jd-intel 0.2.0 → 0.3.0

package/README.md

@@ -196,6 +196,7 @@ No custom parsing per company.
 | Ashby | Shipped | Growing fast with startups |
 | Lever | Shipped | Common at mid-stage companies |
 | SmartRecruiters | Shipped | Enterprise and mid-market |
+| TeamTailor | Shipped | European startups and scale-ups |
 | BambooHR | Planned | Mid-market companies |
 | Workday | Planned | Large enterprises |
 
@@ -222,14 +223,14 @@ All filters AND together. Deep dive on patterns and gotchas: [docs/filters.md](d
 
 **Shipped**
 - Library, CLI, and MCP server (three surfaces of one toolkit)
-- Greenhouse, Ashby, Lever, SmartRecruiters adapters
+- Greenhouse, Ashby, Lever, SmartRecruiters, TeamTailor adapters
 - Title, topic, location, and date filters
 - Salary extraction from JD text
-- Verified company registry (100+ companies)
+- Verified company registry (145+ companies)
 
 **Next**
-- TeamTailor adapter (European startup coverage)
 - Anthropic MCP marketplace submission
+- BambooHR and Workable adapters
 
 **Planned**
 - BambooHR and Workable adapters

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jd-intel",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Fetch and normalize job descriptions across every major ATS (Greenhouse, Lever, Ashby) — for your AI assistant, no copy-paste.",
   "type": "module",
   "main": "src/index.js",

package/registry/teamtailor.json

@@ -0,0 +1,17 @@
+[
+  {"slug": "polestar",  "name": "Polestar",  "sector": "automotive / ev"},
+  {"slug": "quinyx",    "name": "Quinyx",    "sector": "workforce management"},
+  {"slug": "qliro",     "name": "Qliro",     "sector": "payments"},
+  {"slug": "tibber",    "name": "Tibber",    "sector": "energy tech"},
+  {"slug": "funnel",    "name": "Funnel",    "sector": "marketing data"},
+  {"slug": "anyfin",    "name": "Anyfin",    "sector": "fintech"},
+  {"slug": "hedvig",    "name": "Hedvig",    "sector": "insurtech"},
+  {"slug": "juni",      "name": "Juni",      "sector": "fintech"},
+  {"slug": "bambuser",  "name": "Bambuser",  "sector": "live video commerce"},
+  {"slug": "karma",     "name": "Karma",     "sector": "sustainability"},
+  {"slug": "mate",      "name": "Mate",      "sector": "e-mobility"},
+  {"slug": "billogram", "name": "Billogram", "sector": "fintech / billing"},
+  {"slug": "detectify", "name": "Detectify", "sector": "security"},
+  {"slug": "storytel",  "name": "Storytel",  "sector": "audiobooks"},
+  {"slug": "oneflow",   "name": "Oneflow",   "sector": "contract management"}
+]

package/src/adapters/index.js

@@ -2,12 +2,14 @@ export { fetchGreenhouse, hasGreenhouse } from './greenhouse.js';
 export { fetchLever, hasLever } from './lever.js';
 export { fetchAshby, hasAshby } from './ashby.js';
 export { fetchSmartrecruiters, hasSmartrecruiters } from './smartrecruiters.js';
+export { fetchTeamtailor, hasTeamtailor } from './teamtailor.js';
 
 export const ADAPTERS = {
   greenhouse: { fetch: (...args) => import('./greenhouse.js').then(m => m.fetchGreenhouse(...args)), has: (...args) => import('./greenhouse.js').then(m => m.hasGreenhouse(...args)) },
   lever: { fetch: (...args) => import('./lever.js').then(m => m.fetchLever(...args)), has: (...args) => import('./lever.js').then(m => m.hasLever(...args)) },
   ashby: { fetch: (...args) => import('./ashby.js').then(m => m.fetchAshby(...args)), has: (...args) => import('./ashby.js').then(m => m.hasAshby(...args)) },
   smartrecruiters: { fetch: (...args) => import('./smartrecruiters.js').then(m => m.fetchSmartrecruiters(...args)), has: (...args) => import('./smartrecruiters.js').then(m => m.hasSmartrecruiters(...args)) },
+  teamtailor: { fetch: (...args) => import('./teamtailor.js').then(m => m.fetchTeamtailor(...args)), has: (...args) => import('./teamtailor.js').then(m => m.hasTeamtailor(...args)) },
 };
 
