Some checks failed
CI / Linting (Biome) (push) Failing after 36s
CI / Tests (push) Successful in 5m54s
CI / Type Check (adzuna-extractor) (push) Successful in 1m6s
CI / Type Check (gradcracker-extractor) (push) Successful in 1m9s
CI / Type Check (hiringcafe-extractor) (push) Successful in 1m5s
CI / Type Check (orchestrator) (push) Successful in 1m21s
CI / Type Check (startupjobs-extractor) (push) Successful in 1m4s
CI / Type Check (ukvisajobs-extractor) (push) Successful in 1m4s
CI / Documentation (push) Successful in 1m52s
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>
189 lines
5.7 KiB
TypeScript
189 lines
5.7 KiB
TypeScript
/**
|
|
* Reed.co.uk Jobseeker API.
|
|
*
|
|
* https://www.reed.co.uk/developers/jobseeker
|
|
* GET https://www.reed.co.uk/api/1.0/search?...
|
|
* HTTP Basic with the API key as the username and an empty password.
|
|
*
|
|
* Requires REED_API_KEY (`reedApiKey` setting). The catalog gates this source
|
|
* to UK only via `isSourceAllowedForCountry`.
|
|
*/
|
|
|
|
import type {
|
|
ExtractorManifest,
|
|
ExtractorRunResult,
|
|
} from "@shared/types/extractors";
|
|
import type { CreateJobInput } from "@shared/types/jobs";
|
|
|
|
const API_URL = "https://www.reed.co.uk/api/1.0/search";
|
|
|
|
interface ReedJob {
|
|
jobId?: number;
|
|
jobTitle?: string;
|
|
employerName?: string;
|
|
employerProfileUrl?: string;
|
|
jobDescription?: string;
|
|
jobUrl?: string;
|
|
locationName?: string;
|
|
date?: string;
|
|
expirationDate?: string;
|
|
applications?: number;
|
|
currency?: string;
|
|
minimumSalary?: number;
|
|
maximumSalary?: number;
|
|
yearlyMinimumSalary?: number;
|
|
yearlyMaximumSalary?: number;
|
|
}
|
|
interface ReedResponse {
|
|
totalResults?: number;
|
|
results?: ReedJob[];
|
|
}
|
|
|
|
function asString(value: unknown): string | undefined {
|
|
if (typeof value !== "string") return undefined;
|
|
const trimmed = value.trim();
|
|
return trimmed ? trimmed : undefined;
|
|
}
|
|
|
|
function mapJob(raw: ReedJob): CreateJobInput | null {
|
|
const jobUrl = asString(raw.jobUrl);
|
|
if (!jobUrl) return null;
|
|
return {
|
|
source: "reed",
|
|
sourceJobId: raw.jobId != null ? String(raw.jobId) : undefined,
|
|
title: asString(raw.jobTitle) ?? "Unknown Title",
|
|
employer: asString(raw.employerName) ?? "Unknown Employer",
|
|
employerUrl: asString(raw.employerProfileUrl),
|
|
jobUrl,
|
|
applicationLink: jobUrl,
|
|
location: asString(raw.locationName),
|
|
datePosted: asString(raw.date),
|
|
deadline: asString(raw.expirationDate),
|
|
jobDescription: asString(raw.jobDescription),
|
|
salaryMinAmount:
|
|
typeof raw.minimumSalary === "number" ? raw.minimumSalary : undefined,
|
|
salaryMaxAmount:
|
|
typeof raw.maximumSalary === "number" ? raw.maximumSalary : undefined,
|
|
salaryCurrency: asString(raw.currency) ?? "GBP",
|
|
salaryInterval: raw.yearlyMinimumSalary != null ? "yearly" : undefined,
|
|
};
|
|
}
|
|
|
|
async function fetchPage(args: {
|
|
apiKey: string;
|
|
keywords: string;
|
|
locationName?: string;
|
|
resultsToTake: number;
|
|
resultsToSkip: number;
|
|
}): Promise<ReedResponse> {
|
|
const url = new URL(API_URL);
