Trakstar Hire Jobs API.

# RSS feed URL pattern
company_slug = "terrapower"
company_name = "TerraPower"  # Note: capitalization matters in the path

rss_url = f"https://{company_slug}.hire.trakstar.com/jobfeeds/{company_name}"
print(f"RSS Feed URL: {rss_url}")
# Output: https://terrapower.hire.trakstar.com/jobfeeds/TerraPower

import requests
import xml.etree.ElementTree as ET

def fetch_trakstar_jobs(company_slug: str, company_name: str) -> list:
    rss_url = f"https://{company_slug}.hire.trakstar.com/jobfeeds/{company_name}"

    response = requests.get(rss_url, timeout=30)
    response.raise_for_status()

    # Parse XML with namespace support
    root = ET.fromstring(response.content)

    # Define namespaces
    namespaces = {
        'job': 'https://recruiterbox.com/rss/job/'
    }

    jobs = []
    for item in root.findall('.//item'):
        job = {
            'title': item.find('title').text,
            'link': item.find('link').text,
            'description': item.find('description').text,
            'pub_date': item.find('pubDate').text,
            'location_city': item.find('job:locationCity', namespaces).text if item.find('job:locationCity', namespaces) is not None else None,
            'location_state': item.find('job:locationState', namespaces).text if item.find('job:locationState', namespaces) is not None else None,
            'location_country': item.find('job:locationCountry', namespaces).text if item.find('job:locationCountry', namespaces) is not None else None,
            'position_type': item.find('job:positionType', namespaces).text if item.find('job:positionType', namespaces) is not None else None,
            'team': item.find('job:team', namespaces).text if item.find('job:team', namespaces) is not None else None,
            'close_date': item.find('job:closeDate', namespaces).text if item.find('job:closeDate', namespaces) is not None else None,
        }
        jobs.append(job)

    return jobs

jobs = fetch_trakstar_jobs("terrapower", "TerraPower")
print(f"Found {len(jobs)} jobs")

from datetime import datetime

def process_job_data(jobs: list) -> list:
    processed = []
    for job in jobs:
        # Extract job ID from URL
        job_id = job['link'].rstrip('/').split('/')[-1]

        # Parse publication date
        pub_date = None
        if job.get('pub_date'):
            try:
                pub_date = datetime.strptime(job['pub_date'], '%a, %d %b %Y %H:%M:%S %z')
            except ValueError:
                pass

        # Parse close date (application deadline)
        close_date = None
        if job.get('close_date'):
            try:
                close_date = datetime.strptime(job['close_date'], '%Y-%m-%d')
            except ValueError:
                pass

        processed.append({
            'id': job_id,
            'title': job.get('title'),
            'url': job.get('link'),
            'description_html': job.get('description'),
            'location': {
                'city': job.get('location_city'),
                'state': job.get('location_state'),
                'country': job.get('location_country'),
            },
            'department': job.get('team'),
            'employment_type': job.get('position_type'),
            'published_at': pub_date.isoformat() if pub_date else None,
            'closes_at': close_date.isoformat() if close_date else None,
        })

    return processed

processed_jobs = process_job_data(jobs)
for job in processed_jobs[:3]:
    print(f"{job['title']} - {job['location'].get('city', 'Unknown')}")

import requests
import xml.etree.ElementTree as ET
from typing import Optional

def fetch_jobs_safe(company_slug: str, company_name: str) -> Optional[list]:
    """Fetch jobs with comprehensive error handling."""
    rss_url = f"https://{company_slug}.hire.trakstar.com/jobfeeds/{company_name}"

    try:
        response = requests.get(rss_url, timeout=30)

        if response.status_code == 404:
            print(f"RSS feed not found. Check company name capitalization.")
            # Try fallback: check sitemap
            sitemap_url = f"https://{company_slug}.hire.trakstar.com/sitemap.xml"
            sitemap_resp = requests.get(sitemap_url, timeout=10)
            if sitemap_resp.status_code == 200:
                print("Sitemap available as fallback for job URLs")
            return None

        response.raise_for_status()

        root = ET.fromstring(response.content)
        items = root.findall('.//item')

        if not items:
            print("No jobs found in RSS feed")
            return []

        return items

    except requests.Timeout:
        print("Request timed out")
        return None
    except requests.RequestException as e:
        print(f"Request failed: {e}")
        return None
    except ET.ParseError as e:
        print(f"XML parsing failed: {e}")
        return None

# Usage
jobs = fetch_jobs_safe("terrapower", "TerraPower")

import requests
from bs4 import BeautifulSoup

def scrape_html_fallback(company_slug: str) -> list:
    """Scrape jobs from HTML pages when RSS is unavailable."""
    base_url = f"https://{company_slug}.hire.trakstar.com"
    jobs = []
    page = 1

    while True:
        url = f"{base_url}/?p={page}"
        response = requests.get(url, timeout=30)
        soup = BeautifulSoup(response.content, 'html.parser')

        # Find job listings
        openings = soup.select('.opening')
        if not openings:
            break

        for opening in openings:
            title_elem = opening.select_one('h3 a')
            location_elem = opening.select_one('.location')
            dept_elem = opening.select_one('.department')

            if title_elem:
                jobs.append({
                    'title': title_elem.text.strip(),
                    'url': base_url + title_elem.get('href', ''),
                    'location': location_elem.text.strip() if location_elem else None,
                    'department': dept_elem.text.strip() if dept_elem else None,
                })

        # Check for next page
        paginator = soup.select_one('.pagination')
        if not paginator or f'?p={page + 1}' not in str(paginator):
            break

        page += 1

    return jobs

# Use as fallback
# jobs = scrape_html_fallback("terrapower")