feat(extractors): expand catalog, smoke coverage, and sourcing docs

Adds Arc.dev, BC T-Net, Eluta, iCIMS tenants, QAJobsBoard, and SmartRecruiters manifests with registry/settings/UI wiring; registers full extractor list in smoke-extractors and documents supplementary board access paths. Aligns Careerjet v4 with the url query parameter and fixes strict typing in QAJobsBoard. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-15 22:36:23 -04:00 · 2026-05-15 22:36:23 -04:00 · c840f289e1
commit c840f289e1
parent 67508d56ea
50 changed files with 2926 additions and 101 deletions
--- a/.env.example
+++ b/.env.example
@ -200,6 +200,7 @@ ADZUNA_APP_KEY=
 # LEVER_COMPANIES=netflix,figma
 # ASHBY_COMPANIES=ramp,linear
 # GREENHOUSE_COMPANIES=stripe,airbnb
+# Canadian QA-employer examples (full table): docs-site/docs/extractors/canadian-companies-qa-ats.md

 # =============================================================================
 # Workday (public career sites) - optional
@ -210,3 +211,46 @@ ADZUNA_APP_KEY=
 #   2) A JSON object with explicit fields:
 #      {"company":"NVIDIA","tenantUrl":"https://nvidia.wd5.myworkdayjobs.com","tenant":"nvidia","site":"NVIDIAExternalCareerSite","locale":"en-US"}
 # WORKDAY_TENANTS=
+
+# =============================================================================
+# SmartRecruiters (public Posting API) - optional
+# =============================================================================
+# Comma- or newline-separated company identifiers (API path segment), e.g.
+# jobs.smartrecruiters.com/smartrecruiters/... → "smartrecruiters".
+# SMARTRECRUITERS_COMPANIES=smartrecruiters
+# SMARTRECRUITERS_MAX_JOBS_PER_COMPANY=100
+
+# =============================================================================
+# Eluta (Canada, RSS by location) - optional
+# =============================================================================
+# Comma- or newline-separated location strings for https://www.eluta.ca/rss?location=...
+# Example: ELUTA_RSS_LOCATIONS=Toronto, ON|Vancouver, BC
+# ELUTA_MAX_JOBS_PER_TERM=100
+
+# =============================================================================
+# BC T-Net (British Columbia tech jobs RSS) — optional
+# =============================================================================
+# Default feed is built into the extractor when this is unset:
+# https://www.bctechnology.com/rss/jobs/tnetjobs.xml
+# Override with JSON array or newline-separated URLs (custom feeds from T-Net builder).
+# BCTENET_RSS_URLS=
+# Prefer Settings: bctenetRssUrls (JSON array), bctenetMaxJobsPerTerm (default 400).
+
+# =============================================================================
+# iCIMS tenant portals (anonymous HTML search) — optional
+# =============================================================================
+# Comma- or newline-separated hosts, e.g. careers-example.icims.com
+# ICIMS_TENANTS=
+# Caps via Settings: icimsMaxJobsPerTenant (default 250), icimsMaxPagesPerSearch (default 10).
+
+# =============================================================================
+# QAJobsBoard (QA JobBoardly JSON) — optional
+# =============================================================================
+# Configure caps via Settings: qajobsboardMaxJobsPerTerm (default 100).
+
+# =============================================================================
+# Arc.dev remote listings — optional
+# =============================================================================
+# Comma-separated paths under https://arc.dev used when seeding defaults (e.g. Playwright + Cypress feeds).
+# ARC_REMOTE_JOBS_PATHS=/remote-jobs/playwright,/remote-jobs/cypress
+# Prefer Settings for overrides: arcRemoteJobsPaths (JSON array), arcMaxJobsPerPath (default 120).
--- a/docs-site/docs/extractors/arcdev.md
+++ b/docs-site/docs/extractors/arcdev.md
@ -0,0 +1,34 @@
+---
+id: arcdev
+title: Arc.dev Extractor
+description: Remote tech roles from Arc.dev listing pages via embedded Next.js data.
+sidebar_position: 17
+---
+
+## What it is
+
+[Arc.dev](https://arc.dev) exposes remote job listings on paths such as `/remote-jobs/playwright` and `/remote-jobs/cypress`. The extractor downloads SSR HTML and parses the embedded `__NEXT_DATA__` payload (Arc-managed and external rows).
+
+Implementation: `extractors/arcdev/manifest.ts`.
+
+## Why it exists
+
+Curated remote hiring with explicit tooling-oriented feeds; many roles are open to North America when labeled that way on the site.
+
+## How to use it
+
+1. Enable **Arc.dev** in pipeline sources (no credentials).
+2. Configure **`arcRemoteJobsPaths`** as a JSON array of path strings (defaults include Playwright and Cypress remote feeds). Optionally seed defaults from **`ARC_REMOTE_JOBS_PATHS`** (comma-separated paths).
+3. Set **`arcMaxJobsPerPath`** (default `120`, max `300`) to cap rows per listing URL after deduplication.
+4. Align **`searchTerms`** with titles or stacks you care about; empty-term behavior is handled inside the manifest per path.
+
+## Common problems
+
+- **HTML changes:** If Arc ships a new payload shape, parsing may need an update; smoke-test with `npx tsx scripts/smoke-extractors.ts arcdev`, or run the full extractor suite with `npx tsx scripts/smoke-extractors.ts`.
+- **`Arc talent network` employer:** Some Arc-managed rows omit a company name; the mapper uses that placeholder.
+
+## Related pages
+
+- [Extractors overview](/docs/next/extractors/overview)
+- [Canadian QA contracting firms](/docs/next/extractors/qa-contract-staffing-canada)
+- [Manual Import](/docs/next/extractors/manual)
--- a/docs-site/docs/extractors/canadian-companies-qa-ats.md
+++ b/docs-site/docs/extractors/canadian-companies-qa-ats.md
@ -0,0 +1,117 @@
+---
+id: canadian-companies-qa-ats
+title: Canadian companies — strong QA orgs and scrapable ATS
+description: Reference list of Canadian tech employers with solid QA cultures and practical ATS endpoints for JobOps pipelines.
+sidebar_position: 41
+---
+
+## What it is
+
+A curated reference of **Canadian-headquartered or Canadian-heavy tech employers** where QA / SDET / test automation is often a first-class function, together with **scrapable ATS endpoints** where they exist.
+
+Tier 1 targets map cleanly to the shipped **Ashby**, **Greenhouse**, **Lever**, **Workday**, and **SmartRecruiters** extractors. Tier 2 entries need custom scraping, browser automation, or upstream quirks.
+
+**Verification:** Tier 1 integrations below were probed successfully (**HTTP `200`**, JSON where applicable). **Posting counts change daily** — re-run probes locally when you need exact volumes.
+
+## Why it exists
+
+Canada-focused QA sourcing benefits from **employer-direct ATS feeds** (clean titles, real apply URLs) instead of only aggregator noise. This page maps recognizable brands to **exact integration shapes** so you can paste slugs into Settings or env without rediscovering URLs.
+
+## How to use it
+
+### Tier 1 — Public ATS APIs (shipped extractors)
+
+| Company | HQ | ATS | Endpoint / shape (reference) | JobOps wiring |
+| --- | --- | --- | --- | --- |
+| Wealthsimple | Toronto | Ashby | `GET https://api.ashbyhq.com/posting-api/job-board/wealthsimple` | Add **`wealthsimple`** to **`ashbyCompanies`** / `ASHBY_COMPANIES`. |
+| 1Password | Toronto (remote-first) | Ashby | `.../job-board/1password` | Add **`1password`**. |
+| Jobber | Edmonton / Toronto | Ashby | `.../job-board/jobber` | Add **`jobber`**. |
+| Nylas | Toronto / SF | Ashby | `.../job-board/nylas` | Add **`nylas`**. |
+| Hootsuite | Vancouver | Greenhouse | `GET https://boards-api.greenhouse.io/v1/boards/hootsuite/jobs?content=true` | Add **`hootsuite`** to **`greenhouseCompanies`**. |
+| Faire | Waterloo / SF | Greenhouse | `.../boards/faire/jobs?content=true` | Add **`faire`**. |
+| PointClickCare | Mississauga | Lever | `GET https://api.lever.co/v0/postings/pointclickcare?mode=json` | Add **`pointclickcare`** to **`leverCompanies`**. |
+| Clio | Burnaby / Calgary / Toronto | Workday | `POST https://clio.wd3.myworkdayjobs.com/wday/cxs/clio/ClioCareerSite/jobs` (`limit`, `offset`, `searchText`) | Add **`https://clio.wd3.myworkdayjobs.com/en-US/ClioCareerSite`** to **`workdayTenants`** / `WORKDAY_TENANTS`. |
+| Coveo | Quebec City / Montreal | SmartRecruiters | `GET https://api.smartrecruiters.com/v1/companies/Coveo/postings` | Add **`Coveo`** to **`smartrecruitersCompanies`**. API stays **`200`**; **`totalFound`** may be **zero** between hiring waves. |
+
+Optional Ashby query parameter `?includeCompensation=true` works in browsers and `curl` for richer payloads; the bundled Ashby extractor calls the **same path without that query** and still returns full job lists.
+
+**Example Settings JSON (merge with your existing lists):**
+
+```json
+["wealthsimple", "1password", "jobber", "nylas"]
+```
+
+```json
+["hootsuite", "faire"]
+```
+
+```json
+["pointclickcare"]
+```
+
+```json
+["https://clio.wd3.myworkdayjobs.com/en-US/ClioCareerSite"]
+```
+
+```json
+["Coveo"]
+```
+
+### Tier 2 — Harder or custom surfaces
+
+| Company | HQ | ATS | Notes |
+| --- | --- | --- | --- |
+| Shopify | Ottawa / remote | Ashby (custom) | Hosted board / GraphQL (`jobs.ashbyhq.com/api/non-user-graphql`, `organizationHostedJobsPageName: "shopify"`) or parse careers HTML — not covered by the slug-based Ashby extractor today. |
+| Lightspeed Commerce | Montreal | Custom (often Cloudflare) | Careers HTML at `https://www.lightspeedhq.com/careers/openings/` — browser or tolerant fetcher; no shipped extractor. |
+| RBC Borealis | Toronto / Montreal | Greenhouse (embedded) | `boards-api` path **`rbcborealis`** returned **404** when probed — scrape `https://rbcborealis.com/careers/` or rediscover the active board slug before using Greenhouse JSON. |
+| Vidyard | Kitchener–Waterloo | JS-heavy site | `https://careers.vidyard.com/` — Playwright/Puppeteer if automating. |
+| Loblaw Digital | Toronto | Workday (parent) | Parent Workday host may need the correct site segment; careers marketing site often lists roles — browser-backed discovery may be more reliable than guessing CXS paths. |
+
+### Ready-to-use CLI filters (QA-oriented titles)
+
+Ashby (example: Wealthsimple):
+
+```bash
+curl -s 'https://api.ashbyhq.com/posting-api/job-board/wealthsimple?includeCompensation=true' \
+  | jq '.jobs[] | select(.title | test("QA|SDET|Test|Automation"; "i")) | {title, location, url: .jobUrl}'
+```
+
+Greenhouse (example: Hootsuite):
+
+```bash
+curl -s 'https://boards-api.greenhouse.io/v1/boards/hootsuite/jobs?content=true' \
+  | jq '.jobs[] | select(.title | test("QA|SDET|Test|Automation"; "i")) | {title, location: .location.name, url: .absolute_url}'
+```
+
+Lever (PointClickCare):
+
+```bash
+curl -s 'https://api.lever.co/v0/postings/pointclickcare?mode=json' \
+  | jq '.[] | select(.text | test("QA|SDET|Test|Automation"; "i")) | {title: .text, location: .categories.location, url: .hostedUrl}'
+```
+
+Workday (Clio — QA search text):
+
+```bash
+curl -s -X POST 'https://clio.wd3.myworkdayjobs.com/wday/cxs/clio/ClioCareerSite/jobs' \
+  -H 'Content-Type: application/json' \
+  -d '{"limit":50,"offset":0,"searchText":"QA"}' \
+  | jq '.jobPostings[] | select(.title | test("QA|SDET|Test|Automation"; "i")) | {title, location: .locationsText}'
+```
+
+### Other strong-QA Canadian employers (ATS not deep-verified here)
+
+Worth manual checks or Eluta / LinkedIn cross-reference: **Wattpad**, **Knix**, **Ada**, **Hopper**, **Plusgrade**, **D2L**, **Kinaxis**, **TELUS Digital / Mirum**, **Trulioo**, **OpenText / Hubdoc**.
+
+## Common problems
+
+- **Ashby counts vs `includeCompensation`:** Omitting the query param still returns jobs; compensation fields may be sparser.
+- **Greenhouse board slug drift:** If `boards-api` returns `404`, the employer may have renamed the board — inspect their careers page embed or HTML source for the current board id.
+- **SmartRecruiters zero postings:** Still a valid integration; don’t treat empty arrays as a broken extractor.
+
+## Related pages
+
+- [Extractors overview](/docs/next/extractors/overview)
+- [Canadian / NA QA contracting firms](/docs/next/extractors/qa-contract-staffing-canada)
+- [Eluta](/docs/next/extractors/eluta)
+- [Manual Import](/docs/next/extractors/manual)
--- a/docs-site/docs/extractors/eluta.md
+++ b/docs-site/docs/extractors/eluta.md
@ -0,0 +1,44 @@
+---
+id: eluta
+title: Eluta Extractor
+description: Canadian job discovery via Eluta.ca public RSS feeds.
+sidebar_position: 15
+---
+
+## What it is
+
+Original site: [eluta.ca](https://www.eluta.ca)
+
+The extractor lives in `extractors/eluta/manifest.ts`. It requests one or more public RSS URLs of the form `https://www.eluta.ca/rss?location=...`, parses items (title, employer, location, link, description), filters by pipeline search terms, and merges feeds while de-duplicating by `guid` / URL.
+
+## Why it exists
+
+Eluta surfaces Canadian roles indexed directly from employer career sites, often with less aggregator noise than generic job search. RSS provides a stable, low-auth integration compared to scraping HTML.
+
+## How to use it
+
+1. Choose **location strings** Eluta accepts in the RSS `location` query parameter (for example `Toronto, ON`, `Vancouver, BC`). Very broad values such as a whole country may return empty feeds; prefer metros or provinces.
+2. In **Settings**, set **Eluta RSS locations** (`elutaRssLocations`) as a JSON array or comma/newline-separated list, or set `ELUTA_RSS_LOCATIONS` in the environment (for example `Toronto, ON|Montreal, QC`).
+3. Optionally set **Eluta max jobs per term** (`elutaMaxJobsPerTerm`, default `100`).
+4. Set your search geography to **Canada** — Eluta is **Canada-only** and is skipped automatically when the resolved pipeline country is not Canada.
+5. Enable **Eluta** in pipeline sources and run the pipeline.
+
+## Common problems
+
+### Eluta is skipped for my run
+
+- Search geography is not Canada (city/country/Indeed country resolution). Align geography to Canada or disable Eluta for non-Canada profiles.
+
+### Empty feeds
+
+- The `location` string may be too broad or spelled differently than Eluta expects. Try a major city plus province (e.g. `Calgary, AB`).
+
+### RSS HTTP errors
+
+- Eluta may block unusual clients; the extractor sends a conventional User-Agent. Retry later or reduce the number of location feeds per run.
+
+## Related pages
+
+- [Extractors Overview](/docs/next/extractors/overview)
+- [Add an Extractor](/docs/next/workflows/add-an-extractor)
+- [Settings](/docs/next/features/settings)
--- a/docs-site/docs/extractors/overview.md
+++ b/docs-site/docs/extractors/overview.md
@ -19,6 +19,12 @@ Extractor integrations are now registered through manifests and loaded automatic
 | [Hiring Cafe](/docs/next/extractors/hiring-cafe) | Browser-backed discovery using Hiring Cafe search APIs | Subject to upstream anti-bot checks; uses browser context and encoded search-state payloads | `HIRING_CAFE_SEARCH_TERMS`, `HIRING_CAFE_COUNTRY`, `HIRING_CAFE_MAX_JOBS_PER_TERM`, `HIRING_CAFE_DATE_FETCHED_PAST_N_DAYS` | Uses existing pipeline term/country/budget knobs and maps directly to normalized jobs |
 | [startup.jobs](/docs/next/extractors/startup-jobs) | Startup-focused discovery through the published `startup-jobs-scraper` package | No credentials required; detail enrichment depends on Playwright browser binaries being installed | existing pipeline `searchTerms`, selected country/cities, `jobspyResultsWanted`; `npx playwright install` for fresh environments | Algolia-backed search plus detail-page enrichment via package import; orchestrator maps normalized records and de-duplicates by `jobUrl` |
 | [UKVisaJobs](/docs/next/extractors/ukvisajobs) | UK visa sponsorship-focused roles | Requires authenticated session and periodic token/cookie refresh | `UKVISAJOBS_EMAIL`, `UKVISAJOBS_PASSWORD`, `UKVISAJOBS_MAX_JOBS`, `UKVISAJOBS_SEARCH_KEYWORD` | API pagination + dataset output; orchestrator de-dupes and may fetch missing descriptions |
+| [SmartRecruiters](/docs/next/extractors/smartrecruiters) | Enterprise employers on SmartRecruiters public boards | No auth; needs configured company identifiers; one HTTP round-trip per posting for apply URLs + descriptions | `SMARTRECRUITERS_COMPANIES`, `SMARTRECRUITERS_MAX_JOBS_PER_COMPANY` | Paginates the public Posting API, filters by pipeline terms, normalizes to `CreateJobInput` |
+| iCIMS tenants (HTML) | Large employers on iCIMS portals | No auth; HTML search varies by tenant — maintain explicit tenant hosts | `ICIMS_TENANTS`, Settings: `icimsTenants`, `icimsMaxJobsPerTenant`, `icimsMaxPagesPerSearch` | Fetches `/jobs/search` with iframe-style params, parses listing links, caps per tenant |
+| BC T-Net (RSS) | BC tech aggregate via T-Net | Canada-only; free RSS (default feed built-in); optional extra feeds | `BCTENET_RSS_URLS`, Settings: `bctenetRssUrls`, `bctenetMaxJobsPerTerm` | Fetches RSS item blocks, normalizes quirky CDATA link fragments, filters by pipeline terms |
+| [Eluta](/docs/next/extractors/eluta) | Canadian listings aggregated from employer career sites (RSS) | Canada-only source (skipped when search geography is not Canada); RSS `location` strings must be set | `ELUTA_RSS_LOCATIONS`, `ELUTA_MAX_JOBS_PER_TERM` | Fetches one or more `eluta.ca` RSS feeds, filters by terms, de-duplicates by guid/URL |
+| [QAJobsBoard](/docs/next/extractors/qajobsboard) | QA / SDET / automation-heavy board (global JSON feed) | No auth; geography skew is manual/filter downstream | `qajobsboardMaxJobsPerTerm` | Fetches JobBoardly JSON, filters by pipeline terms |
+| [Arc.dev](/docs/next/extractors/arcdev) | Remote roles from Arc.dev listing pages (tool-tagged paths) | Parses SSR `__NEXT_DATA__`; relies on stable Next payload | `ARC_REMOTE_JOBS_PATHS` (seeds defaults), `arcRemoteJobsPaths`, `arcMaxJobsPerPath` | Merges Arc-managed + external rows; dedupes by URL |
 | [Manual Import](/docs/next/extractors/manual) | One-off jobs not covered by scrapers | Inference quality depends on model/provider and input quality; some URLs cannot be fetched reliably | App/API endpoints (`/api/manual-jobs/infer`, `/api/manual-jobs/import`) | Accepts text/HTML/URL, runs inference, then saves and scores job after review |

