feat(extractors): add 17 job source extractors and cross-source dedup

Adds extractor packages: arbeitnow, ashby, careerjet, fourdayweek,
greenhouse, himalayas, jobicy, jooble, lever, reed, remoteok, remotive,
themuse, usajobs, weworkremotely, workday — each with manifest, package
metadata and README.

Pipeline / shared:
- shared/job-fingerprint: stable hash for cross-source dedup, with tests
- discover-jobs: dedup via fingerprint and richer per-source merging
- jobs repository: fingerprint-aware upsert / lookup
- settings-registry, settings types/routes, demo-defaults: knobs for the
  new sources
- shared extractors index: register the new manifests
- location-support, profiles route: small fixes for the new sources

Tooling:
- scripts/smoke-extractors.ts to sanity-check each source locally
- scripts/jobber-cron-{cherepaha,dobkin}.env.example: per-host cron
  templates (CHANGEME placeholders only)
- .env.example: documented env vars for the new extractors
- .gitignore: ignore extractors/*/storage/ runtime caches (was ukvisajobs only)

Co-authored-by: Cursor <cursoragent@cursor.com>

extractors/arbeitnow/manifest.ts

@@ -0,0 +1,172 @@
+/**
+ * Arbeitnow public job board API.
+ *
+ * https://www.arbeitnow.com/api/job-board-api?page=N
+ *
+ * No auth. Returns 100 results per page, sorted by creation date.
+ * No server-side search — we paginate and filter client-side by
+ * title + tags against each pipeline search term.
+ *
+ * Aggregates listings from Greenhouse, SmartRecruiters, Join,
+ * TeamTailor, Recruitee, and Comeet.
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+const API_URL = "https://www.arbeitnow.com/api/job-board-api";
+const MAX_PAGES = 5;
+
+interface ArbeitnowJob {
+  slug?: string;
+  company_name?: string;
+  title?: string;
+  description?: string;
+  remote?: boolean;
+  url?: string;
+  tags?: string[];
+  job_types?: string[];
+  location?: string;
+  created_at?: number;
+}
+
+interface ArbeitnowResponse {
+  data?: ArbeitnowJob[];
+  links?: { next?: string | null };
+  meta?: { current_page?: number };
+}
+
+function asString(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  const trimmed = value.trim();
+  return trimmed || undefined;
+}
+
+function matchesTerm(job: ArbeitnowJob, term: string): boolean {
+  const lower = term.toLowerCase();
+  if (job.title?.toLowerCase().includes(lower)) return true;
+  if (
+    Array.isArray(job.tags) &&
+    job.tags.some(
+      (t) => typeof t === "string" && t.toLowerCase().includes(lower),
+    )
+  )
+    return true;
+  return false;
+}
+
+function mapJob(raw: ArbeitnowJob): CreateJobInput | null {
+  const jobUrl = asString(raw.url);
+  if (!jobUrl) return null;
+
+  const tags = Array.isArray(raw.tags)
+    ? raw.tags.filter((t): t is string => typeof t === "string" && t.length > 0)
+    : [];
+
+  const jobTypes = Array.isArray(raw.job_types)
+    ? raw.job_types
+        .filter((t): t is string => typeof t === "string" && t.length > 0)
+        .join(", ")
+    : undefined;
+
+  const datePosted =
+    typeof raw.created_at === "number"
+      ? new Date(raw.created_at * 1000).toISOString()
+      : undefined;
+
+  return {
+    source: "arbeitnow",
+    sourceJobId: asString(raw.slug),
+    title: asString(raw.title) ?? "Unknown Title",
+    employer: asString(raw.company_name) ?? "Unknown Employer",
+    jobUrl,
+    applicationLink: jobUrl,
+    location: asString(raw.location) ?? "Unknown",
+    isRemote: raw.remote === true,
+    jobType: jobTypes || undefined,
+    datePosted,
+    jobDescription: asString(raw.description),
+    disciplines: tags.length > 0 ? tags.join(", ") : undefined,
+  };
+}
+
+async function fetchPage(page: number): Promise<ArbeitnowResponse> {
+  const url = `${API_URL}?page=${page}`;
+  const response = await fetch(url, {
+    headers: { Accept: "application/json" },
+  });
+  if (!response.ok) {
+    throw new Error(`Arbeitnow request failed with status ${response.status}`);
+  }
+  return (await response.json()) as ArbeitnowResponse;
+}
+
+export const manifest: ExtractorManifest = {
+  id: "arbeitnow",
+  displayName: "Arbeitnow",
+  providesSources: ["arbeitnow"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const maxJobs = context.settings.arbeitnowMaxJobsPerTerm
+      ? Number.parseInt(context.settings.arbeitnowMaxJobsPerTerm, 10)
+      : 100;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [];
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    try {
+      for (let page = 1; page <= MAX_PAGES; page += 1) {
+        if (context.shouldCancel?.()) break;
+        if (out.length >= maxJobs * Math.max(terms.length, 1)) break;
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: 0,
+          termsTotal: 1,
+          currentUrl: `page ${page}`,
+          detail: `Arbeitnow: fetching page ${page}`,
+        });
+
+        const body = await fetchPage(page);
+        const jobs = Array.isArray(body.data) ? body.data : [];
+
+        if (jobs.length === 0) break;
+
+        for (const raw of jobs) {
+          if (terms.length > 0 && !terms.some((t) => matchesTerm(raw, t))) {
+            continue;
+          }
+          const mapped = mapJob(raw);
+          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: 0,
+          termsTotal: 1,
+          currentUrl: `page ${page}`,
+          jobPagesProcessed: out.length,
+          detail: `Arbeitnow: page ${page} done (${out.length} matched so far)`,
+        });
+
+        if (!body.links?.next) break;
+      }
+    } 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;