mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-10 21:07:15 +01:00
Krzysztof kuhy Rudnicki
a0fb279b1b
New agent_ready/ package (dist and live-url modes, 100% branch coverage) checks robots, sitemap, llms.txt, ai-catalog, 404, no-JS text, markdown mirrors and JSON-LD. repo_contract gains web-repo detection and installs the agent-ready pre-commit hook, CI workflow and check_agent_ready.sh shim; scripts/check_agent_ready.sh is the shared entry point. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NBScELfMUiieK9ManFbS3Y
187 lines
7.0 KiB
Python
187 lines
7.0 KiB
Python
"""Find stage: AR-FIND-01..04 (robots.txt, agent access, sitemap, AI Catalog)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from urllib.parse import urlsplit
|
|
|
|
from agent_ready import formats
|
|
from agent_ready.context import CATALOG, HOME, LLMS, Ctx, link_header_href
|
|
from agent_ready.report import summarize
|
|
|
|
# Training, search-index and user-initiated fetchers named in the spec's
|
|
# crawl-policy notes. Real UA strings for the two training crawlers.
|
|
AGENT_UAS = {
|
|
"ClaudeBot": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)",
|
|
"GPTBot": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GPTBot/1.1; +https://openai.com/gptbot)",
|
|
"Claude-SearchBot": "Claude-SearchBot/1.0",
|
|
"OAI-SearchBot": "OAI-SearchBot/1.0; +https://openai.com/searchbot",
|
|
"Claude-User": "Claude-User/1.0",
|
|
"ChatGPT-User": "ChatGPT-User/1.0; +https://openai.com/bot",
|
|
}
|
|
_CHALLENGE = (
|
|
"just a moment",
|
|
"cf-chl",
|
|
"challenge-platform",
|
|
"attention required",
|
|
"captcha",
|
|
)
|
|
XML_TYPES = ("application/xml", "text/xml", "application/rss+xml")
|
|
|
|
|
|
def check_robots(ctx: Ctx) -> None:
|
|
"""AR-FIND-01: robots.txt exists, is plain text and blocks no agent."""
|
|
resp = ctx.site.get("/robots.txt")
|
|
if resp.status != 200:
|
|
ctx.report.fail("AR-FIND-01", f"/robots.txt: HTTP {resp.status}")
|
|
return
|
|
problems = ctx.type_problem(resp, ("text/plain",), "/robots.txt")
|
|
if formats.looks_like_html(resp.text):
|
|
ctx.report.fail(
|
|
"AR-FIND-01",
|
|
"; ".join([*problems, "/robots.txt body is an HTML page (SPA fallback?)"]),
|
|
)
|
|
return
|
|
ctx.robots_text = resp.text
|
|
groups = formats.parse_robots(resp.text)
|
|
if not formats.has_wildcard_group(groups):
|
|
problems.append("no 'User-agent: *' group (spec: one rule for all agents)")
|
|
blocked = formats.blocked_agents(groups)
|
|
if blocked:
|
|
problems.append(f"blanket Disallow for: {', '.join(blocked)}")
|
|
ctx.report.verdict(
|
|
"AR-FIND-01",
|
|
problems,
|
|
"robots.txt is plain text, has a * group and blocks no agent",
|
|
)
|
|
|
|
|
|
def check_agent_access(ctx: Ctx) -> None:
|
|
"""AR-FIND-01 (bot protection): homepage is 200 for each agent UA (url mode)."""
|
|
if not ctx.live:
|
|
ctx.report.skip("AR-FIND-01", "agent user-agent fetches need url mode")
|
|
return
|
|
base, _ = ctx.home()
|
|
ctx.site.prefetch([HOME], tuple(AGENT_UAS.values()))
|
|
bad = []
|
|
for name, ua in AGENT_UAS.items():
|
|
resp = ctx.site.get(HOME, ua)
|
|
lowered = resp.text[:20000].lower()
|
|
if resp.status != 200:
|
|
bad.append(f"{name} HTTP {resp.status}")
|
|
elif resp.body != base.body and any(m in lowered for m in _CHALLENGE):
|
|
bad.append(f"{name} got a challenge page")
|
|
ctx.report.verdict("AR-FIND-01", bad, f"homepage 200 for {', '.join(AGENT_UAS)}")
|
|
|
|
|
|
def _sitemap_paths(ctx: Ctx) -> list[str]:
|
|
"""Sitemap locations from robots.txt (also fixes the dist-mode origin)."""