 ## Which extractor should I use?
@ -29,10 +35,38 @@ Extractor integrations are now registered through manifests and loaded automatic
 - Use **startup.jobs** when you want startup-heavy listings without maintaining another scraper locally.
 - Use **Gradcracker** when targeting graduate pipelines in the UK.
 - Use **UKVisaJobs** for sponsorship-specific UK searches.
+- Use **SmartRecruiters** when you can list target employers’ public SmartRecruiters company identifiers.
+- Use **iCIMS tenants** when you can list target `*.icims.com` career hosts (anonymous portal HTML search).
+- Use **BC T-Net** for British Columbia tech RSS listings (runs only when search geography is Canada).
+- Use **Eluta** for Canadian employer-direct listings via RSS (set metro/province `location` strings).
+- Use **QAJobsBoard** or **Arc.dev** when you want QA- or remote-stack-focused feeds without extra credentials.
 - Use **Manual Import** when you already have a specific posting and need direct import.

 Many runs combine sources: broad discovery first, then manual import for high-priority jobs that scraping misses.

+### QA-focused boards (shipped extractors)
+
+- **[QAJobsBoard](/docs/next/extractors/qajobsboard)** — Large QA-oriented index via public JSON; filter geography downstream.
+- **[Arc.dev](/docs/next/extractors/arcdev)** — Remote feeds (e.g. Playwright / Cypress paths); good for vetted remote slices.
+
+### Canadian QA contracting firms (reference)
+
+Staffing and consultancy firms that frequently post QA automation contracts — scrape hints and CLI probes: **[Canadian / NA QA contracting firms](/docs/next/extractors/qa-contract-staffing-canada)**.
+
+### Canadian employers — QA-strong ATS (reference)
+
+Direct ATS JSON / extractor wiring for well-known Canadian tech brands (Ashby, Greenhouse, Lever, Workday, SmartRecruiters): **[Canadian companies — strong QA orgs and scrapable ATS](/docs/next/extractors/canadian-companies-qa-ats)**.
+
+## Supplementary job boards
+
+Some boards are **credential-gated**, **approval-gated**, or **scraping-hostile** — see **[Supplementary sources — access notes](/docs/next/extractors/supplementary-sources-access-notes)** for realistic paths (Careerjet, Reed, Job Bank XML policy, sponsorship data sources, etc.).
+
+JobOps ships **BC T-Net** and **iCIMS tenant HTML** extractors for two cases that are usually workable without vendor contracts; everything else in the old “long tail” list still lands best via **[Manual Import](/docs/next/extractors/manual)** until someone promotes it to a manifest.
+
+### Still common manual-import targets
+
+- **Wellfound** (formerly AngelList), **Otta**, **Welcome to the Jungle**, **Dice**, **Job Bank** (unless you qualify for syndication), regional boards without stable feeds — use Manual Import or an external tool, then normalize here.
+
 ## Related extractor docs

 - [Gradcracker](/docs/next/extractors/gradcracker)
@ -41,5 +75,12 @@ Many runs combine sources: broad discovery first, then manual import for high-pr
 - [Hiring Cafe](/docs/next/extractors/hiring-cafe)
 - [startup.jobs](/docs/next/extractors/startup-jobs)
 - [UKVisaJobs](/docs/next/extractors/ukvisajobs)
+- [SmartRecruiters](/docs/next/extractors/smartrecruiters)
+- [Supplementary sources — access notes](/docs/next/extractors/supplementary-sources-access-notes)
+- [Eluta](/docs/next/extractors/eluta)
+- [QAJobsBoard](/docs/next/extractors/qajobsboard)
+- [Arc.dev](/docs/next/extractors/arcdev)
+- [Canadian / NA QA contracting firms](/docs/next/extractors/qa-contract-staffing-canada)
+- [Canadian companies — QA-strong ATS](/docs/next/extractors/canadian-companies-qa-ats)
 - [Manual Import](/docs/next/extractors/manual)
 - [Add an Extractor](/docs/next/workflows/add-an-extractor)
--- a/docs-site/docs/extractors/qa-contract-staffing-canada.md
+++ b/docs-site/docs/extractors/qa-contract-staffing-canada.md
@ -0,0 +1,92 @@
+---
+id: qa-contract-staffing-canada
+title: Canadian / NA QA contracting firms
+description: Staffing and consultancy boards that often post QA automation contracts, with JobOps wiring notes and scrape hints.
+sidebar_position: 40
+---
+
+## What it is
+
+A curated list of Canadian and North American **staffing firms and consultancies** that regularly carry **QA / SDET / test automation** contract roles. Coverage emphasizes targets that are **live**, **contract-heavy**, and roughly ordered by **scraping ease** for automation.
+
+This is **not** an extractor implementation checklist: several firms need HTML or browser automation. Use native JobOps extractors where they apply, and [Manual Import](/docs/next/extractors/manual) elsewhere.
+
+## Why it exists
+
+Contract QA pipelines often come through agencies before they appear on Indeed or LinkedIn runs. Mapping firms to **ATS type** (Workday, Greenhouse, Lever, custom API, JS-rendered site) saves weeks of one-off research.
+
+Counts and role titles **change daily** — re-verify listings before relying on them for outreach.
+
+## How to use it
+
+### Tier 1 — Confirmed live QA contracts + scrapable
+
+| Firm | HQ | Where to scrape | Confirmed QA / contract notes |
+| --- | --- | --- | --- |
+| Procom | Toronto | [Find a job](https://procomservices.com/en-ca/find-a-job/) (~230+ roles when checked; paginated HTML). Titles such as “QA/QC Analyst”, “Automation QA Analyst”, “Sr QA Analyst” appear regularly. | Strong banking-sector volume; typical **4–6 month** contracts. No shipped extractor — HTML or browser automation. |
+| S.i. Systems | Calgary / Toronto | [Search IT jobs (`q=QA`)](https://www.sisystems.com/search-it-jobs/?q=QA) — custom web API behind the UI; inspect DevTools network for JSON. | Frequent **Sr QA**, **Mobile QE** (WebdriverIO / Appium) and similar; lots of **GTA** roles; postings refresh often. |
+| Synechron | NYC / Toronto / Montreal | Workday CXS: `POST https://synechron.wd1.myworkdayjobs.com/wday/cxs/synechron/SynechronCareers/jobs` with e.g. `{"limit":20,"offset":0,"searchText":"QA automation"}`. | Often **20+** QA automation-facing rows when searched; includes **Playwright** and related stacks. Add **`https://synechron.wd1.myworkdayjobs.com/en-US/SynechronCareers`** to **`workdayTenants`** / `WORKDAY_TENANTS` and use QA search terms (bundled extractor sends empty facets — see CLI snippet below for Canada facet example). |
+| Capco | London / Toronto | Greenhouse: [boards-api capco](https://boards-api.greenhouse.io/v1/boards/capco/jobs?content=true) | Large board (**700+** roles when checked); dozens QA-related titles but many **India / Poland** — **filter by location** (Toronto / Canada metros). Add **`capco`** to **`greenhouseCompanies`**. |
+| Foilcon | Toronto | [CVViz — Foilcon](https://jobs.cvviz.com/foilcon) | Lower volume; roles such as **Systems Testing QA Specialist** show up when hiring. |
+| Robert Half (Technology) | Toronto / intl | [Jobs — QA automation keyword](https://www.roberthalf.com/ca/en/jobs?keywords=qa+automation) (often Workday-backed listings) | Discover tenant/host patterns from network tab if you want bulk Workday-style pulls; otherwise HTML/manual. |
+| Hays Canada | Toronto | [QA automation search](https://www.hays.ca/job-search/qa-automation) — `/job-detail/...` permalinks | Custom HTML board; manual import or custom crawler. |
+| Randstad Digital | Toronto / Montreal | [Randstad Canada jobs](https://www.randstad.ca/jobs/) | Site listings plus heavy **LinkedIn** contract volume under the Randstad Digital brand; often manual cross-check. |
+| Compunnel | NJ / Toronto | [Job search](https://www.compunnel.com/job-search/) — **JS-rendered** | **Quality Assurance Automation Engineer** (and similar) titles recur; use **Playwright** if automating. |
+| Pyramid Consulting | Atlanta / Toronto | [Job openings](https://www.pyramidci.com/careers/job-openings/) | **QA Automation Engineer** style roles often cross-posted on **LinkedIn** under their brand. |
+| Qualitest Group | NYC / global | [Careers](https://careers.qualitestgroup.com) | Pure-play QA consultancy — schema varies by region; inspect ATS per locale. |
+
+### Tier 2 — Active in Canadian QA contracting but smaller / harder to scrape
+
+| Firm | Notes |
+| --- | --- |
+| Jarvis Consulting Group (`jrvs.ca`) | Toronto; [jobs.jrvs.ca/home/](https://jobs.jrvs.ca/home/) is **JS-rendered** — **Playwright** if scraping; SDET roles also surface on LinkedIn. |
+| Electric Mind (formerly Intelliware) | Toronto. Lever: [`electricmind` postings JSON](https://api.lever.co/v0/postings/electricmind?mode=json) — add **`electricmind`** to **`leverCompanies`** when hiring opens; volume can be **small** (e.g. only a handful of open reqs) and sometimes **no QA** until project demand spikes. |
+| Light Consulting (LightCI) | Toronto. Lever: [`lightci` postings JSON](https://api.lever.co/v0/postings/lightci?mode=json). Often **empty** publicly — they may prefer direct outreach. |
+| Yoush Consulting | Toronto IT staffing; **no structured job board** — SDET contracts often only on **LinkedIn** company presence. |
+| Accenture / Deloitte / EY / KPMG / PwC | Big-four **Canadian banking-tech QA** contract pools; usually **Workday** per brand (e.g. **EY** → `ey.wd3.myworkdayjobs.com`). Add each tenant you care about to **`workdayTenants`**. |
+| CGI | Montreal (large gov / enterprise contractor). [cgi.com/en/careers](https://www.cgi.com/en/careers) — HTML / embedded ATS; inspect for stable patterns. |
+| TEKsystems | US-based with Canadian offices — [Find a job (Canada)](https://www.teksystems.com/en-ca/careers/find-a-job). Enterprise staffing; HTML/search UX varies. |
+| Robertson & Company | Often referenced from **LinkedIn** QA contract threads — treat as manual / referral-led unless you find a stable feed. |
+| Plan A Technologies | Legit shop — [planatechnologies.com](https://www.planatechnologies.com); **no public job board** in many periods; **LinkedIn / referrals**. |
+
+### Ready-to-use CLI probes
+
+Greenhouse (Capco) — Canada-oriented QA filter (tweak city regex as needed):
+
+```bash
+curl -s 'https://boards-api.greenhouse.io/v1/boards/capco/jobs?content=true' \
+  | jq '.jobs[]
+      | select(.title | test("QA|SDET|Test|Automation|Quality"; "i"))
+      | select(.location.name | test("Toronto|Canada|Montreal|Vancouver|Calgary|Ottawa"; "i"))
+      | {title, location: .location.name, url: .absolute_url}'
+```
+
+Synechron Workday — `QA automation` search plus example **country facet** (`appliedFacets.locationCountry`). Facet IDs are **tenant-specific** and **expire or change** — if this stops matching, capture a fresh id from the career site’s network panel.
+
+```bash
+curl -s 'https://synechron.wd1.myworkdayjobs.com/wday/cxs/synechron/SynechronCareers/jobs' \
+  -X POST \
+  -H 'Content-Type: application/json' \
+  -d '{"limit":50,"offset":0,"searchText":"QA automation","appliedFacets":{"locationCountry":["bc33aa3152ec42d4995f4791a106ed09"]}}' \
+  | jq '.jobPostings[]
+      | {title, location: .locationsText, url: ("https://synechron.wd1.myworkdayjobs.com" + .externalPath)}'
+```
+
+### Heads-up: Ionosphere and “Reqd”
+
+- **Ionosphere Inc.** — May only show a **LinkedIn** presence plus legacy **Google Sites** (e.g. `sites.google.com/a/ionosphereinc.com/...`) **without** a real careers board or steady postings — **not** a dependable scrape target unless you confirm a dedicated jobs URL. (“Ionosphere” is also used by unrelated firms — disambiguate by legal name and domain.)
+- **Reqd** — No widely confirmed Canadian IT staffing brand spelled exactly **Reqd**. Possible leads to double-check: **Recroot**, **Reqroute**, **Recruitio**, **Required Technologies**, etc. If you have a **website or sample posting URL**, verify before adding to any automation list.
+
+## Common problems
+
+- **Workday without facets:** The bundled Workday extractor posts `appliedFacets: {}`. You still get roles via **`searchText`**; use tighter terms or post-filter for Canada.
+- **Greenhouse volume:** Boards like Capco are large — always filter by title regex and location text before importing hundreds of rows.
+
+## Related pages
+
+- [Extractors overview](/docs/next/extractors/overview)
+- [Canadian companies — QA-strong ATS](/docs/next/extractors/canadian-companies-qa-ats)
+- [Eluta](/docs/next/extractors/eluta) (Canada employer-direct RSS)
+- [QAJobsBoard](/docs/next/extractors/qajobsboard)
+- [Arc.dev](/docs/next/extractors/arcdev)
+- [Manual Import](/docs/next/extractors/manual)
--- a/docs-site/docs/extractors/qajobsboard.md
+++ b/docs-site/docs/extractors/qajobsboard.md
@ -0,0 +1,36 @@
+---
+id: qajobsboard
+title: QAJobsBoard Extractor
+description: QA and automation-focused listings via the board’s public JSON feed.
+sidebar_position: 16
+---
+
+## What it is
+
+[QAJobsBoard](https://www.qajobsboard.com) publishes postings through JobBoardly. The extractor calls:
+
+`GET https://qajobsboard.jobboardly.com/jobs.json`
+
+Implementation: `extractors/qajobsboard/manifest.ts`.
+
+## Why it exists
+
+Dense QA / SDET / automation signal versus generic boards; categories often reflect tooling (Playwright, Cypress, Selenium). Geography skews India-remote unless you combine region filtering downstream.
+
+## How to use it
+
+1. Enable **QAJobsBoard** in pipeline sources (no credentials).
+2. Set **`qajobsboardMaxJobsPerTerm`** (default `100`) to cap mapped rows after term filtering.
+3. Tune **`searchTerms`** for QA-focused phrases (`QA automation`, `SDET`, `Playwright`, etc.).
+4. Optional: narrow by geography using orchestrator city/country filters where applicable.
+
+## Common problems
+
+- **Few or no rows:** Terms may be too narrow; broaden titles or temporarily remove strict city filters.
+- **Irrelevant locales:** The feed is global; pair with geography or employer filters in your pipeline profile.
+
+## Related pages
+
+- [Extractors overview](/docs/next/extractors/overview)
+- [Canadian QA contracting firms](/docs/next/extractors/qa-contract-staffing-canada)
+- [Manual Import](/docs/next/extractors/manual)
--- a/docs-site/docs/extractors/smartrecruiters.md
+++ b/docs-site/docs/extractors/smartrecruiters.md
@ -0,0 +1,44 @@
+---
+id: smartrecruiters
+title: SmartRecruiters Extractor
+description: Public SmartRecruiters Posting API discovery with per-company identifiers.
+sidebar_position: 14
+---
+
+## What it is
+
+Original API: [SmartRecruiters Posting API](https://developers.smartrecruiters.com/reference/v1listpostings)
+
+The extractor lives in `extractors/smartrecruiters/manifest.ts`. It calls the public JSON endpoints (no API key for public boards), paginates active **PUBLIC** postings per configured company, optionally matches pipeline search terms against title and location, then loads each posting’s detail document so `jobUrl` / `applicationLink` and HTML descriptions resolve to the same URLs candidates see on `jobs.smartrecruiters.com`.
+
+## Why it exists
+
+Many large employers (including a significant share in Canada and the EU) publish on SmartRecruiters. This source complements Greenhouse, Lever, Ashby, and Workday by covering another major ATS with a predictable public API.
+
+## How to use it
+
+1. Find each employer’s **company identifier** — the path segment in their public board URL (for example `jobs.smartrecruiters.com/smartrecruiters/...` → `smartrecruiters`).
+2. In **Settings**, set **SmartRecruiters companies** (`smartrecruitersCompanies`) to a JSON array or comma/newline-separated list of those identifiers, or set `SMARTRECRUITERS_COMPANIES` in the environment.
+3. Optionally set **SmartRecruiters max jobs per company** (`smartrecruitersMaxJobsPerCompany`, default `100`, max `500`) to cap pagination after term filtering.
+4. Set your pipeline **search geography** and **search terms** as usual; terms filter postings by title, location text, and company display name.
+5. Enable **SmartRecruiters** in pipeline sources and run the pipeline.
+
+## Common problems
+
+### SmartRecruiters never appears in source toggles
+
+- No companies are configured (`smartrecruitersCompanies` / `SMARTRECRUITERS_COMPANIES` is empty).
+
+### Zero jobs for a slug I know is correct
+
+- The identifier must match the **public Posting API** path, not necessarily the marketing site name. Confirm listings exist on `jobs.smartrecruiters.com/<identifier>/`.
+
+### Rate limiting or intermittent HTTP errors
+
+- Reduce `smartrecruitersMaxJobsPerCompany` or the number of configured companies; each kept posting triggers a detail request after the list pass.
+
+## Related pages
+
+- [Extractors Overview](/docs/next/extractors/overview)
+- [Add an Extractor](/docs/next/workflows/add-an-extractor)
+- [Settings](/docs/next/features/settings)
--- a/docs-site/docs/extractors/supplementary-sources-access-notes.md
+++ b/docs-site/docs/extractors/supplementary-sources-access-notes.md
@ -0,0 +1,73 @@
+---
+id: supplementary-sources-access-notes
+title: Supplementary sources — access notes
+description: Credential gates, sources to skip, and practical alternatives for boards without a native JobOps extractor.
+sidebar_position: 15
+---
+
+This page captures **verified access paths** and realistic integration effort for boards that are not fully wired as pipeline extractors. Pair it with [Extractors overview](/docs/next/extractors/overview), [Manual Import](/docs/next/extractors/manual), and [Add an Extractor](/docs/next/workflows/add-an-extractor).
+
+## Credential-gated APIs (usually straightforward)
+
+### Careerjet (v4)
+
+- **Sign-up:** [careerjet.com/partners](https://www.careerjet.com/partners) → add your site → Access API → register **server egress IP(s)**.
+- **Endpoint:** `https://search.api.careerjet.net/v4/query`
+- **Important parameters:** `affid` (publisher key), **`user_ip`** (documented as end-user IP; for headless/server runs use an IP you allowlisted — fraud-checked), **`user_agent`**, **`url`** (referrer URL where results would appear — maps to `CAREERJET_REFERER` / query `url` + `Referer` header). Missing `user_ip` or `user_agent` tends to yield **403**.
+- **Tip:** Official Python client: [`careerjet/careerjet-api-client-python`](https://github.com/careerjet/careerjet-api-client-python).
+
+### Reed
+
+- **Sign-up:** [reed.co.uk/developers](https://www.reed.co.uk/developers) — API key is issued via their contact flow (often ~1–2 business days).
+- **Endpoint:** e.g. `https://www.reed.co.uk/api/1.0/search?keywords=...&locationName=...&resultsToTake=100`
+- **Auth:** HTTP Basic — username = API key, password empty (`curl -u "YOUR_API_KEY:" ...`).
+- **Pagination:** `resultsToTake` max **100** per request; advance with `resultsToSkip`.
+- **Scope:** UK-centric; still useful for remote UK employers.
+
+## Usually not worth scraping yourself
+
+### Job Bank (Canada)
+
+XML syndication is **manual approval**: active Canadian Business Number, established Canadian-facing employment site. No simple public JSON/RSS for arbitrary candidates. HTML exists but is heavy JSF / anti-bot — treat as **skip** unless you qualify for the feed.
+
+### Jobboom / Workopolis / BCJobs
+
+No stable public API/RSS documented for generic job discovery. Third-party scrapers often need **residential proxies** and paid runtime — **skip or pay** for a maintained provider.
+
+### Jobillico
+
+Employer-oriented XML/OAuth API (posting and limited pull). Needs a **business account** — not a candidate discovery API.
+
+### MyVisaJobs / H1BGrader
+
+No practical public API for their enriched UX. Alternatives: **DOL OFLC LCA disclosure** quarterly CSVs (public, bulk), then join to your own job corpus; paid marketplace scrapers if you accept cost/compliance tradeoffs. Browser extensions may still be useful **personally**.
+
+### Untapped (Jopwell)
+
+Closed candidate platform — **no public job-posting API** for arbitrary ingestion.
+
+## Practical additions in JobOps
+
+### iCIMS (per-tenant HTML)
+
+Many tenants expose anonymous search HTML suitable for stable scraping patterns, e.g.:
+
+`https://{tenant}.icims.com/jobs/search?ss=1&searchKeyword=…&in_iframe=1`
+
+Pagination often uses `pr=`; job URLs commonly follow `/jobs/{id}/{slug}/job`. Maintain a **tenant host list** (similar to Greenhouse/Lever company lists). This is **not** the authenticated iCIMS Job Portal API.
+
+Shipped extractor: **iCIMS tenants (HTML)** — configure `icimsTenants` (+ caps in Settings).
+
+### BC T-Net RSS
+
+Free aggregate RSS (example): `https://www.bctechnology.com/rss/jobs/tnetjobs.xml` — useful for **BC / Vancouver** tech roles; custom slices via the site’s RSS builder.
+
+Shipped extractor: **BC T-Net (RSS)** — Canada geography only; optional `bctenetRssUrls` overrides default feed.
+
+## Related pages
+
+- [Extractors overview](/docs/next/extractors/overview)
+- [Eluta](/docs/next/extractors/eluta) (Canada RSS)
+- [SmartRecruiters](/docs/next/extractors/smartrecruiters)
+- [Canadian companies — QA-strong ATS](/docs/next/extractors/canadian-companies-qa-ats)
+- [Manual Import](/docs/next/extractors/manual)
--- a/docs-site/docs/workflows/add-an-extractor.md
+++ b/docs-site/docs/workflows/add-an-extractor.md
@ -41,7 +41,8 @@ That keeps runtime wiring dynamic while preserving compile-time safety in API an
   - append to `EXTRACTOR_SOURCE_IDS`
   - add an entry in `EXTRACTOR_SOURCE_METADATA`
 5. Ensure your extractor maps output to `CreateJobInput[]`.
-6. Run the full CI checks.
+6. Register it in `scripts/smoke-extractors.ts` (`ALL_TARGETS`): add one row per manifest so `npx tsx scripts/smoke-extractors.ts` exercises every shipped extractor (keyed sources `SKIP` until env vars exist).
+7. Run the full CI checks.

