@reddoorla/maintenance 0.93.1 → 0.94.1

package/dist/{chunk-BJQCIJOY.js → chunk-REJCSA4H.js}

@@ -1,3 +1,22 @@
+import {
+  AI_AGENTS,
+  CLASSICAL_AGENTS,
+  USER_AGENT,
+  buildJourney,
+  canonicalizeUrl,
+  crawlSite,
+  defaultCrawlDeps,
+  defaultHttpProbeDeps,
+  pacedEach,
+  probeHttp,
+  readCapped,
+  readStack,
+  resolveNavigable,
+  runSiteChecks,
+  sleep,
+  summarizeAccessibility,
+  usablePages
+} from "./chunk-WJMPCVOR.js";
 import {
   checkGoal
 } from "./chunk-T7ZUUOZ2.js";
@@ -5,699 +24,6 @@ import {
   isPrivateOrLoopbackHost
 } from "./chunk-RARREDQE.js";
 
-// src/prospect/crawl.ts
-import { parse as parse2, NodeType as NodeType2 } from "node-html-parser";
-
-// src/prospect/pages.ts
-function fetchedOk(page) {
-  return page.status !== null && page.status < 400;
-}
-var INFRA_SEGMENTS = [/^cdn-cgi$/i, /^wp-admin$/i, /^wp-json$/i, /^xmlrpc\.php$/i];
-function isInfraPath(url) {
-  let path;
-  try {
-    path = new URL(url).pathname;
-  } catch {
-    return false;
-  }
-  return path.split("/").filter(Boolean).some((segment) => INFRA_SEGMENTS.some((re) => re.test(segment)));
-}
-function usablePages(pages) {
-  const candidates = pages.filter((p) => fetchedOk(p) && !isInfraPath(p.url));
-  const withRendered = candidates.filter((p) => p.rendered !== null);
-  const withRaw = candidates.filter((p) => p.raw !== null);
-  const view = withRendered.length >= withRaw.length ? "rendered" : "raw";
-  const kept = view === "rendered" ? withRendered : withRaw;
-  const usable = [];
-  for (const page of kept) {
-    const extract = view === "rendered" ? page.rendered : page.raw;
-    if (extract) usable.push({ page, extract });
-  }
-  return {
-    pages: usable,
-    view,
-    excluded: candidates.length - usable.length,
-    anchorsMeasured: usable.length > 0 && usable.every((p) => p.extract.anchors !== void 0)
-  };
-}
-
-// src/prospect/extract.ts
-import { parse, NodeType } from "node-html-parser";
-var MAX_ANCHORS = 300;
-var NON_FIELD_INPUTS = /* @__PURE__ */ new Set(["hidden", "submit", "button", "image", "reset"]);
-var CONTACT_FIELD = /\b(e-?mail|phone|tel|mobile|contact)\b/i;
-var toWords = (s) => s.replace(/([a-z0-9])([A-Z])/g, "$1 $2").replace(/[_\-.]+/g, " ");
-var UNRENDERED_TAGS = /* @__PURE__ */ new Set(["STYLE", "NOSCRIPT", "TEMPLATE", "SVG"]);
-var BLOCK = /* @__PURE__ */ new Set([
-  "ADDRESS",
-  "ARTICLE",
-  "ASIDE",
-  "BLOCKQUOTE",
-  "BR",
-  "DD",
-  "DIV",
-  "DL",
-  "DT",
-  "FIELDSET",
-  "FIGCAPTION",
-  "FIGURE",
-  "FOOTER",
-  "FORM",
-  "H1",
-  "H2",
-  "H3",
-  "H4",
-  "H5",
-  "H6",
-  "HEADER",
-  "HR",
-  "LI",
-  "MAIN",
-  "NAV",
-  "OL",
-  "P",
-  "PRE",
-  "SECTION",
-  "TABLE",
-  "TD",
-  "TH",
-  "TR",
-  "UL"
-]);
-var collapse = (s) => s.replace(/\s+/g, " ").trim();
-var MAX_WALK_DEPTH = 100;
-function textOf(el) {
-  const parts = [];
-  const walk = (node, depth) => {
-    if (depth > MAX_WALK_DEPTH) return;
-    for (const child of node.childNodes) {
-      if (child.nodeType === NodeType.TEXT_NODE) {
-        parts.push(child.text);
-        continue;
-      }
-      if (child.nodeType !== NodeType.ELEMENT_NODE) continue;
-      const e = child;
-      const tag = e.tagName;
-      if (UNRENDERED_TAGS.has(tag) || tag === "SCRIPT" || tag === "TITLE") continue;
-      const block = BLOCK.has(tag);
-      if (block) parts.push("\n");
-      walk(e, depth + 1);
-      if (block) parts.push("\n");
-    }
-  };
-  walk(el, 0);
-  return collapse(parts.join(""));
-}
-function collect(el, out, depth = 0) {
-  if (depth > MAX_WALK_DEPTH) return;
-  for (const child of el.childNodes) {
-    if (child.nodeType !== NodeType.ELEMENT_NODE) continue;
-    const e = child;
-    const tag = e.tagName;
-    if (UNRENDERED_TAGS.has(tag)) continue;
-    switch (tag) {
-      case "META":
-        out.metas.push(e);
-        break;
-      case "LINK":
-        out.links.push(e);
-        break;
-      case "IMG":
-        out.images.push(e);
-        break;
-      case "A":
-        if ((e.getAttribute("href") ?? "").trim()) out.anchors.push(e);
-        break;
-      case "FORM":
-        out.forms.push(e);
-        break;
-      case "TITLE":
-        if (out.title === null) out.title = collapse(e.text) || null;
-        break;
-      case "SCRIPT":
-        if ((e.getAttribute("type") ?? "").toLowerCase().trim() === "application/ld+json") {
-          out.jsonLd.push(e.text);
-        }
-        continue;
-      case "H1":
-      case "H2":
-      case "H3":
