thejayman77
2145622b59
og:image extraction rejected any URL containing "branded_news" as a generic share image, but that's BBC's normal CDN path for real article photos. So every BBC hero fell back to the 240px RSS thumbnail (blurry when shown large). Drop that marker; keep the genuine placeholder markers (facebook-default, og-default, etc.). Updated the test to assert BBC branded_news paths pass through. 99 tests pass. (One-time: cleared image_checked_at on the 57 previously-checked articles and re-enriched recent briefs so existing thumbnails upgrade to og:images.) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
86 lines
4.7 KiB
Python
86 lines
4.7 KiB
Python
import pytest
|
|
|
|
from goodnews.db import connect, init_db
|
|
from goodnews.enrich import og_image_from_html, _host_is_public, enrich_brief_images
|
|
|
|
|
|
def test_og_image_parser_handles_attr_order_and_fallback():
|
|
assert og_image_from_html(b'<head><meta property="og:image" content="https://x.com/a.jpg"></head>') == "https://x.com/a.jpg"
|
|
assert og_image_from_html(b'<meta content="https://x.com/b.jpg" property="og:image">') == "https://x.com/b.jpg"
|
|
assert og_image_from_html(b'<meta name="twitter:image" content="https://x.com/c.jpg">') == "https://x.com/c.jpg"
|
|
assert og_image_from_html(b"<html><body>nope</body></html>") is None
|
|
|
|
|
|
def test_og_image_only_reads_head():
|
|
# a meta after </head> must be ignored
|
|
assert og_image_from_html(b'<head></head><meta property="og:image" content="https://x.com/d.jpg">') is None
|
|
|
|
|
|
def test_host_public_guard_blocks_internal_ranges():
|
|
assert _host_is_public("8.8.8.8") # public
|
|
assert not _host_is_public("127.0.0.1") # loopback
|
|
assert not _host_is_public("10.0.0.1") # private
|
|
assert not _host_is_public("192.168.1.1") # private
|
|
assert not _host_is_public("169.254.0.1") # link-local
|
|
assert not _host_is_public("0.0.0.0") # unspecified
|
|
assert not _host_is_public("")
|
|
assert not _host_is_public(None)
|
|
|
|
|
|
@pytest.fixture
|
|
def conn():
|
|
c = connect(":memory:"); init_db(c)
|
|
c.execute("INSERT INTO sources (id,name,feed_url,trust_score) VALUES (1,'S','http://s/f',5)")
|
|
c.execute("INSERT INTO articles (id,source_id,canonical_url,title,url_hash) VALUES (1,1,'https://phys.org/x','t1','h1')")
|
|
c.execute("INSERT INTO daily_briefs (id,brief_date,title) VALUES (1,'2026-05-31','B')")
|
|
c.execute("INSERT INTO daily_brief_items (brief_id,article_id,rank) VALUES (1,1,1)")
|
|
c.commit(); yield c; c.close()
|
|
|
|
|
|
def test_enrich_sets_image_and_stamps(conn):
|
|
calls = []
|
|
found = enrich_brief_images(conn, "2026-05-31", fetch=lambda u: calls.append(u) or "https://img.example/p.jpg")
|
|
assert found == 1 and calls == ["https://phys.org/x"]
|
|
r = conn.execute("SELECT image_url, image_checked_at FROM articles WHERE id=1").fetchone()
|
|
assert r["image_url"] == "https://img.example/p.jpg" and r["image_checked_at"] is not None
|
|
|
|
|
|
def test_enrich_caches_failure_and_does_not_retry(conn):
|
|
calls = []
|
|
fail = lambda u: calls.append(u) or None
|
|
assert enrich_brief_images(conn, "2026-05-31", fetch=fail) == 0
|
|
r = conn.execute("SELECT image_url, image_checked_at FROM articles WHERE id=1").fetchone()
|
|
assert r["image_url"] is None and r["image_checked_at"] is not None # checked, cached
|
|
assert enrich_brief_images(conn, "2026-05-31", fetch=fail) == 0
|
|
assert len(calls) == 1 # not retried once checked
|
|
|
|
|
|
def test_enrich_upgrades_existing_feed_image(tmp_path):
|
|
# A brief item with a (small) feed image should be upgraded to og:image.
|
|
from goodnews.db import connect as _c, init_db as _i
|
|
c = _c(":memory:"); _i(c)
|
|
c.execute("INSERT INTO sources (id,name,feed_url,trust_score) VALUES (1,'S','http://s/f',5)")
|
|
c.execute("INSERT INTO articles (id,source_id,canonical_url,title,url_hash,image_url) "
|
|
"VALUES (1,1,'https://bbc.com/x','t1','h1','https://bbc.com/tiny-thumb.jpg')")
|
|
c.execute("INSERT INTO daily_briefs (id,brief_date,title) VALUES (1,'2026-05-31','B')")
|
|
c.execute("INSERT INTO daily_brief_items (brief_id,article_id,rank) VALUES (1,1,1)")
|
|
c.commit()
|
|
found = enrich_brief_images(c, "2026-05-31", fetch=lambda u: "https://bbc.com/big-og.jpg")
|
|
assert found == 1
|
|
assert c.execute("SELECT image_url FROM articles WHERE id=1").fetchone()["image_url"] == "https://bbc.com/big-og.jpg"
|
|
c.close()
|
|
|
|
|
|
def test_rejects_generic_share_images():
|
|
# genuine placeholder/default share images are skipped
|
|
assert og_image_from_html(b'<meta name="twitter:image" content="https://media.npr.org/include/images/facebook-default-wide-s.jpg">') is None
|
|
assert og_image_from_html(b'<meta property="og:image" content="https://x.com/og-default.jpg">') is None
|
|
# a real article image comes through
|
|
assert og_image_from_html(b'<meta property="og:image" content="https://x.com/real-photo.jpg">') == "https://x.com/real-photo.jpg"
|
|
# BBC's branded_news path is a REAL photo path, not a placeholder — keep it
|
|
assert og_image_from_html(b'<meta property="og:image" content="https://ichef.bbci.co.uk/news/1024/branded_news/x.jpg">') == "https://ichef.bbci.co.uk/news/1024/branded_news/x.jpg"
|
|
# if the first og is a generic placeholder but a later one is real, take the real one
|
|
html = (b'<meta property="og:image" content="https://x.com/og-default.jpg">'
|
|
b'<meta property="og:image" content="https://x.com/article.jpg">')
|
|
assert og_image_from_html(html) == "https://x.com/article.jpg"
|