|
|
url.searchParams.set("keywords", args.keywords);
|
|
if (args.locationName)
|
|
url.searchParams.set("locationName", args.locationName);
|
|
url.searchParams.set("resultsToTake", String(args.resultsToTake));
|
|
url.searchParams.set("resultsToSkip", String(args.resultsToSkip));
|
|
|
|
const auth = Buffer.from(`${args.apiKey}:`).toString("base64");
|
|
const response = await fetch(url.toString(), {
|
|
headers: {
|
|
Accept: "application/json",
|
|
Authorization: `Basic ${auth}`,
|
|
},
|
|
});
|
|
if (!response.ok) {
|
|
throw new Error(`Reed request failed with status ${response.status}`);
|
|
}
|
|
return (await response.json()) as ReedResponse;
|
|
}
|
|
|
|
export const manifest: ExtractorManifest = {
|
|
id: "reed",
|
|
displayName: "Reed",
|
|
providesSources: ["reed"],
|
|
requiredEnvVars: ["REED_API_KEY"],
|
|
async run(context): Promise<ExtractorRunResult> {
|
|
if (context.shouldCancel?.()) return { success: true, jobs: [] };
|
|
|
|
const apiKey =
|
|
context.settings.reedApiKey?.trim() || process.env.REED_API_KEY?.trim();
|
|
if (!apiKey) {
|
|
return {
|
|
success: false,
|
|
jobs: [],
|
|
error: "Reed extractor requires REED_API_KEY",
|
|
};
|
|
}
|
|
|
|
const maxJobsPerTerm = context.settings.reedMaxJobsPerTerm
|
|
? Number.parseInt(context.settings.reedMaxJobsPerTerm, 10)
|
|
: 100;
|
|
// Reed accepts up to 100 per page.
|
|
const pageSize = Math.min(100, maxJobsPerTerm);
|
|
|
|
const terms = context.searchTerms.length > 0 ? context.searchTerms : [""];
|
|
const locationName =
|
|
context.settings.searchCities?.split("|")[0]?.trim() || undefined;
|
|
|
|
const seen = new Set<string>();
|
|
const out: CreateJobInput[] = [];
|
|
|
|
try {
|
|
for (let i = 0; i < terms.length; i += 1) {
|
|
if (context.shouldCancel?.()) break;
|
|
const term = terms[i].trim();
|
|
context.onProgress?.({
|
|
phase: "list",
|
|
termsProcessed: i,
|
|
termsTotal: terms.length,
|
|
currentUrl: term || "(all)",
|
|
detail: `Reed: term ${i + 1}/${terms.length}`,
|
|
});
|
|
|
|
let collected = 0;
|
|
let resultsToSkip = 0;
|
|
while (collected < maxJobsPerTerm) {
|
|
if (context.shouldCancel?.()) break;
|
|
const body = await fetchPage({
|
|
apiKey,
|
|
keywords: term,
|
|
locationName,
|
|
resultsToTake: pageSize,
|
|
resultsToSkip,
|
|
});
|
|
const items = Array.isArray(body.results) ? body.results : [];
|
|
if (items.length === 0) break;
|
|
for (const raw of items) {
|
|
const mapped = mapJob(raw);
|
|
if (!mapped) continue;
|
|
const key = mapped.sourceJobId || mapped.jobUrl;
|
|
if (seen.has(key)) continue;
|
|
seen.add(key);
|
|
out.push(mapped);
|
|
collected += 1;
|
|
if (collected >= maxJobsPerTerm) break;
|
|
}
|
|
if (items.length < pageSize) break;
|
|
resultsToSkip += pageSize;
|
|
if (resultsToSkip > 5000) break;
|
|
}
|
|
|
|
context.onProgress?.({
|
|
phase: "list",
|
|
termsProcessed: i + 1,
|
|
termsTotal: terms.length,
|
|
currentUrl: term || "(all)",
|
|
jobPagesProcessed: out.length,
|
|
detail: `Reed: completed term ${i + 1}/${terms.length} (${collected} found)`,
|
|
});
|
|
}
|
|
} 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;
|