 Example manifest:

@ -77,6 +78,22 @@ Subprocess extractors are supported. Keep subprocess spawning inside `run(contex
 - Add the new source id to `shared/src/extractors/index.ts`.
 - Confirm metadata exists for that source id.

+### Smoke connectivity
+
+After wiring settings/env, run:
+
+```bash
+npx tsx scripts/smoke-extractors.ts myextractor
+```
+
+Or the full suite (may take several minutes — JobSpy invokes Python, Hiring Cafe / startup.jobs may need browser deps):
+
+```bash
+npx tsx scripts/smoke-extractors.ts
+```
+
+Keep `ALL_TARGETS` in that script aligned with manifests under each `extractors/<name>/` package (`manifest.ts` or `src/manifest.ts`).
+
 ### Source appears in shared catalog but is unavailable at runtime

 - The manifest was not loaded successfully.
--- a/docs-site/sidebars.ts
+++ b/docs-site/sidebars.ts
@ -46,6 +46,11 @@ const sidebars: SidebarsConfig = {
      label: "Extractors",
      items: [
        "extractors/overview",
+        "extractors/supplementary-sources-access-notes",
+        "extractors/qajobsboard",
+        "extractors/arcdev",
+        "extractors/qa-contract-staffing-canada",
+        "extractors/canadian-companies-qa-ats",
        "extractors/gradcracker",
        "extractors/jobspy",
        "extractors/adzuna",
--- a/extractors/arcdev/README.md
+++ b/extractors/arcdev/README.md
@ -0,0 +1,15 @@
+# arcdev-extractor
+
+Reads Arc remote-job listings from **SSR HTML**: each page embeds `__NEXT_DATA__` with `arcJobs` (Arc talent network) and `externalJobs` (partner postings).
+
+Configure **`arcRemoteJobsPaths`** as URL paths on `https://arc.dev`, for example:
+
+- `/remote-jobs/playwright`
+- `/remote-jobs/cypress`
+- `/remote-jobs/selenium`
+
+Or set `ARC_REMOTE_JOBS_PATHS` (comma/newline-separated). Defaults include Playwright and Cypress stacks.
+
+**Employer names:** External jobs include `company.name`. Arc-managed listings omit company names in the payload — those rows use employer `"Arc talent network"` while preserving titles and skill categories.
+
+Cap merged matches per configuration fetch via `arcMaxJobsPerPath` (applied separately per path, default `120`).
--- a/extractors/arcdev/manifest.ts
+++ b/extractors/arcdev/manifest.ts
@ -0,0 +1,329 @@
+/**
+ * Arc.dev remote jobs — parse embedded Next.js __NEXT_DATA__ from SSR HTML.
+ *
+ * Listing URLs look like https://arc.dev/remote-jobs/playwright
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+const ORIGIN = "https://arc.dev";
+
+interface ArcCategory {
+  name?: string;
+  urlString?: string;
+}
+
+interface ArcCompanyJson {
+  randomKey?: string | null;
+  urlString?: string;
+  name?: string;
+}
+
+interface ArcJobJson {
+  randomKey?: string;
+  title?: string;
+  jobType?: string;
+  jobRole?: string;
+  urlString?: string;
+  postedAt?: number;
+  company?: ArcCompanyJson;
+  categories?: ArcCategory[];
+  requiredCountries?: string[];
+  minAnnualSalary?: number | null;
+  maxAnnualSalary?: number | null;
+  minHourlyRate?: number | null;
+  maxHourlyRate?: number | null;
+  timeZone?: string | null;
+  positionType?: string;
+  experienceLevel?: string;
+  experienceLevels?: string[];
+}
+
+function readPaths(raw: string | undefined): string[] {
+  if (!raw) return [];
+  try {
+    const parsed = JSON.parse(raw);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .map((entry) => (typeof entry === "string" ? entry.trim() : ""))
+        .filter(Boolean);
+    }
+  } catch {
+    // fall through
+  }
+  return raw
+    .split(/[\n,;|]+/)
+    .map((entry) => entry.trim())
+    .filter(Boolean);
+}
+
+function defaultArcPaths(): string[] {
+  const raw =
+    typeof process !== "undefined" ? process.env.ARC_REMOTE_JOBS_PATHS : "";
+  const parsed = readPaths(raw);
+  return parsed.length > 0
+    ? parsed
+    : ["/remote-jobs/playwright", "/remote-jobs/cypress"];
+}
+
+function asString(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  const t = value.trim();
+  return t ? t : undefined;
+}
+
+function categoryHaystack(job: ArcJobJson): string {
+  if (!Array.isArray(job.categories)) return "";
+  return job.categories
+    .map((c) => `${c.name ?? ""} ${c.urlString ?? ""}`)
+    .join(" ")
+    .toLowerCase();
+}
+
+function matchesTerm(job: ArcJobJson, term: string): boolean {
+  const lower = term.toLowerCase();
+  if (job.title?.toLowerCase().includes(lower)) return true;
+  if (categoryHaystack(job).includes(lower)) return true;
+  if (job.jobRole?.toLowerCase().includes(lower)) return true;
+  if (job.positionType?.toLowerCase().includes(lower)) return true;
+  if (
+    Array.isArray(job.experienceLevels) &&
+    job.experienceLevels.some((l) => l.toLowerCase().includes(lower))
+  )
+    return true;
+  if (job.experienceLevel?.toLowerCase().includes(lower)) return true;
+  return false;
+}
+
+function salaryParts(job: ArcJobJson): string | undefined {
+  const bits: string[] = [];
+  if (
+    typeof job.minAnnualSalary === "number" &&
+    typeof job.maxAnnualSalary === "number"
+  ) {
+    bits.push(`USD ${job.minAnnualSalary}–${job.maxAnnualSalary} / yr`);
+  } else if (typeof job.minAnnualSalary === "number") {
+    bits.push(`USD ${job.minAnnualSalary}+ / yr`);
+  }
+  if (
+    typeof job.minHourlyRate === "number" ||
+    typeof job.maxHourlyRate === "number"
+  ) {
+    bits.push(`$${job.minHourlyRate ?? "?"}–${job.maxHourlyRate ?? "?"} / hr`);
+  }
+  return bits.length > 0 ? bits.join("; ") : undefined;
+}
+
+function locationLine(job: ArcJobJson): string {
+  if (
+    Array.isArray(job.requiredCountries) &&
+    job.requiredCountries.length > 0
+  ) {
+    return job.requiredCountries.join(", ");
+  }
+  if (job.timeZone) return job.timeZone;
+  return "Remote";
+}
+
+function postedIso(postedAt: number | undefined): string | undefined {
+  if (typeof postedAt !== "number" || !Number.isFinite(postedAt))
+    return undefined;
+  return new Date(postedAt * 1000).toISOString();
+}
+
+function parseNextPageProps(html: string): {
+  arcJobs: ArcJobJson[];
+  externalJobs: ArcJobJson[];
+} | null {
+  const match = html.match(
+    /<script id="__NEXT_DATA__"[^>]*>([\s\S]*?)<\/script>/,
+  );
+  if (!match?.[1]) return null;
+  try {
+    const parsed = JSON.parse(match[1]) as {
+      props?: { pageProps?: unknown };
+    };
+    const pageProps = parsed.props?.pageProps as
+      | {
+          arcJobs?: ArcJobJson[];
+          externalJobs?: ArcJobJson[];
+        }
+      | undefined;
+    if (!pageProps) return null;
+    return {
+      arcJobs: Array.isArray(pageProps.arcJobs) ? pageProps.arcJobs : [],
+      externalJobs: Array.isArray(pageProps.externalJobs)
+        ? pageProps.externalJobs
+        : [],
+    };
+  } catch {
+    return null;
+  }
+}
+
+function mapExternalJob(job: ArcJobJson): CreateJobInput | null {
+  const rk = asString(job.randomKey);
+  const slug = asString(job.urlString);
+  if (!rk || !slug) return null;
+  const jobUrl = `${ORIGIN}/remote-jobs/j/${slug}-${rk}`;
+  const employer = asString(job.company?.name)?.trim() || "Unknown employer";
+
+  const disciplines = Array.isArray(job.categories)
+    ? job.categories
+        .map((c) => c.name?.trim())
+        .filter((v): v is string => Boolean(v))
+        .join(", ")
+    : undefined;
+
+  return {
+    source: "arcdev",
+    sourceJobId: slug,
+    title: asString(job.title) ?? "Unknown Title",
+    employer,
+    jobUrl,
+    applicationLink: jobUrl,
+    location: locationLine(job),
+    datePosted: postedIso(job.postedAt),
+    jobType: asString(job.jobType),
+    salary: salaryParts(job),
+    disciplines,
+    jobLevel:
+      job.experienceLevels?.join(", ") ??
+      asString(job.experienceLevel) ??
+      undefined,
+    isRemote: true,
+  };
+}
+
+function mapArcManagedJob(job: ArcJobJson): CreateJobInput | null {
+  const rk = asString(job.randomKey);
+  const slug = asString(job.urlString);
+  if (!rk || !slug) return null;
+  const jobUrl = `${ORIGIN}/remote-jobs/details/${slug}-${rk}`;
+
+  const disciplines = Array.isArray(job.categories)
+    ? job.categories
+        .map((c) => c.name?.trim())
+        .filter((v): v is string => Boolean(v))
+        .join(", ")
+    : undefined;
+
+  const employer = "Arc talent network";
+
+  return {
+    source: "arcdev",
+    sourceJobId: `${slug}-${rk}`,
+    title: asString(job.title) ?? "Unknown Title",
+    employer,
+    jobUrl,
+    applicationLink: jobUrl,
+    location: locationLine(job),
+    datePosted: postedIso(job.postedAt),
+    jobType: asString(job.jobType),
+    salary: salaryParts(job),
+    disciplines,
+    jobLevel: asString(job.experienceLevel),
+    jobFunction: asString(job.jobRole),
+    isRemote: true,
+  };
+}
+
+export const manifest: ExtractorManifest = {
+  id: "arcdev",
+  displayName: "Arc.dev (remote)",
+  providesSources: ["arcdev"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    let paths = readPaths(context.settings.arcRemoteJobsPaths);
+    if (paths.length === 0) paths = defaultArcPaths();
+
+    paths = paths.map((p) => (p.startsWith("/") ? p : `/${p}`));
+
+    const maxPerPath = context.settings.arcMaxJobsPerPath
+      ? Number.parseInt(context.settings.arcMaxJobsPerPath, 10)
+      : 120;
+    const cap = Number.isFinite(maxPerPath)
+      ? Math.min(Math.max(maxPerPath, 1), 300)
+      : 120;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [];
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    try {
+      for (let i = 0; i < paths.length; i += 1) {
+        if (context.shouldCancel?.()) break;
+        const path = paths[i];
+        const pageUrl = `${ORIGIN}${path}`;
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i,
+          termsTotal: paths.length,
+          currentUrl: pageUrl,
+          detail: `Arc.dev: fetching (${i + 1}/${paths.length}) ${path}`,
+        });
+
+        const response = await fetch(pageUrl, {
+          headers: {
+            Accept: "text/html",
+            "User-Agent":
+              "Mozilla/5.0 (compatible; JobOps/1.0; +https://github.com)",
+          },
+        });
+        if (!response.ok) {
+          throw new Error(
+            `Arc.dev "${path}" failed with status ${response.status}`,
+          );
+        }
+        const html = await response.text();
+        const payload = parseNextPageProps(html);
+        if (!payload) {
+          throw new Error(`Arc.dev "${path}": missing __NEXT_DATA__ payload`);
+        }
+
+        let pathAdded = 0;
+
+        const labeled = [
+          ...payload.arcJobs.map((job) => ({ job, kind: "arc" as const })),
+          ...payload.externalJobs.map((job) => ({ job, kind: "ext" as const })),
+        ];
+
+        for (const { job: raw, kind } of labeled) {
+          if (pathAdded >= cap) break;
+          if (terms.length > 0 && !terms.some((t) => matchesTerm(raw, t))) {
+            continue;
+          }
+          const mapped =
+            kind === "arc" ? mapArcManagedJob(raw) : mapExternalJob(raw);
+          if (!mapped) continue;
+          if (seen.has(mapped.jobUrl)) continue;
+          seen.add(mapped.jobUrl);
+          out.push(mapped);
+          pathAdded += 1;
+        }
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i + 1,
+          termsTotal: paths.length,
+          currentUrl: pageUrl,
+          jobPagesProcessed: out.length,
+          detail: `Arc.dev: ${path} → ${pathAdded} kept (${payload.arcJobs.length} arc + ${payload.externalJobs.length} external rows)`,
+        });
+      }
+
+      return { success: true, jobs: out };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: out, error: message };
+    }
+  },
+};
+
+export default manifest;
--- a/extractors/arcdev/package.json
+++ b/extractors/arcdev/package.json
@ -0,0 +1,17 @@
+{
+  "name": "arcdev-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "Arc.dev remote jobs extractor (__NEXT_DATA__ SSR)",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}
--- a/extractors/arcdev/tsconfig.json
+++ b/extractors/arcdev/tsconfig.json
@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}
--- a/extractors/bctenet/README.md
+++ b/extractors/bctenet/README.md
@ -0,0 +1,9 @@
+# bctenet-extractor
+
+Consumes the public **BC T-Net** aggregated tech-jobs RSS feed (no auth).
+
+Default feed: `https://www.bctechnology.com/rss/jobs/tnetjobs.xml`
+
+Controls: `bctenetRssUrls` (optional extra feeds from the T-Net RSS builder), `bctenetMaxJobsPerTerm`.
+
+Canada-focused listings (British Columbia). The orchestrator skips this source when pipeline geography is not Canada (`countryAllowlist`).
--- a/extractors/bctenet/manifest.ts
+++ b/extractors/bctenet/manifest.ts
@ -0,0 +1,194 @@
+/**
+ * BC T-Net — public RSS aggregate of BC tech jobs.
+ *
+ * Default: https://www.bctechnology.com/rss/jobs/tnetjobs.xml
+ *
+ * Feeds may embed `<![CDATA[&]]>` inside `<link>` URLs — normalized before fetch.
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+interface BcItem {
+  title?: string;
+  link?: string;
+  guid?: string;
+  description?: string;
+  pubDate?: string;
+  category?: string;
+}
+
+function xmlText(xml: string, tag: string): string | undefined {
+  const pattern = new RegExp(`<${tag}[^>]*>([\\s\\S]*?)</${tag}>`);
+  const match = xml.match(pattern);
+  if (!match?.[1]) return undefined;
+  return (
+    match[1].replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, "$1").trim() || undefined
+  );
+}
+
+function normalizeFeedLink(raw: string): string {
+  return raw.replace(/<!\[CDATA\[&\]\]>/g, "&").trim();
+}
+
+function parseItems(xml: string): BcItem[] {
+  const items: BcItem[] = [];
+  const blocks = xml.match(/<item>([\s\S]*?)<\/item>/g) ?? [];
+
+  for (const raw of blocks) {
+    const block = raw.replace(/^<item>/, "").replace(/<\/item>$/, "");
+    const linkRaw = xmlText(block, "link");
+    items.push({
+      title: xmlText(block, "title"),
+      link: linkRaw ? normalizeFeedLink(linkRaw) : undefined,
+      guid: xmlText(block, "guid"),
+      description: xmlText(block, "description"),
+      pubDate: xmlText(block, "pubDate"),
+      category: xmlText(block, "category"),
+    });
+  }
+
+  return items;
+}
+
+function readUrls(raw: string | undefined): string[] {
+  if (!raw) return [];
+  try {
+    const parsed = JSON.parse(raw);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .map((entry) => (typeof entry === "string" ? entry.trim() : ""))
+        .filter(Boolean);
+    }
+  } catch {
+    // fall through
+  }
+  return raw
+    .split(/[\n|]+/)
+    .map((entry) => entry.trim())
+    .filter(Boolean);
+}
+
+function decodeHtmlEntities(html: string): string {
+  return html
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&#x2f;/gi, "/")
+    .replace(/&#x26;/gi, "&");
+}
+
+function matchesTerm(item: BcItem, term: string): boolean {
+  const lower = term.toLowerCase();
+  const hay =
+    `${item.title ?? ""} ${item.description ?? ""} ${item.category ?? ""}`.toLowerCase();
+  return hay.includes(lower);
+}
+
+function mapJob(item: BcItem): CreateJobInput | null {
+  const jobUrl = item.link?.trim();
+  if (!jobUrl) return null;
+
+  const title = item.title ? decodeHtmlEntities(item.title) : "Unknown Title";
+  const employer = item.category?.trim() || "Unknown Employer";
+
+  return {
+    source: "bctenet",
+    sourceJobId: item.guid ?? jobUrl,
+    title,
+    employer,
+    jobUrl,
+    applicationLink: jobUrl,
+    location: "British Columbia, Canada",
+    datePosted: item.pubDate,
+    jobDescription: item.description
+      ? decodeHtmlEntities(item.description)
+      : undefined,
+  };
+}
+
+export const manifest: ExtractorManifest = {
+  id: "bctenet",
+  displayName: "BC T-Net (RSS)",
+  providesSources: ["bctenet"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const defaults = ["https://www.bctechnology.com/rss/jobs/tnetjobs.xml"];
+    const configured = readUrls(context.settings.bctenetRssUrls);
+    const urls = configured.length > 0 ? configured : defaults;
+
+    const maxJobs = context.settings.bctenetMaxJobsPerTerm
+      ? Number.parseInt(context.settings.bctenetMaxJobsPerTerm, 10)
+      : 400;
+    const cap = Number.isFinite(maxJobs)
+      ? Math.min(Math.max(maxJobs, 1), 2000)
+      : 400;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [];
+    const maxTotal = cap * Math.max(terms.length, 1);
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    try {
+      for (let i = 0; i < urls.length; i += 1) {
+        if (context.shouldCancel?.()) break;
+        const rssUrl = urls[i];
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i,
+          termsTotal: urls.length,
+          currentUrl: rssUrl,
+          detail: `BC T-Net: fetching (${i + 1}/${urls.length})`,
+        });
+
+        const response = await fetch(rssUrl, {
+          headers: {
+            Accept: "application/rss+xml, application/xml, text/xml",
+            "User-Agent":
+              "Mozilla/5.0 (compatible; JobOps/1.0) BC T-Net RSS consumer",
+          },
+        });
+        if (!response.ok) {
+          throw new Error(`BC T-Net RSS failed: ${response.status}`);
+        }
+
+        const xml = await response.text();
+        const items = parseItems(xml);
+
+        for (const item of items) {
+          if (out.length >= maxTotal) break;
+          if (terms.length > 0 && !terms.some((t) => matchesTerm(item, t))) {
+            continue;
+          }
+          const mapped = mapJob(item);
+          if (!mapped) continue;
+          const key = mapped.sourceJobId || mapped.jobUrl;
+          if (seen.has(key)) continue;
+          seen.add(key);
+          out.push(mapped);
+        }
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i + 1,
+          termsTotal: urls.length,
+          currentUrl: rssUrl,
+          jobPagesProcessed: out.length,
+          detail: `BC T-Net: ${items.length} items (${out.length} kept total)`,
+        });
+      }
+
+      return { success: true, jobs: out };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: out, error: message };
+    }
+  },
+};
+
+export default manifest;
--- a/extractors/bctenet/package.json
+++ b/extractors/bctenet/package.json
@ -0,0 +1,17 @@
+{
+  "name": "bctenet-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "BC T-Net public RSS job feed (British Columbia tech roles)",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}
--- a/extractors/bctenet/tsconfig.json
+++ b/extractors/bctenet/tsconfig.json
@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}
--- a/extractors/careerjet/manifest.ts
+++ b/extractors/careerjet/manifest.ts
@ -8,8 +8,11 @@
 * Referer header and `user_ip` / `user_agent` query params. Register your
 * server's outbound IP(s) in the Careerjet publisher dashboard.
 *
- * Env: CAREERJET_AFFID (API key), CAREERJET_REFERER (job-search page URL),
- * CAREERJET_USER_IP (must match an allowlisted IP), optional CAREERJET_USER_AGENT.
+ * Publisher signup: careerjet.com/partners → register allowlisted server IP(s).
+ * Env: CAREERJET_AFFID (API key for Basic auth username), CAREERJET_REFERER (maps to
+ * Referer header and the API `url` query param — page where results would appear),
+ * CAREERJET_USER_IP (public egress IP allowlisted in dashboard; fraud-checked),
+ * optional CAREERJET_USER_AGENT. Missing user_ip / user_agent yields 403 per docs.
 */

 import type {
@ -117,6 +120,7 @@ async function fetchPage(args: {
  url.searchParams.set("page_size", String(args.pageSize));
  url.searchParams.set("user_ip", args.userIp);
  url.searchParams.set("user_agent", args.userAgent);
+  url.searchParams.set("url", args.referer);