-      case "H4":
-      case "H5":
-      case "H6": {
-        const text = textOf(e);
-        if (text) out.headings.push({ level: Number(tag.slice(1)), text });
-        break;
-      }
-    }
-    collect(e, out, depth + 1);
-  }
-}
-var NON_ENQUIRY_SEGMENTS = /* @__PURE__ */ new Set([
-  // Account doors
-  "login",
-  "log-in",
-  "log_in",
-  "logon",
-  "signin",
-  "sign-in",
-  "sign_in",
-  "signup",
-  "sign-up",
-  "sign_up",
-  "register",
-  "registration",
-  // Commerce
-  "checkout",
-  "cart",
-  "basket",
-  // Retrieval, not contact
-  "search",
-  // WordPress, whose comment endpoint is a fixed path on a great many sites
-  "wp-login",
-  "wp-signup",
-  "wp-register",
-  "wp-comments-post"
-]);
-function isNonEnquiryAction(action) {
-  if (!action) return false;
-  let path;
-  try {
-    path = new URL(action, "https://form.invalid/").pathname;
-  } catch {
-    path = action;
-  }
-  return path.toLowerCase().split("/").some((segment) => NON_ENQUIRY_SEGMENTS.has(segment.replace(/\.[a-z0-9]+$/, "")));
-}
-function formShape(form) {
-  const controls = form.querySelectorAll("input, textarea, select");
-  let fieldCount = 0;
-  let contactFieldCount = 0;
-  let hasContactField = false;
-  let hasPassword = false;
-  let hasTextarea = false;
-  let hasSubmit = form.querySelectorAll("button").length > 0;
-  for (const control of controls) {
-    const type = (control.getAttribute("type") ?? "").toLowerCase().trim();
-    if (control.tagName === "INPUT" && NON_FIELD_INPUTS.has(type)) {
-      if (type === "submit" || type === "image") hasSubmit = true;
-      continue;
-    }
-    if (control.tagName === "TEXTAREA") hasTextarea = true;
-    if (control.tagName === "INPUT" && type === "password") hasPassword = true;
-    fieldCount += 1;
-    const signature = toWords(
-      [
-        type,
-        control.getAttribute("name") ?? "",
-        control.getAttribute("id") ?? "",
-        control.getAttribute("placeholder") ?? "",
-        control.getAttribute("autocomplete") ?? "",
-        control.getAttribute("aria-label") ?? ""
-      ].join(" ")
-    );
-    if (type === "email" || type === "tel" || CONTACT_FIELD.test(signature)) {
-      hasContactField = true;
-      contactFieldCount += 1;
-    }
-  }
-  const action = form.getAttribute("action")?.trim() || null;
-  const isAccountForm = hasPassword || isNonEnquiryAction(action);
-  const asksSomethingBack = hasTextarea || fieldCount - contactFieldCount >= 2;
-  return {
-    // A lone contact field is a newsletter box, not an enquiry form. See
-    // `FormKind`: on one audited site a footer email box put every page at zero
-    // clicks from "reaching them", when the only form that reaches a person
-    // was the nine-field one on its contact page.
-    kind: isAccountForm || !hasContactField ? "other" : fieldCount >= 2 && asksSomethingBack ? "enquiry" : "subscribe",
-    action,
-    method: (form.getAttribute("method") ?? "get").toLowerCase().trim() || "get",
-    fieldCount,
-    hasContactField,
-    hasSubmit
-  };
-}
-function extractPage(html) {
-  const root = parse(html);
-  const documentEl = root.querySelector("html") ?? root;
-  const out = {
-    metas: [],
-    links: [],
-    jsonLd: [],
-    images: [],
-    headings: [],
-    title: null,
-    anchors: [],
-    forms: []
-  };
-  collect(documentEl, out);
-  const social = {};
-  let metaDescription = null;
-  let hasViewportMeta = false;
-  for (const m of out.metas) {
-    const key = (m.getAttribute("property") ?? m.getAttribute("name") ?? "").toLowerCase().trim();
-    if (!key) continue;
-    const content = (m.getAttribute("content") ?? "").trim();
-    if (key === "description") metaDescription = content || null;
-    else if (key === "viewport") hasViewportMeta = content.length > 0;
-    else if (key.startsWith("og:") || key.startsWith("twitter:")) social[key] = content;
-  }
-  const canonicalEl = out.links.find(
-    (l) => (l.getAttribute("rel") ?? "").toLowerCase().trim() === "canonical"
-  );
-  return {
-    title: out.title,
-    metaDescription,
-    canonical: canonicalEl?.getAttribute("href")?.trim() || null,
-    social,
-    headings: out.headings,
-    jsonLd: out.jsonLd,
-    images: {
-      total: out.images.length,
-      withAlt: out.images.filter((i) => (i.getAttribute("alt") ?? "").trim().length > 0).length
-    },
-    hasViewportMeta,
-    // Body-scoped: <head> has no visible text, and scoping here rather than
-    // filtering keeps the rule obvious.
