File size: 2,172 Bytes
dbb1bf9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | import requests
from errors import get_logger, fmt_exc
log = get_logger("worldmonitor")
# World Monitor's own internal nginx, reachable only inside this container.
WM_INTERNAL_URL = "http://127.0.0.1:8080"
def get_news_digest(lang: str = "it", max_items: int = 8) -> list[dict]:
"""Interroga l'istanza locale di World Monitor per un digest di notizie recenti.
Ritorna [] se World Monitor non è raggiungibile (es. ancora in avvio) o non
ha ancora dati — la ricerca web di GenerAI resta il percorso principale,
questo è un arricchimento opzionale.
"""
try:
r = requests.get(
f"{WM_INTERNAL_URL}/api/news/v1/list-feed-digest",
params={"variant": "full", "lang": lang},
timeout=5,
)
if r.status_code != 200:
log.debug("World Monitor digest non disponibile (HTTP %s)", r.status_code)
return []
data = r.json()
except Exception as e:
log.debug("World Monitor non raggiungibile: %s", fmt_exc(e))
return []
items = []
for category in (data.get("categories") or {}).values():
for item in category.get("items", []):
title = item.get("title", "").strip()
if not title:
continue
items.append({
"title": title,
"url": item.get("link", ""),
"source": item.get("source", ""),
"score": item.get("importanceScore", 0),
})
items.sort(key=lambda x: -x["score"])
return items[:max_items]
def find_relevant(query: str, max_items: int = 3) -> list[dict]:
"""Filtra il digest di World Monitor per gli item con parole in comune con la query."""
words = {w for w in query.lower().split() if len(w) > 3}
if not words:
return []
digest = get_news_digest(max_items=40)
if not digest:
return []
scored = []
for item in digest:
overlap = sum(1 for w in words if w in item["title"].lower())
if overlap > 0:
scored.append((overlap, item))
scored.sort(key=lambda x: -x[0])
return [item for _, item in scored[:max_items]]
|