  const response = await fetch(url.toString(), {
    headers: {
@ -213,11 +217,7 @@ export const manifest: ExtractorManifest = {
        let collected = 0;
        let page = 1;
        let totalPages = Number.POSITIVE_INFINITY;
-        while (
-          collected < maxJobsPerTerm &&
-          page <= totalPages &&
-          page <= 10
-        ) {
+        while (collected < maxJobsPerTerm && page <= totalPages && page <= 10) {
          if (context.shouldCancel?.()) break;
          const body = await fetchPage({
            apiKey,
--- a/extractors/eluta/README.md
+++ b/extractors/eluta/README.md
@ -0,0 +1,9 @@
+# eluta-extractor
+
+Pulls Canadian job postings from [Eluta.ca](https://www.eluta.ca) public **RSS** feeds (`https://www.eluta.ca/rss?location=...`). Listings are indexed from employer career sites.
+
+- Configure **`elutaRssLocations`**: JSON array or comma/newline-separated location strings passed to the `location` query parameter (e.g. `Toronto, ON`, `Vancouver, BC`). RSS for very broad regions (e.g. a whole country) may return an empty feed; prefer metro/province strings.
+- Optional: `ELUTA_RSS_LOCATIONS` environment default (same format).
+- **`elutaMaxJobsPerTerm`** caps how many RSS items are kept after pipeline search-term filtering (default 100).
+
+This source is **Canada-only**: it is automatically skipped when your search geography is not Canada.
--- a/extractors/eluta/manifest.ts
+++ b/extractors/eluta/manifest.ts
@ -0,0 +1,201 @@
+/**
+ * Eluta.ca — public RSS feeds (Canadian employer-direct listings).
+ *
+ * Example: https://www.eluta.ca/rss?location=Toronto%2C%20ON
+ *
+ * No auth. Multiple `elutaRssLocations` values each fetch a feed; results are
+ * merged and de-duplicated by guid/link.
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+const RSS_BASE = "https://www.eluta.ca/rss";
+
+interface ElutaItem {
+  title?: string;
+  link?: string;
+  guid?: string;
+  description?: string;
+  pubDate?: string;
+  employer?: string;
+  location?: string;
+}
+
+function xmlText(xml: string, tag: string): string | undefined {
+  const pattern = new RegExp(`<${tag}[^>]*>([\\s\\S]*?)</${tag}>`);
+  const match = xml.match(pattern);
+  if (!match?.[1]) return undefined;
+  return (
+    match[1].replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, "$1").trim() || undefined
+  );
+}
+
+function parseItems(xml: string): ElutaItem[] {
+  const items: ElutaItem[] = [];
+  const blocks = xml.match(/<item>([\s\S]*?)<\/item>/g) ?? [];
+
+  for (const raw of blocks) {
+    const block = raw.replace(/^<item>/, "").replace(/<\/item>$/, "");
+    items.push({
+      title: xmlText(block, "title"),
+      link: xmlText(block, "link"),
+      guid: xmlText(block, "guid"),
+      description: xmlText(block, "description"),
+      pubDate: xmlText(block, "pubDate"),
+      employer: xmlText(block, "employer"),
+      location: xmlText(block, "location"),
+    });
+  }
+
+  return items;
+}
+
+function readLocations(raw: string | undefined): string[] {
+  if (!raw) return [];
+  try {
+    const parsed = JSON.parse(raw);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .map((entry) => (typeof entry === "string" ? entry.trim() : ""))
+        .filter(Boolean);
+    }
+  } catch {
+    // fall through
+  }
+  return raw
+    .split(/[\n,;|]+/)
+    .map((entry) => entry.trim())
+    .filter(Boolean);
+}
+
+function decodeHtmlEntities(html: string): string {
+  return html
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">");
+}
+
+function matchesTerm(item: ElutaItem, term: string): boolean {
+  const lower = term.toLowerCase();
+  if (item.title?.toLowerCase().includes(lower)) return true;
+  if (item.description?.toLowerCase().includes(lower)) return true;
+  if (item.employer?.toLowerCase().includes(lower)) return true;
+  if (item.location?.toLowerCase().includes(lower)) return true;
+  return false;
+}
+
+function mapJob(item: ElutaItem): CreateJobInput | null {
+  const jobUrl = item.link || item.guid;
+  if (!jobUrl) return null;
+
+  const title = item.title ? decodeHtmlEntities(item.title) : "Unknown Title";
+  const employer = item.employer?.trim() || "Unknown Employer";
+  const location = item.location?.trim() || "Canada";
+
+  return {
+    source: "eluta",
+    sourceJobId: item.guid ?? item.link,
+    title,
+    employer,
+    jobUrl,
+    applicationLink: jobUrl,
+    location,
+    datePosted: item.pubDate,
+    jobDescription: item.description
+      ? decodeHtmlEntities(item.description)
+      : undefined,
+  };
+}
+
+export const manifest: ExtractorManifest = {
+  id: "eluta",
+  displayName: "Eluta",
+  providesSources: ["eluta"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const locations = readLocations(context.settings.elutaRssLocations);
+    if (locations.length === 0) {
+      return {
+        success: true,
+        jobs: [],
+        error:
+          'No Eluta RSS locations configured. Set ELUTA_RSS_LOCATIONS or elutaRssLocations (comma- or newline-separated, e.g. "Toronto, ON|Vancouver, BC").',
+      };
+    }
+
+    const maxJobs = context.settings.elutaMaxJobsPerTerm
+      ? Number.parseInt(context.settings.elutaMaxJobsPerTerm, 10)
+      : 100;
+    const cap = Number.isFinite(maxJobs)
+      ? Math.min(Math.max(maxJobs, 1), 500)
+      : 100;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [];
+    const maxTotal = cap * Math.max(terms.length, 1);
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    try {
+      for (let i = 0; i < locations.length; i += 1) {
+        if (context.shouldCancel?.()) break;
+        const loc = locations[i];
+        const rssUrl = `${RSS_BASE}?location=${encodeURIComponent(loc)}`;
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i,
+          termsTotal: locations.length,
+          currentUrl: rssUrl,
+          detail: `Eluta: fetching RSS (${i + 1}/${locations.length}) — ${loc}`,
+        });
+
+        const response = await fetch(rssUrl, {
+          headers: {
+            Accept: "application/rss+xml, application/xml, text/xml",
+            "User-Agent": "JobOps/1.0 (+https://github.com) Eluta RSS consumer",
+          },
+        });
+        if (!response.ok) {
+          throw new Error(`Eluta RSS failed (${loc}): ${response.status}`);
+        }
+
+        const xml = await response.text();
+        const items = parseItems(xml);
+
+        for (const item of items) {
+          if (out.length >= maxTotal) break;
+          if (terms.length > 0 && !terms.some((t) => matchesTerm(item, t))) {
+            continue;
+          }
+          const mapped = mapJob(item);
+          if (!mapped) continue;
+          const key = mapped.sourceJobId || mapped.jobUrl;
+          if (seen.has(key)) continue;
+          seen.add(key);
+          out.push(mapped);
+        }
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i + 1,
+          termsTotal: locations.length,
+          currentUrl: rssUrl,
+          jobPagesProcessed: out.length,
+          detail: `Eluta: ${loc} → ${items.length} items in feed (${out.length} matched total)`,
+        });
+      }
+
+      return { success: true, jobs: out };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: out, error: message };
+    }
+  },
+};
+
+export default manifest;
--- a/extractors/eluta/package.json
+++ b/extractors/eluta/package.json
@ -0,0 +1,17 @@
+{
+  "name": "eluta-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "Eluta.ca RSS feed extractor (Canadian employer-direct listings)",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}
--- a/extractors/eluta/tsconfig.json
+++ b/extractors/eluta/tsconfig.json
@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}
--- a/extractors/icims/README.md
+++ b/extractors/icims/README.md
@ -0,0 +1,13 @@
+# icims-extractor
+
+Lightweight fetch of **anonymous iCIMS portal HTML search results** per configured tenant host.
+
+Example host: `careers-appliedsystems.icims.com`
+
+Controls:
+
+- `icimsTenants` — newline/comma-separated hosts or JSON array of hosts
+- `icimsMaxJobsPerTenant` — cap rows accepted per tenant host (default `250`)
+- `icimsMaxPagesPerSearch` — max `pr=` pages per keyword query (default `10`)
+
+This does **not** use the authenticated iCIMS Job Portal API.
--- a/extractors/icims/manifest.ts
+++ b/extractors/icims/manifest.ts
@ -0,0 +1,233 @@
+/**
+ * iCIMS tenant portal — anonymous HTML search (`/jobs/search`) pattern.
+ *
+ * Many tenants expose listings suitable for HTML extraction when loaded with
+ * `ss=1` + `in_iframe=1`. Job links typically follow `/jobs/{id}/{slug}/job`.
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+interface ParsedJobRow {
+  url: string;
+  title: string;
+}
+
+function parseHosts(raw: string | undefined): string[] {
+  if (!raw) return [];
+  try {
+    const parsed = JSON.parse(raw);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .map((entry) => (typeof entry === "string" ? entry.trim() : ""))
+        .filter(Boolean);
+    }
+  } catch {
+    // fall through
+  }
+  return raw
+    .split(/[\n,]+/)
+    .map((entry) => entry.trim())
+    .filter(Boolean);
+}
+
+function normalizeHost(hostOrUrl: string): string {
+  const trimmed = hostOrUrl.trim();
+  if (!trimmed) return "";
+  try {
+    if (trimmed.includes("://")) {
+      const url = new URL(trimmed);
+      return url.host;
+    }
+  } catch {
+    return trimmed.replace(/^\/\//, "");
+  }
+  return trimmed.replace(/^\/\//, "");
+}
+
+function canonicalJobUrl(url: string): string {
+  try {
+    const parsed = new URL(url);
+    parsed.search = "";
+    return parsed.toString();
+  } catch {
+    return url.replace(/\?[^#]*/, "");
+  }
+}
+
+function extractRows(html: string): ParsedJobRow[] {
+  const out: ParsedJobRow[] = [];
+  const seen = new Set<string>();
+
+  const primary =
+    /<a[^>]*href="(https:\/\/[^"]+\/jobs\/\d+\/[^"]+\/job)(?:\?[^"]*)?"[^>]*title="\d+\s*-\s*([^"]+)"/gi;
+  for (;;) {
+    const match = primary.exec(html);
+    if (match === null) break;
+    const url = canonicalJobUrl(match[1]);
+    const title = match[2]?.trim();
+    if (!url || !title || seen.has(url)) continue;
+    seen.add(url);
+    out.push({ url, title });
+  }
+
+  const fallback =
+    /<a[^>]*href="(https:\/\/[^"]+\/jobs\/\d+\/([^"/]+)\/job)(?:\?[^"]*)?"[^>]*>/gi;
+  for (;;) {
+    const match = fallback.exec(html);
+    if (match === null) break;
+    const url = canonicalJobUrl(match[1]);
+    const slug = match[2];
+    if (!url || seen.has(url)) continue;
+    seen.add(url);
+    const title = slug
+      ? decodeURIComponent(slug.replace(/\+/g, " "))
+      : "Unknown Title";
+    out.push({ url, title });
+  }
+
+  return out;
+}
+
+function matchesTerm(row: ParsedJobRow, term: string): boolean {
+  const lower = term.toLowerCase();
+  return row.title.toLowerCase().includes(lower);
+}
+
+function employerFromHost(host: string): string {
+  const prefix = host.replace(/^careers-/, "").replace(/^careers\./, "");
+  const base = prefix.replace(/\.icims\.com$/i, "");
+  return base.replace(/[-_.]/g, " ").trim() || host;
+}
+
+export const manifest: ExtractorManifest = {
+  id: "icims",
+  displayName: "iCIMS tenants (HTML)",
+  providesSources: ["icims"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const hosts = parseHosts(context.settings.icimsTenants)
+      .map(normalizeHost)
+      .filter(Boolean);
+
+    if (hosts.length === 0) {
+      return {
+        success: false,
+        jobs: [],
+        error: "No icimsTenants configured",
+      };
+    }
+
+    const maxPagesRaw = context.settings.icimsMaxPagesPerSearch;
+    const maxPages = maxPagesRaw ? Number.parseInt(maxPagesRaw, 10) : 10;
+    const pages = Number.isFinite(maxPages)
+      ? Math.min(Math.max(maxPages, 1), 50)
+      : 10;
+
+    const maxPerTenantRaw = context.settings.icimsMaxJobsPerTenant;
+    const maxPerTenant = maxPerTenantRaw
+      ? Number.parseInt(maxPerTenantRaw, 10)
+      : 250;
+    const tenantCap = Number.isFinite(maxPerTenant)
+      ? Math.min(Math.max(maxPerTenant, 1), 2000)
+      : 250;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [""];
+
+    const jobs: CreateJobInput[] = [];
+    const seenGlobal = new Set<string>();
+
+    try {
+      let tenantIndex = 0;
+      for (const rawHost of hosts) {
+        if (context.shouldCancel?.()) break;
+
+        const host = normalizeHost(rawHost);
+        tenantIndex += 1;
+        let tenantCount = 0;
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: tenantIndex - 1,
+          termsTotal: hosts.length,
+          currentUrl: host,
+          detail: `iCIMS tenant ${tenantIndex}/${hosts.length}: ${host}`,
+        });
+
+        for (const term of terms) {
+          if (tenantCount >= tenantCap) break;
+
+          for (let page = 1; page <= pages; page += 1) {
+            if (tenantCount >= tenantCap) break;
+
+            const query = new URLSearchParams({
+              ss: "1",
+              in_iframe: "1",
+              searchKeyword: term,
+              pr: String(page),
+            });
+
+            const searchUrl = `https://${host}/jobs/search?${query.toString()}`;
+            const response = await fetch(searchUrl, {
+              headers: {
+                Accept: "text/html",
+                "User-Agent":
+                  "Mozilla/5.0 (compatible; JobOps/1.0) iCIMS portal reader",
+              },
+            });
+
+            if (!response.ok) {
+              throw new Error(
+                `iCIMS fetch failed (${host}): ${response.status}`,
+              );
+            }
+
+            const html = await response.text();
+            const rows = extractRows(html).filter((row) =>
+              term ? matchesTerm(row, term) : true,
+            );
+
+            if (rows.length === 0) break;
+
+            for (const row of rows) {
+              if (tenantCount >= tenantCap) break;
+              if (seenGlobal.has(row.url)) continue;
+
+              seenGlobal.add(row.url);
+              tenantCount += 1;
+
+              jobs.push({
+                source: "icims",
+                sourceJobId: row.url,
+                title: row.title,
+                employer: employerFromHost(host),
+                jobUrl: row.url,
+                applicationLink: row.url,
+              });
+            }
+
+            context.onProgress?.({
+              phase: "list",
+              termsProcessed: tenantIndex - 1,
+              termsTotal: hosts.length,
+              currentUrl: host,
+              jobPagesProcessed: jobs.length,
+              detail: `iCIMS ${host}: page ${page}, +${rows.length} rows`,
+            });
+          }
+        }
+      }
+
+      return { success: true, jobs };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs, error: message };
+    }
+  },
+};
+
+export default manifest;
--- a/extractors/icims/package.json
+++ b/extractors/icims/package.json
@ -0,0 +1,17 @@
+{
+  "name": "icims-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "iCIMS tenant job portal HTML search (anonymous iframe-style listings)",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}
--- a/extractors/icims/tsconfig.json
+++ b/extractors/icims/tsconfig.json
@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}
--- a/extractors/qajobsboard/README.md
+++ b/extractors/qajobsboard/README.md
@ -0,0 +1,10 @@
+# qajobsboard-extractor
+
+Loads QA-focused postings from [QAJobsBoard](https://www.qajobsboard.com) via the host’s public JSON feed:
+
+`GET https://qajobsboard.jobboardly.com/jobs.json`
+
+RSS is also published at `jobs.rss`; this extractor uses JSON for structured fields.
+
+- Caps matches via `qajobsboardMaxJobsPerTerm` (default `100`).
+- Filters client-side by pipeline search terms against title, categories, and description HTML.
--- a/extractors/qajobsboard/manifest.ts
+++ b/extractors/qajobsboard/manifest.ts
@ -0,0 +1,217 @@
+/**
+ * QAJobsBoard (JobBoardly) — public jobs listing JSON.
+ *
+ * https://qajobsboard.jobboardly.com/jobs.json
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+const JOBS_URL = "https://qajobsboard.jobboardly.com/jobs.json";
+
+interface JobCategory {
+  name?: string;
+}
+
+interface SalaryBand {
+  schedule?: string;
+  minimum?: number | null;
+  maximum?: number | null;
+}
+
+interface DescriptionBlock {
+  html?: string;
+}
+
+interface QaJobBoardlyJob {
+  title?: string;
+  arrangement?: string;
+  location?: string;
+  location_limits?: string[];
+  published_at?: string;