-    text: textOf(root.querySelector("body") ?? documentEl),
-    anchors: out.anchors.slice(0, MAX_ANCHORS).map((a) => ({
-      href: (a.getAttribute("href") ?? "").trim(),
-      // The visible label, not the raw text: an anchor wrapping an icon and a
-      // span should read as its span. `textOf` already drops the unrendered
-      // subtrees an icon sprite lives in.
-      text: textOf(a).slice(0, 120),
-      rel: (a.getAttribute("rel") ?? "").toLowerCase().trim()
-    })),
-    // The TRUE total, so a capped list is never mistaken for a complete one.
-    anchorCount: out.anchors.length,
-    imageSrcs: out.images.map((i) => (i.getAttribute("src") ?? "").trim()).filter((src) => src.length > 0),
-    forms: out.forms.map(formShape)
-  };
-}
-
-// src/prospect/crawl.ts
-var AI_AGENTS = [
-  "GPTBot",
-  "OAI-SearchBot",
-  "ClaudeBot",
-  "PerplexityBot",
-  "Google-Extended",
-  "CCBot"
-];
-var CLASSICAL_AGENTS = ["Googlebot", "Bingbot"];
-var ALL_AGENTS = [...AI_AGENTS, ...CLASSICAL_AGENTS];
-function parseRobots(txt) {
-  const groups = [];
-  let current = null;
-  let lastWasAgent = false;
-  for (const rawLine of txt.split(/\r?\n/)) {
-    const line = (rawLine.split("#")[0] ?? "").trim();
-    if (!line) continue;
-    const idx = line.indexOf(":");
-    if (idx < 0) continue;
-    const field = line.slice(0, idx).trim().toLowerCase();
-    const value = line.slice(idx + 1).trim();
-    if (field === "user-agent") {
-      if (!current || !lastWasAgent) {
-        current = { agents: [], rules: [] };
-        groups.push(current);
-      }
-      current.agents.push(value.toLowerCase());
-      lastWasAgent = true;
-    } else if (field === "allow" || field === "disallow") {
-      if (!current) continue;
-      current.rules.push({ type: field === "allow" ? "allow" : "disallow", path: value, line });
-      lastWasAgent = false;
-    }
-  }
-  return groups;
-}
-function pathCoversRoot(pattern) {
-  if (!pattern) return false;
-  const anchored = pattern.endsWith("$");
-  const body = anchored ? pattern.slice(0, -1) : pattern;
-  const source = body.split("*").map((part) => part.replace(/[.+?^${}()|[\]\\]/g, "\\$&")).join(".*");
-  return new RegExp(`^${source}${anchored ? "$" : ""}`).test("/");
-}
-function evaluateAgentAccess(robotsTxt) {
-  if (robotsTxt === null) {
-    return ALL_AGENTS.map((agent) => ({ agent, allowed: true, matchedRule: null }));
-  }
-  const groups = parseRobots(robotsTxt);
-  return ALL_AGENTS.map((agent) => {
-    const lower = agent.toLowerCase();
-    const named = groups.filter((g) => g.agents.includes(lower));
-    const matched = named.length > 0 ? named : groups.filter((g) => g.agents.includes("*"));
-    if (matched.length === 0) return { agent, allowed: true, matchedRule: null };
-    const header = `User-agent: ${named.length > 0 ? agent : "*"}`;
-    const rootRules = matched.flatMap((g) => g.rules).filter((r) => pathCoversRoot(r.path));
-    const block = rootRules.find((r) => r.type === "disallow");
-    const allow = rootRules.find((r) => r.type === "allow");
-    if (block && !allow) return { agent, allowed: false, matchedRule: `${header} \u2192 ${block.line}` };
-    return { agent, allowed: true, matchedRule: allow ? `${header} \u2192 ${allow.line}` : null };
-  });
-}
-var MAX_WALK_DEPTH2 = 100;
-function sameOriginLinks(html, baseUrl) {
-  const site = new URL(baseUrl);
-  const doc = parse2(html);
-  const baseHref = doc.querySelector("base")?.getAttribute("href");
-  let resolveBase = site;
-  if (baseHref) {
-    try {
-      resolveBase = new URL(baseHref, site);
-    } catch {
-    }
-  }
-  const out = [];
-  const seen = /* @__PURE__ */ new Set();
-  const walk = (el, depth) => {
-    if (depth > MAX_WALK_DEPTH2) return;
-    for (const child of el.childNodes) {
-      if (child.nodeType !== NodeType2.ELEMENT_NODE) continue;
-      const e = child;
-      if (UNRENDERED_TAGS.has(e.tagName)) continue;
-      if (e.tagName === "A") {
-        const href = e.getAttribute("href");
-        if (href) {
-          let u;
-          try {
-            u = new URL(href, resolveBase);
-          } catch {
-            u = null;
-          }
-          if (u && u.origin === site.origin && (u.protocol === "http:" || u.protocol === "https:")) {
-            u.hash = "";
-            const norm = u.toString();
-            if (!seen.has(norm)) {
-              seen.add(norm);
-              out.push(norm);
-            }
-          }
-        }
-      }
-      walk(e, depth + 1);
-    }
-  };
-  walk(doc, 0);
-  return out;
-}
-function decodeXmlText(s) {
