Add resumable US policy news collectors and provenance
Collect official crypto and US policy documents with deterministic screening, full bodies and attachments, bounded retries, and durable history cursors. Preserve publication precision and source identity while keeping new collectors disabled. Add real Congress, GovInfo, DOJ and Federal Register fixtures, offline capture replay, isolated database validation, and rollout instructions. Validate 982 backend tests, frontend checks, and 57 deployment control tests.
This commit is contained in:
1 parent
dc8a283571
commit
89c729092c
31 files changed
+2199
-23
No files matched your search
@@ -33,7 +33,7 @@ ITEM = """<item><title>Bitcoin & Ethereum</title>
|
||||
<dc:creator>News desk</dc:creator><category>Markets</category></item>"""
|
||||
|
||||
|
||||
@pytest.mark.parametrize("source", ["CoinDeskSpider", "FedSpider", "BeaSpider"])
|
||||
@pytest.mark.parametrize("source", ["CoinDeskSpider", "BeaSpider"])
|
||||
def test_rss_preserves_original_summary_time_and_provenance(trading, source):
|
||||
from alphapulse.crawler.spiders import rss
|
||||
spider = make_spider(getattr(rss, source))
|
||||
@@ -53,8 +53,8 @@ def test_rss_preserves_original_summary_time_and_provenance(trading, source):
|
||||
|
||||
|
||||
def test_rss_identity_survives_revisions_and_different_subfeeds(trading):
|
||||
from alphapulse.crawler.spiders.rss import FedSpider
|
||||
spider = make_spider(FedSpider)
|
||||
from alphapulse.crawler.spiders.rss import CoinDeskSpider
|
||||
spider = make_spider(CoinDeskSpider)
|
||||
original, = spider.parse_feed(feed_response(ITEM))
|
||||
revised, = spider.parse_feed(feed_response(ITEM.replace("Bitcoin & Ethereum", "Revised headline"), "https://example.invalid/other.xml"))
|
||||
assert original["external_id"] == revised["external_id"]
|
||||
|
||||
Reference in new issue
Block a user