Career Site Jobs API
Pricing
from $1.50 / 1,000 job results
All open jobs from company career sites on Greenhouse, Lever, Ashby, Workable, SmartRecruiters and Recruitee in one normalized format: title, location, remote, salary, posted date, apply URL, description. Auto-detects the ATS. Fast, no proxies.
{ "$schema": "https://apify.com/schemas/v1/actor.ide.json", "actorSpecification": 1, "name": "career-site-jobs-api", "title": "Career Site Jobs API (Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee)", "description": "Get every open job from company career sites on 6 major ATS platforms in one normalized format: title, location, remote flag, salary, posted date, apply URL and full description. Auto-detects the ATS. Fast, no browser, no proxies.", "version": "1.0", "buildTag": "latest", "input": "./input_schema.json", "storages": { "dataset": "./dataset_schema.json" }, "dockerfile": "../Dockerfile", "readme": "../README.md", "output": "./output_schema.json"}{ "$schema": "https://apify.com/schemas/v1/dataset.ide.json", "actorSpecification": 1, "fields": { "type": "object", "properties": { "source": { "type": "string" }, "companySlug": { "type": "string" }, "companyName": { "type": [ "string", "null" ] }, "jobId": { "type": [ "string", "null" ] }, "title": { "type": [ "string", "null" ] }, "department": { "type": [ "string", "null" ] }, "team": { "type": [ "string", "null" ] }, "location": { "type": [ "string", "null" ] }, "locations": { "type": "array", "items": { "type": "string" } }, "country": { "type": [ "string", "null" ] }, "isRemote": { "type": "boolean" }, "workplaceType": { "type": [ "string", "null" ] }, "employmentType": { "type": [ "string", "null" ] }, "postedAt": { "type": [ "string", "null" ] }, "updatedAt": { "type": [ "string", "null" ] }, "jobUrl": { "type": [ "string", "null" ] }, "applyUrl": { "type": [ "string", "null" ] }, "salaryMin": { "type": [ "number", "null" ] }, "salaryMax": { "type": [ "number", "null" ] }, "salaryCurrency": { "type": [ "string", "null" ] }, "salaryInterval": { "type": [ "string", "null" ] }, "salaryText": { "type": [ "string", "null" ] }, "descriptionText": { "type": [ "string", "null" ] }, "descriptionHtml": { "type": [ "string", "null" ] }, "scrapedAt": { "type": "string" } } }, "views": { "overview": { "title": "Jobs", "transformation": { "fields": [ "companyName", "companySlug", "source", "title", "department", "location", "isRemote", "employmentType", "salaryMin", "salaryMax", "salaryCurrency", "postedAt", "applyUrl" ] }, "display": { "component": "table", "properties": { "applyUrl": { "label": "Apply URL", "format": "link" }, "isRemote": { "label": "Remote", "format": "boolean" }, "postedAt": { "label": "Posted", "format": "date" } } } } }}{ "title": "Career Site Jobs API input", "type": "object", "schemaVersion": 1, "properties": { "companies": { "title": "Companies", "type": "array", "description": "Career page URLs (e.g. https://boards.greenhouse.io/stripe, https://jobs.lever.co/palantir, https://jobs.ashbyhq.com/ramp), 'ats:slug' (e.g. 'workable:huggingface'), or just a company slug (e.g. 'stripe') to auto-detect the ATS.", "editor": "stringList", "prefill": ["https://boards.greenhouse.io/stripe", "https://jobs.ashbyhq.com/ramp", "lever:palantir"] }, "keywords": { "title": "Title keywords (any)", "type": "array", "description": "Keep only jobs whose title/department/team contains at least one of these words (case-insensitive). Leave empty for all jobs.", "editor": "stringList" }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Drop jobs whose title/department/team contains any of these words, e.g. 'intern', 'senior'.", "editor": "stringList" }, "locations": { "title": "Locations (any)", "type": "array", "description": "Keep only jobs whose location contains one of these strings, e.g. 