-  return s.replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, "$1").replace(/&#x([0-9a-f]+);/gi, (_, hex) => String.fromCodePoint(parseInt(hex, 16))).replace(/&#(\d+);/g, (_, dec) => String.fromCodePoint(Number(dec))).replace(/&lt;/g, "<").replace(/&gt;/g, ">").replace(/&quot;/g, '"').replace(/&apos;/g, "'").replace(/&amp;/g, "&");
-}
-function parseSitemapLocs(xml) {
-  return [...xml.matchAll(/<(?:[\w-]+:)?loc\b[^>]*>([\s\S]*?)<\/(?:[\w-]+:)?loc>/gi)].map((m) => decodeXmlText(m[1] ?? "").trim()).filter(Boolean);
-}
-function isSafeNestedSitemap(child, origin) {
-  let url;
-  try {
-    url = new URL(child, origin);
-  } catch {
-    return false;
-  }
-  if (url.protocol !== "https:" && url.protocol !== "http:") return false;
-  if (url.origin !== origin) return false;
-  return !isPrivateOrLoopbackHost(url.hostname);
-}
-function isSitemapIndex(xml) {
-  return /<(?:[\w-]+:)?sitemapindex[\s>]/i.test(xml);
-}
-var USER_AGENT = "ReddoorAudit/1.0 (+https://reddoorla.com/; operator-run site audit)";
-var ASSET_EXT = /\.(pdf|jpe?g|png|gif|webp|avif|svg|zip|mp4|mov|css|js|xml|json)$/i;
-var MAX_RESPONSE_BYTES = 5e6;
-var RENDER_SETTLE_MS = 1500;
-var ResponseTooLargeError = class extends Error {
-  constructor(url) {
-    super(`response exceeds the ${MAX_RESPONSE_BYTES}-byte limit: ${url}`);
-    this.name = "ResponseTooLargeError";
-  }
-};
-var sleep = (ms) => new Promise((r) => setTimeout(r, ms));
-async function pacedEach(items, delayMs, fn, sleepFn = sleep) {
-  for (let i = 0; i < items.length; i++) {
-    if (i > 0 && delayMs > 0) await sleepFn(delayMs);
-    await fn(items[i]);
-  }
-}
-async function optional(deps, url) {
-  try {
-    const res = await deps.fetchUrl(url);
-    return res.status >= 400 ? { res: null, error: null } : { res, error: null };
-  } catch (err) {
-    if (err instanceof ResponseTooLargeError) return { res: null, error: null };
-    return { res: null, error: err instanceof Error ? err.message : String(err) };
-  }
-}
-async function optionalRobots(deps, url) {
-  const first = await optional(deps, url);
-  return first.error === null ? first : optional(deps, url);
-}
-function textSidecar(res) {
-  if (!res) return null;
-  const body = res.body.trim();
-  if (!body || body.startsWith("<")) return null;
-  return res.body;
-}
-function headerValue(headers, name) {
-  for (const [k, v] of Object.entries(headers)) {
-    if (k.toLowerCase() === name) return v;
-  }
-  return null;
-}
-function samePageKey(u) {
-  const path = u.pathname.replace(/\/+$/, "") || "/";
-  return `${u.origin.toLowerCase()}${path}${u.search}`;
-}
-function normalizeCandidates(urls, origin, max) {
-  const out = [];
-  const seen = /* @__PURE__ */ new Set();
-  for (const raw of urls) {
-    let u;
-    try {
-      u = new URL(raw);
-    } catch {
-      continue;
-    }
-    if (u.origin !== origin) continue;
-    if (ASSET_EXT.test(u.pathname)) continue;
-    if (isInfraPath(u.toString())) continue;
-    u.hash = "";
-    const key = samePageKey(u);
-    if (seen.has(key)) continue;
-    seen.add(key);
-    out.push(u.toString());
-    if (out.length >= max) break;
-  }
-  return out;
-}
-async function fetchSidecars(origin, deps) {
-  const robots = await optionalRobots(deps, `${origin}/robots.txt`);
-  const robotsTxt = textSidecar(robots.res);
-  const agentAccess = evaluateAgentAccess(
-    robotsTxt && /user-agent/i.test(robotsTxt) ? robotsTxt : null
-  );
-  const llms = await optional(deps, `${origin}/llms.txt`);
-  const llmsRaw = textSidecar(llms.res);
-  const llmsTxt = llmsRaw ? {
-    present: true,
-    firstLine: llmsRaw.split(/\r?\n/).find((l) => l.trim())?.trim() ?? null
-  } : { present: false, firstLine: null };
-  const sitemap = await optional(deps, `${origin}/sitemap.xml`);
-  let sitemapUrls = [];
-  let sitemapPresent = false;
-  if (sitemap.res && /<(urlset|sitemapindex)[\s>]/i.test(sitemap.res.body)) {
-    sitemapPresent = true;
-    if (isSitemapIndex(sitemap.res.body)) {
-      const children = parseSitemapLocs(sitemap.res.body).filter((child) => isSafeNestedSitemap(child, origin)).slice(0, 3);
-      for (const child of children) {
-        const nested = await optional(deps, child);
-        if (nested.res) sitemapUrls.push(...parseSitemapLocs(nested.res.body));
-      }
-    } else {
-      sitemapUrls = parseSitemapLocs(sitemap.res.body);
-    }
-  }
-  return {
-    robotsTxt,
-    agentAccess,
-    llmsTxt,
-    sitemapUrls,
-    sitemapPresent,
-    sidecarErrors: { robots: robots.error, llms: llms.error, sitemap: sitemap.error }
-  };
-}
-async function crawlSite(rawUrl, deps) {
-  const start = new URL(rawUrl);
-  start.hash = "";
-  start.username = "";
-  start.password = "";
-  if (isPrivateOrLoopbackHost(start.hostname)) {
-    throw Object.assign(
-      new Error(
