Cornerstone OnDemand (CSOD) Jobs API.

# Modern CSOD URL format:
# https://{company}.csod.com/ux/ats/careersite/{siteId}/home?c={company}

# Examples:
# https://henkel.csod.com/ux/ats/careersite/1/home?c=henkel
# https://thekids.csod.com/ux/ats/careersite/4/home?c=thekids

company = "henkel"
site_id = 1
company_url = f"https://{company}.csod.com/ux/ats/careersite/{site_id}/home?c={company}"
print(f"Target URL: {company_url}")

import re
import requests

response = requests.get(company_url)
html = response.text

# CSOD embeds the token and API region in the page bootstrap JSON
# as "token":"eyJ..." and "cloud":"https://...".
token_match = re.search(r'"token"\s*:\s*"(eyJ[^"]+)"', html)
token = token_match.group(1) if token_match else None

cloud_match = re.search(r'"cloud"\s*:\s*"([^"]+)"', html)
cloud_endpoint = cloud_match.group(1).rstrip("/") if cloud_match else None

if not token:
    raise Exception("Failed to extract JWT token")

# If the page did not expose a region, probe the known hosts (see Step 3).
print(f"Token length: {len(token)}")
print(f"Cloud endpoint: {cloud_endpoint}")

import requests

KNOWN_API_REGIONS = [
    "https://eu-fra.api.csod.com",
    "https://uk.api.csod.com",
    "https://api.csod.com",
    "https://us.api.csod.com",
]

payload = {
    "careerSiteId": site_id,
    "careerSitePageId": 1,
    "pageNumber": 1,
    "pageSize": 25,
    "cultureId": 1,
    "searchText": "",
    "cultureName": "en-US",
    "states": [],
    "countryCodes": [],
    "cities": [],
    "placeID": "",
    "radius": None,
    "postingsWithinDays": None,
    "customFieldCheckboxKeys": [],
    "customFieldDropdowns": [],
    "customFieldRadios": [],
}

headers = {
    "Authorization": f"Bearer {token}",
    "Content-Type": "application/json",
    "Origin": f"https://{company}.csod.com",
    "Referer": f"https://{company}.csod.com/",
    "Csod-Accept-Language": "en-US",
}

def search_jobs(region):
    resp = requests.post(f"{region}/rec-job-search/external/jobs",
                         headers=headers, json=payload)
    return resp

regions = [cloud_endpoint] if cloud_endpoint else KNOWN_API_REGIONS
for region in regions:
    resp = search_jobs(region)
    data = resp.json() if resp.ok else {}
    if data.get("status") == "Success":
        cloud_endpoint = region
        break

print(f"Found {data.get('data', {}).get('totalCount', 0)} total jobs")

jobs = []
for req in data.get("data", {}).get("requisitions", []):
    job = {
        "id": req.get("requisitionId"),
        "title": req.get("displayJobTitle") or req.get("postingTitle"),
        "description": req.get("externalDescription"),  # full text, inline
        "locations": [
            {
                "city": loc.get("city"),
                "state": loc.get("state"),
                "country": loc.get("country"),
            }
            for loc in req.get("locations", [])
        ],
        "posted_date": req.get("postingEffectiveDate"),
        "expiration_date": req.get("postingExpirationDate"),
        "detail_url": f"https://{company}.csod.com/ux/ats/careersite/{site_id}/home/requisition/{req.get('requisitionId')}?c={company}",
    }
    jobs.append(job)

print(f"Parsed {len(jobs)} jobs")
print(f"First job title: {jobs[0]['title'] if jobs else 'No jobs found'}")

import time

all_jobs = []
page_number = 1
page_size = 25

while True:
    payload["pageNumber"] = page_number
    payload["pageSize"] = page_size

    response = requests.post(f"{cloud_endpoint}/rec-job-search/external/jobs",
                             headers=headers, json=payload)
    data = response.json()
    requisitions = data.get("data", {}).get("requisitions", [])

    if not requisitions:
        break

    all_jobs.extend(requisitions)
    total_count = data.get("data", {}).get("totalCount", 0)
    print(f"Page {page_number}: {len(requisitions)} jobs (total: {len(all_jobs)}/{total_count})")

    if len(all_jobs) >= total_count or len(requisitions) < page_size:
        break

    page_number += 1
    time.sleep(0.3)  # pace requests

print(f"Collected {len(all_jobs)} total jobs")

import re
import requests

def get_fresh_token(company_url):
    """Re-fetch a JWT token and cloud region from the career site page."""
    html = requests.get(company_url).text
    token_match = re.search(r'"token"\s*:\s*"(eyJ[^"]+)"', html)
    cloud_match = re.search(r'"cloud"\s*:\s*"([^"]+)"', html)
    if not token_match:
        raise Exception("Failed to extract JWT token")
    cloud = cloud_match.group(1).rstrip("/") if cloud_match else None
    return token_match.group(1), cloud

def fetch_jobs_with_retry(company, site_id, payload, max_retries=2):
    company_url = f"https://{company}.csod.com/ux/ats/careersite/{site_id}/home?c={company}"
    for attempt in range(max_retries + 1):
        token, cloud_endpoint = get_fresh_token(company_url)
        headers = {
            "Authorization": f"Bearer {token}",
            "Content-Type": "application/json",
        }
        response = requests.post(f"{cloud_endpoint}/rec-job-search/external/jobs",
                                 headers=headers, json=payload)
        if response.status_code == 401:
            print(f"Token expired, refreshing... (attempt {attempt + 1})")
            continue
        response.raise_for_status()
        return response.json()
    raise Exception("Failed to fetch jobs after token refresh")