TalentNest Jobs API.

from urllib.parse import urlparse

HOST_SUFFIX = ".talentnest.com"

def parse_talentnest(url: str) -> dict:
    parsed = urlparse(url)
    host = parsed.netloc.lower()
    if not host.endswith(HOST_SUFFIX):
        raise ValueError("not a TalentNest host")

    tenant = host[: -len(HOST_SUFFIX)]
    if not tenant or "." in tenant:
        raise ValueError("unexpected TalentNest host shape")

    parts = [p for p in parsed.path.strip("/").split("/") if p]
    job_id = None
    if len(parts) == 3 and parts[1] == "posting" and parts[2].isdigit():
        job_id = parts[2]
    elif len(parts) == 2 and parts[0] == "posting" and parts[1].isdigit():
        job_id = parts[1]

    return {
        "tenant": tenant,
        "job_id": job_id,
        "board_url": f"https://{tenant}{HOST_SUFFIX}/en",
    }

print(parse_talentnest("https://5corners.talentnest.com/en/posting/239775"))
# {'tenant': '5corners', 'job_id': '239775', 'board_url': 'https://5corners.talentnest.com/en'}

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

session = requests.Session()
session.headers["Accept"] = "text/html,application/xhtml+xml"

def parse_rows(board_url: str, html: str) -> list[dict]:
    soup = BeautifulSoup(html, "html.parser")
    rows = []
    for row in soup.select(".job-row[data-job-row-url]"):
        href = row.get("data-job-row-url")
        detail = urljoin(board_url + "/", href)
        identity = parse_talentnest(detail)
        if not identity["job_id"]:
            continue                      # a row that does not resolve is a rejection
        rows.append({
            "job_id": identity["job_id"],
            "title": " ".join(row.get_text(" ", strip=True).split())[:120],
            "listing_url": detail,
        })
    return rows

board = parse_talentnest("https://5corners.talentnest.com/en")
first = session.get(board["board_url"], timeout=30)
first.raise_for_status()
print(len(parse_rows(board["board_url"], first.text)), "rows on page 1")

def crawl_board(board: dict, max_pages: int = 100) -> list[dict]:
    collected, seen = [], set()
    page_url = board["board_url"]

    for _ in range(max_pages):
        resp = session.get(page_url, timeout=30)
        resp.raise_for_status()
        soup = BeautifulSoup(resp.text, "html.parser")

        for row in parse_rows(board["board_url"], resp.text):
            if row["job_id"] not in seen:
                seen.add(row["job_id"])
                collected.append(row)

        nxt = soup.select_one("a.next_page[rel='next']:not(.disabled)")
        if nxt is None or not nxt.get("href"):
            return collected

        candidate = urljoin(board["board_url"] + "/", nxt["href"])
        if parse_talentnest(candidate)["tenant"] != board["tenant"]:
            raise RuntimeError("next-page link escaped the employer board")
        page_url = candidate

    raise RuntimeError("TalentNest pagination exceeded its page bound")

listings = crawl_board(board)
print(f"{len(listings)} postings")

import json
import time

def find_job_posting(soup) -> dict | 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":
                return node
    return None

def hydrate(board: dict, row: dict) -> dict | None:
    canonical = f"{board['board_url']}/posting/{row['job_id']}"
    resp = session.get(canonical, timeout=30)
    if resp.status_code in (404, 410):
        return None                       # the only removal evidence TalentNest gives
    resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")
    og_url = (soup.select_one("meta[property='og:url']") or {}).get("content", "")
    if parse_talentnest(og_url)["job_id"] != row["job_id"]:
        raise RuntimeError("og:url contradicted the requested posting")

    posting = find_job_posting(soup)
    if not posting:
        raise RuntimeError("detail page carried no JobPosting JSON-LD")

    identifier = (posting.get("identifier") or {}).get("value")
    if str(identifier) != row["job_id"]:
        raise RuntimeError("JSON-LD identifier contradicted the requested posting")

    return {
        "job_id": row["job_id"],
        "title": posting.get("title"),
        "description_html": posting.get("description"),
        "posted_at": posting.get("datePosted"),
        "employment_type": posting.get("employmentType"),
        "listing_url": canonical,
    }

for row in listings[:3]:
    print(hydrate(board, row)["title"])
    time.sleep(0.15)