-        `${start.toString()} is a private address (${start.hostname}) \u2014 refusing to crawl it.`
-      ),
-      { exitCode: 1 }
-    );
-  }
-  let home;
-  try {
-    home = await deps.fetchUrl(start.toString());
-  } catch (err) {
-    throw Object.assign(
-      new Error(
-        `Could not reach ${start.toString()}: ${err instanceof Error ? err.message : String(err)}`
-      ),
-      { exitCode: 1 }
-    );
-  }
-  if (home.status >= 400) {
-    throw Object.assign(
-      new Error(`${start.toString()} returned HTTP ${home.status} \u2014 nothing to audit.`),
-      { exitCode: 1 }
-    );
-  }
-  let resolved;
-  try {
-    resolved = new URL(home.url ?? start.toString());
-  } catch {
-    resolved = start;
-  }
-  if (isPrivateOrLoopbackHost(resolved.hostname)) {
-    throw Object.assign(
-      new Error(
-        `${start.toString()} redirected to a private address (${resolved.hostname}) \u2014 refusing to crawl it.`
-      ),
-      { exitCode: 1 }
-    );
-  }
-  const resolvedUrl = resolved.toString();
-  const origin = resolved.origin;
-  const sidecars = await fetchSidecars(origin, deps);
-  const pageUrls = normalizeCandidates(
-    [resolvedUrl, ...sidecars.sitemapUrls, ...sameOriginLinks(home.body, resolvedUrl)],
-    origin,
-    deps.maxPages
-  );
-  const rendered = await deps.renderPages(pageUrls).catch(() => /* @__PURE__ */ new Map());
-  const pages = [];
-  for (const url of pageUrls) {
-    let res = null;
-    let error = null;
-    if (url === resolvedUrl) {
-      res = home;
-    } else {
-      if (deps.delayMs > 0) await sleep(deps.delayMs);
-      try {
-        res = await deps.fetchUrl(url);
-      } catch (err) {
-        error = err instanceof Error ? err.message : String(err);
-      }
-    }
-    const renderedHtml = rendered.get(url) ?? null;
-    const contentType = res ? headerValue(res.headers, "content-type") : null;
-    const notHtmlReason = contentType !== null && !contentType.toLowerCase().includes("html") ? `not HTML (${contentType})` : null;
-    const usable = res !== null && res.status < 400 && notHtmlReason === null;
-    pages.push({
-      url,
-      status: res?.status ?? null,
-      raw: usable ? extractPage(res.body) : null,
-      // Gated on `usable` for the same reason `raw` is. A browser paints
-      // something for a 404 — Cloudflare's email-protection interstitial is the
-      // case that bit us — and a captured paint is not evidence that the URL is
-      // a page of this website. Leaving it non-null let every cross-page check
-      // that asked "is there an extract?" admit a page the server refused, and
-      // that one URL became the only dead end and the only off-template page
-      // found in the entire stored corpus.
-      rendered: usable && renderedHtml ? extractPage(renderedHtml) : null,
-      error: error ?? (res && res.status >= 400 ? `HTTP ${res.status}` : notHtmlReason)
-    });
-  }
-  const homeHeaders = {};
-  for (const [k, v] of Object.entries(home.headers)) homeHeaders[k.toLowerCase()] = v;
-  return {
-    origin,
-    robotsTxt: sidecars.robotsTxt,
-    agentAccess: sidecars.agentAccess,
-    sitemap: { present: sidecars.sitemapPresent, urlCount: sidecars.sitemapUrls.length },
-    llmsTxt: sidecars.llmsTxt,
-    sidecarErrors: sidecars.sidecarErrors,
-    homeHeaders,
-    pages
-  };
-}
-async function readCapped(res, url) {
-  const declared = res.headers.get("content-length");
-  if (declared !== null && Number(declared) > MAX_RESPONSE_BYTES) {
-    throw new ResponseTooLargeError(url);
-  }
-  if (!res.body) return "";
-  const reader = res.body.getReader();
-  const chunks = [];
-  let total = 0;
-  for (; ; ) {
-    const { done, value } = await reader.read();
-    if (done) break;
-    if (!value) continue;
-    total += value.byteLength;
-    if (total > MAX_RESPONSE_BYTES) {
-      await reader.cancel();
-      throw new ResponseTooLargeError(url);
-    }
-    chunks.push(value);
-  }
-  const merged = new Uint8Array(total);
-  let offset = 0;
-  for (const chunk of chunks) {
-    merged.set(chunk, offset);
-    offset += chunk.byteLength;
-  }
-  return new TextDecoder("utf-8").decode(merged);
-}
-function defaultCrawlDeps(over = {}) {
-  const maxPages = over.maxPages ?? 20;
-  const delayMs = over.delayMs ?? 500;
-  return {
-    async fetchUrl(url) {
-      const res = await fetch(url, {
-        headers: {
-          "user-agent": USER_AGENT,
-          accept: "text/html,application/xhtml+xml,text/plain,*/*"
-        },
-        redirect: "follow",
-        signal: AbortSignal.timeout(2e4)
-      });
-      const headers = {};
-      res.headers.forEach((v, k) => {
-        headers[k] = v;
-      });
