AIが引用した参考資料やリンクが実在するか確認する

from pathlib import Path
from urllib.request import Request, urlopen
from urllib.error import HTTPError, URLError
import html
import json
import re

checks = [
    {
        "reference": "urllib.request",
        "url": "https://docs.python.org/3/library/urllib.request.html",
        "claim": "Python provides urllib.request for opening URLs.",
        "terms": ["urllib.request", "URL"],
    },
    {
        "reference": "json",
        "url": "https://docs.python.org/3/library/json.html",
        "claim": "Python's json module provides JSON encoding and decoding.",
        "terms": ["json", "encoding", "decoding"],
    },
    {
        "reference": "Synthetic fake reference",
        "url": "https://example.invalid/fake-reference",
        "claim": "This page documents an AI-specific reference verifier.",
        "terms": ["reference", "verifier"],
    },
]

output_dir = Path("outputs")
if output_dir.exists():
    raise SystemExit("outputs already exists; remove or rename it before running again")
output_dir.mkdir()

results = []

for item in checks:
    result = {
        "reference": item["reference"],
        "url": item["url"],
        "claim": item["claim"],
        "reachable": False,
        "status": None,
        "final_url": None,
        "term_matches": {},
        "error": None,
    }

    try:
        request = Request(
            item["url"],
            headers={"User-Agent": "Worknote reference checker/1.0"},
        )
        with urlopen(request, timeout=10) as response:
            result["status"] = response.status
            result["final_url"] = response.geturl()
            raw = response.read(500_000).decode("utf-8", errors="replace")

        text = re.sub(r"<script.*?</script>", " ", raw, flags=re.I | re.S)
        text = re.sub(r"<style.*?</style>", " ", text, flags=re.I | re.S)
        text = re.sub(r"<[^>]+>", " ", text)
        text = html.unescape(text)
        text = re.sub(r"\s+", " ", text)

        result["reachable"] = True
        lowered = text.casefold()
        result["term_matches"] = {
            term: term.casefold() in lowered for term in item["terms"]
        }

    except HTTPError as exc:
        result["status"] = exc.code
        result["error"] = f"HTTPError: {exc}"
    except URLError as exc:
        result["error"] = f"URLError: {exc.reason}"
    except Exception as exc:
        result["error"] = f"{type(exc).__name__}: {exc}"

    results.append(result)

report_path = output_dir / "reference_check.json"
report_path.write_text(
    json.dumps(results, indent=2, ensure_ascii=False),
    encoding="utf-8",
)

for result in results:
    print(result["reference"])
    print("  reachable:", result["reachable"])
    print("  status:", result["status"])
    print("  final URL:", result["final_url"])
    print("  term matches:", result["term_matches"])
    print("  error:", result["error"])

print(f"Saved: {report_path}")