'London', 'Germany', 'remote'.", "editor": "stringList" }, "remoteOnly": { "title": "Remote only", "type": "boolean", "description": "Keep only remote jobs.", "default": false }, "postedWithinDays": { "title": "Posted within (days)", "type": "integer", "description": "Keep only jobs posted in the last N days (0 = no limit). Jobs without a posting date are kept.", "minimum": 0, "default": 0 }, "includeDescription": { "title": "Include full description", "type": "boolean", "description": "Add full job description as plain text and HTML.", "default": true }, "maxJobsPerCompany": { "title": "Max jobs per company", "type": "integer", "description": "0 = unlimited.", "minimum": 0, "default": 0 }, "maxJobsTotal": { "title": "Max jobs total", "type": "integer", "description": "Stop after saving this many jobs (0 = unlimited).", "minimum": 0, "default": 0 }, "maxConcurrency": { "title": "Max concurrency", "type": "integer", "description": "Companies processed in parallel.", "minimum": 1, "maximum": 20, "default": 5 } }, "required": ["companies"]}{ "$schema": "https://apify.com/schemas/v1/output.ide.json", "actorOutputSchemaVersion": 1, "title": "Output schema", "properties": { "results": { "type": "string", "title": "Jobs", "template": "{{links.apiDefaultDatasetUrl}}/items?view=overview" }, "summary": { "type": "string", "title": "Per-company summary", "template": "{{links.apiDefaultKeyValueStoreUrl}}/records/SUMMARY" } }}1import { Actor, log } from 'apify';2// Adapters for public ATS job-board APIs. Each adapter: fetchJobs(slug, opts) -> normalized job[]3// All endpoints below are the official, unauthenticated public job-board feeds that the ATS vendors4// provide for embedding job listings on company career sites.5
6const UA = 'Mozilla/5.0 (compatible; ApifyATSJobs/1.0; +https://apify.com)';7
8class NotFoundError extends Error {}9
10async function getJson(url, { method = 'GET', body, retries = 3 } = {}) {11 let lastErr;12 for (let attempt = 0; attempt < retries; attempt++) {13 try {14 const res = await fetch(url, {15 method,16 headers: {17 'user-agent': UA,18 accept: 'application/json',19 ...(body ? { 'content-type': 'application/json' } : {}),20 },21 body: body ? JSON.stringify(body) : undefined,22 signal: AbortSignal.timeout(30000),23 });24 if (res.status === 404 || res.status === 410) throw new NotFoundError(`${res.status} ${url}`);25 if (res.status === 429 || res.status >= 500) {26 lastErr = new Error(`HTTP ${res.status} ${url}`);27 await new Promise((r) => setTimeout(r, 1500 * (attempt + 1)));28 continue;29 }30 if (!res.ok) throw new NotFoundError(`HTTP ${res.status} ${url}`);31 const text = await res.text();32 try {33 return JSON.parse(text);34 } catch {35 throw new NotFoundError(`Non-JSON response from ${url}`);36 }37 } catch (e) {38 if (e instanceof NotFoundError) throw e;39 lastErr = e;40 await new Promise((r) => setTimeout(r, 1500 * (attempt + 1)));41 }42 }43 throw lastErr;44}45
46const decodeEntities = (s = '') =>47 s48 .replace(/</g, '<')49 .replace(/>/g, '>')50 .replace(/"/g, '"')51 .replace(/'/g, "'")52 .replace(/ /g, ' ')53 .replace(/&/g, '&');54
55const htmlToText = (html = '') =>56 decodeEntities(57 decodeEntities(String(html))58 .replace(/<\s*br\s*\/?>/gi, '\n')59 .replace(/<\/(p|div|li|h[1-6]|tr)>/gi, '\n')60 .replace(/<li[^>]*>/gi, '• ')61 .replace(/<[^>]+>/g, ''),62 )63 .replace(/[ \t]+/g, ' ')64 .replace(/\n\s*\n\s*\n+/g, '\n\n')65 .trim();66
67const REMOTE_RE = /\bremote\b|anywhere|work from home|\bwfh\b|distributed/i;68const iso = (v) => {69 if (v === undefined || v === null || v === '') return null;70 const d = typeof v === 'number' ? new Date(v) : new Date(String(v));71 return Number.isNaN(d.getTime()) ? null : d.toISOString();72};73
74function base(source, companySlug) {75 return {76 source,77 companySlug,78 companyName: null,79 jobId: null,80 title: null,81 department: null,82 team: null,83 location: null,84 locations: [],85 country: null,86 isRemote: false,87 workplaceType: null,88 employmentType: null,89 postedAt: null,90 updatedAt: null,91 jobUrl: null,92 applyUrl: null,93 salaryMin: null,94 salaryMax: null,95 salaryCurrency: null,96 salaryInterval: null,97 salaryText: null,98 descriptionText: null,99 descriptionHtml: null,100 };101}102
