Healthcare Talent Source Jobs API.

import re
from urllib.parse import urlparse, unquote

SUFFIX = ".hctsportals.com"
JOB_PATH = re.compile("^([0-9]+)(?:-|$)")
TENANT = re.compile("^[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?$", re.IGNORECASE)

def parse_hcts(url: str) -> dict | None:
    parsed = urlparse(url)
    host = parsed.netloc.lower().rstrip(".")
    if not host.endswith(SUFFIX):
        return None

    tenant = host[: -len(SUFFIX)]
    if tenant in ("www", "") or "." in tenant or not TENANT.match(tenant):
        return None

    segments = [s for s in parsed.path.split("/") if s]
    job_id = None
    if segments:
        if segments[0] != "jobs" or len(segments) > 2:
            return None
        if len(segments) == 2 and segments[1] != "search":
            match = JOB_PATH.match(unquote(segments[1]))
            if not match:
                return None
            job_id = match.group(1)

    return {"tenant": tenant, "job_id": job_id,
            "board_url": f"https://{tenant}.hctsportals.com/jobs/search"}

print(parse_hcts("https://careers-waterbury.hctsportals.com/jobs/2191162"))

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import time

FINGERPRINT = "connect.healthcaretalentsource.com"

def is_same_search(candidate: str, tenant: str) -> bool:
    identity = parse_hcts(candidate)
    parsed = urlparse(candidate)
    return bool(identity and identity["tenant"] == tenant
                and parsed.path.lower() == "/jobs/search")

def scrape_board(session, tenant: str, max_pages: int = 25) -> list[dict]:
    url = f"https://{tenant}.hctsportals.com/jobs/search"
    jobs, seen = [], set()

    for _ in range(max_pages):
        resp = session.get(url, headers={"Accept": "text/html"}, timeout=30)
        resp.raise_for_status()
        if FINGERPRINT not in resp.text:
            raise RuntimeError("page omitted the Healthcare Talent Source fingerprint")

        soup = BeautifulSoup(resp.text, "html.parser")
        for row in parse_rows(soup, url, tenant):
            if row["id"] not in seen:
                seen.add(row["id"])
                jobs.append(row)

        nxt = soup.select_one("a.next_page[rel='next']")
        if not nxt or not nxt.get("href"):
            break
        candidate = urljoin(url, nxt["href"])
        if not is_same_search(candidate, tenant):
            break
        url = candidate
        time.sleep(0.1)
    return jobs

from urllib.parse import urlsplit, urlunsplit

def canonical(url: str) -> str:
    parts = urlsplit(url)
    return urlunsplit((parts.scheme, parts.netloc, parts.path, "", ""))

def parse_rows(soup: BeautifulSoup, page_url: str, tenant: str) -> list[dict]:
    rows = []
    for item in soup.select(".jobs-section__item"):
        anchor = item.select_one("a[href*='/jobs/']")
        if not anchor or not anchor.get("href"):
            continue

        detail_url = canonical(urljoin(page_url, anchor["href"]))
        identity = parse_hcts(detail_url)
        title = " ".join(anchor.get_text().split())
        if not identity or not identity["job_id"] or not title:
            continue
        if identity["tenant"] != tenant:
            continue

        rows.append({
            "id": identity["job_id"],
            "title": title,
            "url": detail_url,
            "apply_url": detail_url,
        })
    return rows

session = requests.Session()
listings = scrape_board(session, "careers-waterbury")
print(f"{len(listings)} open jobs")

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

    body_html = resp.text
    if FINGERPRINT not in body_html:
        return None
    # The page publishes its own route; require it to match the job we requested.
    marker = 'tm_vars.search_url = "/jobs/' + listing["id"] + '"'
    if marker not in body_html:
        return None

    soup = BeautifulSoup(body_html, "html.parser")
    heading = soup.select_one("#job h1")
    body = soup.select_one("#job .job__details-copy")
    if not heading or not body:
        return None

    location = soup.select_one("#job .job__details-list li span:not(.text-muted)")
    return {
        "id": listing["id"],
        "title": " ".join(heading.get_text().split()),
        "description_html": body.decode_contents().strip(),
        "location": (" ".join(location.get_text().split())
                     if location else None),
        "url": listing["url"],
        "apply_url": listing["url"],
    }

for listing in listings[:3]:
    print(fetch_detail(session, listing))
    time.sleep(0.1)