Files
2dph/bin/web/search
T
eSlider 63d3be0e19 build(ci): uv toolchain, release-please semver; feat(skills): vendor tools self-contained (no symlinks, relative refs)
- bin/db/psql-yq + bin/web/search + tools/{yamlout,websearch} vendored as real files
- bin/db/ssh-tunnel added (OnlyOffice VM pg on 5433)
- skills reference local bin/ paths; no agent-skills/abs links in git
- pyproject.toml + uv.lock; CI installs via uv sync --frozen
- release-please auto-tags semver from conventional commits when green
- LICENSE MIT, badges/mermaid README
2026-08-10 21:24:42 +01:00

151 lines
5.8 KiB
Python
Executable File

#!/usr/bin/env python3
"""web/search - web search through the self-hosted SearXNG at search.ops.io.
bin/web/search "LadybugDB vector search"
bin/web/search "model2vec multilingual" --site github.com
bin/web/search "uclancy" --category it -n 3 --json | jq -r '.results[].url'
bin/web/search "sqlite-vec" --refresh # ignore the cached answer
This complements bin/kb/search: the knowledge base holds our own facts, this
reaches the public web. Use it as the second, independent source that the
detective method asks for.
Exit codes: 0 results, 2 refused as possible PII, 3 throttled (not "nothing
found" - the instance answers 200 with an empty list when it throttles).
"""
from __future__ import annotations
import argparse
import fcntl
import json
import os
import sys
import time
import urllib.parse
import urllib.request
from pathlib import Path
TOOLS = Path(__file__).resolve().parents[1].parent / "tools"
sys.path.insert(0, str(TOOLS))
sys.path.insert(0, str(TOOLS / "web-search"))
import websearch as ws # noqa: E402
from yamlout import to_yaml # noqa: E402
CONFIG = Path(os.environ.get("BRAIN_SEARCH_ENV", Path.home() / ".config/brain/search.env"))
CACHE = Path(os.environ.get("BRAIN_SEARCH_CACHE", Path.home() / ".cache/brain/web-search.sqlite"))
LOCK = CACHE.with_suffix(".lock")
def load_config() -> dict:
if not CONFIG.exists():
sys.exit(f"no credentials at {CONFIG} (mode 600, BRAIN_SEARCH_URL/USER/PASS)")
conf = {}
for line in CONFIG.read_text().splitlines():
line = line.strip()
if not line or line.startswith("#") or "=" not in line:
continue
key, _, value = line.partition("=")
conf[key.strip()] = value.strip().strip("\"'")
missing = {"BRAIN_SEARCH_URL", "BRAIN_SEARCH_USER", "BRAIN_SEARCH_PASS"} - conf.keys()
if missing:
sys.exit(f"{CONFIG} is missing {', '.join(sorted(missing))}")
return conf
def fetch(conf: dict, query: str, params: dict, timeout: int) -> dict:
args = {"q": query, "format": "json", **params}
url = f"{conf['BRAIN_SEARCH_URL'].rstrip('/')}/search?{urllib.parse.urlencode(args)}"
request = urllib.request.Request(url)
token = f"{conf['BRAIN_SEARCH_USER']}:{conf['BRAIN_SEARCH_PASS']}".encode()
import base64
request.add_header("Authorization", "Basic " + base64.b64encode(token).decode())
with urllib.request.urlopen(request, timeout=timeout) as response:
return json.loads(response.read().decode())
def main() -> int:
parser = argparse.ArgumentParser(description="web search via SearXNG")
parser.add_argument("query")
parser.add_argument("-n", "--limit", type=int, default=ws.DEFAULT_LIMIT)
parser.add_argument("--site", help="restrict to one domain")
parser.add_argument("--lang", help="language code, e.g. de")
parser.add_argument("--fresh", choices=["day", "week", "month", "year"],
help="time range")
parser.add_argument("--category", help="SearXNG category, e.g. it, science, news")
parser.add_argument("--engines", help="comma separated engine list")
parser.add_argument("--json", action="store_true")
parser.add_argument("--refresh", action="store_true", help="bypass the cache")
parser.add_argument("--ttl", type=float, default=ws.CACHE_TTL)
parser.add_argument("--timeout", type=int, default=25)
parser.add_argument("--force", action="store_true",
help="send even if the query looks like PII")
args = parser.parse_args()
query = f"site:{args.site} {args.query}" if args.site else args.query
reason = ws.phi_reason(query)
if reason and not args.force:
print(f"refused: {reason}. This query would leave the host.", file=sys.stderr)
print("Rephrase without identifiers, or pass --force if it is genuinely public.",
file=sys.stderr)
return 2
params = {}
if args.lang:
params["language"] = args.lang
if args.fresh:
params["time_range"] = args.fresh
if args.category:
params["categories"] = args.category
if args.engines:
params["engines"] = args.engines
key = ws.cache_key(query, params)
conn = ws.open_cache(CACHE)
if not args.refresh:
cached = ws.cache_get(conn, key, ttl=args.ttl)
if cached is not None:
out = ws.project(cached, limit=args.limit)
out["cached"] = True
sys.stdout.write(json.dumps(out, indent=2, ensure_ascii=False) + "\n"
if args.json else to_yaml(out))
return 0
conf = load_config()
LOCK.parent.mkdir(parents=True, exist_ok=True)
# One request at a time across every agent on this host: the instance
# suspends engines for minutes when several of us ask at once.
with open(LOCK, "w") as lock:
fcntl.flock(lock, fcntl.LOCK_EX)
payload = None
for attempt in range(1 + len(ws.RETRY_BACKOFF)):
delay = ws.wait_for(ws.last_call(conn), time.time())
if delay:
time.sleep(delay)
ws.mark_call(conn)
try:
payload = fetch(conf, query, params, args.timeout)
except Exception as error: # noqa: BLE001 - report, do not crash
print(f"request failed: {error}", file=sys.stderr)
return 3
if ws.classify(payload) == "ok":
break
if attempt < len(ws.RETRY_BACKOFF):
time.sleep(ws.RETRY_BACKOFF[attempt])
if ws.classify(payload) == "ok":
ws.cache_put(conn, key, payload)
out = ws.project(payload, limit=args.limit)
sys.stdout.write(json.dumps(out, indent=2, ensure_ascii=False) + "\n"
if args.json else to_yaml(out))
return 0 if out["status"] == "ok" else 3
if __name__ == "__main__":
sys.exit(main())