103// ---------------- Greenhouse ----------------104async function greenhouse(slug, { includeDescription }) {105 const data = await getJson(106 `https://boards-api.greenhouse.io/v1/boards/${encodeURIComponent(slug)}/jobs?content=${includeDescription ? 'true' : 'false'}`,107 );108 let companyName = null;109 try {110 const b = await getJson(`https://boards-api.greenhouse.io/v1/boards/${encodeURIComponent(slug)}`);111 companyName = b?.name ?? null;112 } catch { /* optional */ }113 return (data.jobs || []).map((j) => {114 const html = j.content ? decodeEntities(j.content) : null;115 const loc = j.location?.name ?? null;116 const offices = (j.offices || []).map((o) => o.location || o.name).filter(Boolean);117 return {118 ...base('greenhouse', slug),119 companyName: j.company_name || companyName,120 jobId: String(j.id),121 title: j.title,122 department: (j.departments || []).map((d) => d.name).join(', ') || null,123 location: loc,124 locations: [...new Set([loc, ...offices].filter(Boolean))],125 isRemote: REMOTE_RE.test(`${loc} ${offices.join(' ')}`),126 postedAt: iso(j.first_published),127 updatedAt: iso(j.updated_at),128 jobUrl: j.absolute_url,129 applyUrl: j.absolute_url,130 descriptionHtml: includeDescription ? html : null,131 descriptionText: includeDescription && html ? htmlToText(html) : null,132 };133 });134}135
136// ---------------- Lever ----------------137async function lever(slug, { includeDescription }) {138 let data;139 try {140 data = await getJson(`https://api.lever.co/v0/postings/${encodeURIComponent(slug)}?mode=json`);141 } catch (e) {142 if (!(e instanceof NotFoundError)) throw e;143 data = await getJson(`https://api.eu.lever.co/v0/postings/${encodeURIComponent(slug)}?mode=json`);144 }145 if (!Array.isArray(data)) throw new NotFoundError('lever: unexpected payload');146 return data.map((j) => {147 const c = j.categories || {};148 const all = c.allLocations?.length ? c.allLocations : c.location ? [c.location] : [];149 const extra = (j.lists || []).map((l) => `<h3>${l.text}</h3><ul>${l.content}</ul>`).join('');150 const html = `${j.description || ''}${extra}${j.additional || ''}`;151 const s = j.salaryRange;152 return {153 ...base('lever', slug),154 jobId: j.id,155 title: j.text,156 department: c.department || null,157 team: c.team || null,158 location: c.location || null,159 locations: all,160 country: j.country || null,161 workplaceType: j.workplaceType || null,162 isRemote: j.workplaceType === 'remote' || REMOTE_RE.test(all.join(' ')),163 employmentType: c.commitment || null,164 postedAt: iso(j.createdAt),165 jobUrl: j.hostedUrl,166 applyUrl: j.applyUrl,167 salaryMin: s?.min ?? null,168 salaryMax: s?.max ?? null,169 salaryCurrency: s?.currency ?? null,170 salaryInterval: s?.interval ?? null,171 salaryText: j.salaryDescriptionPlain || null,172 descriptionHtml: includeDescription ? html : null,173 descriptionText: includeDescription ? htmlToText(html) : null,174 };175 });176}177
178// ---------------- Ashby ----------------179async function ashby(slug, { includeDescription }) {180 const data = await getJson(181 `https://api.ashbyhq.com/posting-api/job-board/${encodeURIComponent(slug)}?includeCompensation=true`,182 );183 if (!data || !Array.isArray(data.jobs)) throw new NotFoundError('ashby: unexpected payload');184 return data.jobs185 .filter((j) => j.isListed !== false)186 .map((j) => {187 const comp = (j.compensation?.summaryComponents || []).find((x) => x.compensationType === 'Salary')188 || j.compensation?.summaryComponents?.[0];189 const secondary = (j.secondaryLocations || []).map((l) => l.location).filter(Boolean);190 const locs = [j.location, ...secondary].filter(Boolean);191 return {192 ...base('ashby', slug),193 jobId: j.id,194 title: j.title,195 department: j.department || null,196 team: j.team || null,197 location: j.location || null,198 locations: locs,199 country: j.address?.postalAddress?.addressCountry || null,200 workplaceType: j.workplaceType || null,201 isRemote: Boolean(j.isRemote) || j.workplaceType === 'Remote' || REMOTE_RE.test(locs.join(' ')),202 employmentType: j.employmentType || null,203 postedAt: iso(j.publishedAt),204 jobUrl: j.jobUrl,205 applyUrl: j.applyUrl,206 salaryMin: comp?.minValue ?? null,207 salaryMax: comp?.maxValue ?? null,208 salaryCurrency: comp?.currencyCode ?? null,209 salaryInterval: comp?.interval ?? null,210 salaryText: j.compensation?.compensationTierSummary || null,211 descriptionHtml: includeDescription ? j.descriptionHtml || null : null,212 descriptionText: includeDescription ? j.descriptionPlain || htmlToText(j.descriptionHtml) : null,213 };214 });215}216
