Tribepad Jobs API.

import requests
from urllib.parse import urlparse

# Vendor board: {tenant}.tribepad.com / .tribepad.io
# White-label board: a customer's own careers domain
board_url = "https://twinkl.tribepad.com"
parts = urlparse(board_url)
origin = f"{parts.scheme}://{parts.netloc}"
print(origin)  # https://twinkl.tribepad.com

import re
from bs4 import BeautifulSoup

RECORD_RE = re.compile(r"[?&]record=(\d+)", re.I)

def fetch_v2_page(origin, page):
    url = f"{origin}/v2/job/search?location_country=1&page={page}"
    resp = requests.get(url, timeout=15)
    if resp.status_code in (404, 410):
        return None  # not a v2 board — fall back to classic
    resp.raise_for_status()
    return resp.text

def parse_v2_cards(html, origin):
    soup = BeautifulSoup(html, "html.parser")
    jobs = []
    for a in soup.select("a.tbp-li-title"):
        m = RECORD_RE.search(a.get("href", ""))
        if not m:
            continue
        jobs.append({
            "external_id": m.group(1),
            "title": " ".join(a.get_text().split()),
            "detail_url": requests.compat.urljoin(origin + "/", a["href"]),
        })
    return jobs

RESULTS_TOTAL_RE = re.compile(r"(\d[\d,]*)\s+Search\s+Results", re.I)

def scrape_v2(origin, max_pages=50):
    html = fetch_v2_page(origin, 1)
    if html is None:
        return None  # tenant is a classic board, not v2

    total = RESULTS_TOTAL_RE.search(BeautifulSoup(html, "html.parser").get_text())
    print("advertised total:", total.group(1) if total else "unknown")

    all_jobs, seen = [], set()
    for page in range(1, max_pages + 1):
        if page > 1:
            html = fetch_v2_page(origin, page)
        new = [j for j in parse_v2_cards(html, origin) if j["external_id"] not in seen]
        if not new:          # empty or repeated page -> board exhausted
            break
        seen.update(j["external_id"] for j in new)
        all_jobs.extend(new)
    return all_jobs

CLASSIC_ID_RE = re.compile(r"/jobs/job/[^/]+/(\d+)", re.I)

def scrape_classic(origin, max_pages=50):
    first = requests.get(f"{origin}/jobs/search", timeout=15)
    if first.status_code in (404, 410):
        return None
    first.raise_for_status()

    all_jobs, seen, html = [], set(), first.text
    for page in range(1, max_pages + 1):
        if page > 1:
            r = requests.get(f"{origin}/jobs/search/-1/{page}", timeout=15)
            if r.status_code in (404, 410):
                break
            r.raise_for_status()
            html = r.text
        soup = BeautifulSoup(html, "html.parser")
        new = []
        for a in soup.select("a[href*='/jobs/job/']"):
            m = CLASSIC_ID_RE.search(a.get("href", ""))
            if not m or m.group(1) in seen:
                continue
            title_el = a.select_one(".job-list-title") or a
            new.append({
                "external_id": m.group(1),
                "title": title_el.get_text(strip=True),
                "detail_url": requests.compat.urljoin(origin + "/", a["href"]),
            })
        if not new:
            break
        seen.update(j["external_id"] for j in new)
        all_jobs.extend(new)
    return all_jobs

import json

def fetch_detail(detail_url):
    html = requests.get(detail_url, timeout=15).text
    soup = BeautifulSoup(html, "html.parser")

    # classic detail pages embed a JSON-LD JobPosting
    for tag in soup.select('script[type="application/ld+json"]'):
        try:
            data = json.loads(tag.string or "{}")
        except json.JSONDecodeError:
            continue
        if data.get("@type") == "JobPosting":
            return {
                "title": data.get("title"),
                "description": data.get("description"),
                "employment_type": data.get("employmentType"),
                "posted_at": data.get("datePosted"),
                "closes_at": data.get("validThrough"),
            }

    # v2 detail pages: structured advert HTML, no JSON-LD
    body = soup.select_one("div.job-advert-content") or soup.select_one(".job-advert-content")
    fields = {}
    for row in soup.select(".job_details_table .row"):
        cols = row.select(".col-sm-6")
        if len(cols) >= 2:
            label = cols[0].get_text(strip=True).rstrip(":").lower()
            fields[label] = cols[1].get_text(strip=True)
    h1 = soup.select_one("h1")
    return {
        "title": h1.get_text(strip=True) if h1 else None,
        "description": body.decode_contents().strip() if body else None,
        "salary": fields.get("salary"),
        "contract_type": fields.get("contract type"),
        "location": fields.get("location"),
        "closing_date": fields.get("closing date"),
    }