jd-intel 0.3.1 → 0.4.0

package/README.md

@@ -34,6 +34,17 @@ Done.
 
 ---
 
+## Why not just scrape?
+
+Because scraping breaks where jd-intel doesn't:
+
+- **Full JDs when browsing fails.** SPA-rendered boards, slow loads, auth walls, and geo-restrictions block a browser. They don't block a public API call.
+- **Structured data, not HTML soup.** Salary, location type, department, and clean markdown, normalized across every ATS.
+- **No keys, no browser.** Public APIs only. Runs anywhere your AI does.
+- **One schema, every platform.** Greenhouse, Lever, Ashby, SmartRecruiters, TeamTailor, Recruitee return the same shape.
+
+---
+
 ## What you can do with it
 
 - Look up open roles at any company directly from your AI, no copy-paste
@@ -197,8 +208,9 @@ No custom parsing per company.
 | 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 |
+| Recruitee | Shipped | Dutch / EU SMBs and scale-ups |
+| Personio | Planned | German / EU mid-market |
+| Workday | Planned | Large enterprises (scoped scraper) |
 
 Adding a new ATS is a single adapter file. See [Contributing](#contributing).
 
@@ -223,17 +235,17 @@ 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, TeamTailor adapters
+- Greenhouse, Ashby, Lever, SmartRecruiters, TeamTailor, Recruitee adapters
 - Title, topic, location, and date filters
 - Salary extraction from JD text
-- Verified company registry (145+ companies)
+- Verified company registry (155+ companies)
 
 **Next**
+- Personio adapter (German / EU mid-market)
 - Anthropic MCP marketplace submission
-- BambooHR and Workable adapters
 
 **Planned**
-- BambooHR and Workable adapters
+- Workable adapter (parked — needs SPA shortcode resolution)
 - Workday support (scoped scraper — large enterprise universe)
 - Temporal tracking (when roles open, close, reopen)
 - Change detection

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jd-intel",
-  "version": "0.3.1",
+  "version": "0.4.0",
   "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/recruitee.json

@@ -0,0 +1,13 @@
+[
+  {"slug": "incentro",   "name": "Incentro",   "sector": "it consultancy"},
+  {"slug": "channable",  "name": "Channable",  "sector": "ecommerce / feed management"},
+  {"slug": "vandebron",  "name": "Vandebron",  "sector": "energy"},
+  {"slug": "effectory",  "name": "Effectory",  "sector": "hr tech"},
+  {"slug": "nmbrs",      "name": "Nmbrs",      "sector": "hr / payroll"},
+  {"slug": "shypple",    "name": "Shypple",    "sector": "logistics / freight"},
+  {"slug": "floryn",     "name": "Floryn",     "sector": "fintech / financing"},
+  {"slug": "bridgefund", "name": "BridgeFund", "sector": "fintech / sme lending"},
+  {"slug": "sendcloud",  "name": "Sendcloud",  "sector": "shipping saas"},
+  {"slug": "brenger",    "name": "Brenger",    "sector": "logistics / delivery"},
+  {"slug": "youwe",      "name": "Youwe",      "sector": "digital commerce agency"}
+]

package/src/adapters/index.js

@@ -3,6 +3,7 @@ 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 { fetchRecruitee, hasRecruitee } from './recruitee.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)) },
@@ -10,6 +11,7 @@ export const ADAPTERS = {
   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)) },
+  recruitee: { fetch: (...args) => import('./recruitee.js').then(m => m.fetchRecruitee(...args)), has: (...args) => import('./recruitee.js').then(m => m.hasRecruitee(...args)) },
 };
 
 export const ATS_NAMES = Object.keys(ADAPTERS);

package/src/adapters/recruitee.js

@@ -0,0 +1,69 @@
+import { normalize, stripHtml } from '../normalizer.js';
+
+/**
+ * Fetch jobs from a Recruitee career site.
+ * Public API, no auth required.
+ * Docs: https://docs.recruitee.com/reference/offers
+ *
+ * Single GET returns every offer with the full HTML description
+ * inline — no N+1 (unlike SmartRecruiters), no XML (unlike
+ * TeamTailor/Personio). The simplest adapter shape in the toolkit.
+ *
+ * @param {string} slug - Recruitee company subdomain (e.g., 'vandebron')
+ * @returns {Promise<Array>} Normalized job objects
+ */
+export async function fetchRecruitee(slug) {
+  const url = `https://${slug}.recruitee.com/api/offers/`;
+  const resp = await fetch(url);
+
+  if (!resp.ok) {
+    if (resp.status === 404) return []; // No Recruitee site for this slug
+    throw new Error(`Recruitee API error for ${slug}: ${resp.status}`);
+  }
+
+  const data = await resp.json();
+  const offers = data.offers || [];
+
+  return offers.map(offer => {
+    const place = [offer.city, offer.country].filter(Boolean).join(', ');
+    let location = place;
+    if (offer.remote) location = place ? `Remote - ${place}` : 'Remote';
+
+    let postedAt = null;
+    if (offer.created_at) {
+      // Recruitee returns "2026-05-13 07:38:11 UTC"; coerce to ISO.
+      const iso = offer.created_at.replace(' UTC', 'Z').replace(' ', 'T');
+      const d = new Date(iso);
+      if (!Number.isNaN(d.getTime())) postedAt = d.toISOString();
+    }
+
+    return normalize({
+      companySlug: slug,
+      company: offer.company_name || slug,
+      title: offer.title || '',
+      department: offer.department || '',
+      location,
+      description: stripHtml(offer.description || ''),
+      url: offer.careers_url || offer.careers_apply_url || '',
+      postedAt,
+      salary: null, // No structured salary; normalizer parses from text
+      metadata: {
+        recruiteeId: offer.guid || offer.id,
+        employmentType: offer.employment_type_code || '',
+        category: offer.category_code || '',
+      },
+    }, 'recruitee');
+  });
+}
+
+/**
+ * Check if a company has a Recruitee career site.
+ */
+export async function hasRecruitee(slug) {
+  try {
+    const resp = await fetch(`https://${slug}.recruitee.com/api/offers/`);
+    return resp.ok;
+  } catch {
+    return false;
+  }
+}

package/src/normalizer.js

@@ -3,8 +3,11 @@ import { createHash } from 'node:crypto';
 /**
  * Generate a stable ID for a job posting.
  */
-export function jobId(company, title, ats) {
-  const raw = `${company}|${title}|${ats}`.toLowerCase().trim();
+export function jobId(company, title, ats, location = '') {
+  // Location is part of identity: the same role posted in multiple
+  // offices is distinct requisitions with distinct URLs. Omitting it
+  // collapsed multi-office postings to one id (see issue #17).
+  const raw = `${company}|${title}|${ats}|${location}`.toLowerCase().trim();
   return createHash('md5').update(raw).digest('hex').substring(0, 12);
 }
 
@@ -14,7 +17,7 @@ export function jobId(company, title, ats) {
 export function normalize(raw, ats) {
   const now = new Date().toISOString();
   return {
-    id: jobId(raw.company || raw.companySlug, raw.title, ats),
+    id: jobId(raw.company || raw.companySlug, raw.title, ats, raw.location || ''),
     company: raw.company || raw.companySlug || '',
     companySlug: raw.companySlug || '',
     ats,