Recooty Jobs API.

import requests
import xml.etree.ElementTree as ET
from urllib.parse import urlparse

def discover_companies_from_sitemap():
    """Extract unique company slugs from Recooty sitemap."""
    sitemap_url = "https://jobs.recooty.com/sitemap.xml"
    response = requests.get(sitemap_url, timeout=30)
    response.raise_for_status()

    root = ET.fromstring(response.content)
    companies = set()

    # Parse all URLs and extract company slugs
    for url in root.findall('.//{http://www.sitemaps.org/schemas/sitemap/0.9}loc'):
        path = urlparse(url.text).path
        parts = path.strip('/').split('/')
        if parts:
            companies.add(parts[0])

    print(f"Found {len(companies)} unique companies")
    return list(companies)

companies = discover_companies_from_sitemap()

import requests
from bs4 import BeautifulSoup

def fetch_listings_page(company_slug: str, page: int = 1):
    """Fetch the HTML listings page for a company."""
    base_url = "https://careerspage.io"
    url = f"{base_url}/{company_slug}"

    if page > 1:
        url = f"{url}?page={page}"

    headers = {
        "User-Agent": "Mozilla/5.0 (compatible; JobScraper/1.0)"
    }

    response = requests.get(url, headers=headers, timeout=30)
    response.raise_for_status()

    return response.text

html = fetch_listings_page("recooty-inc")
print(f"Fetched {len(html)} bytes")

from bs4 import BeautifulSoup

def parse_job_listings(html: str, company_slug: str):
    """Parse job listings from Recooty HTML."""
    soup = BeautifulSoup(html, 'html.parser')
    jobs = []

    # Find all job card containers
    job_cards = soup.select('div.pt-7.px-xl-9.bg-white.rounded')

    for card in job_cards:
        # Extract job title and URL
        title_link = card.select_one('h3 a.font-size-6.heading-default-color')
        if not title_link:
            continue

        title = title_link.get_text(strip=True)
        href = title_link.get('href', '')

        # Extract metadata from list items
        list_items = card.select('ul.list-unstyled li span')

        location = ""
        employment_type = ""
        experience = ""

        for i, item in enumerate(list_items):
            text = item.get_text(strip=True)
            if i == 0:
                location = text
            elif i == 1:
                employment_type = text
            elif i == 2:
                experience = text

        # Build full URL
        job_url = f"https://careerspage.io{href}" if href.startswith('/') else href

        jobs.append({
            'title': title,
            'location': location,
            'employment_type': employment_type,
            'experience_level': experience,
            'url': job_url,
        })

    return jobs

jobs = parse_job_listings(html, "recooty-inc")
print(f"Found {len(jobs)} jobs")

import json
import requests
from bs4 import BeautifulSoup

def fetch_job_details(job_url: str):
    """Fetch and parse job details including JSON-LD structured data."""
    response = requests.get(job_url, timeout=30)
    response.raise_for_status()

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

    # Extract JSON-LD structured data
    json_ld_data = None
    json_ld_script = soup.select_one('script[type="application/ld+json"]')

    if json_ld_script:
        try:
            json_ld_data = json.loads(json_ld_script.string)
        except json.JSONDecodeError:
            pass

    # Extract HTML description
    description_div = soup.select_one('div.company-profile')
    description = description_div.get_text(separator='\n', strip=True) if description_div else ""

    # Extract posted date from title attribute
    posted_date = None
    date_el = soup.select_one('p.font-size-4.text-gray[title]')
    if date_el:
        posted_date = date_el.get('title')

    job_details = {
        'title': json_ld_data.get('title') if json_ld_data else None,
        'description': description,
        'date_posted': json_ld_data.get('datePosted') or posted_date if json_ld_data else posted_date,
        'employment_type': json_ld_data.get('employmentType') if json_ld_data else None,
        'valid_through': json_ld_data.get('validThrough') if json_ld_data else None,
        'company': json_ld_data.get('hiringOrganization', {}).get('name') if json_ld_data else None,
        'apply_url': f"{job_url}/apply",
    }

    return job_details

details = fetch_job_details(jobs[0]['url'])
print(details)

import requests
from bs4 import BeautifulSoup
import time

def scrape_all_jobs(company_slug: str, delay: float = 1.0):
    """Scrape all jobs from a company, handling pagination."""
    all_jobs = []
    page = 1

    while True:
        html = fetch_listings_page(company_slug, page)
        jobs = parse_job_listings(html, company_slug)

        if not jobs:
            break

        all_jobs.extend(jobs)

        # Check for next page
        soup = BeautifulSoup(html, 'html.parser')
        next_link = soup.select_one(f'a[href*="page={page + 1}"]')

        if not next_link:
            break

        page += 1
        time.sleep(delay)  # Rate limiting

    return all_jobs

def fetch_listings_page(company_slug: str, page: int = 1):
    base_url = "https://careerspage.io"
    url = f"{base_url}/{company_slug}"
    if page > 1:
        url = f"{url}?page={page}"

    response = requests.get(url, timeout=30)
    response.raise_for_status()
    return response.text

all_jobs = scrape_all_jobs("recooty-inc")
print(f"Total jobs found: {len(all_jobs)}")