 export const ATS_NAMES = Object.keys(ADAPTERS);

package/src/adapters/teamtailor.js

@@ -0,0 +1,116 @@
+import { normalize, stripHtml } from '../normalizer.js';
+
+/**
+ * Fetch jobs from a TeamTailor career site via its public RSS feed.
+ *
+ * Why RSS, not the official API:
+ *   TeamTailor's REST API (api.teamtailor.com/v1/jobs) requires a
+ *   per-company API key — 401 without it. Unusable for a public
+ *   registry tool that probes arbitrary companies. The public,
+ *   unauthenticated path is the career site's jobs.rss feed, which
+ *   carries the full HTML job description (jd-intel's whole point).
+ *
+ * Slug maps to `{slug}.teamtailor.com`. The /jobs.rss path serves
+ * directly on that subdomain even when the site root 301-redirects
+ * to a custom domain (e.g. jobs.tibber.com).
+ *
+ * RSS quirk: descriptions are HTML-entity-encoded inside the XML
+ * (`<p>...`). We decode that outer layer to real HTML, then
+ * hand it to stripHtml() which strips tags and resolves the inner
+ * entities. Decode order matters — `&` resolves LAST so that
+ * double-encoded sequences (`&`) collapse correctly.
+ *
+ * @param {string} slug - TeamTailor career-site slug (e.g., 'tibber')
+ * @returns {Promise<Array>} Normalized job objects
+ */
+export async function fetchTeamtailor(slug) {
+  const url = `https://${slug}.teamtailor.com/jobs.rss`;
+  const resp = await fetch(url, { redirect: 'follow' });
+
+  if (!resp.ok) {
+    if (resp.status === 404) return []; // No TeamTailor site for this slug
+    throw new Error(`TeamTailor RSS error for ${slug}: ${resp.status}`);
+  }
+
+  const xml = await resp.text();
+
+  const company = (
+    xml.match(/<channel>[\s\S]*?<title>([\s\S]*?)<\/title>/)?.[1] || slug
+  ).trim();
+
+  const items = [...xml.matchAll(/<item>([\s\S]*?)<\/item>/g)].map(m => m[1]);
+
+  return items.map(item => {
+    const pick = (tag) => {
+      const m = item.match(new RegExp(`<${tag}[^>]*>([\\s\\S]*?)</${tag}>`));
+      return m ? m[1].trim() : '';
+    };
+
+    const title = decodeEntities(pick('title'));
+    const link = pick('link');
+    const guid = pick('guid');
+    const pubDateRaw = pick('pubDate');
+    const department = decodeEntities(pick('tt:department'));
+    const city = decodeEntities(pick('tt:city'));
+    const country = decodeEntities(pick('tt:country'));
+    const remoteStatus = decodeEntities(pick('remoteStatus'));
+
+    let location = [city, country].filter(Boolean).join(', ');
+    if (/remote/i.test(remoteStatus)) {
+      location = location ? `Remote - ${location}` : 'Remote';
+    }
+
+    let postedAt = null;
+    if (pubDateRaw) {
+      const d = new Date(pubDateRaw);
+      if (!Number.isNaN(d.getTime())) postedAt = d.toISOString();
+    }
+
+    return normalize({
+      companySlug: slug,
+      company,
+      title,
+      department,
+      location,
+      description: stripHtml(decodeEntities(pick('description'))),
+      url: link,
+      postedAt,
+      salary: null, // No structured salary; normalizer parses from text
+      metadata: {
+        teamtailorId: guid,
+        remoteStatus,
+      },
+    }, 'teamtailor');
+  });
+}
+
+/**
+ * Decode the RSS entity/CDATA layer to real HTML.
+ * `&amp;` is intentionally resolved LAST.
+ */
+function decodeEntities(s) {
+  if (!s) return '';
+  return s
+    .replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, '$1')
+    .replace(/&lt;/g, '<')
+    .replace(/&gt;/g, '>')
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&apos;/g, "'")
+    .replace(/&amp;/g, '&');
+}
+
+/**
+ * Check if a company has a TeamTailor career site.
+ */
+export async function hasTeamtailor(slug) {
+  try {
+    const resp = await fetch(`https://${slug}.teamtailor.com/jobs.rss`, {
+      method: 'HEAD',
+      redirect: 'follow',
+    });
+    return resp.ok;
+  } catch {
+    return false;
+  }
+}