Hireful (SiteHub) Jobs API.

import html as html_lib
import json
import re
from urllib.parse import unquote

import requests

BOARD_URL = "https://jobs.carterjonas.co.uk/"
BINDING = re.compile(r'data-collection-bind\s*=\s*["\']([^"\']+)["\']', re.I)

def discover_collection_id(board_url: str) -> str:
    page = requests.get(board_url, timeout=15).text
    if "api.sitehub.io" not in page:
        raise ValueError("Not a supported Hireful SiteHub board")
    for raw in BINDING.findall(page):
        try:
            binding = json.loads(unquote(html_lib.unescape(raw)))
        except json.JSONDecodeError:
            continue  # a board has many bindings; skip non-JSON ones
        cid = binding.get("id", "")
        if binding.get("name", "").lower() == "jobs" and re.fullmatch(r"[a-f0-9]{24}", cid):
            return cid
    raise ValueError("No Jobs collection id found on board")

collection_id = discover_collection_id(BOARD_URL)
print(collection_id)

PAGE_SIZE = 100

def fetch_page(collection_id: str, offset: int = 0) -> dict:
    url = f"https://api.sitehub.io/collection/{collection_id}/items"
    params = {
        "order": "updatedAt_DESC",
        "limit": PAGE_SIZE,
        "offset": offset,
        "distinct": "",
        "paginate": "true",
        "filter[columns.web-published]": "1",
    }
    resp = requests.get(url, params=params, timeout=15)
    resp.raise_for_status()
    return resp.json()

page = fetch_page(collection_id)
print(page["total"], "published jobs")

from urllib.parse import urljoin

HREF = re.compile(r'href\s*=\s*["\']([^"\']+)["\']', re.I)

def parse_item(item: dict, board_url: str) -> dict:
    cols = item.get("columns") or {}
    m = HREF.search(cols.get("apply-url-new") or "")
    apply_url = html_lib.unescape(m.group(1)).strip() if m else None
    slug = (cols.get("slug") or "").strip()
    sections = [s["content"].strip() for s in (cols.get("content") or []) if (s.get("content") or "").strip()]
    if (cols.get("description") or "").strip():
        sections.append(cols["description"].strip())
    location = ", ".join(v for v in (cols.get("location"), cols.get("region"), cols.get("postcode")) if v)
    return {
        "external_id": (cols.get("job-id") or "").strip(),  # native Hireful key
        "title": (cols.get("title") or "").strip(),
        "listing_url": urljoin(board_url, f"job/{slug}"),
        "apply_url": apply_url,
        "location": location or None,
        "department": cols.get("department"),
        "salary_text": cols.get("salary"),
        "closes_at": cols.get("closing-date"),
        "description": "\n".join(sections),
    }

import time

def scrape_board(board_url: str) -> list[dict]:
    collection_id = discover_collection_id(board_url)
    jobs, offset = [], 0
    while True:
        page = fetch_page(collection_id, offset)
        rows = page.get("collection") or []
        total = page.get("total", 0)
        if not rows:
            break
        jobs.extend(parse_item(row, board_url) for row in rows)
        offset += len(rows)
        if offset >= total:  # authoritative total reached
            break
        time.sleep(0.05)  # be polite between requests
    return jobs

print(len(scrape_board(BOARD_URL)), "jobs scraped")