Careerpuck Jobs API.

import requests
import re

sitemap_url = "https://app.careerpuck.com/sitemap.xml"
response = requests.get(sitemap_url)
pattern = r'https://app\.careerpuck\.com/job-board/([^<]+)'

companies = re.findall(pattern, response.text)
print(f"Found {len(companies)} company job boards")
print(f"Sample companies: {companies[:5]}")

import requests

company = "earnest"
url = f"https://api.careerpuck.com/v1/public/job-boards/{company}"
headers = {
    "accept": "*/*",
    "origin": "https://app.careerpuck.com",
    "referer": "https://app.careerpuck.com/"
}

response = requests.get(url, headers=headers)
data = response.json()

jobs = data.get("jobs", [])
print(f"Found {len(jobs)} active jobs")

import html

for job in jobs:
    # HTML-decode the content field (unescape twice if double-encoded)
    description = html.unescape(job.get("content", ""))

    print({
        "id": job.get("atsSourceId") or job.get("permalink"),
        "title": job.get("title"),
        "location": job.get("location"),
        "department": job.get("department"),
        "team": job.get("team"),
        "work_type": job.get("workType"),
        "workplace_type": job.get("workplaceType"),
        "url": job.get("publicUrl"),
        "apply_url": job.get("applyUrl"),
        "posted_at": job.get("postedAt"),
        "source_platform": job.get("atsSourcePlatform"),
        "description_html": description[:200],
    })

employer = data.get("employerProfile", {})
departments = data.get("departments", [])

print({
    "company_name": employer.get("name") or employer.get("companyName"),
    "website": employer.get("website"),
    "career_page_url": employer.get("careerPageUrl"),
    "departments": departments,
})

import requests
import time

def fetch_careerpuck_jobs(company: str) -> list:
    url = f"https://api.careerpuck.com/v1/public/job-boards/{company}"
    headers = {
        "accept": "*/*",
        "origin": "https://app.careerpuck.com",
        "referer": "https://app.careerpuck.com/"
    }

    try:
        response = requests.get(url, headers=headers, timeout=10)
        if response.status_code == 404:
            print(f"Company '{company}' not found")
            return []
        if response.status_code in (403, 429):
            print(f"Throttled or blocked ({response.status_code}); backing off")
            time.sleep(5)
            return []
        response.raise_for_status()
        data = response.json()
        # Keep only published roles
        return [j for j in data.get("jobs", []) if j.get("status") == "public"]
    except requests.exceptions.RequestException as e:
        print(f"Request failed: {e}")
        return []

jobs = fetch_careerpuck_jobs("earnest")