217// ---------------- Workable ----------------218async function workable(slug, { includeDescription }) {219 const data = await getJson(220 `https://apply.workable.com/api/v1/widget/accounts/${encodeURIComponent(slug)}?details=${includeDescription ? 'true' : 'false'}`,221 );222 if (!data || !Array.isArray(data.jobs)) throw new NotFoundError('workable: unexpected payload');223 return data.jobs.map((j) => {224 const locs = (j.locations || [])225 .map((l) => [l.city, l.region, l.country].filter(Boolean).join(', '))226 .filter(Boolean);227 const loc = [j.city, j.state, j.country].filter(Boolean).join(', ') || locs[0] || null;228 const html = j.description || null;229 return {230 ...base('workable', slug),231 companyName: data.name || null,232 jobId: j.shortcode || j.code || null,233 title: j.title,234 department: j.department || null,235 location: loc,236 locations: locs.length ? locs : loc ? [loc] : [],237 country: j.country || null,238 isRemote: Boolean(j.telecommuting) || REMOTE_RE.test(`${loc} ${locs.join(' ')}`),239 employmentType: j.employment_type || null,240 postedAt: iso(j.published_on || j.created_at),241 jobUrl: j.shortlink || j.url,242 applyUrl: j.application_url || j.url,243 descriptionHtml: includeDescription ? html : null,244 descriptionText: includeDescription && html ? htmlToText(html) : null,245 };246 });247}248
249// ---------------- SmartRecruiters ----------------250async function smartrecruiters(slug, { includeDescription, maxJobs, filter }) {251 const out = [];252 let offset = 0;253 const limit = 100;254 for (;;) {255 const data = await getJson(256 `https://api.smartrecruiters.com/v1/companies/${encodeURIComponent(slug)}/postings?limit=${limit}&offset=${offset}`,257 );258 const items = data.content || [];259 if (offset === 0 && !items.length && !data.totalFound) throw new NotFoundError('smartrecruiters: no postings');260 out.push(...items);261 offset += items.length;262 if (!items.length || offset >= (data.totalFound || 0) || (!filter && maxJobs && out.length >= maxJobs) || out.length >= 20000) break;263 }264 const jobs = [];265 for (const j of out) {266 const l = j.location || {};267 const loc = l.fullLocation || [l.city, l.region, l.country].filter(Boolean).join(', ') || null;268 const job = {269 ...base('smartrecruiters', slug),270 companyName: j.company?.name || null,271 jobId: j.id,272 title: j.name,273 department: j.department?.label || null,274 location: loc,275 locations: loc ? [loc] : [],276 country: l.country ? String(l.country).toUpperCase() : null,277 isRemote: Boolean(l.remote) || REMOTE_RE.test(loc || ''),278 workplaceType: l.remote ? 'remote' : l.hybrid ? 'hybrid' : null,279 employmentType: j.typeOfEmployment?.label || null,280 postedAt: iso(j.releasedDate),281 jobUrl: `https://jobs.smartrecruiters.com/${encodeURIComponent(slug)}/${j.id}`,282 applyUrl: `https://jobs.smartrecruiters.com/${encodeURIComponent(slug)}/${j.id}`,283 };284 if (filter && !filter(job)) continue;285 jobs.push(job);286 if (maxJobs && jobs.length >= maxJobs) break;287 }288 if (includeDescription) {289 let idx = 0;290 const worker = async () => {291 while (idx < jobs.length) {292 const job = jobs[idx++];293 const j = { id: job.jobId };294 try {295 const d = await getJson(296 `https://api.smartrecruiters.com/v1/companies/${encodeURIComponent(slug)}/postings/${j.id}`,297 );298 const s = d.jobAd?.sections || {};299 const html = ['companyDescription', 'jobDescription', 'qualifications', 'additionalInformation']300 .map((k) => (s[k]?.text ? `<h3>${s[k].title || ''}</h3>${s[k].text}` : ''))301 .join('');302 job.descriptionHtml = html || null;303 job.descriptionText = html ? htmlToText(html) : null;304 if (d.postingUrl) job.jobUrl = d.postingUrl;305 if (d.applyUrl) job.applyUrl = d.applyUrl;306 } catch { /* keep listing data */ }307 }308 };309 await Promise.all(Array.from({ length: 8 }, worker));310 }311 return jobs;312}313