+  application_link?: string;
+  description?: DescriptionBlock;
+  company?: { name?: string; logo?: string };
+  salary?: SalaryBand;
+  categories?: JobCategory[];
+  links?: { self?: string };
+}
+
+function asString(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  const trimmed = value.trim();
+  return trimmed ? trimmed : undefined;
+}
+
+function decodeHtmlEntities(value: string): string {
+  return value
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&nbsp;/g, " ");
+}
+
+function stripHtml(html: string): string {
+  const noTags = html.replace(/<[^>]+>/g, " ");
+  return decodeHtmlEntities(noTags).replace(/\s+/g, " ").trim();
+}
+
+function salaryLabel(raw: SalaryBand | undefined): string | undefined {
+  if (!raw) return undefined;
+  const schedule = raw.schedule ? `${raw.schedule}: ` : "";
+  if (
+    typeof raw.minimum === "number" &&
+    typeof raw.maximum === "number" &&
+    Number.isFinite(raw.minimum) &&
+    Number.isFinite(raw.maximum)
+  ) {
+    return `${schedule}${raw.minimum}–${raw.maximum}`;
+  }
+  if (typeof raw.minimum === "number" && Number.isFinite(raw.minimum)) {
+    return `${schedule}${raw.minimum}+`;
+  }
+  if (typeof raw.maximum === "number" && Number.isFinite(raw.maximum)) {
+    return `${schedule}≤${raw.maximum}`;
+  }
+  return schedule.trim() || undefined;
+}
+
+function locationLabel(job: QaJobBoardlyJob): string {
+  const limits = Array.isArray(job.location_limits)
+    ? job.location_limits.filter(
+        (v): v is string => typeof v === "string" && v.trim().length > 0,
+      )
+    : [];
+  if (limits.length > 0) return limits.join(", ");
+  const loc = asString(job.location);
+  if (loc) return loc;
+  return "Unknown";
+}
+
+function matchesTerm(job: QaJobBoardlyJob, term: string): boolean {
+  const lower = term.toLowerCase();
+  if (job.title?.toLowerCase().includes(lower)) return true;
+  const cats = Array.isArray(job.categories)
+    ? job.categories.map((c) => c.name?.toLowerCase() ?? "").join(" ")
+    : "";
+  if (cats.includes(lower)) return true;
+  const html = job.description?.html ?? "";
+  if (stripHtml(html).toLowerCase().includes(lower)) return true;
+  return false;
+}
+
+function mapJob(raw: QaJobBoardlyJob): CreateJobInput | null {
+  const jobUrl = asString(raw.links?.self);
+  if (!jobUrl) return null;
+
+  const employer =
+    asString(raw.company?.name)
+      ?.replace(/^[\s–-]+/, "")
+      .trim() || "Unknown Employer";
+
+  const applicationLink = asString(raw.application_link) ?? jobUrl;
+
+  const descHtml = raw.description?.html;
+  const jobDescription = descHtml ? stripHtml(descHtml) : undefined;
+
+  const salary = salaryLabel(raw.salary);
+
+  const cats = Array.isArray(raw.categories)
+    ? raw.categories
+        .map((c) => c?.name?.trim())
+        .filter((v): v is string => Boolean(v))
+        .join(", ")
+    : undefined;
+
+  return {
+    source: "qajobsboard",
+    sourceJobId: jobUrl.split("/").pop(),
+    title: asString(raw.title) ?? "Unknown Title",
+    employer,
+    jobUrl,
+    applicationLink,
+    location: locationLabel(raw),
+    isRemote: asString(raw.location)?.toLowerCase() === "remote",
+    datePosted: asString(raw.published_at),
+    jobDescription,
+    jobType: asString(raw.arrangement),
+    salary,
+    disciplines: cats,
+    companyLogo: asString(raw.company?.logo),
+  };
+}
+
+export const manifest: ExtractorManifest = {
+  id: "qajobsboard",
+  displayName: "QAJobsBoard",
+  providesSources: ["qajobsboard"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const maxJobs = context.settings.qajobsboardMaxJobsPerTerm
+      ? Number.parseInt(context.settings.qajobsboardMaxJobsPerTerm, 10)
+      : 100;
+    const cap = Number.isFinite(maxJobs)
+      ? Math.min(Math.max(maxJobs, 1), 500)
+      : 100;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [];
+
+    context.onProgress?.({
+      phase: "list",
+      termsProcessed: 0,
+      termsTotal: 1,
+      currentUrl: JOBS_URL,
+      detail: "QAJobsBoard: fetching jobs.json",
+    });
+
+    try {
+      const response = await fetch(JOBS_URL, {
+        headers: { Accept: "application/json", "User-Agent": "JobOps/1.0" },
+      });
+      if (!response.ok) {
+        throw new Error(
+          `QAJobsBoard request failed with status ${response.status}`,
+        );
+      }
+      const body = (await response.json()) as unknown;
+      const rows = Array.isArray(body) ? body : [];
+
+      const seen = new Set<string>();
+      const out: CreateJobInput[] = [];
+
+      for (const row of rows as QaJobBoardlyJob[]) {
+        if (out.length >= cap) break;
+        if (terms.length > 0 && !terms.some((t) => matchesTerm(row, t)))
+          continue;
+        const mapped = mapJob(row);
+        if (!mapped) continue;
+        const key = mapped.sourceJobId || mapped.jobUrl;
+        if (seen.has(key)) continue;
+        seen.add(key);
+        out.push(mapped);
+      }
+
+      context.onProgress?.({
+        phase: "list",
+        termsProcessed: 1,
+        termsTotal: 1,
+        currentUrl: JOBS_URL,
+        jobPagesProcessed: out.length,
+        detail: `QAJobsBoard: ${out.length} matched (${rows.length} total listings)`,
+      });
+
+      return { success: true, jobs: out };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: [], error: message };
+    }
+  },
+};
+
+export default manifest;
--- a/extractors/qajobsboard/package.json
+++ b/extractors/qajobsboard/package.json
@ -0,0 +1,17 @@
+{
+  "name": "qajobsboard-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "QAJobsBoard (JobBoardly) public jobs.json extractor",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}
--- a/extractors/qajobsboard/tsconfig.json
+++ b/extractors/qajobsboard/tsconfig.json
@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}
--- a/extractors/smartrecruiters/README.md
+++ b/extractors/smartrecruiters/README.md
@ -0,0 +1,11 @@
+# smartrecruiters-extractor
+
+Fetches public job postings from the [SmartRecruiters Posting API](https://developers.smartrecruiters.com/reference/v1listpostings):
+
+`GET https://api.smartrecruiters.com/v1/companies/{companyIdentifier}/postings`
+
+No API key is required for public listings. Configure one **company identifier** per employer (the slug from `jobs.smartrecruiters.com/<identifier>/...` or `careers.smartrecruiters.com/<identifier>`).
+
+- Set `smartrecruitersCompanies` (JSON array or comma/newline-separated identifiers), or `SMARTRECRUITERS_COMPANIES` in the environment.
+- Optional: `smartrecruitersMaxJobsPerCompany` caps how many postings are pulled **per company** after search-term filtering (default 100).
+- The manifest loads posting **details** for each match so `jobUrl` / `applicationLink` and HTML descriptions resolve correctly.
--- a/extractors/smartrecruiters/manifest.ts
+++ b/extractors/smartrecruiters/manifest.ts
@ -0,0 +1,287 @@
+/**
+ * SmartRecruiters public Posting API (no auth for public boards).
+ *
+ * https://developers.smartrecruiters.com/reference/v1listpostings
+ *   GET https://api.smartrecruiters.com/v1/companies/{companyIdentifier}/postings
+ *   GET https://api.smartrecruiters.com/v1/companies/{companyIdentifier}/postings/{postingId}
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+const LIST_LIMIT = 100;
+
+interface SrCompany {
+  identifier?: string;
+  name?: string;
+}
+
+interface SrLocation {
+  fullLocation?: string;
+  city?: string;
+  region?: string;
+  country?: string;
+  remote?: boolean;
+  hybrid?: boolean;
+}
+
+interface SrPostingSummary {
+  id?: string;
+  name?: string;
+  releasedDate?: string;
+  company?: SrCompany;
+  location?: SrLocation;
+  typeOfEmployment?: { label?: string };
+  experienceLevel?: { id?: string; label?: string };
+}
+
+interface SrListResponse {
+  content?: SrPostingSummary[];
+  totalFound?: number;
+  offset?: number;
+  limit?: number;
+}
+
+interface SrDetail extends SrPostingSummary {
+  postingUrl?: string;
+  applyUrl?: string;
+  jobAd?: {
+    sections?: Record<string, { title?: string; text?: string } | undefined>;
+  };
+}
+
+function asString(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  const trimmed = value.trim();
+  return trimmed ? trimmed : undefined;
+}
+
+function readCompanies(raw: string | undefined): string[] {
+  if (!raw) return [];
+  try {
+    const parsed = JSON.parse(raw);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .map((entry) => (typeof entry === "string" ? entry.trim() : ""))
+        .filter(Boolean);
+    }
+  } catch {
+    // fall through
+  }
+  return raw
+    .split(/[\n,;|]+/)
+    .map((entry) => entry.trim())
+    .filter(Boolean);
+}
+
+function decodeHtmlEntities(value: string): string {
+  return value
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&nbsp;/g, " ");
+}
+
+function stripHtml(html: string): string {
+  const noTags = html.replace(/<[^>]+>/g, " ");
+  return decodeHtmlEntities(noTags).replace(/\s+/g, " ").trim();
+}
+
+function locationString(loc: SrLocation | undefined): string {
+  if (!loc) return "Unknown";
+  const full = asString(loc.fullLocation);
+  if (full) return full;
+  const parts = [loc.city, loc.region, loc.country]
+    .map((p) => asString(p))
+    .filter(Boolean) as string[];
+  return parts.length > 0 ? parts.join(", ") : "Unknown";
+}
+
+function extractDescription(detail: SrDetail): string | undefined {
+  const sections = detail.jobAd?.sections;
+  if (!sections || typeof sections !== "object") return undefined;
+  const chunks: string[] = [];
+  for (const block of Object.values(sections)) {
+    const text = block && typeof block.text === "string" ? block.text : "";
+    if (text.trim()) chunks.push(text);
+  }
+  if (chunks.length === 0) return undefined;
+  return stripHtml(chunks.join("\n\n"));
+}
+
+function matchesTerm(summary: SrPostingSummary, term: string): boolean {
+  const lower = term.toLowerCase();
+  if (summary.name?.toLowerCase().includes(lower)) return true;
+  if (locationString(summary.location).toLowerCase().includes(lower))
+    return true;
+  if (summary.company?.name?.toLowerCase().includes(lower)) return true;
+  return false;
+}
+
+async function fetchPostingsPage(
+  company: string,
+  offset: number,
+): Promise<SrListResponse> {
+  const base = `https://api.smartrecruiters.com/v1/companies/${encodeURIComponent(company)}/postings`;
+  const url = `${base}?destination=PUBLIC&limit=${LIST_LIMIT}&offset=${offset}`;
+  const response = await fetch(url, {
+    headers: { Accept: "application/json" },
+  });
+  if (response.status === 404) {
+    return { content: [], totalFound: 0, offset: 0, limit: LIST_LIMIT };
+  }
+  if (!response.ok) {
+    throw new Error(
+      `SmartRecruiters list for "${company}" failed with status ${response.status}`,
+    );
+  }
+  return (await response.json()) as SrListResponse;
+}
+
+async function fetchPostingDetail(
+  company: string,
+  postingId: string,
+): Promise<SrDetail | null> {
+  const url = `https://api.smartrecruiters.com/v1/companies/${encodeURIComponent(company)}/postings/${encodeURIComponent(postingId)}`;
+  const response = await fetch(url, {
+    headers: { Accept: "application/json" },
+  });
+  if (!response.ok) return null;
+  return (await response.json()) as SrDetail;
+}
+
+function mapDetailToJob(detail: SrDetail): CreateJobInput | null {
+  const postingId = asString(detail.id);
+  if (!postingId) return null;
+
+  const jobUrl = asString(detail.applyUrl) ?? asString(detail.postingUrl);
+  if (!jobUrl) return null;
+
+  const employer =
+    asString(detail.company?.name) ??
+    asString(detail.company?.identifier) ??
+    "Unknown Employer";
+
+  const jobType = asString(detail.typeOfEmployment?.label);
+  const jobLevel = asString(detail.experienceLevel?.label);
+
+  return {
+    source: "smartrecruiters",
+    sourceJobId: postingId,
+    title: asString(detail.name) ?? "Unknown Title",
+    employer,
+    jobUrl,
+    applicationLink: asString(detail.applyUrl) ?? jobUrl,
+    location: locationString(detail.location),
+    isRemote: detail.location?.remote === true,
+    datePosted: asString(detail.releasedDate),
+    jobDescription: extractDescription(detail),
+    jobType: jobType || undefined,
+    jobLevel: jobLevel || undefined,
+  };
+}
+
+export const manifest: ExtractorManifest = {
+  id: "smartrecruiters",
+  displayName: "SmartRecruiters (ATS)",
+  providesSources: ["smartrecruiters"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const companies = readCompanies(context.settings.smartrecruitersCompanies);
+    if (companies.length === 0) {
+      return {
+        success: true,
+        jobs: [],
+        error:
+          "No SmartRecruiters companies configured. Set SMARTRECRUITERS_COMPANIES or smartrecruitersCompanies (comma- or newline-separated company identifiers).",
+      };
+    }
+
+    const maxPerCompany = context.settings.smartrecruitersMaxJobsPerCompany
+      ? Number.parseInt(context.settings.smartrecruitersMaxJobsPerCompany, 10)
+      : 100;
+    const cap = Number.isFinite(maxPerCompany)
+      ? Math.min(Math.max(maxPerCompany, 1), 500)
+      : 100;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [];
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    try {
+      for (let i = 0; i < companies.length; i += 1) {
+        if (context.shouldCancel?.()) break;
+        const company = companies[i];
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i,
+          termsTotal: companies.length,
+          currentUrl: company,
+          detail: `SmartRecruiters: ${company} (${i + 1}/${companies.length})`,
+        });
+
+        const matchedSummaries: SrPostingSummary[] = [];
+        let offset = 0;
+        let totalFound = Number.POSITIVE_INFINITY;
+
+        while (matchedSummaries.length < cap && offset < totalFound) {
+          if (context.shouldCancel?.()) break;
+          const page = await fetchPostingsPage(company, offset);
+          const batch = Array.isArray(page.content) ? page.content : [];
+          totalFound =
+            typeof page.totalFound === "number" ? page.totalFound : offset;
+          if (batch.length === 0) break;
+
+          for (const row of batch) {
+            if (matchedSummaries.length >= cap) break;
+            if (terms.length > 0 && !terms.some((t) => matchesTerm(row, t))) {
+              continue;
+            }
+            matchedSummaries.push(row);
+          }
+
+          offset += batch.length;
+          if (offset >= totalFound) break;
+        }
+
+        let added = 0;
+        for (const summary of matchedSummaries) {
+          if (context.shouldCancel?.()) break;
+          const id = asString(summary.id);
+          if (!id) continue;
+          const detail = await fetchPostingDetail(company, id);
+          if (!detail) continue;
+          const mapped = mapDetailToJob(detail);
+          if (!mapped) continue;
+          const key = mapped.sourceJobId || mapped.jobUrl;
+          if (seen.has(key)) continue;
+          seen.add(key);
+          out.push(mapped);
+          added += 1;
+        }
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i + 1,
+          termsTotal: companies.length,
+          currentUrl: company,
+          jobPagesProcessed: out.length,
+          detail: `SmartRecruiters: ${company} → ${added} jobs (${out.length} total)`,
+        });
+      }
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: out, error: message };
+    }
+
+    return { success: true, jobs: out };
+  },
+};
+
+export default manifest;
--- a/extractors/smartrecruiters/package.json
+++ b/extractors/smartrecruiters/package.json
@ -0,0 +1,17 @@
+{
+  "name": "smartrecruiters-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "SmartRecruiters public Posting API extractor",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}
--- a/extractors/smartrecruiters/tsconfig.json
+++ b/extractors/smartrecruiters/tsconfig.json
@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}
--- a/orchestrator/src/client/api/client.ts
+++ b/orchestrator/src/client/api/client.ts
@ -503,7 +503,9 @@ async function fetchApi<T>(
 ): Promise<T> {
  const method = (options?.method || "GET").toUpperCase();
  const activeCreds = getActiveBasicAuthCredentials();
-  let authHeader = activeCreds ? encodeBasicAuthHeaderValue(activeCreds) : undefined;
+  let authHeader = activeCreds
+    ? encodeBasicAuthHeaderValue(activeCreds)
+    : undefined;
  let authAttempt = 0;
  let usernameHint = activeCreds?.username;

