Engage ATS Jobs API.

import requests

def fetch_page(origin: str, page: int = 1) -> str:
    body = (
        "searchControlViewModel.Criteria="
        "&searchControlViewModel.PostCode="
        "&searchControlViewModel.TravelDistance="
        "&searchControlViewModel.SortBy="
        "&searchControlViewModel.Type=External"
        f"&searchControlViewModel.PageNo={page}"
    )
    resp = requests.post(
        f"{origin}/V2/Vacancy/ApplySearchFilter",
        data=body,
        headers={
            "Accept": "application/json",
            "Content-Type": "application/x-www-form-urlencoded",
            "Referer": f"{origin}/V2/Vacancy",
        },
        timeout=30,
    )
    resp.raise_for_status()
    # The vacancy markup is a string nested inside the JSON response.
    return resp.json()["searchResults"]

origin = "https://barnsley.engageats.co.uk"
fragment = fetch_page(origin)

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

# /Vacancies/{channel}/{organisationId}/{sequence}/{id}/{locationId}/{slug}
CARD_URL = re.compile(
    r"/Vacanc(?:y|ies)/([^/?#]+)/(\d+)/(\d+)/(\d+)/(\d+)/[^/?#]+",
    re.IGNORECASE,
)

def parse_cards(fragment: str, origin: str) -> list[dict]:
    soup = BeautifulSoup(fragment, "html.parser")
    jobs = []
    for button in soup.select("button.btn-search-results-view[data-param1]"):
        url = urljoin(origin, (button.get("data-param1") or "").strip())
        match = CARD_URL.search(url)
        if not match:
            continue
        channel, org_id, _seq, vacancy_id, location_id = match.groups()
        card = button.find_parent(class_=["ats-gray-panel", "ats-white-panel"])
        title_el = card.select_one(".ats-heading-font") if card else None
        jobs.append({
            "external_id": vacancy_id,
            "listing_url": url,
            "title": title_el.get_text(strip=True) if title_el else None,
            "channel_id": channel,
            "organisation_id": org_id,
            "location_id": location_id,
        })
    return jobs

PAGE_COUNT = re.compile(r"Page\s+(\d+)\s+of\s+(\d+)", re.IGNORECASE)

def total_pages(fragment: str, current_page: int) -> int:
    text = BeautifulSoup(fragment, "html.parser").get_text(" ")
    match = PAGE_COUNT.search(text)
    return int(match.group(2)) if match else current_page

def scrape_all(origin: str) -> list[dict]:
    page, results = 1, []
    while True:
        fragment = fetch_page(origin, page)
        cards = parse_cards(fragment, origin)
        if not cards:
            break
        results.extend(cards)
        if page >= total_pages(fragment, page):
            break
        page += 1
    return results

def fetch_detail(listing: dict) -> dict | None:
    html = requests.get(listing["listing_url"], timeout=30).text
    soup = BeautifulSoup(html, "html.parser")
    root = soup.select_one(".view-vacancy-container")
    save_btn = soup.select_one("#btn-save-vacancy[data-vacancyid]")
    native_id = save_btn.get("data-vacancyid") if save_btn else None
    # Guard against a mismatched or stale detail page.
    if root is None or native_id != listing["external_id"]:
        return None
    title_el = root.select_one("[role='heading'][aria-level='1'].ats-title-font")
    desc_el = root.select_one("div.order-md-1 > div.row > div.ats-normal-font")
    apply_btn = root.select_one("button.apply-application-btn[data-vacancyapplyurl]")
    apply_url = (
        urljoin(listing["listing_url"], apply_btn["data-vacancyapplyurl"])
        if apply_btn else None
    )
    return {
        **listing,
        "title": title_el.get_text(strip=True) if title_el else listing["title"],
        "description": desc_el.get_text(" ", strip=True) if desc_el else None,
        "apply_url": apply_url,
    }