-      return { status: res.status, body: await readCapped(res, url), headers, url: res.url };
-    },
-    async renderPages(urls) {
-      const { chromium } = await import("@playwright/test");
-      const out = /* @__PURE__ */ new Map();
-      const browser = await chromium.launch();
-      try {
-        const ctx = await browser.newContext({ userAgent: USER_AGENT });
-        const page = await ctx.newPage();
-        await pacedEach(urls, delayMs, async (url) => {
-          try {
-            await page.goto(url, { waitUntil: "load", timeout: 2e4 });
-            await page.waitForTimeout(RENDER_SETTLE_MS);
-            out.set(url, await page.content());
-          } catch {
-          }
-        });
-      } finally {
-        await browser.close();
-      }
-      return out;
-    },
-    maxPages,
-    delayMs,
-    ...over
-  };
-}
-
 // src/prospect/consistency.ts
 var PHONE_IN_TEXT = /(?<!\d)(?:\+?1[\s.-]?)?\(?\d{3}\)?[\s.-]?\d{3}[\s.-]?\d{4}(?!\d)/g;
 var COPYRIGHT_YEAR = /(?:©|&copy;|copyright)([^\d<>]{0,30}?)(?:(\d{4})\s*[-–—]\s*)?(\d{4})/gi;
@@ -776,114 +102,6 @@ function checkConsistency(pages) {
   };
 }
 
-// src/prospect/journey.ts
-function canonicalizeUrl(raw) {
-  try {
-    const u = new URL(raw);
-    if (u.protocol !== "http:" && u.protocol !== "https:") return null;
-    const path = u.pathname.replace(/\/+$/, "") || "/";
-    return `${u.hostname.replace(/^www\./i, "").toLowerCase()}${path}`;
-  } catch {
-    return null;
-  }
-}
-function resolveNavigable(href, pageUrl) {
-  const trimmed = href.trim();
-  if (!trimmed || trimmed.startsWith("#")) return null;
-  if (/^(tel:|mailto:|javascript:|sms:|data:)/i.test(trimmed)) return null;
-  try {
-    return new URL(trimmed, pageUrl).toString();
-  } catch {
-    return null;
-  }
-}
-var TEL_HREF = /^tel:(.+)$/i;
-var MAILTO_HREF = /^mailto:([^?]+)/i;
-function affordancesOn(page, view) {
-  const extract = view ?? page.rendered ?? page.raw;
-  if (!extract) return [];
-  const found = [];
-  for (const anchor of extract.anchors ?? []) {
-    const tel = TEL_HREF.exec(anchor.href);
-    if (tel?.[1]) {
-      found.push({ kind: "tel", page: page.url, detail: tel[1].trim() });
-      continue;
-    }
-    const mail = MAILTO_HREF.exec(anchor.href);
-    if (mail?.[1]) {
-      found.push({ kind: "mailto", page: page.url, detail: mail[1].trim() });
-    }
-  }
-  for (const form of extract.forms ?? []) {
-    if (form.kind !== "enquiry") continue;
-    found.push({ kind: "form", page: page.url, detail: form.action ?? page.url });
-  }
-  return found;
-}
-function buildJourney(pages) {
-  const usable = usablePages(pages);
-  const nodes = /* @__PURE__ */ new Map();
-  for (const entry of usable.pages) {
-    const key = canonicalizeUrl(entry.page.url);
-    if (key) nodes.set(key, entry);
-  }
-  const affordances = [];
-  const hasContact = /* @__PURE__ */ new Set();
-  for (const [key, entry] of nodes) {
-    const found = affordancesOn(entry.page, entry.extract);
-    affordances.push(...found);
-    if (found.length > 0) hasContact.add(key);
-  }
-  const outgoing = /* @__PURE__ */ new Map();
-  const incoming = /* @__PURE__ */ new Map();
-  for (const [key, entry] of nodes) {
-    const out = /* @__PURE__ */ new Set();
-    for (const anchor of entry.extract.anchors ?? []) {
-      const abs = resolveNavigable(anchor.href, entry.page.url);
-      if (!abs) continue;
-      const target = canonicalizeUrl(abs);
-      if (!target || target === key || !nodes.has(target)) continue;
-      out.add(target);
-      if (!incoming.has(target)) incoming.set(target, /* @__PURE__ */ new Set());
-      incoming.get(target)?.add(key);
-    }
-    outgoing.set(key, out);
-  }
-  const distance = /* @__PURE__ */ new Map();
-  let frontier = [...hasContact];
-  for (const key of frontier) distance.set(key, 0);
-  let depth = 0;
-  while (frontier.length > 0) {
-    depth += 1;
-    const next = [];
-    for (const key of frontier) {
-      for (const source of incoming.get(key) ?? []) {
-        if (distance.has(source)) continue;
-        distance.set(source, depth);
-        next.push(source);
-      }
-    }
-    frontier = next;
-  }
-  const journeys = [...nodes.entries()].map(([key, entry]) => ({
-    url: entry.page.url,
-    clicksToContact: usable.anchorsMeasured ? distance.get(key) ?? null : null,
-    internalLinks: outgoing.get(key)?.size ?? 0
-  }));
-  const reachable = journeys.map((j) => j.clicksToContact).filter((d) => d !== null);
-  return {
-    affordances,
-    pages: journeys,
-    // Without recorded anchors there is no evidence either way, so there is no
-    // finding — not "every page is a dead end", which is what reading the
-    // absent array as an empty one used to produce.