--- a/orchestrator/src/client/pages/orchestrator/utils.ts
+++ b/orchestrator/src/client/pages/orchestrator/utils.ts
@ -210,6 +210,11 @@ export const getEnabledSources = (
  const hasGreenhouseCompanies =
    (settings.greenhouseCompanies?.value ?? []).length > 0;
  const hasWorkdayTenants = (settings.workdayTenants?.value ?? []).length > 0;
+  const hasSmartrecruitersCompanies =
+    (settings.smartrecruitersCompanies?.value ?? []).length > 0;
+  const hasElutaRssLocations =
+    (settings.elutaRssLocations?.value ?? []).length > 0;
+  const hasIcimsTenants = (settings.icimsTenants?.value ?? []).length > 0;

  for (const source of orderedSources) {
    if (source === "gradcracker") {
@ -272,6 +277,22 @@ export const getEnabledSources = (
      if (hasWorkdayTenants) enabled.push(source);
      continue;
    }
+    if (source === "smartrecruiters") {
+      if (hasSmartrecruitersCompanies) enabled.push(source);
+      continue;
+    }
+    if (source === "icims") {
+      if (hasIcimsTenants) enabled.push(source);
+      continue;
+    }
+    if (source === "bctenet") {
+      enabled.push(source);
+      continue;
+    }
+    if (source === "eluta") {
+      if (hasElutaRssLocations) enabled.push(source);
+      continue;
+    }
    if (
      source === "indeed" ||
      source === "linkedin" ||
@ -286,7 +307,9 @@ export const getEnabledSources = (
      source === "arbeitnow" ||
      source === "himalayas" ||
      source === "weworkremotely" ||
-      source === "fourdayweek"
+      source === "fourdayweek" ||
+      source === "qajobsboard" ||
+      source === "arcdev"
    ) {
      enabled.push(source);
    }
--- a/orchestrator/src/server/api/routes/settings.ts
+++ b/orchestrator/src/server/api/routes/settings.ts
@ -10,9 +10,9 @@ import { asyncRoute, fail, ok } from "@infra/http";
 import { logger } from "@infra/logger";
 import { getRequestId } from "@infra/request-context";
 import { isDemoMode, sendDemoBlocked } from "@server/config/demo";
-import { getJobOwnerProfileId } from "@server/infra/request-context";
-import { DEFAULT_JOB_OWNER_PROFILE_ID } from "@server/infra/job-owner-context";
 import { parseBasicAuthUsername } from "@server/infra/basic-auth-credentials";
+import { DEFAULT_JOB_OWNER_PROFILE_ID } from "@server/infra/job-owner-context";
+import { getJobOwnerProfileId } from "@server/infra/request-context";
 import * as profilesRepo from "@server/repositories/profiles";
 import { getSetting } from "@server/repositories/settings";
 import { setBackupSettings } from "@server/services/backup/index";
@ -30,11 +30,11 @@ import {
 } from "@server/services/rxresume";
 import { getEffectiveSettings } from "@server/services/settings";
 import { applySettingsUpdates } from "@server/services/settings-update";
+import { jobSearchProfileSchema } from "@shared/settings-registry";
 import {
  type UpdateSettingsInput,
  updateSettingsSchema,
 } from "@shared/settings-schema";
-import { jobSearchProfileSchema } from "@shared/settings-registry";
 import { type Request, type Response, Router } from "express";

 export const settingsRouter = Router();
@ -251,9 +251,12 @@ settingsRouter.patch(
      ) {
        const parsed = jobSearchProfileSchema.safeParse(input.jobSearchProfile);
        if (parsed.success) {
-          const username = parseBasicAuthUsername(req.headers.authorization)?.trim();
-          const dataWithOwner =
-            username ? { ...parsed.data, basicAuthUser: username } : parsed.data;
+          const username = parseBasicAuthUsername(
+            req.headers.authorization,
+          )?.trim();
+          const dataWithOwner = username
+            ? { ...parsed.data, basicAuthUser: username }
+            : parsed.data;
          await profilesRepo.updateProfile(ownerId, { data: dataWithOwner });
        }
      }
--- a/orchestrator/src/server/config/demo-defaults.data.ts
+++ b/orchestrator/src/server/config/demo-defaults.data.ts
@ -272,6 +272,12 @@ export const DEMO_SOURCE_BASE_URLS: Record<JobSource, string> = {
  lever: "https://jobs.lever.co",
  greenhouse: "https://boards.greenhouse.io",
  workday: "https://workday.com",
+  smartrecruiters: "https://www.smartrecruiters.com",
+  icims: "https://www.icims.com",
+  bctenet: "https://www.bctechnology.com",
+  eluta: "https://www.eluta.ca",
+  qajobsboard: "https://www.qajobsboard.com",
+  arcdev: "https://arc.dev",
  manual: "https://example.com",
 };

--- a/orchestrator/src/server/pipeline/steps/discover-jobs.ts
+++ b/orchestrator/src/server/pipeline/steps/discover-jobs.ts
@ -12,13 +12,13 @@ import {
  normalizeCountryKey,
 } from "@shared/location-support.js";
 import { resolveBlockedCompanyKeywordsFromStoredString } from "@shared/resolve-blocked-company-keywords.js";
-import { jobSearchProfileSchema } from "@shared/settings-registry.js";
 import {
  inferCountryKeyFromSearchGeography,
  matchesRequestedCity,
  resolveSearchCities,
  shouldApplyStrictCityFilter,
 } from "@shared/search-cities.js";
+import { jobSearchProfileSchema } from "@shared/settings-registry.js";
 import type { CreateJobInput, PipelineConfig } from "@shared/types";
 import { type CrawlSource, progressHelpers, updateProgress } from "../progress";

