None) == \"a\":\\n+ href = str(node.get(\"href\") or \"\")\\n+ next_url = urljoin(base, href)\\n+ if (re.fullmatch(r\"/news/[a-z0-9][a-z0-9-]+/?\",\\n+ urlsplit(next_url).path)\\n+ and next_url != current_url):\\n+ break\\n+ if isinstance(node, str):\\n+ published = _date_from_text(node)\\n+ if published is not None:\\n+ return published\\n+ return None\\n+\\n+\\n+def _parse_aerospaceglobalnews(soup: BeautifulSoup, base: str) -> list[dict]:\\n+ \"\"\"Aerospace Global News latest-news listing.\\n+\\n+ The page repeats some article links for the image and headline. Keep one\\n+ dated /news// entry per URL and ignore navigation, topic and\\n+ undated recommendation links.\\n+ \"\"\"\\n+ items, seen = [], set()\\n+ path_re = re.compile(r\"^/news/[a-z0-9][a-z0-9-]+/?$\")\\n+ base_host = urlsplit(base).netloc.lower()\\n+ for anchor in soup.find_all(\"a\", href=True):\\n+ url = urljoin(base, str(anchor[\"href\"]))\\n+ parts = urlsplit(url)\\n+ if parts.netloc.lower() != base_host or not path_re.fullmatch(parts.path):\\n+ continue\\n+ title = _collapse(anchor.get(\"title\") or anchor.get_text(\" \", strip=True))\\n+ if url in seen or len(title) < 12 or title.lower() == \"news\":\\n+ continue\\n+ published = _agn_date_after(anchor, base)\\n+ if published is None:\\n+ continue\\n+ seen.add(url)\\n+ image = anchor.find(\"img\", src=True)\\n+ items.append({\\n+ \"title\": title,\\n+ \"url\": url,\\n+ \"published\": published,\\n+ \"summary\": \"\",\\n+ \"image\": urljoin(base, image[\"src\"]) if image else None,\\n+ })\\n+ return items\\n+\\n+\\n def _parse_airbus(soup: BeautifulSoup, base: str) -> list[dict]:\\n \"\"\"Airbus newsroom cards: official stories and press releases.\\n \\n@@ -428,6 +481,7 @@ def _parse_airbus(soup: BeautifulSoup, base: str) -> list[dict]:\\n \"faa\": _parse_faa,\\n \"icao\": _parse_icao,\\n \"eurocontrol\": _parse_eurocontrol,\\n+ \"aerospaceglobalnews\": _parse_aerospaceglobalnews,\\n \"airbus\": _parse_airbus,\\n }\\n \\n@@ -0,0 +1,96 @@\\n+import sys\\n+import unittest\\n+from pathlib import Path\\n+\\n+from bs4 import BeautifulSoup\\n+\\n+ROOT = Path(__file__).resolve().parent.parent\\n+sys.path.insert(0, str(ROOT / \"pipeline\"))\\n+\\n+import common # noqa: E402\\n+import fetch # noqa: E402\\n+\\n+\\n+AGN_HTML = \"\"\"\\n+
\\n+ \\n+ \\n+ \\n+ \\n+
\\n+\"\"\"\\n+\\n+\\n+class AerospaceGlobalNewsTests(unittest.TestCase):\\n+ def test_source_is_public_direct_html_feed(self):\\n+ source = common.SOURCES[\"aerospaceglobalnews\"]\\n+\\n+ self.assertEqual(source[\"name\"], \"Aerospace Global News\")\\n+ self.assertEqual(source[\"kind\"], \"media\")\\n+ self.assertEqual(source[\"fmt\"], \"HTML\")\\n+ self.assertEqual(\\n+ source[\"endpoint\"],\\n+ \"https://aerospaceglobalnews.com/latest-news/\",\\n+ )\\n+ self.assertEqual(source[\"type\"], \"html\")\\n+ self.assertTrue(source.get(\"public\", True))\\n+ self.assertIs(\\n+ fetch.HTML_PARSERS[\"aerospaceglobalnews\"],\\n+ fetch._parse_aerospaceglobalnews,\\n+ )\\n+\\n+ def test_latest_news_parser_keeps_unique_dated_articles(self):\\n+ items = fetch._parse_aerospaceglobalnews(\\n+ BeautifulSoup(AGN_HTML, \"lxml\"),\\n+ \"https://aerospaceglobalnews.com/latest-news/\",\\n+ )\\n+\\n+ self.assertEqual(\\n+ [item[\"title\"] for item in items],\\n+ [\\n+ \"GA-ATS gives the Do228 a new lease of life with NXT launch\",\\n+ \"China C919 high-altitude variant completes maiden flight\",\\n+ ],\\n+ )\\n+ self.assertEqual(\\n+ [item[\"url\"] for item in items],\\n+ [\\n+ (\\n+ \"https://aerospaceglobalnews.com/news/\"\\n+ \"ga-ats-gives-the-do228-a-new-lease-of-life-with-nxt-launch/\"\\n+ ),\\n+ (\\n+ \"https://aerospaceglobalnews.com/news/\"\\n+ \"china-c919-high-altitude-variant-completes-maiden-flight/\"\\n+ ),\\n+ ],\\n+ )\\n+ self.assertEqual(\\n+ [item[\"published\"].isoformat() for item in items],\\n+ [\\n+ \"2026-07-29T00:00:00+00:00\",\\n+ \"2026-07-28T00:00:00+00:00\",\\n+ ],\\n+ )\\n+\\n+\\n+if __name__ == \"__main__\":\\n+ unittest.main()" }