HiBob Jobs API.

import requests

def build_headers(tenant: str) -> dict:
    """HiBob's careers backend enforces a Referer/Origin check on the tenant
    subdomain. Requests without a matching Referer return HTTP 401, so always
    send it — this applies to both the job-ad and career-site endpoints."""
    base = f"https://{tenant}.careers.hibob.com/"
    return {
        "Referer": base,
        "Accept": "application/json",
    }

# The tenant is the first host label of the careers URL, e.g.
# "iren" in https://iren.careers.hibob.com/ (keep any -hex suffix intact).
tenant = "iren"
headers = build_headers(tenant)

import requests

def fetch_job_ads(tenant: str, headers: dict) -> list[dict]:
    """One call returns every open role for the tenant — there is no pagination."""
    url = f"https://{tenant}.careers.hibob.com/api/job-ad"
    resp = requests.get(url, headers=headers, timeout=15)
    resp.raise_for_status()
    return resp.json().get("jobAdDetails", []) or []

ads = fetch_job_ads(tenant, headers)
print(f"Found {len(ads)} jobs for {tenant}")

def build_description(ad: dict) -> str:
    """Concatenate the four HTML sections HiBob splits the body into. Per-tenant
    sectionLabels override the default headings when present."""
    labels = ad.get("sectionLabels") or {}
    sections = [
        (None, ad.get("description")),  # lead section: no heading
        (labels.get("responsibilities") or "Responsibilities", ad.get("responsibilities")),
        (labels.get("requirements") or "Requirements", ad.get("requirements")),
        (labels.get("benefits") or "Benefits", ad.get("benefits")),
    ]
    html = ""
    for label, body in sections:
        if not body:
            continue
        if label:
            html += f"<h3>{label}</h3>"
        html += body
    return html

def build_location(ad: dict) -> str:
    """The 'site' field is free-form (e.g. 'Remote — EMEA'); don't split it.
    Combine it with the structured 'country' field for display."""
    site = (ad.get("site") or "").strip()
    country = (ad.get("country") or "").strip()
    if site and country:
        return f"{site}, {country}"
    return site or country

for ad in ads:
    if not ad.get("id"):
        continue  # skip malformed entries
    print({
        "external_id": ad["id"],
        "title": (ad.get("title") or "").strip(),
        "url": f"https://{tenant}.careers.hibob.com/jobs/{ad['id']}",
        "department": ad.get("department"),
        "employment_type": ad.get("employmentType"),
        "workspace_type": ad.get("workspaceTypeId"),  # on_site | remote | hybrid
        "location": build_location(ad),
        "published_at": ad.get("publishedAt"),
    })

import requests

def fetch_company_name(tenant: str, headers: dict) -> str | None:
    """Best-effort branding lookup. Non-fatal: listings should not fail because
    the branding endpoint hiccuped."""
    url = f"https://{tenant}.careers.hibob.com/api/career-site"
    try:
        resp = requests.get(url, headers=headers, timeout=10)
        resp.raise_for_status()
        return (resp.json().get("companyName") or "").strip() or None
    except requests.RequestException:
        return None

company_name = fetch_company_name(tenant, headers)

import requests

def scrape_hibob(tenant: str) -> list[dict]:
    """Full HiBob careers scraper: one listing call plus best-effort branding."""
    headers = build_headers(tenant)
    company_name = fetch_company_name(tenant, headers)

    url = f"https://{tenant}.careers.hibob.com/api/job-ad"
    try:
        resp = requests.get(url, headers=headers, timeout=15)
        resp.raise_for_status()
    except requests.HTTPError as e:
        status = e.response.status_code
        if status == 401:
            # We always send Referer, so a 401 means the tenant does not exist.
            print(f"Tenant '{tenant}' not found on HiBob")
        elif status in (403, 429):
            print(f"Blocked or rate limited for '{tenant}' — back off and retry")
        return []

    ads = resp.json().get("jobAdDetails", []) or []
    results, seen = [], set()
    for ad in ads:
        job_id = ad.get("id")
        if not job_id or job_id in seen:
            continue
        seen.add(job_id)
        results.append({
            "external_id": job_id,
            "title": (ad.get("title") or "").strip(),
            "company": company_name,
            "url": f"https://{tenant}.careers.hibob.com/jobs/{job_id}",
            "department": ad.get("department"),
            "employment_type": ad.get("employmentType"),
            "workspace_type": ad.get("workspaceTypeId"),
            "location": build_location(ad),
            "description": build_description(ad),
            "published_at": ad.get("publishedAt"),
        })
    return results

jobs = scrape_hibob("iren")
print(f"Scraped {len(jobs)} jobs")