TriNet Hire Jobs API.

import requests

BASE_URL = "https://app.trinethire.com"

def listings_url(company_id: str) -> str:
    # company_id looks like "20533-all-weather-insulated-panels".
    # /companies/{id} without /jobs returns 404 — always append /jobs.
    return f"{BASE_URL}/companies/{company_id}/jobs"

url = listings_url("20533-all-weather-insulated-panels")
print(url)

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

JOB_ID_RE = re.compile(r"/jobs/([^/?#]+)", re.IGNORECASE)

def _text(el):
    return " ".join(el.get_text().split()) if el else None

def parse_listings(html: str) -> list[dict]:
    soup = BeautifulSoup(html, "html.parser")
    rows = []
    for row in soup.select("tr.job"):
        anchor = row.select_one("a[href*='/jobs/']")
        href = anchor.get("href") if anchor else None
        if not href:
            continue
        match = JOB_ID_RE.search(href)
        if not match:
            continue
        rows.append({
            "external_id": match.group(1),  # e.g. "116069-chemical-engineer"
            "title": _text(anchor),
            "url": urljoin(BASE_URL, href),
            "location": _text(row.select_one("td.location")),
            "employment_type": _text(row.select_one("td.type")),
        })
    return rows

def parse_detail(html: str) -> dict:
    soup = BeautifulSoup(html, "html.parser")

    title = _text(soup.select_one("h3.job-name"))

    body = (soup.select_one("div.job-descr.content")
            or soup.select_one("article div.job-descr")
            or soup.select_one("article"))
    description_html = body.decode_contents().strip() if body else ""

    location = category = employment_type = min_experience = None
    for li in soup.select("ul.job-meta > li"):
        if li.select_one("span.map-pin-icon"):
            location = _text(li)
            continue
        text = _text(li) or ""
        if ":" not in text:
            continue
        label, _, value = text.partition(":")
        label, value = label.strip().lower(), value.strip()
        if not value:
            continue
        if label == "category":
            category = value
        elif label == "type":
            employment_type = value
        elif label in ("min. experience", "min experience"):
            min_experience = value

    is_filled = "this position has been filled" in soup.get_text().lower()

    return {
        "title": title,
        "location": location,
        "description_html": description_html,
        "category": category,
        "employment_type": employment_type,
        "min_experience": min_experience,
        "is_filled": is_filled,
    }

import time

def scrape_company(company_id: str) -> list[dict]:
    session = requests.Session()
    session.headers["User-Agent"] = "Mozilla/5.0 (compatible; JoboBot/1.0)"

    resp = session.get(listings_url(company_id), timeout=30)
    if resp.status_code == 404:
        raise LookupError(f"Company '{company_id}' not found (did you append /jobs?)")
    if resp.status_code in (401, 403, 429):
        raise RuntimeError(f"Blocked or rate limited (HTTP {resp.status_code})")
    resp.raise_for_status()

    jobs = parse_listings(resp.text)  # single page — boards are not paginated

    detailed = []
    for job in jobs:
        detail = session.get(job["url"], timeout=30)
        if detail.status_code == 404:
            continue  # role pulled since the listing was read — skip it
        detail.raise_for_status()
        detailed.append({**job, **parse_detail(detail.text)})
        time.sleep(0.3)  # DelayBetweenRequestsMs = 300 from the scraper runtime config

    return detailed

roles = scrape_company("20533-all-weather-insulated-panels")
print(f"Scraped {len(roles)} roles")