"""SmartRecruiters: `smartrecruiters:`, paged by offset with a stated total. The identifier is case-sensitive (`BoschGroup`). Written from one real board on 2026-09-23; jobhunt-hq did not read SmartRecruiters. """ from __future__ import annotations import json from collections.abc import Callable from typing import Any from ._shared import Get, Page, Row, only, parse_dt, path_slug_ok NAME = "smartrecruiters" LABEL = "SmartRecruiters" RANK = 50 PATTERNS = ( r"(?:jobs|careers|api)\.smartrecruiters\.com/(?:v1/companies/)?([A-Za-z0-9_-]+)", ) _API = "api.smartrecruiters.com" #: The page size asked for, which is also the most the host serves per page. PAGE_SIZE = 100 def slug_ok(slug: str) -> bool: return path_slug_ok(slug) def allowed(slug: str) -> Callable[[str], bool]: return only(_API) def careers_url(slug: str) -> str: return f"https://jobs.smartrecruiters.com/{slug}" def probe_url(slug: str) -> str: return f"https://{_API}/v1/companies/{slug}/postings?limit=1" def probe_ok(body: bytes) -> bool: """An unknown identifier answers an empty listing, so a listing without postings counts as no board.""" return b'"totalFound":' in body and b'"totalFound":0' not in body def page(get: Get, slug: str, cursor: Any) -> Page: offset = int(cursor or 0) data = json.loads(get(f"https://{_API}/v1/companies/{slug}/postings" f"?offset={offset}&limit={PAGE_SIZE}")) content = data.get("content") or [] return data, content, data.get("totalFound"), offset + len(content) if content else None def parse(body: bytes, slug: str) -> list[Row]: return rows(json.loads(body), slug) def rows(data: dict[str, Any], slug: str) -> list[Row]: """One page of https://api.smartrecruiters.com/v1/companies/{slug}/postings -> `{"offset", "limit", "totalFound", "content": [...]}`. At most 100 a page, whatever `limit` asks for; the next is `?offset=` further on. The list omits the job description (only the per-posting detail endpoint has it, and fetching one per row would be hundreds of extra requests per board), so `description` stays empty here.""" out = [] for j in data.get("content") or []: title = (j.get("name") or "").strip() job_id = str(j.get("id") or "") if not title or not job_id: continue location = j.get("location") or {} loc_text = (location.get("fullLocation") or ", ".join(p for p in (location.get("city"), location.get("country")) if p)) out.append({ "source_id": job_id, "title": title, "location": (loc_text or "").strip(), "url": f"https://jobs.smartrecruiters.com/{slug}/{job_id}", "posted": parse_dt(j.get("releasedDate")), "department": ((j.get("department") or {}).get("label") or "").strip(), "description": "", "remote": location.get("remote"), "salary_text": "", # SmartRecruiters' list endpoint states no pay at all }) return out