JazzHR Jobs API.

import requests
import xml.etree.ElementTree as ET

def discover_jazzhr_companies():
    companies = set()

    # Parse all 5 sitemap feeds (indices 0-4)
    for i in range(5):
        url = f"https://app.jazz.co/feeds/google/xml/{i}"
        response = requests.get(url, timeout=30)
        root = ET.fromstring(response.content)

        # Extract company slugs from URLs
        for url_elem in root.findall('.//{*}loc'):
            job_url = url_elem.text
            # URL format: https://{company}.applytojob.com/apply/{JOB_ID}/...
            if 'applytojob.com' in job_url:
                slug = job_url.split('//')[1].split('.')[0]
                companies.add(slug)

    return list(companies)

companies = discover_jazzhr_companies()
print(f"Found {len(companies)} companies")

import requests
from bs4 import BeautifulSoup

company_slug = "agil3tech"
url = f"https://{company_slug}.applytojob.com/apply"

# Always use HTTPS (some links may use HTTP which can timeout)
response = requests.get(url, timeout=15, allow_redirects=False)

# Check if company is valid (invalid companies redirect away)
if response.status_code in (301, 302):
    redirect_location = response.headers.get('Location', '')
    if 'info.jazzhr.com' in redirect_location or 'jazz.co' in redirect_location:
        print(f"Company '{company_slug}' does not exist")
        exit()

soup = BeautifulSoup(response.text, 'html.parser')
print(f"Successfully fetched job board for {company_slug}")

from bs4 import BeautifulSoup

def parse_job_listings(soup):
    jobs = []

    # Primary selector: list-group structure
    job_items = soup.select('li.list-group-item')

    for item in job_items:
        # Extract job URL and title
        title_elem = item.select_one('h4.list-group-item-heading a')
        if not title_elem:
            title_elem = item.select_one('a[href*="/apply/"]')

        if title_elem:
            job_url = title_elem.get('href', '')
            title = title_elem.get_text(strip=True)

            # Extract location and department
            info_items = item.select('ul.list-inline.list-group-item-text li')
            location = info_items[0].get_text(strip=True) if len(info_items) > 0 else None
            department = info_items[1].get_text(strip=True) if len(info_items) > 1 else None

            # Extract job ID from URL
            import re
            job_id_match = re.search(r'/apply/([A-Za-z0-9]{8,})', job_url)
            job_id = job_id_match.group(1) if job_id_match else None

            jobs.append({
                'id': job_id,
                'title': title,
                'url': job_url,
                'location': location,
                'department': department,
            })

    return jobs

jobs = parse_job_listings(soup)
print(f"Found {len(jobs)} jobs")

import requests
from bs4 import BeautifulSoup
import re

def fetch_job_details(job_url):
    # Normalize HTTP to HTTPS
    if job_url.startswith('http://'):
        job_url = job_url.replace('http://', 'https://')

    response = requests.get(job_url, timeout=15)
    soup = BeautifulSoup(response.text, 'html.parser')

    details = {}

    # Title
    title_elem = soup.select_one('div.job-header h1, h1')
    details['title'] = title_elem.get_text(strip=True) if title_elem else None

    # Location
    location_elem = soup.select_one("div.job-attributes-container div[title='Location']")
    details['location'] = location_elem.get_text(strip=True) if location_elem else None

    # Description
    desc_elem = soup.select_one('#job-description, .job-details .description')
    details['description'] = desc_elem.get_text(strip=True) if desc_elem else None

    # Compensation (dedicated field)
    comp_elem = soup.select_one("div.job-attributes-container div[title='Compensation'], "
                                 "div.job-attributes-container div[title='Salary'], "
                                 "#resumator-job-salary")
    details['compensation'] = comp_elem.get_text(strip=True) if comp_elem else None

    # If no dedicated compensation field, search in description
    if not details['compensation'] and details['description']:
        salary_match = re.search(r'\$[\d,]+(?:\s*-\s*\$?[\d,]+)?(?:\s*(?:per|/)\s*\w+)?',
                                  details['description'])
        if salary_match:
            details['compensation'] = salary_match.group()

    return details

# Fetch details for first job
if jobs:
    job_details = fetch_job_details(jobs[0]['url'])
    print(job_details)

import requests
import time
from bs4 import BeautifulSoup

def scrape_jazzhr_company(company_slug, delay_seconds=1):
    base_url = f"https://{company_slug}.applytojob.com/apply"

    try:
        # Fetch listings
        response = requests.get(base_url, timeout=15, allow_redirects=False)

        # Validate company exists
        if response.status_code in (301, 302):
            return {'error': 'Company not found', 'jobs': []}

        if response.status_code != 200:
            return {'error': f'HTTP {response.status_code}', 'jobs': []}

        soup = BeautifulSoup(response.text, 'html.parser')
        jobs = parse_job_listings(soup)

        # Fetch details for each job with delay
        for i, job in enumerate(jobs):
            try:
                details = fetch_job_details(job['url'])
                job.update(details)
                print(f"Processed {i+1}/{len(jobs)}: {job['title']}")
            except requests.RequestException as e:
                job['error'] = str(e)

            # Rate limiting delay
            if i < len(jobs) - 1:
                time.sleep(delay_seconds)

        return {'company': company_slug, 'jobs': jobs}

    except requests.RequestException as e:
        return {'error': str(e), 'jobs': []}

# Scrape a company
result = scrape_jazzhr_company("agil3tech", delay_seconds=1.5)
print(f"Total jobs scraped: {len(result['jobs'])}")