OCCY Jobs API.

from urllib.parse import urlparse


def resolve_board(url: str):
    """Return (board_kind, company_key) for an OCCY board URL."""
    parsed = urlparse(url)
    host = (parsed.hostname or "").lower()

    if host.endswith(".cp.occy.com"):
        # Legacy company host: the subdomain is the tenant key (lowercase).
        return "legacy", host[: -len(".cp.occy.com")]

    if host == "app.occy.com":
        # Shared host: /p/jobs/{ULID}; the 26-char key is case-sensitive.
        segments = [s for s in parsed.path.split("/") if s]
        if len(segments) == 3 and segments[:2] == ["p", "jobs"]:
            return "shared", segments[2].upper()

    raise ValueError(f"Unrecognised OCCY board URL: {url}")

import requests

BASE = "https://api.occy.com/api/public"


def list_jobs(kind: str, company_key: str):
    # OCCY enforces perPage <= 50 on both listing endpoints.
    if kind == "legacy":
        path, key_param = "careersite/company/jobs", "domain"
    else:
        path, key_param = "jobs", "companyId"

    page, rows = 1, []
    while True:
        resp = requests.get(
            f"{BASE}/{path}",
            params={
                key_param: company_key,
                "perPage": 50,
                "page": page,
                "sort": "createdAt",
                "sortDir": "DESC",
            },
            timeout=30,
        )
        resp.raise_for_status()
        data = resp.json()

        batch = data.get("jobs", [])
        rows.extend(batch)

        total = data.get("total", 0)
        per_page = data.get("perPage") or len(batch)
        consumed = (page - 1) * per_page + len(batch)
        if not batch or consumed >= total:
            break
        page += 1

    return rows

def posting_ids(kind: str, rows: list[dict]) -> list[str]:
    ids: list[str] = []

    if kind == "legacy":
        # A legacy job can carry several postings.
        for job in rows:
            for posting in job.get("postingDetails", []):
                pid = (posting.get("id") or "").strip()
                if pid:
                    ids.append(pid)
    else:
        # Shared-host rows carry the posting key directly.
        for job in rows:
            pid = (job.get("posting_id") or "").strip()
            if pid:
                ids.append(pid)

    return ids

def get_details(posting_id: str, kind: str, company_key: str):
    # Legacy detail calls include ?domain=; shared-host calls omit it.
    params = {"domain": company_key} if kind == "legacy" else {}
    resp = requests.get(
        f"{BASE}/jobs/posting/{posting_id}/details",
        params=params,
        timeout=30,
    )
    if resp.status_code in (404, 410):
        return None  # posting was removed
    resp.raise_for_status()
    return resp.json()


# End-to-end
kind, key = resolve_board("https://wearewithyou.cp.occy.com/p/jobs")
rows = list_jobs(kind, key)
for pid in posting_ids(kind, rows):
    details = get_details(pid, kind, key)
    if details:
        print(details.get("title"))