@ -106,19 +106,14 @@ const ROLE_TOKEN_STOPWORDS = new Set([
 ]);

 function normalizeText(value: string | null | undefined): string {
-  return (value ?? "")
-    .toLowerCase()
-    .replace(/\s+/g, " ")
-    .trim();
+  return (value ?? "").toLowerCase().replace(/\s+/g, " ").trim();
 }

 function buildRoleMatchers(phrases: string[]): {
  phraseMatchers: string[];
  tokenMatchers: string[];
 } {
-  const phraseMatchers = phrases
-    .map((p) => normalizeText(p))
-    .filter(Boolean);
+  const phraseMatchers = phrases.map((p) => normalizeText(p)).filter(Boolean);

  const tokenSet = new Set<string>();
  for (const phrase of phraseMatchers) {
@ -164,7 +159,10 @@ function filterJobsBySearchProfile(args: {
    const body = normalizeText(job.jobDescription);
    const haystack = `${title}\n${body}`;

-    if (dealBreakersLower.length > 0 && matchesAny(haystack, dealBreakersLower)) {
+    if (
+      dealBreakersLower.length > 0 &&
+      matchesAny(haystack, dealBreakersLower)
+    ) {
      return false;
    }

--- a/package-lock.json
+++ b/package-lock.json
@ -14,6 +14,7 @@
      "devDependencies": {
        "@types/node": "^25.2.3",
        "dotenv": "^17.2.3",
+        "job-ops-shared": "workspace:*",
        "knip": "^5.83.1",
        "tsx": "^4.19.2",
        "typescript": "^5.9.3"
@ -125,6 +126,27 @@
        "undici-types": "~7.16.0"
      }
    },
+    "extractors/arcdev": {
+      "name": "arcdev-extractor",
+      "version": "0.0.1",
+      "dependencies": {
+        "job-ops-shared": "^1.0.0"
+      },
+      "devDependencies": {
+        "@types/node": "^24.0.0",
+        "typescript": "~5.9.0"
+      }
+    },
+    "extractors/arcdev/node_modules/@types/node": {
+      "version": "24.12.4",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.12.4.tgz",
+      "integrity": "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.16.0"
+      }
+    },
    "extractors/ashby": {
      "name": "ashby-extractor",
      "version": "0.0.1",
@ -146,6 +168,27 @@
        "undici-types": "~7.16.0"
      }
    },
+    "extractors/bctenet": {
+      "name": "bctenet-extractor",
+      "version": "0.0.1",
+      "dependencies": {
+        "job-ops-shared": "^1.0.0"
+      },
+      "devDependencies": {
+        "@types/node": "^24.0.0",
+        "typescript": "~5.9.0"
+      }
+    },
+    "extractors/bctenet/node_modules/@types/node": {
+      "version": "24.12.4",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.12.4.tgz",
+      "integrity": "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.16.0"
+      }
+    },
    "extractors/careerjet": {
      "name": "careerjet-extractor",
      "version": "0.0.1",
@ -167,6 +210,27 @@
        "undici-types": "~7.16.0"
      }
    },
+    "extractors/eluta": {
+      "name": "eluta-extractor",
+      "version": "0.0.1",
+      "dependencies": {
+        "job-ops-shared": "^1.0.0"
+      },
+      "devDependencies": {
+        "@types/node": "^24.0.0",
+        "typescript": "~5.9.0"
+      }
+    },
+    "extractors/eluta/node_modules/@types/node": {
+      "version": "24.12.4",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.12.4.tgz",
+      "integrity": "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.16.0"
+      }
+    },
    "extractors/fourdayweek": {
      "name": "fourdayweek-extractor",
      "version": "0.0.1",
@ -308,6 +372,27 @@
        "undici-types": "~7.16.0"
      }
    },
+    "extractors/icims": {
+      "name": "icims-extractor",
+      "version": "0.0.1",
+      "dependencies": {
+        "job-ops-shared": "^1.0.0"
+      },
+      "devDependencies": {
+        "@types/node": "^24.0.0",
+        "typescript": "~5.9.0"
+      }
+    },
+    "extractors/icims/node_modules/@types/node": {
+      "version": "24.12.4",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.12.4.tgz",
+      "integrity": "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.16.0"
+      }
+    },
    "extractors/jobicy": {
      "name": "jobicy-extractor",
      "version": "0.0.1",
@ -371,6 +456,27 @@
        "undici-types": "~7.16.0"
      }
    },
+    "extractors/qajobsboard": {
+      "name": "qajobsboard-extractor",
+      "version": "0.0.1",
+      "dependencies": {
+        "job-ops-shared": "^1.0.0"
+      },
+      "devDependencies": {
+        "@types/node": "^24.0.0",
+        "typescript": "~5.9.0"
+      }
+    },
+    "extractors/qajobsboard/node_modules/@types/node": {
+      "version": "24.12.4",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.12.4.tgz",
+      "integrity": "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.16.0"
+      }
+    },
    "extractors/reed": {
      "name": "reed-extractor",
      "version": "0.0.1",
@ -434,6 +540,27 @@
        "undici-types": "~7.16.0"
      }
    },
+    "extractors/smartrecruiters": {
+      "name": "smartrecruiters-extractor",
+      "version": "0.0.1",
+      "dependencies": {
+        "job-ops-shared": "^1.0.0"
+      },
+      "devDependencies": {
+        "@types/node": "^24.0.0",
+        "typescript": "~5.9.0"
+      }
+    },
+    "extractors/smartrecruiters/node_modules/@types/node": {
+      "version": "24.12.4",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.12.4.tgz",
+      "integrity": "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.16.0"
+      }
+    },
    "extractors/startupjobs": {
      "name": "startupjobs-extractor",
      "version": "0.0.1",
@ -9725,6 +9852,10 @@
      "resolved": "extractors/arbeitnow",
      "link": true
    },
+    "node_modules/arcdev-extractor": {
+      "resolved": "extractors/arcdev",
+      "link": true
+    },
    "node_modules/arg": {
      "version": "5.0.2",
      "resolved": "https://registry.npmjs.org/arg/-/arg-5.0.2.tgz",
@ -10008,6 +10139,10 @@
      "integrity": "sha512-x+VAiMRL6UPkx+kudNvxTl6hB2XNNCG2r+7wixVfIYwu/2HKRXimwQyaumLjMveWvT2Hkd/cAJw+QBMfJ/EKVw==",
      "license": "MIT"
    },
+    "node_modules/bctenet-extractor": {
+      "resolved": "extractors/bctenet",
+      "link": true
+    },
    "node_modules/better-sqlite3": {
      "version": "12.6.2",
      "resolved": "https://registry.npmjs.org/better-sqlite3/-/better-sqlite3-12.6.2.tgz",
@ -12298,6 +12433,10 @@
      "integrity": "sha512-3vifjt1HgrGW/h76UEeny+adYApveS9dH2h3p57JYzBSXJIKUJAvtmIytDKjcSCt9xHfrNCFJ7gts6vkhuq++w==",
      "license": "ISC"
    },
+    "node_modules/eluta-extractor": {
+      "resolved": "extractors/eluta",
+      "link": true
+    },
    "node_modules/emoji-regex": {
      "version": "8.0.0",
      "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
@ -14774,6 +14913,10 @@
        "node": ">=10.18"
      }
    },
+    "node_modules/icims-extractor": {
+      "resolved": "extractors/icims",
+      "link": true
+    },
    "node_modules/iconv-lite": {
      "version": "0.7.2",
      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.2.tgz",
@ -21784,6 +21927,10 @@
        "node": ">=16.0.0"
      }
    },
+    "node_modules/qajobsboard-extractor": {
+      "resolved": "extractors/qajobsboard",
+      "link": true
+    },
    "node_modules/qs": {
      "version": "6.14.2",
      "resolved": "https://registry.npmjs.org/qs/-/qs-6.14.2.tgz",
@ -23500,6 +23647,10 @@
        "npm": ">= 3.0.0"
      }
    },
+    "node_modules/smartrecruiters-extractor": {
+      "resolved": "extractors/smartrecruiters",
+      "link": true
+    },
    "node_modules/smol-toml": {
      "version": "1.6.0",
      "resolved": "https://registry.npmjs.org/smol-toml/-/smol-toml-1.6.0.tgz",
--- a/package.json
+++ b/package.json
@ -26,6 +26,7 @@
  "devDependencies": {
    "dotenv": "^17.2.3",
    "@types/node": "^25.2.3",
+    "job-ops-shared": "workspace:*",
    "knip": "^5.83.1",
    "tsx": "^4.19.2",
    "typescript": "^5.9.3"
--- a/scripts/smoke-extractors.ts
+++ b/scripts/smoke-extractors.ts
@ -1,8 +1,14 @@
 /**
- * Tiny smoke-test for new extractors: imports each manifest, runs it with a
- * minimal context, and prints the count of mapped jobs + a few samples.
+ * Smoke-test helper for extractor manifests: imports each manifest, runs it with a
+ * minimal context, and prints mapped job counts + a sample row.
 *
- * Run from repo root:  npx tsx scripts/smoke-extractors.ts [comma,separated,ids]
+ * Run from repo root:
+ *   npx tsx scripts/smoke-extractors.ts
+ *   npx tsx scripts/smoke-extractors.ts arcdev,icims
+ *   npx tsx scripts/smoke-extractors.ts indeed    # alias → `jobspy` (same manifest)
+ *
+ * Keep `ALL_TARGETS` aligned with every shipped manifest under each
+ * `extractors/<name>/` package (`manifest.ts` or `src/manifest.ts`).
 *
 * Loads repo-root `.env` so keyed extractors match orchestrator behavior (plain
 * `tsx` does not read `.env` automatically).
@ -14,7 +20,7 @@ import { config as loadEnv } from "dotenv";
 import type {
  ExtractorManifest,
  ExtractorRuntimeContext,
-} from "../shared/src/types/extractors";
+} from "job-ops-shared/types/extractors";

 const repoRoot = path.resolve(
  path.dirname(fileURLToPath(import.meta.url)),
@ -22,54 +28,56 @@ const repoRoot = path.resolve(
 );
 loadEnv({ path: path.join(repoRoot, ".env") });

+/** Left column width for log alignment (longest pipeline source id today). */
+const ID_COL = 15;
+
+/** JobSpy serves Indeed / LinkedIn / Glassdoor; CLI filter accepts those ids as aliases. */
+const JOBSPY_SITE_IDS = ["indeed", "linkedin", "glassdoor"] as const;
+
+function expandSmokeFilter(ids: Set<string>): Set<string> {
+  const next = new Set(ids);
+  for (const site of JOBSPY_SITE_IDS) {
+    if (next.has(site)) {
+      next.add("jobspy");
+      break;
+    }
+  }
+  return next;
+}
+
 interface Target {
  id: string;
  importPath: string;
  needs?: string[]; // env vars required to run; skipped if missing
  settings?: Record<string, string>;
+  /** When set, replaces the default smoke search terms (use [] for sources that filter client-side). */
+  searchTerms?: string[];
+  /** Geography passed as `selectedCountry` (must match what each extractor expects). */
+  selectedCountry?: string;
 }

 const ALL_TARGETS: Target[] = [
  {
-    id: "jobicy",
-    importPath: "../extractors/jobicy/manifest",
-    settings: { jobicyMaxJobsPerTerm: "10" },
-  },
-  {
-    id: "themuse",
-    importPath: "../extractors/themuse/manifest",
-    settings: { themuseMaxJobsPerTerm: "10" },
-  },
-  {
-    id: "usajobs",
-    importPath: "../extractors/usajobs/manifest",
-    needs: ["USAJOBS_API_KEY", "USAJOBS_USER_AGENT"],
-    settings: { usajobsMaxJobsPerTerm: "10" },
-  },
-  {
-    id: "jooble",
-    importPath: "../extractors/jooble/manifest",
-    needs: ["JOOBLE_API_KEY"],
-    settings: { joobleMaxJobsPerTerm: "10" },
-  },
-  {
-    id: "careerjet",
-    importPath: "../extractors/careerjet/manifest",
-    needs: ["CAREERJET_AFFID", "CAREERJET_REFERER", "CAREERJET_USER_IP"],
-    settings: { careerjetMaxJobsPerTerm: "10" },
-  },
-  {
-    id: "reed",
-    importPath: "../extractors/reed/manifest",
-    needs: ["REED_API_KEY"],
-    settings: { reedMaxJobsPerTerm: "10" },
-  },
-  {
-    id: "lever",
-    importPath: "../extractors/lever/manifest",
+    id: "adzuna",
+    importPath: "../extractors/adzuna/manifest",
+    needs: ["ADZUNA_APP_ID", "ADZUNA_APP_KEY"],
+    selectedCountry: "United States",
    settings: {
-      // Known active public Lever board used purely as a connectivity check.
-      leverCompanies: JSON.stringify(["palantir", "netflix"]),
+      adzunaMaxJobsPerTerm: "10",
+      searchCities: "United States",
+    },
+  },
+  {
+    id: "arbeitnow",
+    importPath: "../extractors/arbeitnow/manifest",
+    settings: { arbeitnowMaxJobsPerTerm: "10" },
+  },
+  {
+    id: "arcdev",
+    importPath: "../extractors/arcdev/manifest",
+    settings: {
+      arcRemoteJobsPaths: JSON.stringify(["/remote-jobs/playwright"]),
+      arcMaxJobsPerPath: "20",
    },
  },
  {
@ -79,6 +87,40 @@ const ALL_TARGETS: Target[] = [
      ashbyCompanies: JSON.stringify(["ramp", "linear"]),
    },
  },
+  {
+    id: "bctenet",
+    importPath: "../extractors/bctenet/manifest",
+    selectedCountry: "Canada",
+    settings: {
+      bctenetMaxJobsPerTerm: "25",
+    },
+  },
+  {
+    id: "careerjet",
+    importPath: "../extractors/careerjet/manifest",
+    needs: ["CAREERJET_AFFID", "CAREERJET_REFERER", "CAREERJET_USER_IP"],
+    settings: { careerjetMaxJobsPerTerm: "10", searchCities: "United States" },
+  },
+  {
+    id: "eluta",
+    importPath: "../extractors/eluta/manifest",
+    selectedCountry: "Canada",
+    settings: {
+      elutaRssLocations: JSON.stringify(["Toronto, ON"]),
+      elutaMaxJobsPerTerm: "15",
+    },
+  },
+  {
+    id: "fourdayweek",
+    importPath: "../extractors/fourdayweek/manifest",
+    settings: { fourdayweekMaxJobsPerTerm: "10" },
+  },
+  {
+    id: "gradcracker",
+    importPath: "../extractors/gradcracker/manifest",
+    selectedCountry: "United Kingdom",
+    settings: { gradcrackerMaxJobsPerTerm: "10" },
+  },
  {
    id: "greenhouse",
    importPath: "../extractors/greenhouse/manifest",
@ -87,14 +129,71 @@ const ALL_TARGETS: Target[] = [
    },
  },
  {
-    id: "workday",
-    importPath: "../extractors/workday/manifest",
+    id: "himalayas",
+    importPath: "../extractors/himalayas/manifest",
+    settings: { himalayasMaxJobsPerTerm: "10" },
+  },
+  {
+    id: "hiringcafe",
+    importPath: "../extractors/hiringcafe/manifest",
+    selectedCountry: "United Kingdom",
    settings: {
-      workdayTenants: JSON.stringify([
-        "https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite",
-      ]),
+      searchCities: "UK",
+      jobspyResultsWanted: "10",
+      workplaceTypes: JSON.stringify(["remote", "hybrid", "onsite"]),
    },
  },
+  {
+    id: "icims",
+    importPath: "../extractors/icims/manifest",
+    searchTerms: [],
+    settings: {
+      icimsTenants: JSON.stringify(["careers-appliedsystems.icims.com"]),
+      icimsMaxJobsPerTenant: "15",
+      icimsMaxPagesPerSearch: "2",
+    },
+  },
+  {
+    id: "jobicy",
+    importPath: "../extractors/jobicy/manifest",
+    settings: { jobicyMaxJobsPerTerm: "10" },
+  },
+  {
+    id: "jobspy",
+    importPath: "../extractors/jobspy/manifest",
+    selectedCountry: "United Kingdom",
+    settings: {
+      searchCities: "UK",
+      jobspyCountryIndeed: "UK",
+      jobspyResultsWanted: "5",
+      workplaceTypes: JSON.stringify(["remote", "hybrid", "onsite"]),
+    },
+  },
+  {
+    id: "jooble",
+    importPath: "../extractors/jooble/manifest",
+    needs: ["JOOBLE_API_KEY"],
+    settings: { joobleMaxJobsPerTerm: "10", searchCities: "United States" },
+  },
+  {
+    id: "lever",
+    importPath: "../extractors/lever/manifest",
+    settings: {
+      leverCompanies: JSON.stringify(["palantir", "netflix"]),
+    },
+  },
+  {
+    id: "qajobsboard",
+    importPath: "../extractors/qajobsboard/manifest",
+    settings: { qajobsboardMaxJobsPerTerm: "25" },
+  },
+  {
+    id: "reed",
+    importPath: "../extractors/reed/manifest",
+    needs: ["REED_API_KEY"],
+    selectedCountry: "United Kingdom",
+    settings: { reedMaxJobsPerTerm: "10" },
+  },
  {
    id: "remoteok",
    importPath: "../extractors/remoteok/manifest",
@ -106,14 +205,40 @@ const ALL_TARGETS: Target[] = [
    settings: { remotiveMaxJobsPerTerm: "10" },
  },
  {
-    id: "arbeitnow",
-    importPath: "../extractors/arbeitnow/manifest",
-    settings: { arbeitnowMaxJobsPerTerm: "10" },
+    id: "smartrecruiters",
+    importPath: "../extractors/smartrecruiters/manifest",
+    settings: {
+      smartrecruitersCompanies: JSON.stringify(["smartrecruiters"]),
+      smartrecruitersMaxJobsPerCompany: "5",
+    },
  },
  {
-    id: "himalayas",
-    importPath: "../extractors/himalayas/manifest",
-    settings: { himalayasMaxJobsPerTerm: "10" },
+    id: "startupjobs",
+    importPath: "../extractors/startupjobs/src/manifest",
+    selectedCountry: "United Kingdom",
+    settings: {
+      searchCities: "UK",
+      startupjobsMaxJobsPerTerm: "10",
+      workplaceTypes: JSON.stringify(["remote", "hybrid", "onsite"]),
+    },
+  },
+  {
+    id: "themuse",
+    importPath: "../extractors/themuse/manifest",
+    settings: { themuseMaxJobsPerTerm: "10" },
+  },
+  {
+    id: "ukvisajobs",
+    importPath: "../extractors/ukvisajobs/manifest",
+    needs: ["UKVISAJOBS_EMAIL", "UKVISAJOBS_PASSWORD"],
+    selectedCountry: "United Kingdom",
+    settings: { ukvisajobsMaxJobs: "10" },
+  },
+  {
+    id: "usajobs",
+    importPath: "../extractors/usajobs/manifest",
+    needs: ["USAJOBS_API_KEY", "USAJOBS_USER_AGENT"],
+    settings: { usajobsMaxJobsPerTerm: "10" },
  },
  {
    id: "weworkremotely",
@ -121,22 +246,29 @@ const ALL_TARGETS: Target[] = [
    settings: { weworkremotelyMaxJobsPerTerm: "10" },
  },
  {
-    id: "fourdayweek",
-    importPath: "../extractors/fourdayweek/manifest",
-    settings: { fourdayweekMaxJobsPerTerm: "10" },
+    id: "workday",
+    importPath: "../extractors/workday/manifest",
+    settings: {
+      workdayTenants: JSON.stringify([
+        "https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite",
+      ]),
+    },
  },
 ];