-    deadEnds: usable.anchorsMeasured ? journeys.filter((j) => j.clicksToContact === null).map((j) => j.url) : [],
-    worstClicksToContact: reachable.length > 0 ? Math.max(...reachable) : null,
-    pagesExamined: journeys.length,
-    anchorsMeasured: usable.anchorsMeasured
-  };
-}
-
 // src/prospect/checks.ts
 var SECURITY_HEADERS = [
   "strict-transport-security",
@@ -2786,7 +2004,7 @@ function summarizeUnverified(probed) {
 function extractOf(page) {
   return page.rendered ?? page.raw;
 }
-function collect2(pages, hrefsOf, sameSiteOnly, origin) {
+function collect(pages, hrefsOf, sameSiteOnly, origin) {
   const found = /* @__PURE__ */ new Map();
   const originKey = canonicalizeUrl(origin)?.split("/")[0] ?? "";
   for (const page of pages) {
@@ -2851,8 +2069,8 @@ async function probeAll(jobs, deps) {
   return out;
 }
 async function checkAssets(pages, origin, deps) {
-  const links = collect2(pages, (e) => (e.anchors ?? []).map((a) => a.href), true, origin);
-  const images = collect2(pages, (e) => e.imageSrcs ?? [], false, origin);
+  const links = collect(pages, (e) => (e.anchors ?? []).map((a) => a.href), true, origin);
+  const images = collect(pages, (e) => e.imageSrcs ?? [], false, origin);
   const linkEntries = [...links.entries()].slice(0, deps.maxLinks);
   const imageEntries = [...images.entries()].slice(0, deps.maxImages);
   const jobs = [
@@ -3197,6 +2415,173 @@ async function checkBasics(crawl, deps) {
   };
 }
 
+// src/prospect/dns.ts
+var bootstrapPromise = null;
+async function rdapBootstrap() {
+  bootstrapPromise ??= (async () => {
+    try {
+      const res = await fetch("https://data.iana.org/rdap/dns.json", {
+        signal: AbortSignal.timeout(1e4)
+      });
+      if (!res.ok) return null;
+      const body = await res.json();
+      const map = /* @__PURE__ */ new Map();
+      for (const [tlds, urls] of body.services ?? []) {
+        const base = urls.find((u) => u.startsWith("https://"));
+        if (!base) continue;
+        for (const tld of tlds) map.set(tld.toLowerCase(), base.endsWith("/") ? base : `${base}/`);
+      }
+      return map.size > 0 ? map : null;
+    } catch {
+      return null;
+    }
+  })();
+  return bootstrapPromise;
+}
+async function rdapBaseFor(domain) {
+  const map = await rdapBootstrap();
+  if (!map) return null;
+  const labels = domain.split(".");
+  for (let i = 1; i < labels.length; i++) {
+    const suffix = labels.slice(i).join(".");
+    const base = map.get(suffix);
+    if (base) return base;
+  }
+  return null;
+}
+function defaultDnsDeps() {
+  return {
+    async resolveTxt(name) {
+      const { resolveTxt } = await import("dns/promises");
+      return resolveTxt(name);
+    },
+    async resolveMx(name) {
+      const { resolveMx } = await import("dns/promises");
+      return resolveMx(name);
+    },
+    async rdap(domain) {
+      const base = await rdapBaseFor(domain);
+      if (!base) return null;
+      try {
+        const res = await fetch(`${base}domain/${encodeURIComponent(domain)}`, {
+          headers: { accept: "application/rdap+json" },
+          redirect: "follow",
+          signal: AbortSignal.timeout(1e4)
+        });
+        if (!res.ok) return null;
+        return await res.json();
+      } catch {
+        return null;
+      }
+    }
+  };
+}
+var TWO_LABEL_SUFFIXES = /* @__PURE__ */ new Set([
+  "co.uk",
+  "org.uk",
+  "me.uk",
+  "ac.uk",
+  "gov.uk",
+  "com.au",
+  "net.au",
+  "org.au",
+  "co.nz",
+  "co.za",
+  "com.br",
+  "co.jp",
+  "co.in",
+  "com.mx",
+  "com.sg"
+]);
+function registrableDomain(hostname) {
+  const host = hostname.toLowerCase().replace(/\.$/, "");
+  if (!host || !host.includes(".")) return null;
+  const parts = host.split(".");
+  if (parts.length < 2) return null;
+  const lastTwo = parts.slice(-2).join(".");
+  if (TWO_LABEL_SUFFIXES.has(lastTwo) && parts.length >= 3) return parts.slice(-3).join(".");
+  return lastTwo;
+}
+var joinTxt = (chunks) => chunks.map((c) => c.join(""));
+async function txtStartingWith(deps, name, prefix) {
+  try {
+    const records = joinTxt(await deps.resolveTxt(name));
+    return records.find((r) => prefix.test(r.trim())) ?? null;
+  } catch (err) {