|
|
urls = formats.robots_sitemaps(ctx.robots_text or "")
|
|
if urls and not ctx.live:
|
|
parts = urlsplit(urls[0])
|
|
ctx.site.origin = f"{parts.scheme}://{parts.netloc}"
|
|
paths = [p for u in urls if (p := ctx.site.to_path(u))]
|
|
if ctx.robots_text is None:
|
|
ctx.report.fail("AR-FIND-03", "no valid robots.txt to reference the sitemap")
|
|
elif not urls:
|
|
ctx.report.fail("AR-FIND-03", "robots.txt has no 'Sitemap:' line")
|
|
elif not paths:
|
|
ctx.report.fail(
|
|
"AR-FIND-03", f"robots.txt Sitemap is on another host: {urls[0]}"
|
|
)
|
|
else:
|
|
ctx.report.ok("AR-FIND-03", f"robots.txt references {summarize(urls)}")
|
|
return paths or ["/sitemap.xml"]
|
|
|
|
|
|
def _read_sitemap(ctx: Ctx, path: str, problems: list[str]) -> tuple[str, list[str]]:
|
|
"""Fetch and parse one sitemap; record problems; return (kind, locs)."""
|
|
resp = ctx.site.get(path)
|
|
if resp.status != 200:
|
|
problems.append(f"{path}: HTTP {resp.status}")
|
|
return "", []
|
|
problems.extend(ctx.type_problem(resp, XML_TYPES, path))
|
|
try:
|
|
return formats.parse_sitemap(resp.body)
|
|
except ValueError as exc:
|
|
problems.append(f"{path}: {exc}")
|
|
return "", []
|
|
|
|
|
|
def check_sitemap(ctx: Ctx) -> None:
|
|
"""AR-FIND-03: sitemap referenced from robots.txt, valid XML, on-site <loc>s."""
|
|
problems: list[str] = []
|
|
locs: list[str] = []
|
|
for path in _sitemap_paths(ctx)[:5]:
|
|
kind, found = _read_sitemap(ctx, path, problems)
|
|
if kind == "sitemapindex":
|
|
for child in [p for u in found[:10] if (p := ctx.site.to_path(u))]:
|
|
locs += _read_sitemap(ctx, child, problems)[1]
|
|
else:
|
|
locs += found
|
|
if locs and not ctx.live and ctx.site.origin.endswith("dist.invalid"):
|
|
parts = urlsplit(locs[0])
|
|
ctx.site.origin = f"{parts.scheme}://{parts.netloc}"
|
|
pages = [p for loc in locs if (p := ctx.site.to_path(loc))]
|
|
if len(pages) < len(locs):
|
|
problems.append(
|
|
f"{len(locs) - len(pages)} <loc> URLs are not on {ctx.site.origin}"
|
|
)
|
|
if not locs and not problems:
|
|
problems.append("sitemap has no <loc> entries")
|
|
ctx.sitemap_pages = list(dict.fromkeys(pages))
|
|
ctx.report.verdict(
|
|
"AR-FIND-03", problems, f"sitemap lists {len(ctx.sitemap_pages)} pages"
|
|
)
|
|
|
|
|
|
def check_catalog(ctx: Ctx) -> None:
|
|
"""AR-FIND-04: valid AI Catalog, lists llms.txt, linked from homepage head."""
|
|
resp = ctx.site.get(CATALOG)
|
|
problems: list[str] = []
|
|
if resp.status != 200:
|
|
problems.append(f"{CATALOG}: HTTP {resp.status}")
|
|
else:
|
|
problems += ctx.type_problem(
|
|
resp, ("application/ai-catalog+json", "application/json"), CATALOG
|
|
)
|
|
try:
|
|
doc = json.loads(resp.body)
|
|
except ValueError:
|
|
doc = None
|
|
problems.append(f"{CATALOG} is not JSON")
|
|
if doc is not None:
|
|
problems += formats.catalog_problems(doc)
|
|
listed = {ctx.site.to_path(u) for u in formats.catalog_urls(doc)}
|
|
if ctx.exists(LLMS) and LLMS not in listed:
|
|
problems.append("catalog has no entry for /llms.txt")
|
|
ctx.report.verdict("AR-FIND-04", problems, f"{CATALOG} is a valid AI Catalog")
|
|
home, scan = ctx.home()
|
|
href = scan.link_href("ai-catalog")
|
|
ok = href is not None and ctx.site.to_path(href) == CATALOG
|
|
ctx.report.verdict(
|
|
"AR-FIND-04",
|
|
[]
|
|
if ok
|
|
else [
|
|
'homepage head lacks <link rel="ai-catalog" href="/.well-known/ai-catalog.json">'
|
|
],
|
|
"homepage head links the catalog",
|
|
)
|
|
if not ctx.live:
|
|
ctx.report.skip(
|
|
"AR-FIND-04", "HTTP Link header can only be checked in url mode"
|
|
)
|
|
return
|
|
header = link_header_href(home, "ai-catalog")
|
|
ok = header is not None and ctx.site.to_path(header) == CATALOG
|
|
ctx.report.verdict(
|
|
"AR-FIND-04",
|
|
[]
|
|
if ok
|
|
else [
|
|
'homepage response lacks HTTP header Link: <...ai-catalog.json>; rel="ai-catalog"'
|
|
],
|
|
"homepage sends the ai-catalog Link header",
|
|
)
|