Which ATS does a company use? Detect it from the domain, then build a new-jobs alert (JS + Python)

import { pathToFileURL } from 'node:url'; // detect-ats.mjs: Node 18+, no dependencies. Run: node detect-ats.mjs eightsleep.com coinbase.com const UA = 'my-ats-detector/1.0 (you@example.com)'; // name your client and give a contact const sleep = (ms) => new Promise((r) => setTimeout(r, ms)); // 1. Board URL patterns. Group 1 is the slug. const PATTERNS = [ ['greenhouse', /(?:job-)?boards(?:-api)?\.greenhouse\.io\/(?:v1\/boards\/|embed\/job_board(?:\/js)?\?for=)?([\w-]+)/gi], ['lever', /(?:jobs|api)\.lever\.co\/(?:v0\/postings\/)?([\w.-]+)/gi], ['ashby', /(?:jobs|api)\.ashbyhq\.com\/(?:posting-api\/job-board\/)?([\w.%-]+)/gi], ['workable', /apply\.workable\.com\/(?!api\/|j\/)([\w-]+)/gi], ['workable', /\/\/(?!www\.|apply\.|jobs\.)([a-z0-9-]+)\.workable\.com/gi], ['recruitee', /\/\/(?!www\.|api\.|app\.|careers\.)([a-z0-9-]+)\.recruitee\.com/gi], ]; const NOT_SLUGS = new Set(['embed', 'v1', 'v0', 'api', 'jobs', 'j', 'posting-api', 'js']); // 2. Public job APIs, used to confirm that a board exists and has jobs. const API = { greenhouse: (s) => `https://boards-api.greenhouse.io/v1/boards/${s}/jobs`, lever: (s) => `https://api.lever.co/v0/postings/${s}?mode=json`, ashby: (s) => `https://api.ashbyhq.com/posting-api/job-board/${s}`, workable: (s) => `https://apply.workable.com/api/v1/widget/accounts/${s}`, recruitee: (s) => `https://${s}.recruitee.com/api/offers/`, }; const jobsIn = (data) => (Array.isArray(data) ? data : data?.jobs ?? data?.offers ?? []); async function get(url) { try { const res = await fetch(url, { headers: { 'user-agent': UA }, signal: AbortSignal.timeout(15_000) }); return { status: res.status, url: res.url, text: res.ok ? await res.text() : '' }; } catch { return { status: 0, url, text: '' }; // DNS failure, timeout, TLS error } } // Minimal robots.txt check: honour "Disallow" lines in the "User-agent: *" group. const robots = new Map(); // origin -> robots.txt text, fetched once per site async function allowed(origin, path) { if (!robots.has(origin)) robots.set(origin, (await get(`${origin}/robots.txt`)).text); const text = robots.get(origin); let inStar = false; const rules = []; for (const line of text.split('\n')) { const [k, ...v] = line.split(':'); const key = k.trim().toLowerCase(); const val = v.join(':').trim(); if (key === 'user-agent') inStar = val === '*'; else if (key === 'disallow' && inStar && val) rules.push(val); } return !rules.some((r) => path.startsWith(r)); } export function findBoards(text) { const found = new Map(); for (const [platform, re] of PATTERNS) { for (const m of text.matchAll(re)) { let slug = m[1]; try { slug = decodeURIComponent(slug); } catch {} // keep a malformed %-escape as is slug = slug.replace(/\.+$/, ''); if (!NOT_SLUGS.has(slug.toLowerCase())) found.set(`${platform}:${slug.toLowerCase()}`, { platform, slug }); } } return [...found.values()]; } async function confirm({ platform, slug }) { const { status, text } = await get(API[platform](encodeURIComponent(slug))); if (status !== 200) return null; let openJobs; try { openJobs = jobsIn(JSON.parse(text)).length; } catch { return null; } // not JSON: not a board // An empty board is useless for alerts, and Workable returns empty accounts for some slugs. return openJobs > 0 ? { platform, slug, openJobs, api: API[platform](slug) } : null; } export async function detect(input) { // A careers URL that already points at an ATS needs only the API check. const direct = findBoards(input); if (direct.length) return { input, method: 'url', boards: (await Promise.all(direct.map(confirm))).filter(Boolean) }; const origin = `https://${input.replace(/^https?:\/\//, '').replace(/\/.*$/, '')}`; // Step A: read the company's own careers pages and look for board links or embeds. for (const path of ['/careers', '/jobs', '/']) { if (!(await allowed(origin, path))) continue; const page = await get(origin + path); const hits = findBoards(page.url + ' ' + page.text); const boards = (await Promise.all(hits.map(confirm))).filter(Boolean); if (boards.length) return { input, method: `page ${path}`, boards }; await sleep(1000); // one request per second per site } // Step B: guess the slug from the domain and ask each API. Treat any hit as a candidate. const slug = new URL(origin).hostname.replace(/^www\./, '').split('.')[0]; const boards = []; for (const platform of Object.keys(API)) { const hit = await confirm({ platform, slug }); if (hit) boards.push(hit); } return { input, method: boards.length ? 'slug guess (verify by hand)' : 'not found', boards }; } if (process.argv[1] && import.meta.url === pathToFileURL(process.argv[1]).href) { for (const input of process.argv.slice(2)) console.log(JSON.stringify(await detect(input))); } 

