HireClick Jobs API.

import re
from urllib.parse import urlparse

RESERVED = {"admin", "api", "app", "mail", "secure", "support", "www"}
TENANT = re.compile(r"^[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?$")

def tenant_from_url(url: str) -> str | None:
    host = (urlparse(url).netloc or "").lower().rstrip(".")
    labels = host.split(".")
    # Exactly {tenant}.hireclick.com — a longer host is a lookalike, not a board.
    if len(labels) != 3 or labels[1:] != ["hireclick", "com"]:
        return None
    tenant = labels[0]
    if tenant in RESERVED or not TENANT.match(tenant):
        return None
    return tenant

def board_url(tenant: str) -> str:
    return f"https://{tenant}.hireclick.com/jobboard/"

tenant = tenant_from_url("https://1stmanufacturing.hireclick.com/jb/cnc-machinist/view/249707")
print(board_url(tenant))

import requests
from bs4 import BeautifulSoup

API_PATH = "/api/Controllers/JobBoard/GetSettingsAndJobs"

def fetch_org_guid(session: requests.Session, tenant: str) -> str:
    response = session.get(
        board_url(tenant),
        headers={"Accept": "text/html,application/xhtml+xml"},
        timeout=30,
    )
    response.raise_for_status()

    # The board must reference its own API path — that is the first-party proof.
    if API_PATH.lower() not in response.text.lower():
        raise RuntimeError(f"{tenant} did not serve a HireClick board")

    soup = BeautifulSoup(response.text, "html.parser")
    field = soup.select_one("input#hdnOrgGuid")
    guid = (field.get("value") if field else "") or ""
    if not guid.strip():
        raise RuntimeError("HireClick board omitted its organization GUID")
    return guid.strip().upper()

session = requests.Session()
org_guid = fetch_org_guid(session, "1stmanufacturing")
print(org_guid)

import json

def fetch_job_list(session: requests.Session, tenant: str, org_guid: str) -> list[dict]:
    response = session.get(
        f"https://{tenant}.hireclick.com{API_PATH}",
        params={"orgGUID": org_guid},
        headers={
            "Accept": "application/json,text/javascript;q=0.9,*/*;q=0.8",
            "X-Requested-With": "XMLHttpRequest",
            "Referer": board_url(tenant),
        },
        timeout=30,
    )
    response.raise_for_status()

    payload = response.json()
    # HireClick frequently double-encodes: the outer document is a JSON string
    # whose contents are the real object.
    if isinstance(payload, str):
        payload = json.loads(payload)

    jobs = payload.get("JobList")
    if jobs is None:
        raise RuntimeError("HireClick response omitted its JobList collection")
    return jobs

job_list = fetch_job_list(session, "1stmanufacturing", org_guid)
print(f"{len(job_list)} vacancies on the board")

from urllib.parse import urljoin, urlparse

DETAIL = re.compile(r"^/jb/[^/]+/view/([1-9][0-9]{0,18})$")

def map_row(row: dict, tenant: str) -> dict | None:
    raw = (row.get("JobURL") or "").strip()
    if not raw:
        return None
    absolute = urljoin(board_url(tenant), raw)
    parsed = urlparse(absolute)
    if tenant_from_url(absolute) != tenant:
        return None  # a link that leaves the tenant is never this board's job
    match = DETAIL.match(parsed.path)
    if not match:
        return None  # skips /jb/generalApplication and any other non-vacancy route

    canonical = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
    return {
        "id": match.group(1),
        "title": (row.get("JobTitle") or "").strip() or None,
        "listing_url": canonical,
        "apply_url": canonical,
        "summary": (row.get("JobDescriptionShort") or "").strip() or None,
        "city": (row.get("JobCity") or "").strip() or None,
        "employment_type": (row.get("JobType") or "").strip() or None,
    }

listings = [m for m in (map_row(r, "1stmanufacturing") for r in job_list) if m]
print(f"{len(listings)} mapped of {len(job_list)} received")

def fetch_detail(session: requests.Session, listing: dict) -> dict | None:
    response = session.get(
        listing["listing_url"],
        headers={"Accept": "text/html,application/xhtml+xml"},
        timeout=30,
    )
    if response.status_code in (404, 410):
        return None  # the only responses that prove the posting is gone
    response.raise_for_status()

    soup = BeautifulSoup(response.text, "html.parser")
    for tag in soup.find_all("script", type="application/ld+json"):
        try:
            data = json.loads(tag.string or "")
        except (json.JSONDecodeError, TypeError):
            continue
        for node in (data if isinstance(data, list) else [data]):
            if isinstance(node, dict) and node.get("@type") == "JobPosting":
                return {
                    **listing,
                    "title": node.get("title") or listing["title"],
                    "description_html": node.get("description"),
                    "posted_at": node.get("datePosted"),
                    "valid_through": node.get("validThrough"),
                    "employment_type": node.get("employmentType") or listing["employment_type"],
                    "company": (node.get("hiringOrganization") or {}).get("name"),
                }
    raise RuntimeError("HireClick detail page carried no JobPosting JSON-LD")

for listing in listings[:3]:
    job = fetch_detail(session, listing)
    if job:
        print(job["title"], "-", job["company"])