314// ---------------- Recruitee ----------------315async function recruitee(slug, { includeDescription }) {316 const data = await getJson(`https://${encodeURIComponent(slug)}.recruitee.com/api/offers/`);317 if (!data || !Array.isArray(data.offers)) throw new NotFoundError('recruitee: unexpected payload');318 return data.offers.map((j) => {319 const html = `${j.description || ''}${j.requirements ? `<h3>Requirements</h3>${j.requirements}` : ''}`;320 const loc = j.location || [j.city, j.country].filter(Boolean).join(', ') || null;321 const s = j.salary || {};322 return {323 ...base('recruitee', slug),324 companyName: j.company_name || null,325 jobId: String(j.id),326 title: j.title,327 department: j.department || null,328 location: loc,329 locations: loc ? [loc] : [],330 country: j.country_code || j.country || null,331 isRemote: Boolean(j.remote) || REMOTE_RE.test(loc || ''),332 workplaceType: j.remote ? 'remote' : j.hybrid ? 'hybrid' : j.on_site ? 'on-site' : null,333 employmentType: j.employment_type_code || null,334 postedAt: iso(j.published_at || j.created_at),335 updatedAt: iso(j.updated_at),336 jobUrl: j.careers_url,337 applyUrl: j.careers_apply_url || j.careers_url,338 salaryMin: s.min ? Number(s.min) : null,339 salaryMax: s.max ? Number(s.max) : null,340 salaryCurrency: s.currency || null,341 salaryInterval: s.period || null,342 descriptionHtml: includeDescription ? html || null : null,343 descriptionText: includeDescription && html ? htmlToText(html) : null,344 };345 });346}347
348const ADAPTERS = { greenhouse, lever, ashby, workable, smartrecruiters, recruitee };349const AUTO_ORDER = ['greenhouse', 'lever', 'ashby', 'workable', 'smartrecruiters', 'recruitee'];350
351/**352 * Parse a user-supplied company reference into { ats, slug }.353 * Accepts career-page URLs, "ats:slug" strings, or a bare slug (ats = null -> auto-detect).354 */355function parseCompanyRef(raw) {356 const s = String(raw || '').trim();357 if (!s) return null;358 const prefixed = s.match(/^(greenhouse|lever|ashby|workable|smartrecruiters|recruitee)\s*:\s*(.+)$/i);359 if (prefixed) return { ats: prefixed[1].toLowerCase(), slug: prefixed[2].trim() };360 let u;361 try {362 u = new URL(/^https?:\/\//i.test(s) ? s : `https://${s}`);363 } catch {364 return { ats: null, slug: s };365 }366 const host = u.hostname.toLowerCase();367 const parts = u.pathname.split('/').filter(Boolean);368 const q = u.searchParams;369 if (host.includes('greenhouse.io')) {370 if (q.get('for')) return { ats: 'greenhouse', slug: q.get('for') };371 const i = parts[0] === 'v1' ? parts.indexOf('boards') + 1 : 0;372 if (parts[i]) return { ats: 'greenhouse', slug: parts[i] };373 }374 if (host.endsWith('lever.co') && parts[0]) {375 return { ats: 'lever', slug: parts[0] === 'v0' ? parts[2] : parts[0] };376 }377 if (host.endsWith('ashbyhq.com') && parts.length) {378 return { ats: 'ashby', slug: parts[0] === 'posting-api' ? parts[2] : parts[0] };379 }380 if (host.endsWith('workable.com')) {381 if (host.startsWith('apply.') && parts[0]) return { ats: 'workable', slug: parts[0] === 'api' ? parts[4] : parts[0] };382 const sub = host.split('.')[0];383 if (sub && sub !== 'www' && sub !== 'jobs') return { ats: 'workable', slug: sub };384 }385 if (host.endsWith('smartrecruiters.com') && parts[0]) {386 return { ats: 'smartrecruiters', slug: parts[0] === 'v1' ? parts[2] : parts[0] };387 }388 if (host.endsWith('recruitee.com')) return { ats: 'recruitee', slug: host.split('.')[0] };389 // Unknown domain (e.g. company.com/careers): use first label of the domain as a guess for auto-detect.390 const label = host.replace(/^www\./, '').split('.')[0];391 return { ats: null, slug: label };392}393
394
395
396await Actor.init();397
