Avature Jobs API.

import requests

tenant = "maximus"          # left-most label of {tenant}.avature.net
portal = "careers"          # path segment(s) before /SearchJobs/, kept per tenant
base_url = f"https://{tenant}.avature.net/{portal}"
search_url = f"{base_url}/SearchJobs/"

headers = {"User-Agent": "Mozilla/5.0 (compatible; JobBot/1.0)"}
html = requests.get(search_url, headers=headers, timeout=30).text

import re
from bs4 import BeautifulSoup

DETAIL_RE = re.compile(r"/(FolderDetail|JobDetail)/[^/?#]+/(\d+)(?:[/?#]|$)", re.I)

def parse_listings(page_html, page_url):
    soup = BeautifulSoup(page_html, "html.parser")
    jobs, order = {}, []
    for a in soup.select("a[href]"):
        absolute = requests.compat.urljoin(page_url, a.get("href", ""))
        m = DETAIL_RE.search(absolute)
        if not m:
            continue
        job_id = m.group(2)
        title = (a.get("title") or a.get_text()).strip()
        if job_id in jobs:
            if not jobs[job_id]["title"] and title:  # image + text anchor pair
                jobs[job_id]["title"] = title
            continue
        order.append(job_id)
        jobs[job_id] = {"id": job_id, "title": title, "url": absolute.split("?")[0]}
    return [jobs[i] for i in order]

def results_total(page_html):
    m = re.search(r"(\d[\d,]*)\s+results?\b", page_html, re.I)
    return int(m.group(1).replace(",", "")) if m else None

mode = "folder" if "/FolderDetail/" in html else "job"
offset_param = "folderOffset" if mode == "folder" else "jobOffset"

first = parse_listings(html, search_url)
page_size = len(first) or 6
total = results_total(html)

seen = {j["id"] for j in first}
all_jobs = list(first)
offset, MAX_PAGES = page_size, 500

for _ in range(1, MAX_PAGES):
    if total is not None and len(seen) >= total:
        break
    page_url = f"{search_url}?{offset_param}={offset}"
    page_html = requests.get(page_url, headers=headers, timeout=30).text
    added = 0
    for job in parse_listings(page_html, page_url):
        if job["id"] not in seen:
            seen.add(job["id"])
            all_jobs.append(job)
            added += 1
    if added == 0:            # no new IDs -> pagination exhausted
        break
    offset += page_size

print(f"Collected {len(all_jobs)} of {total or len(all_jobs)} jobs")

import json, html as html_lib

def fetch_detail(url):
    page = requests.get(url, headers=headers, timeout=30).text
    soup = BeautifulSoup(page, "html.parser")

    posting = None
    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":
                posting = node
                break
        if posting:
            break

    job = {"url": url}
    if posting:
        job["title"] = posting.get("title")
        desc = posting.get("description")
        if desc:
            job["description"] = BeautifulSoup(
                html_lib.unescape(desc), "html.parser").get_text(" ", strip=True)
        job["posted_at"] = posting.get("datePosted")
        job["closes_at"] = posting.get("validThrough")
        job["employment_type"] = posting.get("employmentType")
        org = posting.get("hiringOrganization")
        job["company"] = org.get("name") if isinstance(org, dict) else None
    return job, soup

def enrich_from_html(soup, job):
    fields = {}
    for field in soup.select(".article__content__view__field"):
        label = field.select_one(".article__content__view__field__label")
        value = field.select_one(".article__content__view__field__value")
        if label and value:
            fields.setdefault(label.get_text(strip=True), value.get_text(" ", strip=True))

    job["company"] = job.get("company") or fields.get("Company")
    job["location"] = (fields.get("Primary Location")
                       or fields.get("Job Location") or fields.get("Location"))
    job["employment_type"] = (job.get("employment_type")
                              or fields.get("Employment Type") or fields.get("Contract Type"))

    if not (job.get("description") and len(job["description"]) >= 80):
        for article in soup.select(".article.article--details"):
            head = (article.select_one(".article__header__text__title") or article)
            heading = re.sub(r"[^a-z0-9]", "", head.get_text().lower())
            if "description" in heading or heading in {"abouttherole", "therole", "roleoverview"}:
                body = article.select_one(".article__content, .article__body")
                text = body.get_text(" ", strip=True) if body else ""
                if len(text) >= 80:
                    job["description"] = text
                    break

    apply = soup.select_one("a[href*='/ApplicationMethods'], a[href*='/RegisterMethod']")
    if apply:
        job["apply_url"] = requests.compat.urljoin(job["url"], apply.get("href"))
    return job