SuccessFactors Jobs API.

import requests
from bs4 import BeautifulSoup
import re

# SAP-hosted pattern: https://{company}.jobs.hr.cloud.sap/
# Custom domain pattern: https://careers.{company}.com/

company_url = "https://wlgore.jobs.hr.cloud.sap"

# Fetch homepage to get CSRF token and session cookie
session = requests.Session()
response = session.get(company_url)
html = response.text

# Extract CSRF token from HTML (usually in script or meta tags)
csrf_match = re.search(r'x-csrf-token["':\s]+["']([^"']+)["']', html, re.IGNORECASE)
csrf_token = csrf_match.group(1) if csrf_match else None

print(f"CSRF Token: {csrf_token[:20]}..." if csrf_token else "CSRF token not found")

from bs4 import BeautifulSoup

soup = BeautifulSoup(html, 'html.parser')

# Find category links in navigation
# Pattern: /go/{category-name}/{categoryId}/
categories = []
for link in soup.find_all('a', href=True):
    href = link['href']
    match = re.match(r'/go/([^/]+)/(d+)', href)
    if match:
        categories.append({
            'name': match.group(1),
            'id': int(match.group(2))
        })

print(f"Found {len(categories)} categories")
for cat in categories[:5]:
    print(f"  - {cat['name']}: {cat['id']}")

# Use first category or a default
category_id = categories[0]['id'] if categories else None

import requests

api_url = f"{company_url}/services/recruiting/v1/jobs"

headers = {
    "Content-Type": "application/json",
    "x-csrf-token": csrf_token,
}

payload = {
    "locale": "en_US",
    "pageNumber": 0,
    "sortBy": "",
    "keywords": "",
    "location": "",
    "facetFilters": {},
    "brand": "",
    "skills": [],
    "categoryId": category_id,  # Company-specific ID
    "alertId": "",
    "rcmCandidateId": ""
}

response = session.post(api_url, headers=headers, json=payload)
data = response.json()

jobs = data.get("jobSearchResult", [])
print(f"Found {len(jobs)} jobs on page 0")

parsed_jobs = []

for item in jobs:
    job = item.get("response", {})
    parsed_jobs.append({
        "id": job.get("id"),
        "title": job.get("unifiedStandardTitle"),
        "url_title": job.get("urlTitle"),
        "location": job.get("jobLocationShort", [None])[0],
        "country": job.get("jobLocationCountry", [None])[0],
        "state": job.get("jobLocationState", [None])[0],
        "business_unit": job.get("businessUnit_obj", [None])[0],
        "posted_date": job.get("unifiedStandardStart"),
        "currency": job.get("currency", [None])[0],
        "locales": job.get("supportedLocales", []),
    })

# Clean up location string (remove <br/> tags)
for job in parsed_jobs:
    if job["location"]:
        job["location"] = job["location"].replace("<br/>", "").strip()

print(f"Parsed {len(parsed_jobs)} jobs")
print(f"Sample: {parsed_jobs[0]['title']} - {parsed_jobs[0]['location']}")

from bs4 import BeautifulSoup
import time

def fetch_job_details(session, base_url, job):
    """Fetch full job details from the HTML detail page."""
    # Build job detail URL: /job/{urlTitle}/{id}-{locale}/
    detail_url = f"{base_url}/job/{job['url_title']}/{job['id']}-en_US"

    response = session.get(detail_url)
    soup = BeautifulSoup(response.text, 'html.parser')

    # Extract job description (common selectors)
    description = None
    desc_elem = soup.find(class_='job-description')
    if not desc_elem:
        desc_elem = soup.find('main')
    if not desc_elem:
        desc_elem = soup.find('article')

    if desc_elem:
        description = desc_elem.get_text(separator=' ', strip=True)

    # Extract additional fields from HTML
    req_id = None
    for elem in soup.find_all(string=re.compile(r'Reqs*Id:', re.I)):
        req_id = elem.find_next(string=re.compile(r'd+'))
        if req_id:
            req_id = re.search(r'd+', str(req_id)).group()
            break

    return {
        **job,
        "description": description,
        "req_id": req_id,
        "detail_url": detail_url,
    }

# Fetch details for first job as example
job_with_details = fetch_job_details(session, company_url, parsed_jobs[0])
print(f"Description length: {len(job_with_details.get('description', '') or '')} chars")

import time

def fetch_all_jobs(session, base_url, csrf_token, category_id, locale="en_US"):
    """Fetch all jobs with pagination handling."""
    api_url = f"{base_url}/services/recruiting/v1/jobs"
    headers = {
        "Content-Type": "application/json",
        "x-csrf-token": csrf_token,
    }

    all_jobs = []
    page_number = 0

    while True:
        payload = {
            "locale": locale,
            "pageNumber": page_number,
            "sortBy": "",
            "keywords": "",
            "location": "",
            "facetFilters": {},
            "brand": "",
            "skills": [],
            "categoryId": category_id,
            "alertId": "",
            "rcmCandidateId": ""
        }

        response = session.post(api_url, headers=headers, json=payload)
        data = response.json()
        jobs = data.get("jobSearchResult", [])

        if not jobs:
            break

        all_jobs.extend(jobs)
        print(f"Page {page_number}: {len(jobs)} jobs (total: {len(all_jobs)})")

        page_number += 1
        time.sleep(1)  # Rate limiting: ~60 requests/minute

    return all_jobs

all_jobs = fetch_all_jobs(session, company_url, csrf_token, category_id)
print(f"Total jobs fetched: {len(all_jobs)}")