node detect-ats.mjs https://jobs.lever.co/megaport eightsleep.com coinbase.com 1000heads.com 11bitstudios.com anduril.com 

{"input":"https://jobs.lever.co/megaport","method":"url","boards":[{"platform":"lever","slug":"megaport","openJobs":55,"api":"https://api.lever.co/v0/postings/megaport?mode=json"}]} {"input":"eightsleep.com","method":"page /careers","boards":[{"platform":"ashby","slug":"eightsleep","openJobs":39,"api":"https://api.ashbyhq.com/posting-api/job-board/eightsleep"}]} {"input":"coinbase.com","method":"slug guess (verify by hand)","boards":[{"platform":"greenhouse","slug":"coinbase","openJobs":227,"api":"https://boards-api.greenhouse.io/v1/boards/coinbase/jobs"}]} {"input":"1000heads.com","method":"page /careers","boards":[{"platform":"workable","slug":"1000heads","openJobs":16,"api":"https://apply.workable.com/api/v1/widget/accounts/1000heads"}]} {"input":"11bitstudios.com","method":"slug guess (verify by hand)","boards":[{"platform":"recruitee","slug":"11bitstudios","openJobs":6,"api":"https://11bitstudios.recruitee.com/api/offers/"}]} {"input":"anduril.com","method":"not found","boards":[]} 

curl -sO https://raw.githubusercontent.com/neorhapsody/ats-company-directory-sample/main/sample-50.csv 

# new_jobs.py: Python 3.9+, standard library only. Run daily: python3 new_jobs.py sample-50.csv import csv, json, sys, time, urllib.error, urllib.request from pathlib import Path UA = "my-job-alert/1.0 (you@example.com)" # name your client and give a contact STATE = Path("seen.json") # board -> {"etag": ..., "ids": [...]}  # Where each ATS keeps its job list, and how to read one job. FIELDS = { "Greenhouse": ("jobs", lambda j: (j["id"], j["title"], (j.get("location") or {}).get("name"), j["absolute_url"])), "Lever": (None, lambda j: (j["id"], j["text"], (j.get("categories") or {}).get("location"), j["hostedUrl"])), "Ashby": ("jobs", lambda j: (j["id"], j["title"], j.get("location"), j["jobUrl"])), "Workable": ("jobs", lambda j: (j["shortcode"], j["title"], ", ".join(filter(None, [j.get("city"), j.get("country")])), j["url"])), "Recruitee": ("offers", lambda j: (j["id"], j["title"], j.get("location"), j["careers_url"])), } def fetch(url, etag=None, tries=3): headers = {"User-Agent": UA, "Accept": "application/json"} if etag: headers["If-None-Match"] = etag # the server answers 304 if nothing changed  for attempt in range(1, tries + 1): try: with urllib.request.urlopen(urllib.request.Request(url, headers=headers), timeout=30) as r: return r.status, r.headers.get("ETag"), json.load(r) except urllib.error.HTTPError as e: if e.code in (304, 404): return e.code, etag, None Source：https://dev.to/neorhapsody/which-ats-does-a-company-use-detect-it-from-the-domain-then-build-a-new-jobs-alert-js-python-4fi
My favorites