Cadient Talent Jobs API.

from urllib.parse import urlparse, parse_qs

HOST = "cta.cadienttalent.com"
DETAIL_SEQUENCES = {"jobdetails", "positiondetails"}

def parse_cadient(url: str) -> dict | None:
    parsed = urlparse(url)
    if parsed.scheme != "https" or parsed.netloc.lower() != HOST:
        return None
    if parsed.path.lower() != "/index.jsp":
        return None

    query = {k.lower(): v[0] for k, v in parse_qs(parsed.query).items()}
    application = (query.get("applicationname") or "").strip()
    posting_id = (query.get("posting_id") or "").strip()
    sequence = (query.get("seq") or "").strip().lower()
    if not application.isalnum() or not 3 <= len(application) <= 120:
        return None
    if sequence in DETAIL_SEQUENCES and not posting_id.isdigit():
        return None

    return {
        "application_name": application.lower(),
        "posting_id": posting_id if sequence in DETAIL_SEQUENCES else None,
    }

print(parse_cadient("https://cta.cadienttalent.com/index.jsp"
                    "?POSTING_ID=107287505627&SEQ=jobDetails"
                    "&applicationName=aztecshopsltdktmdreqext"))

import requests
from xml.etree import ElementTree

def feed_url(application_name: str) -> str:
    return (f"https://{HOST}/index.jsp"
            f"?applicationName={application_name.lower()}"
            "&locale=en_US"
            "&seq=postingSearchResultsRss"
            "&event=com.deploy.application.ca.plugin.PostingSearch.doSearch")

def fetch_listings(session, application_name: str) -> list[dict]:
    resp = session.get(feed_url(application_name),
                       headers={"Accept": "application/rss+xml"}, timeout=30)
    resp.raise_for_status()

    channel = ElementTree.fromstring(resp.content).find("channel")
    if channel is None:
        raise RuntimeError("Cadient response contained no RSS channel")

    listings = []
    for item in channel.findall("item"):
        link = (item.findtext("link") or item.findtext("guid") or "").strip()
        identity = parse_cadient(link)
        title = (item.findtext("title") or "").strip()
        if not identity or not identity["posting_id"] or not title:
            continue
        if identity["application_name"] != application_name.lower():
            continue

        listings.append({
            "id": identity["posting_id"],
            "title": title,
            "summary": (item.findtext("description") or "").strip(),
            "posted_at": item.findtext("pubDate"),
            "url": link,
        })
    return listings

session = requests.Session()
listings = fetch_listings(session, "AztecShopsLtdKTMDReqExt")
print(f"{len(listings)} open postings")

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

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  # posting removed
    resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")
    body = soup.select_one("#jobDetails")
    heading = soup.select_one("#jobdetail h1") or soup.select_one("h1")
    if not body or not heading:
        return None

    apply_anchor = soup.select_one("#jobdetail a.apply-now-btn[href]")
    apply_url = (urljoin(listing["url"], apply_anchor["href"])
                 if apply_anchor else listing["url"])

    return {
        "id": listing["id"],
        "title": heading.get_text(strip=True),
        "description_html": body.decode_contents(),
        "url": listing["url"],
        "apply_url": apply_url,
    }

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

def read_fields(soup: BeautifulSoup) -> dict:
    fields = {}
    for row in soup.select("#jobdetail .formRow"):
        label_node = row.select_one("[title]")
        value_node = row.select_one("span.field")
        if not label_node or not value_node:
            continue
        label = (label_node.get("title") or "").strip()
        value = value_node.get_text(strip=True)
        if not label or not value:
            continue
        fields.setdefault(label.lower().replace(" ", "_"), value)
    return fields

def enrich(session, listing: dict) -> dict | None:
    resp = session.get(listing["url"], headers={"Accept": "text/html"}, timeout=30)
    resp.raise_for_status()
    soup = BeautifulSoup(resp.text, "html.parser")

    fields = read_fields(soup)
    location = ", ".join(v for v in (fields.get("city"), fields.get("state")) if v)
    return {
        "id": listing["id"],
        "job_code": fields.get("job_code"),
        "department": fields.get("department"),
        "category": fields.get("category"),
        "work_location": fields.get("work_location"),
        "location": location or None,
        "posted_at": fields.get("date_posted") or listing.get("posted_at"),
    }

def classify(html_text: str) -> str:
    lowered = html_text.lower()
    if '"title":"job not found"' in lowered and "no longer available" in lowered:
        return "removed"
    if "id=\"jobdetails\"" in lowered:
        return "active"
    return "inconclusive"

def check_posting(session, url: str) -> str:
    resp = session.get(url, headers={"Accept": "text/html"}, timeout=30)
    if resp.status_code in (404, 410):
        return "removed"
    if not resp.ok:
        return "inconclusive"
    return classify(resp.text)