Breezy HR Jobs API.

import re

def extract_company_slug(careers_url: str) -> str | None:
    """Extract company slug from a Breezy HR URL."""
    pattern = r"https?://([^.]+).breezy.hr"
    match = re.search(pattern, careers_url)
    return match.group(1) if match else None

# Example usage
url = "https://new-incentives.breezy.hr/"
slug = extract_company_slug(url)
print(f"Company slug: {slug}")  # Output: new-incentives

import requests

def fetch_breezy_jobs(company_slug: str) -> list[dict]:
    """Fetch all jobs from a Breezy HR company."""
    url = f"https://{company_slug}.breezy.hr/json"
    params = {"verbose": "true"}

    response = requests.get(url, params=params, timeout=10)
    response.raise_for_status()

    return response.json()

# Example usage
jobs = fetch_breezy_jobs("new-incentives")
print(f"Found {len(jobs)} active jobs")

def parse_job(job: dict) -> dict:
    """Parse a Breezy job object into a clean format."""
    location = job.get("location", {}) or {}

    return {
        "id": job.get("id"),
        "friendly_id": job.get("friendly_id"),
        "title": job.get("name"),
        "department": job.get("department"),
        "location": location.get("name", "Not specified"),
        "is_remote": location.get("is_remote", False),
        "employment_type": job.get("type", {}).get("name"),
        "salary": job.get("salary"),
        "description_html": job.get("description", ""),
        "url": job.get("url"),
        "published_date": job.get("published_date"),
        "company_name": job.get("company", {}).get("name"),
    }

# Parse all jobs
parsed_jobs = [parse_job(job) for job in jobs]
for job in parsed_jobs[:3]:
    print(f"{job['title']} - {job['location']}")

import requests

def validate_company(company_slug: str) -> dict | None:
    """Validate if a Breezy HR company exists."""
    url = f"https://{company_slug}.breezy.hr/json"
    params = {"verbose": "false"}

    try:
        response = requests.get(url, params=params, timeout=10)
        if response.status_code == 404:
            return None
        response.raise_for_status()
        jobs = response.json()
        # Get company name from first job if available
        if jobs:
            return {"name": jobs[0].get("company", {}).get("name"), "job_count": len(jobs)}
        return {"name": None, "job_count": 0}
    except requests.RequestException:
        return None

# Example usage
result = validate_company("new-incentives")
if result:
    print(f"Valid company with {result['job_count']} jobs")
else:
    print("Company not found")

import time
import requests

def fetch_with_retry(company_slug: str, max_retries: int = 3) -> list[dict]:
    """Fetch jobs with retry logic and rate limiting."""
    url = f"https://{company_slug}.breezy.hr/json"
    params = {"verbose": "true"}

    for attempt in range(max_retries):
        try:
            response = requests.get(url, params=params, timeout=10)

            if response.status_code == 404:
                print(f"Company '{company_slug}' not found")
                return []

            if response.status_code in (403, 429):
                wait_time = (attempt + 1) * 2
                print(f"Throttled ({response.status_code}), waiting {wait_time}s...")
                time.sleep(wait_time)
                continue

            response.raise_for_status()
            return response.json()

        except requests.RequestException as e:
            if attempt == max_retries - 1:
                print(f"Failed after {max_retries} attempts: {e}")
                return []
            time.sleep(attempt + 1)

    return []

# Pace requests between companies (~2s matches the reference scraper)
companies = ["new-incentives", "duolingo"]
for company in companies:
    jobs = fetch_with_retry(company)
    print(f"{company}: {len(jobs)} jobs")
    time.sleep(2)