+    const code = err.code;
+    if (code === "ENOTFOUND" || code === "ENODATA") return null;
+    return void 0;
+  }
+}
+function expiryFrom(rdap) {
+  if (!rdap || typeof rdap !== "object") return void 0;
+  const events = rdap.events;
+  if (!Array.isArray(events)) return void 0;
+  for (const e of events) {
+    if (!e || typeof e !== "object") continue;
+    const action = String(e.eventAction ?? "").toLowerCase();
+    if (!/expir/.test(action)) continue;
+    const date = e.eventDate;
+    if (typeof date === "string" && !Number.isNaN(Date.parse(date))) return date;
+  }
+  return void 0;
+}
+async function lookupDns(origin, contactEmails, deps) {
+  let domain = null;
+  try {
+    domain = registrableDomain(new URL(origin).hostname);
+  } catch {
+    domain = null;
+  }
+  if (!domain) {
+    return {
+      measured: false,
+      domain: null,
+      spf: void 0,
+      dmarc: void 0,
+      mx: void 0,
+      contactMx: void 0,
+      expiresAt: void 0
+    };
+  }
+  const [spf, dmarc] = await Promise.all([
+    txtStartingWith(deps, domain, /^v=spf1\b/i),
+    txtStartingWith(deps, `_dmarc.${domain}`, /^v=DMARC1\b/i)
+  ]);
+  let mx;
+  try {
+    mx = (await deps.resolveMx(domain)).sort((a, b) => a.priority - b.priority).map((r) => r.exchange.toLowerCase());
+  } catch (err) {
+    const code = err.code;
+    mx = code === "ENOTFOUND" || code === "ENODATA" ? [] : void 0;
+  }
+  const otherDomains = [
+    ...new Set(
+      contactEmails.map((e) => registrableDomain(e.split("@")[1] ?? "")).filter((d) => d !== null && d !== domain)
+    )
+  ];
+  let contactMx = null;
+  if (otherDomains.length > 0) {
+    const target = otherDomains[0];
+    try {
+      const records = await deps.resolveMx(target);
+      contactMx = { domain: target, hasMx: records.length > 0 };
+    } catch (err) {
+      const code = err.code;
+      contactMx = code === "ENOTFOUND" || code === "ENODATA" ? { domain: target, hasMx: false } : void 0;
+    }
+  }
+  return {
+    measured: true,
+    domain,
+    spf,
+    dmarc,
+    mx,
+    contactMx,
+    expiresAt: expiryFrom(await deps.rdap(domain))
+  };
+}
+
 // src/prospect/measured-fixes.ts
 var plural = (n, one, many) => `${n} ${n === 1 ? one : many}`;
 function measuredFixes(input) {
@@ -3397,6 +2782,16 @@ async function runProspectAudit(url, opts, deps = {}) {
       probeAs: deps.basics?.probeAs ?? (deps.basics?.probe ? (url2) => deps.basics.probe(url2) : defaultBasicsProbe)
     })
   );
+  const stack = await stage(
+    "stack",
+    deps,
+    async () => readStack(crawlData)
+  );
+  const accessibility = await stage(
+    "accessibility",
+    deps,
+    async () => summarizeAccessibility(crawlData.pages)
+  );
   const lighthouse = await stage(
     "lighthouse",
     deps,
@@ -3422,6 +2817,31 @@ async function runProspectAudit(url, opts, deps = {}) {
     )
   ) : { ok: false, error: ANALYZE_SKIPPED };
   const businessName = opts.business?.trim() || (analyze.ok ? analyze.data.businessName : "") || null;
+  const dns = await stage(
+    "dns",
+    deps,
+    async () => lookupDns(
+      crawlData.origin,
+      checks.ok ? (checks.data.consistency?.emails ?? []).map((e) => e.normalized) : [],
+      deps.dns ?? defaultDnsDeps()
+    )
+  );
+  const http = await stage(
+    "http",
+    deps,
+    async () => probeHttp(crawlData, { ...defaultHttpProbeDeps(USER_AGENT), ...deps.http })
+  );
+  const siteChecks = await stage(
+    "siteChecks",
+    deps,
+    async () => runSiteChecks(
+      crawlData,
+      checks.ok ? checks.data : null,
+      businessName,
+      dns.ok ? dns.data : null,
+      http.ok ? http.data : null
+    )
+  );
   const probeOpts = {
     ...deps.probeDelayMs !== void 0 ? { delayMs: deps.probeDelayMs } : {},
     ...deps.probeSleep !== void 0 ? { sleep: deps.probeSleep } : {}
@@ -3511,6 +2931,11 @@ async function runProspectAudit(url, opts, deps = {}) {
     probes,
     assets,
     basics,
+    stack,
+    siteChecks,
+    accessibility,
+    dns,
+    http,
     goalFit,
     accuracy
   };
@@ -3531,4 +2956,4 @@ export {
   mergeFixes,
   runProspectAudit
 };
-//# sourceMappingURL=chunk-BJQCIJOY.js.map
+//# sourceMappingURL=chunk-REJCSA4H.js.map