-function buildContext(
-  source: string,
-  settings: Record<string, string>,
-): ExtractorRuntimeContext {
+function buildContext(args: {
+  source: string;
+  settings: Record<string, string>;
+  searchTerms?: string[];
+  selectedCountry?: string;
+}): ExtractorRuntimeContext {
  return {
-    source,
-    selectedSources: [source],
-    settings,
-    searchTerms: ["software engineer"],
-    selectedCountry: "United States",
+    source: args.source,
+    selectedSources: [args.source],
+    settings: args.settings,
+    searchTerms:
+      args.searchTerms !== undefined ? args.searchTerms : ["software engineer"],
+    selectedCountry: args.selectedCountry ?? "United States",
    getExistingJobUrls: async () => [],
    shouldCancel: () => false,
    onProgress: () => {},
@ -151,7 +283,7 @@ async function runOne(target: Target): Promise<void> {
  const missing = (target.needs ?? []).filter((k) => !process.env[k]);
  if (missing.length > 0) {
    console.log(
-      `${pad(target.id, 12)}  SKIP  missing env: ${missing.join(", ")}`,
+      `${pad(target.id, ID_COL)}  SKIP  missing env: ${missing.join(", ")}`,
    );
    return;
  }
@ -161,20 +293,25 @@ async function runOne(target: Target): Promise<void> {
    mod = await import(target.importPath);
  } catch (err) {
    console.log(
-      `${pad(target.id, 12)}  FAIL  import error: ${(err as Error).message}`,
+      `${pad(target.id, ID_COL)}  FAIL  import error: ${(err as Error).message}`,
    );
    return;
  }

  const manifest = mod.manifest ?? mod.default;
  if (!manifest) {
-    console.log(`${pad(target.id, 12)}  FAIL  manifest export missing`);
+    console.log(`${pad(target.id, ID_COL)}  FAIL  manifest export missing`);
    return;
  }

  const started = Date.now();
  try {
-    const ctx = buildContext(target.id, target.settings ?? {});
+    const ctx = buildContext({
+      source: target.id,
+      settings: target.settings ?? {},
+      searchTerms: target.searchTerms,
+      selectedCountry: target.selectedCountry,
+    });
    const result = await manifest.run(ctx);
    const ms = Date.now() - started;
    const status = result.success ? "OK  " : "ERR ";
@ -183,12 +320,12 @@ async function runOne(target: Target): Promise<void> {
      ? ` | first: "${sample.title}" @ ${sample.employer}`
      : "";
    console.log(
-      `${pad(target.id, 12)}  ${status} jobs=${result.jobs.length}  ${ms}ms${result.error ? ` | error: ${result.error}` : ""}${sampleStr}`,
+      `${pad(target.id, ID_COL)}  ${status} jobs=${result.jobs.length}  ${ms}ms${result.error ? ` | error: ${result.error}` : ""}${sampleStr}`,
    );
  } catch (err) {
    const ms = Date.now() - started;
    console.log(
-      `${pad(target.id, 12)}  CRASH ${ms}ms  ${(err as Error).message}`,
+      `${pad(target.id, ID_COL)}  CRASH ${ms}ms  ${(err as Error).message}`,
    );
  }
 }
@ -196,11 +333,13 @@ async function runOne(target: Target): Promise<void> {
 async function main() {
  const requested = (process.argv[2] ?? "").trim();
  const filter = requested
-    ? new Set(
-        requested
-          .split(",")
-          .map((s) => s.trim())
-          .filter(Boolean),
+    ? expandSmokeFilter(
+        new Set(
+          requested
+            .split(",")
+            .map((s) => s.trim())
+            .filter(Boolean),
+        ),
      )
    : null;
  const targets = filter
--- a/shared/src/extractors/index.ts
+++ b/shared/src/extractors/index.ts
@ -27,6 +27,12 @@ export const EXTRACTOR_SOURCE_IDS = [
  "lever",
  "greenhouse",
  "workday",
+  "smartrecruiters",
+  "icims",
+  "bctenet",
+  "eluta",
+  "qajobsboard",
+  "arcdev",
  "manual",
 ] as const;

@ -203,6 +209,44 @@ export const EXTRACTOR_SOURCE_METADATA: Record<
    category: "pipeline",
    region: "global",
  },
+  smartrecruiters: {
+    label: "SmartRecruiters (ATS)",
+    order: 245,
+    category: "pipeline",
+    region: "global",
+  },
+  icims: {
+    label: "iCIMS tenants (HTML)",
+    order: 241,
+    category: "pipeline",
+    region: "global",
+  },
+  bctenet: {
+    label: "BC T-Net (RSS)",
+    order: 243,
+    category: "pipeline",
+    region: "global",
+    countryAllowlist: ["canada"],
+  },
+  eluta: {
+    label: "Eluta",
+    order: 247,
+    category: "pipeline",
+    region: "global",
+    countryAllowlist: ["canada"],
+  },
+  qajobsboard: {
+    label: "QAJobsBoard",
+    order: 248,
+    category: "pipeline",
+    region: "remote",
+  },
+  arcdev: {
+    label: "Arc.dev",
+    order: 249,
+    category: "pipeline",
+    region: "remote",
+  },
  manual: { label: "Manual", order: 900, category: "manual" },
 };

--- a/shared/src/location-support.test.ts
+++ b/shared/src/location-support.test.ts
@ -59,6 +59,9 @@ describe("location-support", () => {
      true,
    );
    expect(isSourceAllowedForCountry("startupjobs", "worldwide")).toBe(true);
+    expect(isSourceAllowedForCountry("eluta", "canada")).toBe(true);
+    expect(isSourceAllowedForCountry("eluta", "united states")).toBe(false);
+    expect(isSourceAllowedForCountry("smartrecruiters", "japan")).toBe(true);
  });

  it("filters incompatible sources while preserving compatible order", () => {
--- a/shared/src/location-support.ts
+++ b/shared/src/location-support.ts
@ -1,3 +1,4 @@
+import { EXTRACTOR_SOURCE_METADATA } from "./extractors";
 import type { JobSource } from "./types";

 const COUNTRY_ALIASES: Record<string, string> = {
@ -199,6 +200,16 @@ export function isSourceAllowedForCountry(
  if (US_ONLY_SOURCES.has(source)) return isUsCountry(country);
  if (source === "glassdoor") return isGlassdoorCountry(country);
  if (source === "adzuna") return getAdzunaCountryCode(country) !== null;
+
+  const meta =
+    EXTRACTOR_SOURCE_METADATA[source as keyof typeof EXTRACTOR_SOURCE_METADATA];
+  if (meta?.countryAllowlist && meta.countryAllowlist.length > 0) {
+    const key = normalizeCountryKey(country);
+    return meta.countryAllowlist.some(
+      (token) => normalizeCountryKey(token) === key,
+    );
+  }
+
  return true;
 }

--- a/shared/src/settings-registry.ts
+++ b/shared/src/settings-registry.ts
@ -445,6 +445,37 @@ export const settingsRegistry = {
    parse: parseIntOrNull,
    serialize: serializeNullableNumber,
  },
+  qajobsboardMaxJobsPerTerm: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(1000),
+    default: (): number => 100,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
+  /**
+   * Arc.dev remote job listing paths (on https://arc.dev), e.g. /remote-jobs/playwright
+   */
+  arcRemoteJobsPaths: {
+    kind: "typed" as const,
+    schema: z.array(z.string().trim().min(1).max(200)).max(20),
+    default: (): string[] => {
+      const fromEnv = parseCompanyList(
+        typeof process !== "undefined" ? process.env.ARC_REMOTE_JOBS_PATHS : "",
+      );
+      return fromEnv.length > 0
+        ? fromEnv
+        : ["/remote-jobs/playwright", "/remote-jobs/cypress"];
+    },
+    parse: parseJsonArrayOrNull,
+    serialize: serializeNullableJsonArray,
+  },
+  arcMaxJobsPerPath: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(300),
+    default: (): number => 120,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
  /**
   * Comma- or newline-separated company slugs to fetch from public ATS feeds.
   * `lever`, `ashby`, and `greenhouse` each take one entry per company.
@ -493,6 +524,108 @@ export const settingsRegistry = {
    parse: parseJsonArrayOrNull,
    serialize: serializeNullableJsonArray,
  },
+  /**
+   * SmartRecruiters company identifiers (Posting API path segment), e.g.
+   * `jobs.smartrecruiters.com/smartrecruiters/...` → "smartrecruiters".
+   */
+  smartrecruitersCompanies: {
+    kind: "typed" as const,
+    schema: z.array(z.string().trim().min(1).max(100)).max(200),
+    default: (): string[] =>
+      parseCompanyList(
+        typeof process !== "undefined"
+          ? process.env.SMARTRECRUITERS_COMPANIES
+          : "",
+      ),
+    parse: parseJsonArrayOrNull,
+    serialize: serializeNullableJsonArray,
+  },
+  smartrecruitersMaxJobsPerCompany: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(500),
+    default: (): number => 100,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
+  /**
+   * Eluta RSS `location` query values, e.g. "Toronto, ON", "Vancouver, BC".
+   * Very broad values may yield empty feeds; prefer metro/province strings.
+   */
+  elutaRssLocations: {
+    kind: "typed" as const,
+    schema: z.array(z.string().trim().min(1).max(200)).max(50),
+    default: (): string[] =>
+      parseCompanyList(
+        typeof process !== "undefined" ? process.env.ELUTA_RSS_LOCATIONS : "",
+      ),
+    parse: parseJsonArrayOrNull,
+    serialize: serializeNullableJsonArray,
+  },
+  elutaMaxJobsPerTerm: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(1000),
+    default: (): number => 100,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
+  /**
+   * Optional BC T-Net RSS URLs. When empty, the extractor uses the default public
+   * aggregate feed. Env `BCTENET_RSS_URLS` seeds defaults (JSON array or newline-separated).
+   */
+  bctenetRssUrls: {
+    kind: "typed" as const,
+    schema: z.array(z.string().trim().min(1).max(500)).max(20),
+    default: (): string[] => {
+      const raw =
+        typeof process !== "undefined"
+          ? process.env.BCTENET_RSS_URLS?.trim()
+          : "";
+      if (!raw) return [];
+      const parsed = parseJsonArrayOrNull(raw);
+      if (parsed && parsed.length > 0) return parsed;
+      return raw
+        .split(/\n+/)
+        .map((piece) => piece.trim())
+        .filter(Boolean);
+    },
+    parse: parseJsonArrayOrNull,
+    serialize: serializeNullableJsonArray,
+  },
+  bctenetMaxJobsPerTerm: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(2000),
+    default: (): number => 400,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
+  /**
+   * iCIMS tenant hosts (e.g. careers-example.icims.com). Env `ICIMS_TENANTS`
+   * seeds defaults (comma/newline-separated).
+   */
+  icimsTenants: {
+    kind: "typed" as const,
+    schema: z.array(z.string().trim().min(1).max(200)).max(100),
+    default: (): string[] =>
+      parseCompanyList(
+        typeof process !== "undefined" ? process.env.ICIMS_TENANTS : "",
+      ),
+    parse: parseJsonArrayOrNull,
+    serialize: serializeNullableJsonArray,
+  },
+  icimsMaxJobsPerTenant: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(2000),
+    default: (): number => 250,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
+  icimsMaxPagesPerSearch: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(50),
+    default: (): number => 10,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
  searchTerms: {
    kind: "typed" as const,
    schema: z.array(z.string().trim().min(1).max(200)).max(100),
--- a/shared/src/testing/factories.ts
+++ b/shared/src/testing/factories.ts
@ -200,10 +200,30 @@ export const createAppSettings = (
  himalayasMaxJobsPerTerm: { value: 50, default: 50, override: null },
  weworkremotelyMaxJobsPerTerm: { value: 50, default: 50, override: null },
  fourdayweekMaxJobsPerTerm: { value: 50, default: 50, override: null },
+  qajobsboardMaxJobsPerTerm: { value: 100, default: 100, override: null },
+  arcRemoteJobsPaths: {
+    value: ["/remote-jobs/playwright", "/remote-jobs/cypress"],
+    default: ["/remote-jobs/playwright", "/remote-jobs/cypress"],
+    override: null,
+  },
+  arcMaxJobsPerPath: { value: 120, default: 120, override: null },
  leverCompanies: { value: [], default: [], override: null },
  ashbyCompanies: { value: [], default: [], override: null },
  greenhouseCompanies: { value: [], default: [], override: null },
  workdayTenants: { value: [], default: [], override: null },
+  smartrecruitersCompanies: { value: [], default: [], override: null },
+  smartrecruitersMaxJobsPerCompany: {
+    value: 100,
+    default: 100,
+    override: null,
+  },
+  elutaRssLocations: { value: [], default: [], override: null },
+  elutaMaxJobsPerTerm: { value: 100, default: 100, override: null },
+  bctenetRssUrls: { value: [], default: [], override: null },
+  bctenetMaxJobsPerTerm: { value: 400, default: 400, override: null },
+  icimsTenants: { value: [], default: [], override: null },
+  icimsMaxJobsPerTenant: { value: 250, default: 250, override: null },
+  icimsMaxPagesPerSearch: { value: 10, default: 10, override: null },
  searchTerms: {
    value: ["Software Engineer"],
    default: ["Software Engineer"],
--- a/shared/src/types/settings.ts
+++ b/shared/src/types/settings.ts
@ -213,10 +213,22 @@ export interface AppSettings {
  himalayasMaxJobsPerTerm: Resolved<number>;
  weworkremotelyMaxJobsPerTerm: Resolved<number>;
  fourdayweekMaxJobsPerTerm: Resolved<number>;
+  qajobsboardMaxJobsPerTerm: Resolved<number>;
+  arcRemoteJobsPaths: Resolved<string[]>;
+  arcMaxJobsPerPath: Resolved<number>;
  leverCompanies: Resolved<string[]>;
  ashbyCompanies: Resolved<string[]>;
  greenhouseCompanies: Resolved<string[]>;
  workdayTenants: Resolved<string[]>;
+  smartrecruitersCompanies: Resolved<string[]>;
+  smartrecruitersMaxJobsPerCompany: Resolved<number>;
+  elutaRssLocations: Resolved<string[]>;
+  elutaMaxJobsPerTerm: Resolved<number>;
+  bctenetRssUrls: Resolved<string[]>;
+  bctenetMaxJobsPerTerm: Resolved<number>;
+  icimsTenants: Resolved<string[]>;
+  icimsMaxJobsPerTenant: Resolved<number>;
+  icimsMaxPagesPerSearch: Resolved<number>;
  searchTerms: Resolved<string[]>;
  workplaceTypes: Resolved<Array<"remote" | "hybrid" | "onsite">>;
  blockedCompanyKeywords: Resolved<string[]>;