Fusion recruitment platform Jobs API.

import requests

# Host + route are tenant-specific; store the exact pair per deployment.
ORIGIN = "https://jobs.bunzlchs.com"
ROUTE = "Bunzl"
BOARD_URL = f"{ORIGIN}/{ROUTE}/Jobs"

HEADERS = {
    "Accept": "text/html,application/xhtml+xml",
    "Accept-Language": "en-GB,en;q=0.9",
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
        "(KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
    ),
}

session = requests.Session()  # carries the ASP.NET_SessionId cookie into pagination
resp = session.get(BOARD_URL, headers=HEADERS, timeout=20)
resp.raise_for_status()
html = resp.text

from bs4 import BeautifulSoup
from urllib.parse import urljoin

def parse_listings(html: str) -> list[dict]:
    soup = BeautifulSoup(html, "html.parser")
    jobs = []
    for card in soup.select(".job-summary"):
        anchor = card.select_one("h3 a[href*='/JobDescription/']")
        if not anchor:
            continue
        url = urljoin(BOARD_URL, anchor.get("href", ""))
        token = url.rstrip("/").split("/JobDescription/")[-1]

        # Label elements are each followed by their value element.
        fields = {}
        for label in card.select(".job-summary-table-label"):
            key = label.get_text(strip=True).rstrip(":")
            value_el = label.find_next_sibling()
            if key and value_el:
                fields[key] = value_el.get_text(" ", strip=True)

        jobs.append({
            "id": token,  # opaque public token — use verbatim, never decode
            "title": anchor.get_text(" ", strip=True),
            "listing_url": url,
            "apply_url": f"{ORIGIN}/{ROUTE}/ApplyNow/{token}",
            "reference": fields.get("Ref No"),
            "sector": fields.get("Job Sector"),
            "employment_type": fields.get("Employment Type"),
            "salary": fields.get("Salary"),
            "hours": fields.get("Hours of Work"),
            "location": fields.get("Location"),
            "expires": fields.get("Expiry Date"),
        })
    return jobs

listings = parse_listings(html)
print(f"Page 1: {len(listings)} jobs")

import re

def total_pages(html: str) -> int:
    # setJobsCount(...) and navigateJobList(...) markers carry the authoritative state.
    pages = [int(n) for n in re.findall(r"navigateJobList\(\s*['\"]?(\d+)", html)]
    return max(pages) if pages else 1

def fetch_page(session, page: int) -> str:
    resp = session.post(
        f"{ORIGIN}/{ROUTE}/NavigateJobList",
        data={"intPageNumber": page, "arJobLocationIds": "", "arJobSectorIds": ""},
        headers={
            **HEADERS,
            "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
            "X-Requested-With": "XMLHttpRequest",
            "Referer": BOARD_URL,
        },
        timeout=20,
    )
    resp.raise_for_status()
    return resp.text  # HTML fragment, not JSON

all_jobs = list(listings)
seen = {j["id"] for j in all_jobs}
for page in range(2, total_pages(html) + 1):
    page_jobs = [j for j in parse_listings(fetch_page(session, page)) if j["id"] not in seen]
    if not page_jobs:  # defensive: halt if a page yields nothing new
        break
    seen.update(j["id"] for j in page_jobs)
    all_jobs.extend(page_jobs)

import json

def fetch_details(session, listing: dict) -> dict:
    resp = session.get(listing["listing_url"], headers=HEADERS, timeout=20)
    if resp.status_code in (404, 410):
        return {**listing, "removed": True}
    resp.raise_for_status()
    soup = BeautifulSoup(resp.text, "html.parser")

    posting = None
    for tag in soup.select("script[type='application/ld+json']"):
        if "JobPosting" in tag.text:
            posting = json.loads(tag.text)
            break
    if not posting:
        raise ValueError("No JobPosting JSON-LD on detail page")

    location = (posting.get("jobLocation", {})
                       .get("address", {})
                       .get("addressLocality"))
    return {
        **listing,
        "description": posting.get("description"),
        "employment_type": posting.get("employmentType", listing["employment_type"]),
        "industry": posting.get("industry"),
        "company": posting.get("hiringOrganization", {}).get("name"),
        "posted_at": posting.get("datePosted"),
        "closes_at": posting.get("validThrough"),
        "location": location or listing["location"],
    }

detailed = [fetch_details(session, j) for j in all_jobs[:3]]