Files
planet/backend/app/services/collectors/media_news_archive.py
linkong 93eb41a9f7
Some checks failed
ci / backend (push) Has been cancelled
ci / frontend (push) Has been cancelled
ci / delivery (push) Has been cancelled
release / images (push) Has been cancelled
release: bump version to 0.58.0
Release 0.58.0 includes the Earth high-precision boundary PMTiles/MVT pipeline, standardized Earth boundary source collectors, China POV boundary configuration templates, and removal of the legacy low-precision GeoJSON fallback. It also adds Earth news target-location queueing/archive support, fixes datasource task status visibility, documents the Earth surface depth-spacing rules that prevent far-zoom z-fighting snow/black blocks, and updates bilingual operations/developer docs.
2026-05-15 17:40:07 +08:00

58 lines
2.4 KiB
Python

from __future__ import annotations
from typing import Any
from app.services.collectors.base import BaseCollector
from app.services.earth_news_store import list_all_earth_news_records
class MediaNewsArchiveCollector(BaseCollector):
name = "media_news_archive"
priority = "P2"
module = "L4"
frequency_hours = 12
data_type = "news_item"
fail_on_empty = False
async def fetch(self) -> list[dict[str, Any]]:
if not self._db_session:
return []
records = await list_all_earth_news_records(self._db_session)
items: list[dict[str, Any]] = []
for record in records:
location_meta = dict(record.location_meta or {})
target = location_meta.get("target") if isinstance(location_meta.get("target"), dict) else {}
country = target.get("country")
city = target.get("city")
items.append(
{
"id": record.id,
"source_id": record.id,
"name": record.title,
"title": record.title,
"description": record.summary,
"country": country,
"city": city,
"latitude": record.latitude,
"longitude": record.longitude,
"reference_date": record.published_at,
"metadata": {
"url": record.url,
"source": record.source,
"feed_name": record.feed_name,
"region": record.region,
"homepage_url": record.homepage_url,
"published_at": record.published_at.isoformat() if record.published_at else None,
"location_label": record.location_label,
"location_source": record.location_source,
"verified": record.verified,
"location_meta": location_meta,
"first_seen_at": record.first_seen_at.isoformat() if record.first_seen_at else None,
"last_seen_at": record.last_seen_at.isoformat() if record.last_seen_at else None,
"resolved_at": record.resolved_at.isoformat() if record.resolved_at else None,
},
}
)
return items