Greenhouse Jobs API.

from urllib.parse import urlparse

# URL patterns:
# https://job-boards.greenhouse.io/{companyToken}
# https://boards.greenhouse.io/{companyToken}

url = "https://job-boards.greenhouse.io/anthropic"
company_token = urlparse(url).path.strip("/")

print(f"Company token: {company_token}")  # "anthropic"

import requests
import time

def get_greenhouse_jobs(company_token: str) -> list[dict]:
    all_jobs = []
    page = 1
    base_url = f"https://job-boards.greenhouse.io/{company_token}"

    while True:
        url = f"{base_url}?page={page}&_data="
        response = requests.get(url, headers={"Accept": "application/json"})
        response.raise_for_status()

        data = response.json()

        # Jobs are in data["jobPosts"]["data"]
        if data.get("jobPosts", {}).get("data"):
            all_jobs.extend(data["jobPosts"]["data"])

        # Check for more pages
        total_pages = data.get("jobPosts", {}).get("total_pages", 1)
        if page >= total_pages:
            break
        page += 1
        time.sleep(0.3)  # Rate limiting

    return all_jobs

jobs = get_greenhouse_jobs("anthropic")
print(f"Found {len(jobs)} jobs")

import html

for job in jobs:
    # Decode HTML entities in the content
    description = html.unescape(job.get("content", ""))

    parsed = {
        "id": job.get("id"),
        "title": job.get("title"),
        "location": job.get("location", {}).get("name"),
        "department": job.get("departments", [{}])[0].get("name") if job.get("departments") else None,
        "description_html": description[:500],  # Full description available
        "url": f"https://job-boards.greenhouse.io/anthropic/jobs/{job.get('id')}",
    }
    print(parsed)

import requests

def get_job_details(company_token: str, job_id: str) -> dict:
    url = f"https://job-boards.greenhouse.io/{company_token}/jobs/{job_id}?_data="
    response = requests.get(url, headers={"Accept": "application/json"})
    response.raise_for_status()

    data = response.json()

    return {
        "id": data.get("jobPostId"),
        "title": data.get("jobPost", {}).get("title"),
        "location": data.get("job_post_location"),
        "description": data.get("jobPost", {}).get("content"),
        "employment_type": data.get("employment", {}).get("name"),
        "pay_ranges": [
            {
                "min": pr.get("min"),
                "max": pr.get("max"),
                "currency": pr.get("currency"),
                "title": pr.get("title"),
            }
            for pr in data.get("pay_ranges", [])
        ],
        "department": data.get("departments", [{}])[0].get("name") if data.get("departments") else None,
        "published_at": data.get("published_at"),
        "apply_url": f"https://job-boards.greenhouse.io/{company_token}/jobs/{job_id}#app",
    }

details = get_job_details("anthropic", "5431234")
print(f"Title: {details['title']}")
print(f"Pay ranges: {details['pay_ranges']}")

def parse_locations(location_str: str) -> list[str]:
    """Parse semicolon-separated locations into a list."""
    if not location_str:
        return []

    # Split by semicolon and clean up whitespace
    locations = [loc.strip() for loc in location_str.split(";")]
    return [loc for loc in locations if loc]

# Example usage
location_raw = "San Francisco, CA; New York, NY; Remote"
locations = parse_locations(location_raw)
print(f"Locations: {locations}")
# Output: ['San Francisco, CA', 'New York, NY', 'Remote']

import requests

def get_jobs_via_boards_api(company_token: str) -> list[dict]:
    """Fetch all jobs using the simpler Boards API."""
    url = f"https://boards-api.greenhouse.io/v1/boards/{company_token}/jobs"
    response = requests.get(url)
    response.raise_for_status()

    data = response.json()
    # Returns: {"jobs": [{"id", "title", "location": {"name"}, "absolute_url", ...}]}
    return data.get("jobs", [])

jobs = get_jobs_via_boards_api("anthropic")
print(f"Found {len(jobs)} jobs")

for job in jobs[:5]:
    print(f"- {job.get('title')} ({job.get('location', {}).get('name')})")