GetHired Jobs API.

from urllib.parse import urlparse

RESERVED = {"api", "app", "easyapply", "support", "www"}

def parse_board(url: str) -> str | None:
    parsed = urlparse(url)
    if parsed.scheme != "https":
        return None
    labels = parsed.netloc.lower().split(".")
    if len(labels) != 3 or labels[1] != "easyapply" or labels[2] != "co":
        return None

    tenant = labels[0]
    if tenant in RESERVED or not 0 < len(tenant) <= 63:
        return None
    return tenant

def parse_job_id(url: str) -> str | None:
    """Jobs appear as /a/{uuid} or /job/{slug} on either host."""
    segments = [s for s in urlparse(url).path.split("/") if s]
    if len(segments) != 2 or segments[0] not in ("a", "job"):
        return None
    return segments[1]

print(parse_board("https://0758kentonhousinginc.easyapply.co"))

import requests
from xml.etree import ElementTree

def fetch_feed(session, tenant: str) -> list[dict]:
    feed_url = f"https://{tenant}.easyapply.co/rss"
    resp = session.get(feed_url,
                       headers={"Accept": "application/rss+xml"}, timeout=30)
    resp.raise_for_status()

    root = ElementTree.fromstring(resp.content)
    if root.tag.lower() != "rss":
        raise RuntimeError("GetHired response was not an RSS document")
    channel = root.find("channel")
    if channel is None:
        raise RuntimeError("GetHired feed contained no channel")

    company = (channel.findtext("title") or "").strip()
    rows, seen = [], set()
    for item in channel.findall("item"):
        link = (item.findtext("link") or item.findtext("guid") or "").strip()
        job_id = parse_job_id(link)
        if not job_id or job_id in seen:
            continue
        seen.add(job_id)
        rows.append({
            "id": job_id,
            "title": (item.findtext("title") or "").strip(),
            "summary": (item.findtext("description") or "").strip(),
            "location": (item.findtext("category") or "").strip() or None,
            "posted_at": item.findtext("pubDate"),
            "company": company,
            "url": link.split("?")[0],
        })
    return rows

session = requests.Session()
listings = fetch_feed(session, "0758kentonhousinginc")
print(f"{len(listings)} open jobs")

import json
import time
from bs4 import BeautifulSoup

def find_job_posting(html: str) -> dict | None:
    soup = BeautifulSoup(html, "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 node
    return None

def fetch_detail(session, listing: dict, tenant: str) -> dict | None:
    resp = session.get(
        listing["url"],
        headers={"Accept": "text/html",
                 "Referer": f"https://{tenant}.easyapply.co"},
        timeout=30)
    if resp.status_code in (404, 410):
        return None  # job removed
    resp.raise_for_status()

    posting = find_job_posting(resp.text)
    if not posting:
        return None

    address = ((posting.get("jobLocation") or {}).get("address")) or {}
    return {
        "id": listing["id"],
        "title": posting.get("title") or listing["title"],
        "description_html": posting.get("description"),
        "employment_type": posting.get("employmentType"),
        "posted_at": posting.get("datePosted") or listing.get("posted_at"),
        "closes_at": posting.get("validThrough"),
        "company": (posting.get("hiringOrganization") or {}).get("name")
                   or listing.get("company"),
        "city": address.get("addressLocality"),
        "state": address.get("addressRegion"),
        "url": listing["url"],
    }

for listing in listings[:3]:
    print(fetch_detail(session, listing, "0758kentonhousinginc"))
    time.sleep(0.25)

def resolve_tenant(session, job_url: str) -> str | None:
    resp = session.get(job_url, headers={"Accept": "text/html"}, timeout=30)
    if not resp.ok or not find_job_posting(resp.text):
        return None

    soup = BeautifulSoup(resp.text, "html.parser")
    tenants = set()
    for anchor in soup.select("a.vega-default-link[href], a.jobpage_company_logo[href]"):
        tenant = parse_board(anchor["href"])
        if tenant:
            tenants.add(tenant)

    # Ambiguous attribution is worse than none — require exactly one board.
    return tenants.pop() if len(tenants) == 1 else None

print(resolve_tenant(
    session, "https://easyapply.co/a/414e3fef-dd31-4ec6-b192-04175b7f1fa7"))