HR WORKS Jobs API.

import requests

company_id = "x8e2d70"   # 7-char public tenant key from the board URL
language = "de"          # HR WORKS serves "de" or "en" routes

base = "https://jobapplication.hrworks.de"
listing_url = f"{base}/{language}?companyId={company_id}"

FINGERPRINTS = (
    "HrwMeCustomerJobOffersNestedView",
    "HrwMeJobApplicationManagementSession",
)

resp = requests.get(listing_url, headers={"Accept": "text/html"}, timeout=15)
resp.raise_for_status()
html = resp.text

if not any(marker in html for marker in FINGERPRINTS):
    raise RuntimeError("Document is missing the HR WORKS application fingerprint")

import re
from urllib.parse import urljoin, urlparse, parse_qs
from bs4 import BeautifulSoup

soup = BeautifulSoup(html, "html.parser")
jobs, seen = [], set()

for a in soup.select("a.job-offer-content[href]"):
    href = urljoin(listing_url, a["href"])
    query = parse_qs(urlparse(href).query)
    if query.get("companyId", [None])[0] != company_id:
        continue
    job_id = (query.get("id", [None])[0] or "").lower()
    if not re.fullmatch(r"[a-f0-9]{6}", job_id) or job_id in seen:
        continue
    heading = a.h2.get_text(strip=True) if a.h2 else ""
    title = (a.get("title") or heading).strip()
    if not title:
        continue
    seen.add(job_id)
    jobs.append({
        "id": job_id,
        "title": title,
        "url": f"{listing_url}&id={job_id}",
        "apply_url": f"{base}/{language}/apply?companyId={company_id}&id={job_id}",
    })

print(f"Found {len(jobs)} jobs")

import json

def fetch_details(job):
    resp = requests.get(job["url"], headers={"Accept": "text/html"}, timeout=15)
    if resp.status_code in (404, 410):
        return None  # canonical job was removed
    resp.raise_for_status()
    detail = BeautifulSoup(resp.text, "html.parser")

    posting = None
    for tag in detail.select("script[type='application/ld+json']"):
        try:
            data = json.loads(tag.string or "")
        except json.JSONDecodeError:
            continue
        if data.get("@type") == "JobPosting":
            posting = data
            break
    if posting is None or not posting.get("title") or not posting.get("description"):
        return None  # skip records without a usable JobPosting

    org = posting.get("hiringOrganization") or {}
    return {
        **job,
        "description": posting["description"],
        "employment_type": posting.get("employmentType"),
        "posted_at": posting.get("datePosted"),      # interpret as Europe/Berlin
        "closes_at": posting.get("validThrough"),    # interpret as Europe/Berlin
        "company_name": org.get("name"),
        "locations": posting.get("jobLocation"),     # address: locality/postalCode/country
    }

import time

records = []
for job in jobs:
    detail = fetch_details(job)
    if detail:
        records.append(detail)
    time.sleep(0.15)  # ~150ms between requests

print(f"Enriched {len(records)} of {len(jobs)} jobs")