eezd
e8ca4daa0e
Collect official RSS and Atom summaries, preserve historical captures, and poll macro releases with bounded cadence and Retry-After handling. Separate news collectors from the economic calendar worker. Track statistical periods, publication stages, first observations, revisions, and current official series. Include explicit migration files and isolated archive, parsing, and import tests; no migration or import is executed by this commit. Keep dependency declarations and lockfile together for PDF archives and the upcoming captcha integration. Verify the staged snapshot with 90 focused tests.
38 lines
1.4 KiB
Python
38 lines
1.4 KiB
Python
"""新增国外新闻和宏观公告来源。
|
|
|
|
Revision ID: e6f8a2c4d109
|
|
Revises: d2a4c6e8f103
|
|
"""
|
|
|
|
from alembic import op
|
|
import sqlalchemy as sa
|
|
|
|
revision = "e6f8a2c4d109"
|
|
down_revision = "d2a4c6e8f103"
|
|
branch_labels = None
|
|
depends_on = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
sources = sa.table(
|
|
"sources",
|
|
sa.column("code", sa.String), sa.column("name", sa.String), sa.column("list_url", sa.String),
|
|
sa.column("enabled", sa.Boolean), sa.column("interval_seconds", sa.Integer),
|
|
sa.column("backfill_hours", sa.Integer), sa.column("consecutive_failures", sa.Integer),
|
|
)
|
|
op.bulk_insert(sources, [
|
|
{"code": code, "name": name, "list_url": url, "enabled": enabled,
|
|
"interval_seconds": 60, "backfill_hours": 72, "consecutive_failures": 0}
|
|
for code, name, url, enabled in [
|
|
("coindesk", "CoinDesk", "https://www.coindesk.com/arc/outboundfeeds/rss/", True),
|
|
("fed", "美联储·政策与讲话", "https://www.federalreserve.gov/feeds/feeds.htm", True),
|
|
("bls", "美国劳工统计局·CPI/PPI/就业", "https://www.bls.gov/feed/", True),
|
|
("bea", "美国经济分析局", "https://apps.bea.gov/rss/rss.xml", True),
|
|
]
|
|
])
|
|
|
|
|
|
def downgrade() -> None:
|
|
# 已有采集记录时由外键拒绝回退，不级联删除新闻、原始响应或日志。
|
|
op.execute("DELETE FROM sources WHERE code IN ('coindesk', 'fed', 'bls', 'bea')")
|