Add startup.si scraper

startup.si has no public jobs API or feed, so parse the listing page.
It lists every posting since 2019 on one page, so only postings from
the last 90 days are kept. Also decode common named HTML entities
(š, ž, č, dashes, quotes) case-sensitively.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scrapper/README.md

@@ -4,6 +4,13 @@ Scrapes job sites once a day, stores results in SQLite (`data/jobs.sqlite`), and
 
 No runtime dependencies. It uses Bun's built-in SQLite, HTTP server and HTMLRewriter.
 
+## Sources
+
+| Source | How | Notes |
+|---|---|---|
+| 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`) |
+
 ## Run
 
 ```sh

scrapper/src/scrapers/http.ts

@@ -29,6 +29,8 @@ export async function fetchHtml(url: string): Promise<string> {
 
 const NAMED_ENTITIES: Record<string, string> = {
   amp: "&", lt: "<", gt: ">", quot: '"', apos: "'", nbsp: " ", raquo: "»", laquo: "«",
+  scaron: "š", Scaron: "Š", zcaron: "ž", Zcaron: "Ž", ccaron: "č", Ccaron: "Č",
+  ndash: "–", mdash: "—", lsquo: "‘", rsquo: "’", ldquo: "“", rdquo: "”", bdquo: "„", hellip: "…",
 };
 
 /** Decode HTML entities (HTMLRewriter text chunks are not decoded). */
@@ -38,7 +40,7 @@ export function decodeEntities(s: string): string {
       const code = e[1] === "x" || e[1] === "X" ? parseInt(e.slice(2), 16) : parseInt(e.slice(1), 10);
       return Number.isFinite(code) ? String.fromCodePoint(code) : m;
     }
-    return NAMED_ENTITIES[e.toLowerCase()] ?? m;
+    return NAMED_ENTITIES[e] ?? NAMED_ENTITIES[e.toLowerCase()] ?? m;
   });
 }
 

scrapper/src/scrapers/index.ts

@@ -1,4 +1,5 @@
 import { sloTech } from "./slotech";
+import { startupSi } from "./startupsi";
 import type { Scraper } from "./types";
 
 /**
@@ -8,6 +9,7 @@ import type { Scraper } from "./types";
  */
 export const scrapers: Scraper[] = [
   sloTech("Ljubljana"),
+  startupSi(),
 ];
 
 export type { Scraper, ScrapedJob } from "./types";

scrapper/src/scrapers/startupsi.ts

@@ -0,0 +1,94 @@
+import { clean, fetchHtml } from "./http";
+import type { ScrapedJob, Scraper } from "./types";
+
+// startup.si has no public jobs API or feed, so we parse the listing page. It holds every posting
+// on a single page (no pagination), going back years, so old postings are filtered out by age.
+const LIST_URL = "https://www.startup.si/sl-si/za-startupe/oglasi/zaposlitve";
+
+const MONTHS = ["januar", "februar", "marec", "april", "maj", "junij", "julij", "avgust", "september", "oktober", "november", "december"];
+
+/** "21. september 2026" -> ISO date */
+function parseSlDate(s: string): string | undefined {
+  const m = /(\d{1,2})\.\s*([a-zčšž]+)\s+(\d{4})/i.exec(s);
+  const month = m ? MONTHS.indexOf(m[2]!.toLowerCase()) : -1;
+  if (!m || month < 0) return undefined;
+  return new Date(Date.UTC(Number(m[3]), month, Number(m[1]))).toISOString();
+}
+
+/** Links on this site are hand-entered: some are empty, relative, or missing the scheme. */
+function normalizeUrl(href: string): string {
+  const h = clean(href);
+  if (!h) return LIST_URL;
+  if (/^www\./i.test(h)) return `https://${h}`;
+  try {
+    return new URL(h, LIST_URL + "/").href;
+  } catch {
+    return LIST_URL;
+  }
+}
+
+/** Scraper for startup.si job ads. Only postings from the last `maxAgeDays` days are returned. */
+export function startupSi(maxAgeDays = 90): Scraper {
+  return {
+    id: "startup-si",
+    name: "Startup.si",
+    async scrape() {
+      const jobs = await parseStartupSi(await fetchHtml(LIST_URL));
+      if (jobs.length === 0) throw new Error("no job cards found (site layout changed?)");
+      const cutoff = Date.now() - maxAgeDays * 86400_000;
+      return jobs.filter((j) => !j.postedAt || new Date(j.postedAt).getTime() >= cutoff);
+    },
+  };
+}
+
+export async function parseStartupSi(html: string): Promise<ScrapedJob[]> {
+  type Draft = { id: string; title: string; date: string; href?: string };
+  const drafts: Draft[] = [];
+  let cur: Draft | undefined;
+  let lastHref = "";
+
+  await new HTMLRewriter()
+    .on(".advertisment-card", {
+      element() {
+        cur = { id: "", title: "", date: "" };
+        drafts.push(cur);
+      },
+    })
+    .on(".advertisment-card .right > .title", {
+      text(t) {
+        if (cur) cur.title += t.text;
+      },
+    })
+    .on(".advertisment-card .title button", {
+      element(el) {
+        if (cur) cur.id = (el.getAttribute("data-target") ?? "").replace(/^#description/, "");
+      },
+    })
+    .on(".advertisment-card .published-info b", {
+      text(t) {
+        if (cur) cur.date += t.text;
+      },
+    })
+    // The "preberi več" (read more) link is an <a> wrapping span.read-more; descriptions can contain other links.
+    .on(".advertisment-card a", {
+      element(el) {
+        lastHref = el.getAttribute("href") ?? "";
+      },
+    })
+    .on(".advertisment-card span.read-more", {
+      element() {
+        if (cur) cur.href = lastHref;
+      },
+    })
+    .transform(new Response(html))
+    .text();
+
+  return drafts
+    .filter((d) => d.id && clean(d.title))
+    .map((d) => ({
+      externalId: d.id,
+      title: clean(d.title),
+      url: normalizeUrl(d.href ?? ""),
+      postedAt: parseSlDate(clean(d.date)),
+    }));
+}