bvandeusen
9a252c8dde
Runs the Wikipedia summary and SearXNG search concurrently and returns both when available, so current-event questions aren't masked by a generic role article from Wikipedia. When the Wikipedia summary includes a thumbnail, it is cached through the existing image pipeline and surfaced as an embeddable markdown snippet alongside the extract. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
114 lines
4.4 KiB
Python
114 lines
4.4 KiB
Python
"""Wikipedia API: lightweight topic lookups and article search."""
|
|
import logging
|
|
from urllib.parse import quote as url_quote
|
|
|
|
import httpx
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_SUMMARY_URL = "https://en.wikipedia.org/api/rest_v1/page/summary"
|
|
_SEARCH_URL = "https://en.wikipedia.org/w/api.php"
|
|
_TIMEOUT = 5.0
|
|
_USER_AGENT = "FabledAssistant/1.0 (https://fabledsword.com)"
|
|
|
|
|
|
def _extract_thumbnail(data: dict) -> str:
|
|
"""Prefer the 320px thumbnail (kinder to cache/bandwidth) over originalimage."""
|
|
thumb = data.get("thumbnail", {}).get("source", "")
|
|
if thumb:
|
|
return thumb
|
|
return data.get("originalimage", {}).get("source", "")
|
|
|
|
|
|
async def wiki_summary(query: str) -> dict | None:
|
|
"""Fetch a Wikipedia summary for a given title/query.
|
|
|
|
Does a direct title lookup via the REST v1 summary endpoint.
|
|
Returns a dict with title, extract, url, and thumbnail_url on success;
|
|
thumbnail_url is an empty string when the article has no image.
|
|
Returns None on any failure.
|
|
"""
|
|
title = url_quote(query.replace(" ", "_"))
|
|
url = f"{_SUMMARY_URL}/{title}"
|
|
headers = {"User-Agent": _USER_AGENT}
|
|
try:
|
|
async with httpx.AsyncClient() as client:
|
|
resp = await client.get(url, headers=headers, timeout=_TIMEOUT, follow_redirects=True)
|
|
resp.raise_for_status()
|
|
data = resp.json()
|
|
if data.get("type") == "disambiguation":
|
|
logger.debug("wiki_summary: disambiguation page for %r", query)
|
|
return None
|
|
extract = data.get("extract", "").strip()
|
|
if not extract:
|
|
logger.debug("wiki_summary: empty extract for %r", query)
|
|
return None
|
|
return {
|
|
"title": data.get("title", query),
|
|
"extract": extract,
|
|
"url": data.get("content_urls", {}).get("desktop", {}).get("page", ""),
|
|
"thumbnail_url": _extract_thumbnail(data),
|
|
}
|
|
except Exception as exc:
|
|
logger.debug("wiki_summary failed for %r: %s", query, exc)
|
|
return None
|
|
|
|
|
|
async def wiki_search(query: str, limit: int = 3) -> list[dict]:
|
|
"""Search Wikipedia and return summaries for the top results.
|
|
|
|
Uses the MediaWiki search API then fetches summaries for each hit.
|
|
Skips disambiguation pages and empty extracts.
|
|
Returns a list of dicts with title, extract, and url.
|
|
"""
|
|
headers = {"User-Agent": _USER_AGENT}
|
|
params = {
|
|
"action": "query",
|
|
"list": "search",
|
|
"srsearch": query,
|
|
"srlimit": str(limit),
|
|
"format": "json",
|
|
}
|
|
results: list[dict] = []
|
|
try:
|
|
async with httpx.AsyncClient() as client:
|
|
resp = await client.get(
|
|
_SEARCH_URL, params=params, headers=headers, timeout=_TIMEOUT
|
|
)
|
|
resp.raise_for_status()
|
|
data = resp.json()
|
|
hits = data.get("query", {}).get("search", [])
|
|
for hit in hits:
|
|
title = hit.get("title", "")
|
|
encoded = url_quote(title.replace(" ", "_"))
|
|
summary_url = f"{_SUMMARY_URL}/{encoded}"
|
|
try:
|
|
sr = await client.get(
|
|
summary_url, headers=headers, timeout=_TIMEOUT, follow_redirects=True
|
|
)
|
|
sr.raise_for_status()
|
|
sdata = sr.json()
|
|
if sdata.get("type") == "disambiguation":
|
|
logger.debug("wiki_search: skipping disambiguation %r", title)
|
|
continue
|
|
extract = sdata.get("extract", "").strip()
|
|
if not extract:
|
|
logger.debug("wiki_search: empty extract for %r", title)
|
|
continue
|
|
results.append(
|
|
{
|
|
"title": sdata.get("title", title),
|
|
"extract": extract,
|
|
"url": sdata.get("content_urls", {})
|
|
.get("desktop", {})
|
|
.get("page", ""),
|
|
"thumbnail_url": _extract_thumbnail(sdata),
|
|
}
|
|
)
|
|
except Exception as exc:
|
|
logger.debug("wiki_search: summary fetch failed for %r: %s", title, exc)
|
|
except Exception as exc:
|
|
logger.debug("wiki_search failed for %r: %s", query, exc)
|
|
return []
|
|
return results
|