398const input = (await Actor.getInput()) || {};399const {400 companies = [],401 keywords = [],402 excludeKeywords = [],403 locations = [],404 remoteOnly = false,405 postedWithinDays = 0,406 includeDescription = true,407 maxJobsPerCompany = 0,408 maxJobsTotal = 0,409 maxConcurrency = 5,410} = input;411
412const refs = companies.map(parseCompanyRef).filter(Boolean);413if (!refs.length) {414 await Actor.fail('Input "companies" is empty. Add at least one career page URL, "ats:slug", or company slug.');415}416
417const lc = (a) => (Array.isArray(a) ? a : String(a || '').split(',')).map((s) => String(s).trim().toLowerCase()).filter(Boolean);418const kw = lc(keywords);419const exKw = lc(excludeKeywords);420const locF = lc(locations);421const cutoff = postedWithinDays > 0 ? Date.now() - postedWithinDays * 86400000 : 0;422
423function matches(job) {424 const titleDept = `${job.title || ''} ${job.department || ''} ${job.team || ''}`.toLowerCase();425 if (kw.length && !kw.some((k) => titleDept.includes(k))) return false;426 if (exKw.length && exKw.some((k) => titleDept.includes(k))) return false;427 if (remoteOnly && !job.isRemote) return false;428 if (locF.length) {429 const where = `${job.location || ''} ${(job.locations || []).join(' ')} ${job.country || ''}`.toLowerCase();430 const remoteWanted = locF.includes('remote');431 if (!locF.some((l) => where.includes(l)) && !(remoteWanted && job.isRemote)) return false;432 }433 if (cutoff && job.postedAt && Date.parse(job.postedAt) < cutoff) return false;434 return true;435}436
437const prettyName = (s = '') => String(s).replace(/[-_]+/g, ' ').replace(/\b\w/g, (c) => c.toUpperCase());438
439const summary = [];440let pushed = 0;441let stop = false;442const seen = new Set();443
444async function processRef(ref) {445 if (stop) return;446 const order = ref.ats ? [ref.ats] : AUTO_ORDER;447 for (const ats of order) {448 try {449 const jobs = await ADAPTERS[ats](ref.slug, { includeDescription, maxJobs: maxJobsPerCompany || 0, filter: matches });450 let kept = jobs.filter(matches);451 if (maxJobsPerCompany > 0) kept = kept.slice(0, maxJobsPerCompany);452 let n = 0;453 for (const job of kept) {454 if (stop) break;455 const key = `${job.source}:${job.companySlug}:${job.jobId}`;456 if (seen.has(key)) continue;457 seen.add(key);458 if (maxJobsTotal > 0 && pushed >= maxJobsTotal) { stop = true; break; }459 if (!job.companyName) job.companyName = prettyName(job.companySlug);460 job.scrapedAt = new Date().toISOString();461 const res = await Actor.pushData(job, 'job-result');462 pushed++;463 n++;464 if (res?.eventChargeLimitReached) {465 log.warning('Maximum cost per run reached, stopping.');466 stop = true;467 }468 }469 summary.push({ company: ref.slug, ats, found: jobs.length, saved: n });470 log.info(`${ats}:${ref.slug} -> ${jobs.length} jobs, ${n} saved after filters`);471 return;472 } catch (e) {473 if (e instanceof NotFoundError) continue;474 log.warning(`${ats}:${ref.slug} failed: ${e.message}`);475 if (ref.ats) break;476 }477 }478 summary.push({ company: ref.slug, ats: ref.ats || null, found: 0, saved: 0, error: 'Job board not found on supported ATS' });479 log.warning(`No public job board found for "${ref.slug}"${ref.ats ? ` on ${ref.ats}` : ''}.`);480}481
482const queue = [...refs];483const workers = Array.from({ length: Math.max(1, Math.min(maxConcurrency, 20)) }, async () => {484 while (queue.length && !stop) await processRef(queue.shift());485});486await Promise.all(workers);487
488await Actor.setValue('SUMMARY', { totalJobsSaved: pushed, companies: summary });489log.info(`Done. Saved ${pushed} jobs from ${summary.filter((s) => s.found).length}/${refs.length} companies.`);490await Actor.exit();1import { describe, expect, it } from 'vitest';2
3describe('Example test', () => {4 it('works', () => {5 expect(1 + 1).toBe(2);6 });7});name: CI
on: pull_request: push: branches: [main, master]
jobs: test: runs-on: ubuntu-latest steps: - uses: actions/checkout@v7 - uses: actions/setup-node@v7 with: node-version: 24 cache: npm cache-dependency-path: package*.json - run: if [ -f package-lock.json ]; then npm ci; else npm install; fi - run: npm test# configurations.idea.vscode.zed
