From 88420b54e7b287b94ab06aac8bab29c4e7161cb8 Mon Sep 17 00:00:00 2001
From: Nikola Petrov <nikola@petrovv.com>
Date: Mon, 12 Oct 2026 21:06:34 +0200
Subject: [PATCH] Add Adecco (Slovenia, IT) scraper

Adecco has no public API; use the internal JSON endpoint its job search
page calls, filtered by job category. Results are paginated and checked
against the requested category, since the API silently ignores unknown
filters.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 scrapper/README.md              |  1 +
 scrapper/src/scrapers/adecco.ts | 89 +++++++++++++++++++++++++++++++++
 scrapper/src/scrapers/http.ts   |  2 +-
 scrapper/src/scrapers/index.ts  |  2 +
 4 files changed, 93 insertions(+), 1 deletion(-)
 create mode 100644 scrapper/src/scrapers/adecco.ts

diff --git a/scrapper/README.md b/scrapper/README.md
index 92203c1..40a592f 100644
--- a/scrapper/README.md
+++ b/scrapper/README.md
@@ -10,6 +10,7 @@ No runtime dependencies. It uses Bun's built-in SQLite, HTTP server and HTMLRewr
 |---|---|---|
 | slo-tech.com (Ljubljana) | HTML scrape | ~20 newest jobs |
 | startup.si | HTML scrape (no public API or feed) | Site lists every posting since 2019 on one page, so only the last 90 days are kept (`startupSi(days)` in `src/scrapers/index.ts`) |
+| adecco.com (Slovenia, IT) | Internal JSON API the site's job search uses (no public API) | Filtered by category; add more with `adecco("<CategoryFilter value>", "<label>")` |
 
 ## Run
 
diff --git a/scrapper/src/scrapers/adecco.ts b/scrapper/src/scrapers/adecco.ts
new file mode 100644
index 0000000..547172f
--- /dev/null
+++ b/scrapper/src/scrapers/adecco.ts
@@ -0,0 +1,89 @@
+import { USER_AGENT } from "./http";
+import type { ScrapedJob, Scraper } from "./types";
+
+// Adecco has no public API, but its job search page loads results from this internal JSON endpoint
+// (a Solr-style query passed as `queryString`). Unknown filter fields are silently ignored by the
+// API, so results are checked against the requested category.
+const API_URL = "https://www.adecco.com/api/data/jobs/summarized";
+const JOB_PAGE = "https://www.adecco.com/sl-si/prosta-delovna-mesta";
+const MAX_PAGES = 50; // 10 jobs per page
+
+interface AdeccoJob {
+  jobId: string;
+  jobTitle: string;
+  jobLocation: string | null;
+  cityName: string | null;
+  postedDate: string | null;
+  jobCategoryId: string | null;
+  jobSubCategoryId: string | null;
+  contractTypeTitle: string | null;
+  employmentTypeTitle: string | null;
+  industryTypeTitle: string | null;
+}
+
+interface AdeccoResponse {
+  jobs?: AdeccoJob[];
+  pagination?: { total: number; nextRange: number };
+}
+
+/** The site builds "<title>-<location>/<jobid>" URLs; only the job ID matters, the slug is cosmetic. */
+function jobUrl(j: AdeccoJob): string {
+  const slug = `${j.jobTitle}-${j.jobLocation ?? ""}`
+    .normalize("NFD")
+    .replace(/[̀-ͯ]/g, "")
+    .replace(/[^A-Za-z0-9]+/g, "-")
+    .replace(/^-|-$/g, "")
+    .toLowerCase();
+  return `${JOB_PAGE}/${slug}/${j.jobId.toLowerCase()}`;
+}
+
+/**
+ * Scraper for adecco.com (Slovenia), filtered by job category.
+ * `category` is the CategoryFilter value from the site's URL, e.g. "ADCSICAT014" (IT).
+ */
+export function adecco(category: string, label: string): Scraper {
+  return {
+    id: `adecco-si-${category.toLowerCase()}`,
+    name: `Adecco (${label})`,
+    async scrape() {
+      const raw: AdeccoJob[] = [];
+      for (let page = 0, range = 0; page < MAX_PAGES; page++) {
+        const res = await fetch(API_URL, {
+          method: "POST",
+          headers: { "User-Agent": USER_AGENT, "content-type": "text/plain;charset=UTF-8" },
+          body: JSON.stringify({
+            queryString: `&fq=JobCategoryId:${category}`,
+            range,
+            siteName: "adecco",
+            brand: "adecco",
+            countryCode: "SI",
+            languageCode: "sl-SI",
+          }),
+        });
+        if (!res.ok) throw new Error(`POST ${API_URL} -> HTTP ${res.status}`);
+        const data = (await res.json()) as AdeccoResponse;
+        if (!Array.isArray(data.jobs)) throw new Error("unexpected API response (no `jobs` array)");
+        raw.push(...data.jobs);
+        const total = data.pagination?.total ?? 0;
+        if (data.jobs.length === 0 || raw.length >= total || !data.pagination?.nextRange) break;
+        range = data.pagination.nextRange;
+      }
+
+      const jobs = raw.filter((j) => j.jobCategoryId === category || j.jobSubCategoryId === category);
+      if (raw.length > 0 && jobs.length === 0) {
+        throw new Error(`category filter ${category} was ignored by the API (query format changed?)`);
+      }
+
+      return jobs.map((j) => ({
+        externalId: j.jobId,
+        title: j.jobTitle.trim(),
+        url: jobUrl(j),
+        location: j.cityName || j.jobLocation || undefined,
+        tags: [j.contractTypeTitle, j.employmentTypeTitle, j.industryTypeTitle].filter(
+          (t): t is string => !!t?.trim(),
+        ),
+        postedAt: j.postedDate ?? undefined,
+      }));
+    },
+  };
+}
diff --git a/scrapper/src/scrapers/http.ts b/scrapper/src/scrapers/http.ts
index 65a771c..5456fa1 100644
--- a/scrapper/src/scrapers/http.ts
+++ b/scrapper/src/scrapers/http.ts
@@ -1,6 +1,6 @@
 // Shared helpers for scrapers.
 
-const USER_AGENT =
+export const USER_AGENT =
   "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0 Safari/537.36";
 
 // Upper half (0xA0-0xFF) of ISO-8859-2, which Bun's TextDecoder does not support.
diff --git a/scrapper/src/scrapers/index.ts b/scrapper/src/scrapers/index.ts
index ba1a3a0..fade529 100644
--- a/scrapper/src/scrapers/index.ts
+++ b/scrapper/src/scrapers/index.ts
@@ -1,3 +1,4 @@
+import { adecco } from "./adecco";
 import { sloTech } from "./slotech";
 import { startupSi } from "./startupsi";
 import type { Scraper } from "./types";
@@ -10,6 +11,7 @@ import type { Scraper } from "./types";
 export const scrapers: Scraper[] = [
   sloTech("Ljubljana"),
   startupSi(),
+  adecco("ADCSICAT014", "IT"),
 ];
 
 export type { Scraper, ScrapedJob } from "./types";