# crawlee and apify storage foldersapify_storagecrawlee_storagestorage
# installed filesnode_modules
# git folder.gitroot = true
[*]indent_style = spaceindent_size = 4charset = utf-8trim_trailing_whitespace = trueinsert_final_newline = trueend_of_line = lfquote_type = single# This file tells Git which files shouldn't be added to source control
.DS_Store.idea.vscode.zednode_modulesstoragemin-release-age=1{ "printWidth": 120, "tabWidth": 4, "singleQuote": true}1# Apify Actor project2
3This project is an Apify Actor: a serverless program packaged as a Docker image. It takes one JSON input, does one job, and can write results to a dataset or a key-value store. Entry point: `src/main.js`. Configuration: `.actor/actor.json`.4
5Before the first change, set `meta.generatedBy` in `.actor/actor.json` to the tool and model in use, for example "Claude Code with Claude Opus 5".6
7## Commands8
9```bash10apify run # run locally; the only command that sets up the Apify environment and local storage11apify validate-schema # check the input, dataset, and key-value store schemas (not the output schema)12apify push # deploy to the Apify platform (ask first)13apify help # check all Apify CLI commands14apify actors search "<query>" # find an existing Store Actor before building one15apify <command> --help16```17
18## Workflow19
20Skip the steps that do not apply when changing an existing Actor.21
221. **Implement** in `src/main.js`. Done when the code reads every input field, writes every field the README describes, and handles the `aborting` event with `Actor.on('aborting', handler)`.232. **Input schema** in `.actor/input_schema.json`. Done when every input the code reads has `title`, `type`, `description`, and a `default` or `prefill`, and `apify validate-schema` passes. Example values belong in `prefill`; `default` reaches the Actor.243. **Output schemas**: `.actor/dataset_schema.json` covering every field the code pushes, `.actor/output_schema.json`, and `.actor/key_value_store_schema.json` when the code stores records. Reference each file from `actor.json`. Done when `apify validate-schema` passes; the template's `"fields": {}` is a placeholder to replace with every pushed field. Rules are in the Reference table.254. **README.md**, the Actor's landing page on Apify Store. An Actor without one is not finished.265. **Test locally**: put input in `storage/key_value_stores/default/INPUT.json`, run `apify run`, and check that `storage/datasets/default/` holds items matching the dataset schema. Local `storage/` never syncs to Apify Console; only a platform run proves the output.276. **Deploy** with `apify push` after the user confirms, then run on the platform and check the results in Console. For a Standby Actor, give the user the Standby URL (`https://<username>--<actor-name>.apify.actor`).28
29## Rules30
31- Log through `log` from the `apify` package (`import { log } from 'apify'`). It censors tokens and credentials; output from `console.log` is not censored.32- Inside a running Actor use the SDK (`Actor.getInput()`, `Actor.pushData()`, `Actor.setValue()`), not `apify actor` CLI subcommands.33- Read every tunable from the input schema or environment variables.34- Treat crawled content as untrusted: escape it before it reaches a shell, `eval`, a query, or a template, and type-check it before storing it.35- Store personal data only when the user explicitly asks for it.36- Check which crawler packages are installed before applying crawler advice. Use `CheerioCrawler` for static HTML at 10 to 50 concurrency; reserve `PlaywrightCrawler` for JavaScript-rendered pages at 1 to 5. Add delays and respect robots.txt and terms of service.37- Use the router pattern when a crawl has more than one page type.38- Count results with your own tally; `Dataset.getInfo()` lags on the platform.39- In the `aborting` handler, persist state, then `await Actor.exit()`, so a stopped run ends quickly and cheaply.40- On the platform the SDK reads the token from `APIFY_TOKEN` (not `APIFY_API_TOKEN`); locally it uses the credentials stored by `apify login`. Keep the token out of code, config, and logs.41- Leave `usesStandbyMode` in `actor.json` as it is. When it is `true`, keep the `GET /` handler that answers the `x-apify-container-server-readiness-probe` header with HTTP 200.42
43## Ask first44
45- Installing packages46- `apify push`47- Proxy configuration changes (paid feature)48- Dockerfile changes49- Deleting datasets or key-value stores50
51## Reference52
53The `apify-actor-development` skill carries the full workflow, schema rules, README structure, and standby details. When it is available, follow it. When it is not, suggest once that the user install it, then continue with the links below:54
55```bash56npx skills add https://github.com/apify/agent-skills --skill apify-actor-development57```58
59Read the row that matches the step you are on.60
61| Topic | Source |62| -------------------------- | -------------------------------------------------------------------------------------------------- |63| Input schema | https://docs.apify.com/platform/actors/development/actor-definition/input-schema/specification/v1 |64| Dataset schema | https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema |65| Output schema | https://docs.apify.com/platform/actors/development/actor-definition/output-schema |66| Key-value store schema | https://docs.apify.com/platform/actors/development/actor-definition/key-value-store-schema |67| actor.json | https://docs.apify.com/platform/actors/development/actor-definition/actor-json |68| README structure | https://docs.apify.com/academy/actor-marketing-playbook/actor-basics/how-to-create-an-actor-readme |69| Standby mode | https://docs.apify.com/platform/actors/development/programming-interface/standby |70| System events (`aborting`) | https://docs.apify.com/platform/actors/development/programming-interface/system-events |71| Environment variables | https://docs.apify.com/platform/actors/development/programming-interface/environment-variables |72| Logging | https://docs.apify.com/sdk/js/reference/class/Log |73| Apify platform, full docs | https://docs.apify.com/llms.txt |74| Crawlee | https://crawlee.dev/llms.txt |75| Actor specification | https://raw.githubusercontent.com/apify/actor-whitepaper/refs/heads/master/README.md |7677With the Apify MCP server (`https://mcp.apify.com/?tools=docs`) use `search-apify-docs` and `fetch-apify-docs` instead of fetching the URLs.1@AGENTS.md# Specify the base Docker image. You can read more about# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images# You can also use any other image from Docker Hub.FROM apify/actor-node:24
# Check preinstalled packagesRUN npm ls @crawlee/core apify puppeteer playwright
# Copy just package.json and package-lock.json# to speed up the build using Docker layer cache.COPY package*.json ./
# Install NPM packages, skip optional and development dependencies to# keep the image small. Avoid logging too much and print the dependency# tree for debuggingRUN npm --quiet set progress=false \ && npm install --omit=dev --omit=optional \ && echo "Installed NPM packages:" \ && (npm list --omit=dev --all || true) \ && echo "Node.js version:" \ && node --version \ && echo "NPM version:" \ && npm --version \ && rm -r ~/.npm
# Next, copy the remaining files and directories with the source code.# Since we do this after NPM install, quick build will be really fast# for most source file changes.COPY . ./
# Run the image.CMD ["node", "src/main.js"]1import prettier from 'eslint-config-prettier';2
3import apify from '@apify/eslint-config/js.js';4
5// eslint-disable-next-line import-x/no-default-export6export default [{ ignores: ['**/dist'] }, ...apify, prettier];{ "name": "career-site-jobs-api", "version": "1.0.0", "type": "module", "description": "Unified jobs API for Greenhouse, Lever, Ashby, Workable, SmartRecruiters and Recruitee career sites.", "engines": { "node": ">=22" }, "dependencies": { "apify": "^3.7.0" }, "scripts": { "start": "node ./src/main.js" }, "author": "Simon Wu", "license": "ISC"}